arxiv: 2107.02314 · v2 · submitted 2021-07-05 · 💻 cs.CV

Recognition: 1 theorem link

The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification

Aanchal Agarwal, Abhishek Mahajan, Achint K. Singh, Adam E. Flanders, Ahmed W. Moawad, Aikaterini Kotrotsou, Akm Rahman, Alexandru Dusoi, Alida A. Postma, Amit K. Agarwal, Andras Jakab, Anthony F. Miller, Arash Nazeri, Asako Miyakoshi, Atin Saha, Benedikt Wiestler, Bjoern Menze, Bojan D. Petrovic, Brent D. Weinberg, Chiharu Sako, Chintan Shah, Christie Lincoln, Christopher Hess, Christos Davatzikos, Cristina H. Besada, Daniel D. Do-Dai, Daniel Marcus, David Joyner, Elka Miller, Errol Colak, Evan Calabrese, Eyal Lotan, Fanny E. Moron, Felipe C. Kitamura, Gagandeep Choudhary, Gloria J. Guzman Perez-Carrillo, Greg Zaharchuk, Hassan Fathallah-Shaykh, Ichiro Ikuta, Jamal J. Derakhshan, James Eddy, James R. Mason, Javier Villanueva-Meyer, Jaya Nath, Jayashree Kalpathy-Cramer, Jeffrey D. Rudie, Jiaxin Zheng, Johanna Ortiz Jimenez, John B. Freymann, John L. Go, John Mongan, Juan E. Small, Julia Elliott, Justin S. Kirby, Kerem Ozturk, Keyvan Farahani, Laurent Letourneau-Guillon, Loizos Siakallis, Lubdha M. Shah, Luciano Farage, Luciano M. Prevedello, Luiz Otavio Coelho, Manal Nicolas-Jilwan, Manas Sharma, Marc-Andre Weber, Mariana C. Diogo, Mariana Sanchez-Montano, Mark C. Oswood, Michael Iv, Michel Bilello, Mikhail Milchenko, Milos M. Cekic, Mohiuddin Hadi, Neetu Soni, Olivia McDonnell, Onur Simsek, Priscila Crivellaro, Richard Silbergleit, Rivka R. Colen, Robert J. Young, Robert Y. Shih, Roland Wiest, Rong Chai, Russell T. Shinohara, Salil Soman, Sarthak Pati, Satyam Ghodasara, Soonmee Cha, Spyridon Bakas, Suyash Mohan, Sword C. Cambron, Thomas Schaffter, Thomas Yu, Timothy Bergquist, Ujjwal Baid, Vahe M. Zohrabian, Varun Sethi, Virginia B. Hill, Volodymyr Statsevych, Walter Reade, Xuan V. Nguyen, Yingming Chen, Yulia Bronstein

Authors on Pith no claims yet

Pith reviewed 2026-05-14 21:25 UTC · model grok-4.3

classification 💻 cs.CV

keywords brain tumor segmentationMGMT classificationBraTS challengempMRIgliomaradiogenomicsbenchmark datasetalