Publications

2025

1. Towards Reproducible, Stable, and Robust Machine Learning Research in Clinical Environments

   Sarthak Pati

   Technische Universität München, 2025

   Abs HTML

   Towards Reproducible, Stable, and Robust Machine Learning Research in Clinical Environments is a dissertation that guides researchers to analyze their work through the lens of clinical deployment. It highlights the challenges a research project faces when considering clinical translation and the considerations needed to overcome them. It emphasizes the importance of healthcare data in medicine and showcases academic contributions and relevant publications. Finally, it summarizes the results of the work and provides future directions, thus providing a broad outlook.

2. Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction

   Rosanna Turrisi, Sarthak Pati, Giovanni Pioggia, and 3 more authors

   NeuroImage, 2025

   Abs HTML

   Integrating 3D magnetic resonance imaging (MRI) with machine learning has shown promising results in healthcare, especially in detecting Alzheimer’s Disease (AD). However, changes in MRI technologies and acquisition protocols often yield limited data, leading to potential overfitting. This study explores Transfer Learning (TL) approaches to enhance AD diagnosis using a Baseline model consisting of a 3D-Convolutional Neural Network trained on 80 3T MRI scans. Two scenarios are explored: (A) utilizing historical data to address changes in MRI acquisitions (from 1.5T to 3T MRI), and (B) adapting 2D models pre-trained on ImageNet (ResNet18, ResNet50, ResNet101) for 3D image processing when historical data is unavailable. In both scenarios, two modeling approaches are tested. The General Approach involves distinct feature extraction and classification steps, using Radiomic features and TL-based features evaluated with six classifiers. The Deep Approach integrates these steps by fine-tuning the pre-trained models for AD diagnosis. In scenario (A), TL significantly boosts the Baseline’s accuracy from 63% to 99%. In scenario (B), Radiomic features better represents 3D MRI than TL-features in the General Approach. Nonetheless, fine-tuning models pre-trained on natural images can increase the Baseline’s accuracy by up to 12 percentage points, achieving an overall accuracy of 83%.

3. Collaborative evaluation for performance assessment of medical imaging applications

   Hasan Kassem, Akshita Singh, Alejandro Aristizabal, and 6 more authors

   2025

   Abs HTML

   With a growing number of medical imaging applications being developed for clinical use, there comes a need for extensive performance assessment to meet regulatory requirements as well as to build trust among healthcare stakeholders. Evaluation of these applications on external data can contribute to their objective and rigorous validation. Healthcare stakeholders can form partnerships to enable collaborative evaluation of medical imaging applications transparently and under neutral governance. Collaborative evaluation can unlock the power of diverse data, democratize the pursuit of clinically useful applications, and support regulatory compliance. This chapter offers background on validation in the context of product lifecycle, highlighting the importance of external real-world data; it introduces collaborative evaluation while discussing key considerations; it provides existing solutions that support collaborative evaluation; and finally, it lays out ideas for future improvements.

4. Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge

   Dominic LaBella, Ujjwal Baid, Omaditya Khanna, and 119 more authors

   Machine Learning for Biomedical Imaging, 2025

   Abs DOI HTML

   We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

2024

1. Machine learning-based prognostic subgrouping of glioblastoma: A multicenter study

   Hamed Akbari, Spyridon Bakas, Chiharu Sako, and 8 more authors

   Neuro-Oncology, 2024

   Abs HTML

   Background: Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification. Methods: We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan–Meier analysis (Cox proportional model and hazard ratios [HR]). Results: The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I–II and I–III of 1.62 (95% CI: 1.43–1.84, P < .001) and 3.48 (95% CI: 2.94–4.11, P < .001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort. Conclusions: Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach to personalized patient management and clinical trial stratification in GBM.

2. Pan-Cancer Tumor Infiltrating Lymphocyte Detection based on Federated Learning

   Ujjwal Baid, Sarthak Pati, Tahsin M Kurc, and 6 more authors

   2024

   Abs HTML

   Advances in deep learning (DL) have shown great promise in revolutionizing healthcare, notwithstanding their success hinging on the availability of centralized large and diverse data. Such centralization is challenging because of numerous concerns relating to privacy, data-ownership, intellectual property, and compliance with varying regulatory policies. Federated learning (FL), offers a new decentralized paradigm to train DL models in healthcare. In this study, we evaluate the effect of FL in developing DL models for the analysis of digitized tissue sections, specifically whole slide images (WSIs). A classification application was considered as the example use case, to quantify the distribution of Tumor Infiltrating Lymphocytes (TILs), which are a critical biomarker in cancer research, providing valuable insights into patient outcomes. We trained a VGG classification model using 50 × 50 micron patches extracted from the WSIs with their associated TIL/nonTIL label. We simulated a FL environment, where different cancer types are included across each collaborating node. Our results show that the model trained with the federated training approach achieves similar performance, both quantitatively and qualitatively, to that of a model trained with all the training data pooled at a centralized location. Our study shows that FL has tremendous potential for enabling the development of more robust and accurate models for histopathology image analysis without having to collect large and diverse training data at a single location. Particularly for TILs, our FL approach yields a single DL model trained across numerous anatomical sites and able to robustly generalize to unseen cancer types.

3. The image biomarker standardization initiative: standardized convolutional filters for reproducible radiomics and enhanced clinical insights

   Philip Whybra, Alex Zwanenburg, Vincent Andrearczyk, and 8 more authors

   Radiology, 2024

   Abs HTML

   The Image Biomarker Standardization Initiative validated consensus-based reference values for 169 radiomics features, thus enabling calibration and verification of radiomics software.

4. BraTS-Path Challenge: Assessing Heterogeneous Histopathologic Brain Tumor Sub-regions

   Spyridon Bakas, Siddhesh P Thakur, Shahriar Faghani, and 8 more authors

   arXiv preprint arXiv:2405.10871, 2024

   Abs HTML

   Glioblastoma is the most common primary adult brain tumor, with a grim prognosis - median survival of 12-18 months following treatment, and 4 months otherwise. Glioblastoma is widely infiltrative in the cerebral hemispheres and well-defined by heterogeneous molecular and micro-environmental histopathologic profiles, which pose a major obstacle in treatment. Correctly diagnosing these tumors and assessing their heterogeneity is crucial for choosing the precise treatment and potentially enhancing patient survival rates. In the gold-standard histopathology-based approach to tumor diagnosis, detecting various morpho-pathological features of distinct histology throughout digitized tissue sections is crucial. Such "features" include the presence of cellular tumor, geographic necrosis, pseudopalisading necrosis, areas abundant in microvascular proliferation, infiltration into the cortex, wide extension in subcortical white matter, leptomeningeal infiltration, regions dense with macrophages, and the presence of perivascular or scattered lymphocytes. With these features in mind and building upon the main aim of the BraTS Cluster of Challenges this https URL, the goal of the BraTS-Path challenge is to provide a systematically prepared comprehensive dataset and a benchmarking environment to develop and fairly compare deep-learning models capable of identifying tumor sub-regions of distinct histologic profile. These models aim to further our understanding of the disease and assist in the diagnosis and grading of conditions in a consistent manner.

5. Brain tumor segmentation (brats) challenge 2024: Meningioma radiotherapy planning automated segmentation

   Dominic LaBella, Katherine Schumacher, Michael Mix, and 8 more authors

   arXiv preprint arXiv:2405.18383, 2024

   Abs HTML

   The 2024 Brain Tumor Segmentation Meningioma Radiotherapy (BraTS-MEN-RT) challenge aims to advance automated segmentation algorithms using the largest known multi-institutional dataset of radiotherapy planning brain MRIs with expert-annotated target labels for patients with intact or postoperative meningioma that underwent either conventional external beam radiotherapy or stereotactic radiosurgery. Each case includes a defaced 3D post-contrast T1-weighted radiotherapy planning MRI in its native acquisition space, accompanied by a single-label "target volume" representing the gross tumor volume (GTV) and any at-risk postoperative site. Target volume annotations adhere to established radiotherapy planning protocols, ensuring consistency across cases and institutions. For preoperative meningiomas, the target volume encompasses the entire GTV and associated nodular dural tail, while for postoperative cases, it includes at-risk resection cavity margins as determined by the treating institution. Case annotations were reviewed and approved by expert neuroradiologists and radiation oncologists. Participating teams will develop, containerize, and evaluate automated segmentation models using this comprehensive dataset. Model performance will be assessed using an adapted lesion-wise Dice Similarity Coefficient and the 95% Hausdorff distance. The top-performing teams will be recognized at the Medical Image Computing and Computer Assisted Intervention Conference in October 2024. BraTS-MEN-RT is expected to significantly advance automated radiotherapy planning by enabling precise tumor segmentation and facilitating tailored treatment, ultimately improving patient outcomes.

6. Advancing volumetric breast density segmentation: a deep learning approach with digital breast tomosynthesis

   Nehal Doiphode, Vinayak S Ahluwalia, Walter C Mankowski, and 8 more authors

   2024

   Abs HTML

   Recognizing breast density as a critical risk factor for breast cancer, traditionally assessed through subjective radiological evaluation within the BI-RADS framework, this research seeks to mitigate inter-observer variability through automated, quantitative analysis. The transition to DBT offers a quasi-3D perspective potentially enhancing the accuracy of BD assessments yet faces limitations with current FDA-cleared methods for volumetric breast density (VBD) estimation. Addressing these challenges, our work introduces a fully automated computational tool leveraging deep learning to accurately assess VBD from 3D DBT images without reliance on raw 2D data. Employing retrospective data compliant with privacy regulations, this study utilized DBT screening examinations from the Hospital of the University of Pennsylvania. The development of a three-class segmentation model, based on the U-Net architecture, was undertaken to differentiate between non-breast/background, fatty breast tissue, and dense breast tissue in DBT images. A novel two-stage training method was devised to enhance model performance, particularly in avoiding mis-segmentation issues common in high-resolution medio-lateral oblique images. This approach first utilized resized images for global shape information recognition, followed by refined segmentation using a 3D U-Net on filtered input, emphasizing accurate dense tissue identification. Our model demonstrated exemplary performance, with the Dice score—a critical metric for evaluating segmentation accuracy—revealing substantial agreement between the model’s predictions and actual data. Validation of the model’s effectiveness in breast cancer risk estimation was conducted through a case-control study, demonstrating a statistically significant association between DL-estimated VBD and cancer diagnosis. Additional factors, including BMI and age at screening, were also found to be significantly associated with cancer status, underscoring the multifactorial nature of breast cancer risk. The model’s predictive capability was further evidenced by an AUC of 0.63, indicating good performance. The study’s implications are profound, offering a clinically significant tool for personalized breast cancer risk prediction and potentially enhancing screening strategies across diverse populations.

7. Generatect: Text-conditional generation of 3d chest ct volumes

   Ibrahim Ethem Hamamci, Sezgin Er, Anjany Sekuboyina, and 8 more authors

   2024

   Abs HTML

   Text-conditional medical image generation is vital for radiology, augmenting small datasets, preserving data privacy, and enabling patient-specific modeling. However, its applications in 3D medical imaging, such as CT and MRI, which are crucial for critical care, remain unexplored. In this paper, we introduce GenerateCT, the first approach to generating 3D medical imaging conditioned on free-form medical text prompts. GenerateCT incorporates a text encoder and three key components: a novel causal vision transformer for encoding 3D CT volumes, a text-image transformer for aligning CT and text tokens, and a text-conditional super-resolution diffusion model. Without directly comparable methods in 3D medical imaging, we benchmarked GenerateCT against cutting-edge methods, demonstrating its superiority across all key metrics. Importantly, we explored GenerateCT’s clinical applications by evaluating its utility in a multi-abnormality classification task. First, we established a baseline by training a multi-abnormality classifier on our real dataset. To further assess the model’s generalization to external datasets and its performance with unseen prompts in a zero-shot scenario, we employed an external dataset to train the classifier, setting an additional benchmark. We conducted two experiments in which we doubled the training datasets by synthesizing an equal number of volumes for each set using GenerateCT. The first experiment demonstrated an 11% improvement in the AP score when training the classifier jointly on real and generated volumes. The second experiment showed a 7% improvement when training on both real and generated volumes based on unseen prompts. Moreover, GenerateCT enables the scaling of synthetic training datasets to arbitrary sizes. As an example, we generated 100,000 3D CT volumes, fivefold the number in our real dataset, and trained the classifier exclusively on these synthetic volumes. Impressively, this classifier surpassed the performance of the one trained on all available real data by a margin of 8%. Lastly, domain experts evaluated the generated volumes, confirming a high degree of alignment with the text prompts. Access our code, model weights, training data, and generated data at https://github.com/ibrahimethemhamamci/GenerateCT.

8. Privacy preservation for federated learning in health care

   Sarthak Pati, Sourav Kumar, Amokh Varma, and 8 more authors

   Patterns, 2024

   Abs HTML

   Significant improvements can be made to clinical AI applications when multiple health-care institutions collaborate to build models that leverage large and diverse datasets. Federated learning (FL) provides a method for such AI model training, where each institution shares only model updates derived from their private training data, rather than the explicit patient data. This has been demonstrated to advance the state of the art for many clinical AI applications. However, open and persistent federations bring up the question of trust, and model updates have raised considerations of possible information leakage. Prior work has gone into understanding the inherent privacy risks and into developing mitigation techniques. Focusing on FL in health care, we review the privacy risks and the costs and limitations associated with state-of-the-art mitigations. We hope to provide a guide to health-care researchers seeking to engage in FL as a new paradigm of secure and private collaborative AI.

9. BraTS-PEDs: results of the multi-consortium international pediatric brain tumor segmentation challenge 2023

   Anahita Fathi Kazerooni, Nastaran Khalili, Xinyang Liu, and 8 more authors

   arXiv preprint arXiv:2407.08855, 2024

   Abs HTML

   Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTSPEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

10. Best practices to evaluate the impact of biomedical research software—metric collection beyond citations

    Awan Afiaz, Andrey A Ivanov, John Chamberlin, and 8 more authors

    Bioinformatics, 2024

    Abs HTML

    Motivation: Software is vital for the advancement of biology and medicine. Impact evaluations of scientific software have primarily emphasized traditional citation metrics of associated papers, despite these metrics inadequately capturing the dynamic picture of impact and despite challenges with improper citation. Results: To understand how software developers evaluate their tools, we conducted a survey of participants in the Informatics Technology for Cancer Research (ITCR) program funded by the National Cancer Institute (NCI). We found that although developers realize the value of more extensive metric collection, they find a lack of funding and time hindering. We also investigated software among this community for how often infrastructure that supports more nontraditional metrics were implemented and how this impacted rates of papers describing usage of the software. We found that infrastructure such as social media presence, more in-depth documentation, the presence of software health metrics, and clear information on how to contact developers seemed to be associated with increased mention rates. Analysing more diverse metrics can enable developers to better understand user engagement, justify continued funding, identify novel use cases, pinpoint improvement areas, and ultimately amplify their software’s impact. Challenges are associated, including distorted or misleading metrics, as well as ethical and security concerns. More attention to nuances involved in capturing impact across the spectrum of biomedical software is needed. For funders and developers, we outline guidance based on experience from our community. By considering how we evaluate software, we can empower developers to create tools that more effectively accelerate biological and medical research progress. Availability and implementation: More information about the analysis, as well as access to data and code is available at https://github.com/fhdsl/ITCR_Metrics_manuscript_website.

11. GaNDLF-Synth: A Framework to Democratize Generative AI for (Bio) Medical Imaging

    Sarthak Pati, Szymon Mazurek, and Spyridon Bakas

    arXiv preprint arXiv:2410.00173, 2024

    Abs HTML

    Generative Artificial Intelligence (GenAI) is a field of AI that creates new data samples from existing ones. It utilizing deep learning to overcome the scarcity and regulatory constraints of healthcare data by generating new data points that integrate seamlessly with original datasets. This paper explores the background and motivation for GenAI, and introduces the Generally Nuanced Deep Learning Framework for Synthesis (GaNDLF-Synth) to address a significant gap in the literature and move towards democratizing the implementation and assessment of image synthesis tasks in healthcare. GaNDLF-Synth describes a unified abstraction for various synthesis algorithms, including autoencoders, generative adversarial networks, and diffusion models. Leveraging the GANDLF-core framework, it supports diverse data modalities and distributed computing, ensuring scalability and reproducibility through extensive unit testing. The aim of GaNDLF-Synth is to lower the entry barrier for GenAI, and make it more accessible and extensible by the wider scientific community.

12. Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 1: review of current advancements

    Javier E Villanueva-Meyer, Spyridon Bakas, Pallavi Tiwari, and 8 more authors

    The Lancet Oncology, 2024

    Abs HTML

    The development, application, and benchmarking of artificial intelligence (AI) tools to improve diagnosis, prognostication, and therapy in neuro-oncology are increasing at a rapid pace. This Policy Review provides an overview and critical assessment of the work to date in this field, focusing on diagnostic AI models of key genomic markers, predictive AI models of response before and after therapy, and differentiation of true disease progression from treatment-related changes, which is a considerable challenge based on current clinical care in neuro-oncology. Furthermore, promising future directions, including the use of AI for automated response assessment in neuro-oncology, are discussed.

13. Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

    Spyridon Bakas, Philipp Vollmuth, Norbert Galldiks, and 8 more authors

    The Lancet Oncology, 2024

    Abs HTML

    Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.

14. The Brain Tumor Segmentation-Metastases (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI

    Ahmed W Moawad, Anastasia Janas, Ujjwal Baid, and 8 more authors

    ArXiv, 2024

    Abs HTML

    The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in this http URL BraTS-METS 2023 challenge successfully curated well-annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied clinical environments and providing personalized volumetric reports to patients undergoing BM treatment.

15. TMIC-60. BRATS-PATH: ASSESSING HETEROGENEOUS HISTOPATHOLOGIC REGIONS IN GLIOBLASTOMA

    Siddhesh Thakur, Shahriar Faghani, Mana Moassefi, and 8 more authors

    Neuro-Oncology, 2024

    Abs HTML

    Glioblastoma, the most common malignant primary adult brain tumor, poses significant diagnostic and treatment challenges due to its heterogeneous molecular and micro-environmental profiles. To this end, we organize the BraTS-Path challenge to provide a public benchmarking environment and a comprehensive dataset to develop and validate AI models for identifying distinct histopathologic glioblastoma sub-regions in H&E-stained digitized tissue sections. We identified 188 multi-institutional diagnostic slides of glioblastoma (IDH-wt, Gr.4) cases, from the TCGA-GBM and TCGA-LGG data collections, following their reclassification according to the 2021 WHO classification criteria. Sub-regions were selected according to distinctive morphology of histopathologic features and included aggressive tumor biology and areas consistent with potential treatment effect. Selected sub-region annotations included cellular tumor, geographic necrosis, cortical infiltration, pseudopalisading necrosis, microvascular proliferation, white matter penetration, regions dense with macrophages, leptomeningeal infiltration, and presence of lymphocytes. We obtained 107,340 patches of size 512x512 from the 9 sub-regions. A global network of board-certified expert neuropathologists defined and followed a systematic annotation protocol based on clinical definitions and only delineated sub-regions with high confidence, thus ensuring high-quality standardized data. Each tissue section was assigned to an annotator-approver pair, with the annotator delineating sub-regions and the approver ensuring the consistency of the annotations. By crowdsourcing annotations, the BraTS-Path challenge harnesses the collective expertise of clinical neuropathologists and fosters a collaborative environment to advance the neuro-oncology field. The anticipated developed algorithms are expected to integrate state-of-the-art computational methods, achieving high accuracy in identifying diverse histopathologic features and advancing clinical decision-making processes. The BraTS-Path challenge aims to bridge the gap between research and clinical practice by promoting the development of AI-driven tools for precise tumor characterization. This collaborative effort can significantly enhance our understanding of glioblastoma, improve diagnostic accuracy, and inform treatment strategies, thereby contributing to better patient outcomes.

16. Volumetric Breast Density Estimation From Three-Dimensional Reconstructed Digital Breast Tomosynthesis Images Using Deep Learning

    Vinayak S Ahluwalia, Nehal Doiphode, Walter C Mankowski, and 8 more authors

    JCO Clinical Cancer Informatics, 2024

    Abs HTML

    Purpose: Breast density is a widely established independent breast cancer risk factor. With the increasing utilization of digital breast tomosynthesis (DBT) in breast cancer screening, there is an opportunity to estimate volumetric breast density (VBD) routinely. However, current available methods extrapolate VBD from two-dimensional (2D) images acquired using DBT and/or depend on the existence of raw DBT data, which is rarely archived by clinical centers because of storage constraints. Methods: We retrospectively analyzed 1,080 nonactionable three-dimensional (3D) reconstructed DBT screening examinations acquired between 2011 and 2016. Reference tissue segmentations were generated using previously validated software that uses 3D reconstructed slices and raw 2D DBT data. We developed a deep learning (DL) model that segments dense and fatty breast tissue from background. We then applied this model to estimate %VBD and absolute dense volume (ADV) in cm3 in a separate case-control sample (180 cases and 654 controls). We created two conditional logistic regression models, relating each model-derived density measurement to likelihood of contralateral breast cancer diagnosis, adjusted for age, BMI, family history, and menopausal status. Results: The DL model achieved unweighted and weighted Dice scores of 0.88 (standard deviation [SD] = 0.08) and 0.76 (SD = 0.15), respectively, on the held-out test set, demonstrating good agreement between the model and 3D reference segmentations. There was a significant association between the odds of breast cancer diagnosis and model-derived VBD (odds ratio [OR], 1.41 [95 % CI, 1.13 to 1.77]; P = .002), with an AUC of 0.65 (95% CI, 0.60 to 0.69). ADV was also significantly associated with breast cancer diagnosis (OR, 1.45 [95% CI, 1.22 to 1.73]; P < .001) with an AUC of 0.67 (95% CI, 0.62 to 0.71).Conclusion: DL-derived density measures derived from 3D reconstructed DBT images are associated with breast cancer diagnosis.

2023

1. Robust image population based stain color normalization: How many reference slides are enough?

   Jose L Agraz, Caleb M Grenko, Andrew A Chen, and 8 more authors

   IEEE Open Journal of Engineering in Medicine and Biology, 2023

   Abs HTML

   Histopathologic evaluation of Hematoxylin & Eosin (H&E) stained slides is essential for disease diagnosis, revealing tissue morphology, structure, and cellular composition. Variations in staining protocols and equipment result in images with color nonconformity. Although pathologists compensate for color variations, these disparities introduce inaccuracies in computational whole slide image (WSI) analysis, accentuating data domain shift and degrading generalization. Current state-of-the-art normalization methods employ a single WSI as reference, but selecting a single WSI representative of a complete WSI-cohort is infeasible, inadvertently introducing normalization bias. We seek the optimal number of slides to construct a more representative reference based on composite/aggregate of multiple H&E density histograms and stain-vectors, obtained from a randomly selected WSI population (WSI-Cohort-Subset). We utilized 1,864 IvyGAP WSIs as a WSI-cohort, and built 200 WSI-Cohort-Subsets varying in size (from 1 to 200 WSI-pairs) using randomly selected WSIs. The WSI-pairs’ mean Wasserstein Distances and WSI-Cohort-Subsets’ standard deviations were calculated. The Pareto Principle defined the optimal WSI-Cohort-Subset size. The WSI-cohort underwent structure-preserving color normalization using the optimal WSI-Cohort-Subset histogram and stain-vector aggregates. Numerous normalization permutations support WSI-Cohort-Subset aggregates as representative of a WSI-cohort through WSI-cohort CIELAB color space swift convergence, as a result of the law of large numbers and shown as a power law distribution. We show normalization at the optimal (Pareto Principle) WSI-Cohort-Subset size and corresponding CIELAB convergence: a) Quantitatively, using 500 WSI-cohorts; b) Quantitatively, using 8,100 WSI-regions; c) Qualitatively, using 30 cellular tumor normalization permutations. Aggregate-based stain normalization may contribute in increasing computational pathology robustness, reproducibility, and integrity.

2. Why is the winner the best?

   Matthias Eisenmann, Annika Reinke, Vivienn Weru, and 8 more authors

   2023

   Abs HTML

   International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and postprocessing (66%). The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

3. GaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows

   Sarthak Pati, Siddhesh P Thakur, İbrahim Ethem Hamamcı, and 8 more authors

   Communications Engineering, 2023

   Abs HTML

   Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities. However, greater expertise is required to develop DL algorithms, and the variability of implementations hinders their reproducibility, translation, and deployment. Here we present the community-driven Generally Nuanced Deep Learning Framework (GaNDLF), with the goal of lowering these barriers. GaNDLF makes the mechanism of DL development, training, and inference more stable, reproducible, interpretable, and scalable, without requiring an extensive technical background. GaNDLF aims to provide an end-to-end solution for all DL-related tasks in computational precision medicine. We demonstrate the ability of GaNDLF to analyze both radiology and histology images, with built-in support for k-fold cross-validation, data augmentation, multiple modalities and output classes. Our quantitative performance evaluation on numerous use cases, anatomies, and computational tasks supports GaNDLF as a robust application framework for deployment in clinical workflows.

4. Generatect: Text-guided 3d chest ct generation

   Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, and 8 more authors

   CoRR, 2023

   Abs HTML

   GenerateCT, the first approach to generating 3D medical imaging conditioned on free-form medical text prompts, incorporates a text encoder and three key components: a novel causal vision transformer for encoding 3D CT volumes, a text-image transformer for aligning CT and text tokens, and a text-conditional super-resolution diffusion model. Without directly comparable methods in 3D medical imaging, we benchmarked GenerateCT against cutting-edge methods, demonstrating its superiority across all key metrics. Importantly, we evaluated GenerateCT’s clinical applications in a multi-abnormality classification task. First, we established a baseline by training a multi-abnormality classifier on our real dataset. To further assess the model’s generalization to external data and performance with unseen prompts in a zero-shot scenario, we employed an external set to train the classifier, setting an additional benchmark. We conducted two experiments in which we doubled the training datasets by synthesizing an equal number of volumes for each set using GenerateCT. The first experiment demonstrated an 11% improvement in the AP score when training the classifier jointly on real and generated volumes. The second experiment showed a 7% improvement when training on both real and generated volumes based on unseen prompts. Moreover, GenerateCT enables the scaling of synthetic training datasets to arbitrary sizes. As an example, we generated 100,000 3D CTs, fivefold the number in our real set, and trained the classifier exclusively on these synthetic CTs. Impressively, this classifier surpassed the performance of the one trained on all available real data by a margin of 8%. Last, domain experts evaluated the generated volumes, confirming a high degree of alignment with the text prompt. Access our code, model weights, training data, and generated data at https://github.com/ibrahimethemhamamci/GenerateCT

5. GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes

   Ibrahim Ethem Hamamci, Sezgin Er, Anjany Sekuboyina, and 8 more authors

   arXiv e-prints, 2023

   Abs HTML

   GenerateCT, the first approach to generating 3D medical imaging conditioned on free-form medical text prompts, incorporates a text encoder and three key components: a novel causal vision transformer for encoding 3D CT volumes, a text-image transformer for aligning CT and text tokens, and a text-conditional super-resolution diffusion model. Without directly comparable methods in 3D medical imaging, we benchmarked GenerateCT against cutting-edge methods, demonstrating its superiority across all key metrics. Importantly, we evaluated GenerateCT’s clinical applications in a multi-abnormality classification task. First, we established a baseline by training a multi-abnormality classifier on our real dataset. To further assess the model’s generalization to external data and performance with unseen prompts in a zero-shot scenario, we employed an external set to train the classifier, setting an additional benchmark. We conducted two experiments in which we doubled the training datasets by synthesizing an equal number of volumes for each set using GenerateCT. The first experiment demonstrated an 11% improvement in the AP score when training the classifier jointly on real and generated volumes. The second experiment showed a 7% improvement when training on both real and generated volumes based on unseen prompts. Moreover, GenerateCT enables the scaling of synthetic training datasets to arbitrary sizes. As an example, we generated 100,000 3D CTs, fivefold the number in our real set, and trained the classifier exclusively on these synthetic CTs. Impressively, this classifier surpassed the performance of the one trained on all available real data by a margin of 8%. Last, domain experts evaluated the generated volumes, confirming a high degree of alignment with the text prompt. Access our code, model weights, training data, and generated data at https://github.com/ibrahimethemhamamci/GenerateCT

6. Dentex: An abnormal tooth detection with dental enumeration and diagnosis benchmark for panoramic x-rays

   Ibrahim Ethem Hamamci, Sezgin Er, Enis Simsar, and 8 more authors

   arXiv preprint arXiv:2305.19112, 2023

   Abs HTML

   Panoramic X-rays are frequently used in dentistry for treatment planning, but their interpretation can be both time-consuming and prone to error. Artificial intelligence (AI) has the potential to aid in the analysis of these X-rays, thereby improving the accuracy of dental diagnoses and treatment plans. Nevertheless, designing automated algorithms for this purpose poses significant challenges, mainly due to the scarcity of annotated data and variations in anatomical structure. To address these issues, the Dental Enumeration and Diagnosis on Panoramic X-rays Challenge (DENTEX) has been organized in association with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2023. This challenge aims to promote the development of algorithms for multi-label detection of abnormal teeth, using three types of hierarchically annotated data: partially annotated quadrant data, partially annotated quadrant-enumeration data, and fully annotated quadrant-enumeration-diagnosis data, inclusive of four different diagnoses. In this paper, we present the results of evaluating participant algorithms on the fully annotated data, additionally investigating performance variation for quadrant, enumeration, and diagnosis labels in the detection of abnormal teeth. The provision of this annotated dataset, alongside the results of this challenge, may lay the groundwork for the creation of AI-powered tools that can offer more precise and efficient diagnosis and treatment planning in the field of dentistry. The evaluation code and datasets can be accessed at https://github.com/ibrahimethemhamamci/DENTEX.

7. Evaluation of software impact designed for biomedical research: Are we measuring what’s meaningful?

   Awan Afiaz, Andrey A Ivanov, John Chamberlin, and 8 more authors

   ArXiv, 2023

   Abs HTML

   Software is vital for the advancement of biology and medicine. Analysis of usage and impact metrics can help developers determine user and community engagement, justify additional funding, encourage additional use, identify unanticipated use cases, and help define improvement areas. However, there are challenges associated with these analyses including distorted or misleading metrics, as well as ethical and security concerns. More attention to the nuances involved in capturing impact across the spectrum of biological software is needed. Furthermore, some tools may be especially beneficial to a small audience, yet may not have compelling typical usage metrics. We propose more general guidelines, as well as strategies for more specific types of software. We highlight outstanding issues regarding how communities measure or evaluate software impact. To get a deeper understanding of current practices for software evaluations, we performed a survey of participants in the Informatics Technology for Cancer Research (ITCR) program funded by the National Cancer Institute (NCI). We also investigated software among this community and others to assess how often infrastructure that supports such evaluations is implemented and how this impacts rates of papers describing usage of the software. We find that developers recognize the utility of analyzing software usage, but struggle to find the time or funding for such analyses. We also find that infrastructure such as social media presence, more in-depth documentation, the presence of software health metrics, and clear information on how to contact developers seem to be associated with increased usage rates. Our findings can help scientific software developers make the most out of evaluations of their software.

8. Federated benchmarking of medical artificial intelligence with MedPerf

   Alexandros Karargyris, Renato Umeton, Micah J Sheller, and 8 more authors

   Nature machine intelligence, 2023

   HTML
9. Federated learning enables big data for rare cancer boundary detection (vol 13, 7346, 2022)

   Sarthak Pati, Ujjwal Baid, Brandon Edwards, and 8 more authors

   2023

   Abs HTML

   Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n=6,314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

10. 3.11 Federated Learning and Reproducibility in Healthcare

    Sarthak Pati

    Inverse Biophysical Modeling and Machine Learning in Personalized Oncology, 2023

    HTML
11. The Image Biomarker Standardization Initiative: Standardized convolutional filters for quantitative radiomics Authors and affiliations

    Philip Whybra, Alex Zwanenburg, Vincent Andrearczyk, and 8 more authors

    2023

    HTML
12. Panoptica–instance-wise evaluation of 3D semantic and instance segmentation maps

    Florian Kofler, Hendrik Möller, Josef A Buchner, and 8 more authors

    arXiv preprint arXiv:2312.02608, 2023

    HTML
13. The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting

    Florian Kofler, Felix Meissen, Felix Steinbauer, and 8 more authors

    arXiv preprint arXiv:2305.08992, 2023

    HTML

2022

1. Federated Learning for the Classification of Tumor Infiltrating Lymphocytes

   Ujjwal Baid, Sarthak Pati, Tahsin Kurc, and 6 more authors

   arXiv preprint arXiv:2203.16622, 2022

   HTML
2. Artificial-intelligence-driven volumetric breast density estimation with digital breast tomosynthesis in a racially diverse screening cohort.

   Vinayak S Ahluwalia, Walter Mankowski, Sarthak Pati, and 6 more authors

   2022

   HTML
3. MammoFL: Mammographic Breast Density Estimation using Federated Learning

   Ramya Muthukrishnan, Angelina Heyler, Keshava Katti, and 8 more authors

   arXiv preprint arXiv:2206.05575, 2022

   HTML
4. Deep-learning-enabled volumetric breast density estimation with digital breast tomosynthesis

   Vinayak S Ahluwalia, Walter Mankowski, Sarthak Pati, and 6 more authors

   Cancer Research, 2022

   HTML
5. Expert tumor annotations and radiomics for locally advanced breast cancer in DCE-MRI for ACRIN 6657/I-SPY1

   Rhea Chitalia, Sarthak Pati, Megh Bhalerao, and 8 more authors

   Scientific data, 2022

   HTML
6. The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics

   Spyridon Bakas, Chiharu Sako, Hamed Akbari, and 8 more authors

   Scientific data, 2022

   HTML
7. The Federated Tumor Segmentation (FeTS) tool: an open-source solution to further solid tumor research

   Physics in Medicine & Biology, 2022

   HTML
8. OpenFL: The Open Federated Learning library

   Patrick Foley, Micah J Sheller, Brandon Edwards, and 8 more authors

   Physics in Medicine & Biology, 2022

   HTML
9. Biomedical image analysis competitions: The state of current participation practice

   Matthias Eisenmann, Annika Reinke, Vivienn Weru, and 8 more authors

   arXiv preprint arXiv:2212.08568, 2022

   HTML
10. Federated learning enables big data for rare cancer boundary detection

    Sarthak Pati, Ujjwal Baid, Brandon Edwards, and 8 more authors

    Nature Communications, 2022

    HTML
11. NIMG-25. OPTIMIZATION OF ARTIFICIAL INTELLIGENCE ALGORITHMS FOR LOW-RESOURCE/CLINICAL ENVIRONMENTS: FOCUS ON CLINICALLY-RELEVANT GLIOMA REGION DELINEATION

    Bhakti Baheti, Siddhesh Thakur, Sarthak Pati, and 7 more authors

    Neuro-Oncology, 2022

    HTML
12. Leveraging 2D deep learning ImageNet-trained models for native 3D medical image analysis

    Bhakti Baheti, Sarthak Pati, Bjoern Menze, and 1 more author

    2022

    HTML
13. Summary of Best Papers Selected for the 2023 Edition of the IMIA Yearbook, Section Cancer Informatics (CI)

    S Pati, U Baid, B Edwards, and 4 more authors

    IEEE/ACM Trans Comput Biol Bioinform, 2022

    HTML

2021

1. Accurate and Robust Alignment of Differently Stained Histologic Images Based on Greedy Diffeomorphic Registration

   Ludovic Venet, Sarthak Pati, Michael D. Feldman, and 3 more authors

   Applied Sciences, 2021

   HTML
2. The federated tumor segmentation (fets) challenge

   Sarthak Pati, Ujjwal Baid, Maximilian Zenk, and 8 more authors

   arXiv preprint arXiv:2105.05874, 2021

   HTML
3. OpenFL: An open-source framework for Federated Learning

   G Anthony Reina, Alexey Gruzdev, Patrick Foley, and 8 more authors

   arXiv preprint arXiv:2105.06413, 2021

   HTML
4. Federated Tumor Segmentation

   Spyridon Bakas, Micah Sheller, Sarthak Pati, and 8 more authors

   2021

   HTML
5. LabelFusion: Medical Image label fusion of segmentations

   Sarthak Pati, Ujjwal Baid, and Spyridon Bakas

   2021

   HTML
6. The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification

   Ujjwal Baid, Satyam Ghodasara, Suyash Mohan, and 8 more authors

   arXiv preprint arXiv:2107.02314, 2021

   HTML
7. Interactive machine learning-based multi-label segmentation of solid tumors and organs

   Dimitrios Bounias, Ashish Singh, Spyridon Bakas, and 8 more authors

   Applied Sciences, 2021

   HTML
8. Estimating glioblastoma biophysical growth parameters using deep learning regression

   Sarthak Pati, Vaibhav Sharma, Heena Aslam, and 7 more authors

   2021

   HTML
9. The Federated Tumor Segmentation (FeTS) Initiative: The First Real-World Large-Scale Data-Private Collaboration Focusing On Neuro-Oncology

   Ujjwal Baid, Sarthak Pati, Siddhesh Thakur, and 4 more authors

   Neuro-Oncology, 2021

   HTML
10. Classification of infection and ischemia in diabetic foot ulcers using vgg architectures

    Orhun Güley, Sarthak Pati, and Spyridon Bakas

    2021

    HTML
11. Optimization of deep learning based brain extraction in mri for low resource environments

    Siddhesh P Thakur, Sarthak Pati, Ravi Panchumarthy, and 6 more authors

    2021

    HTML
12. Robust, primitive, and unsupervised quality estimation for segmentation ensembles

    Florian Kofler, Ivan Ezhov, Lucas Fidon, and 8 more authors

    Frontiers in Neuroscience, 2021

    HTML

2020

1. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping

   Alex Zwanenburg, Martin Vallières, Mahmoud A Abdalah, and 8 more authors

   Radiology, 2020

   HTML
2. Cancer imaging phenomics via CaPTk: multi-institutional prediction of progression-free survival and pattern of recurrence in glioblastoma

   Anahita Fathi Kazerooni, Hamed Akbari, Gaurav Shukla, and 8 more authors

   JCO clinical cancer informatics, 2020

   HTML
3. ANHIR: automatic non-rigid histological image registration challenge

   Jiřı́ Borovec, Jan Kybic, Ignacio Arganda-Carreras, and 8 more authors

   IEEE transactions on medical imaging, 2020

   HTML
4. The cancer imaging phenomics toolkit (CaPTk): technical overview

   Sarthak Pati, Ashish Singh, Saima Rathore, and 8 more authors

   2020

   HTML
5. Standardization in quantitative imaging: a multicenter comparison of radiomic features from different software packages on digital reference objects and patient data sets

   Michael McNitt-Gray, S Napel, A Jaggi, and 8 more authors

   Tomography, 2020

   HTML
6. Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training

   Siddhesh Thakur, Jimit Doshi, Sarthak Pati, and 8 more authors

   Neuroimage, 2020

   HTML
7. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data

   Micah J Sheller, Brandon Edwards, G Anthony Reina, and 8 more authors

   Scientific reports, 2020

   HTML
8. Standardised convolutional filtering for radiomics

   Adrien Depeursinge, Vincent Andrearczyk, Philip Whybra, and 5 more authors

   arXiv preprint arXiv:2006.05470, 2020

   HTML
9. Multi-institutional noninvasive in vivo characterization of IDH, 1p/19q, and EGFRvIII in glioma using neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk)

   Saima Rathore, Suyash Mohan, Spyridon Bakas, and 8 more authors

   Neuro-oncology advances, 2020

   HTML
10. TMOD-09. GLIOBLASTOMA BIOPHYSICAL GROWTH ESTIMATION USING DEEP LEARNING-BASED REGRESSION

    Sarthak Pati, Vaibhav Sharma, Heena Aslam, and 7 more authors

    Neuro-Oncology, 2020

    HTML
11. Reproducibility analysis of multi-institutional paired expert annotations and radiomic features of the Ivy Glioblastoma Atlas Project (Ivy GAP) dataset

    Sarthak Pati, Ruchika Verma, Hamed Akbari, and 8 more authors

    Medical physics, 2020

    Abs HTML

    Purpose: The availability of radiographic magnetic resonance imaging (MRI) scans for the Ivy Glioblastoma Atlas Project (Ivy GAP) has opened up opportunities for development of radiomic markers for prognostic/predictive applications in glioblastoma (GBM). In this work, we address two critical challenges with regard to developing robust radiomic approaches: (a) the lack of availability of reliable segmentation labels for glioblastoma tumor sub-compartments (i.e., enhancing tumor, non-enhancing tumor core, peritumoral edematous/infiltrated tissue) and (b) identifying “reproducible” radiomic features that are robust to segmentation variability across readers/sites. Acquisition and validation methods: From TCIA’s Ivy GAP cohort, we obtained a paired set (n = 31) of expert annotations approved by two board-certified neuroradiologists at the Hospital of the University of Pennsylvania (UPenn) and at Case Western Reserve University (CWRU). For these studies, we performed a reproducibility study that assessed the variability in (a) segmentation labels and (b) radiomic features, between these paired annotations. The radiomic variability was assessed on a comprehensive panel of 11 700 radiomic features including intensity, volumetric, morphologic, histogram-based, and textural parameters, extracted for each of the paired sets of annotations. Our results demonstrated (a) a high level of inter-rater agreement (median value of DICE ≥0.8 for all sub-compartments), and (b) ≈24% of the extracted radiomic features being highly correlated (based on Spearman’s rank correlation coefficient) to annotation variations. These robust features largely belonged to morphology (describing shape characteristics), intensity (capturing intensity profile statistics), and COLLAGE (capturing heterogeneity in gradient orientations) feature families. Data format and usage notes: We make publicly available on TCIA’s Analysis Results Directory (https://doi.org/10.7937/9j41-7d44), the complete set of (a) multi-institutional expert annotations for the tumor sub-compartments, (b) 11 700 radiomic features, and (c) the associated reproducibility meta-analysis. Potential applications: The annotations and the associated meta-data for Ivy GAP are released with the purpose of enabling researchers toward developing image-based biomarkers for prognostic/predictive applications in GBM.

2019

1. Skull-stripping of glioblastoma MRI scans using 3D deep learning

   Siddhesh P Thakur, Jimit Doshi, Sarthak Pati, and 7 more authors

   2019

   HTML

2018

1. Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome

   Christos Davatzikos, Saima Rathore, Spyridon Bakas, and 8 more authors

   Journal of medical imaging, 2018

   HTML
2. Brain cancer imaging phenomics toolkit (brain-CaPTk): an interactive platform for quantitative analysis of glioblastoma

   Saima Rathore, Spyridon Bakas, Sarthak Pati, and 8 more authors

   2018

   HTML

2016

1. GLISTRboost: combining multimodal MRI segmentation, registration, and biophysical tumor growth modeling with gradient boosting machines for glioma segmentation

   Spyridon Bakas, Ke Zeng, Aristeidis Sotiras, and 6 more authors

   2016

   HTML
2. Segmentation of gliomas in pre-operative and post-operative multimodal magnetic resonance imaging volumes based on a hybrid generative-discriminative framework

   Ke Zeng, Spyridon Bakas, Aristeidis Sotiras, and 5 more authors

   2016

   HTML

2013

1. Accurate pose estimation using single marker single camera calibration system

   Sarthak Pati, Okan Erat, Lejing Wang, and 4 more authors

   2013

   HTML

2010

1. Locomotion classification using EMG signal

   Sarthak Pati, Deepak Joshi, and Ashutosh Mishra

   2010

   HTML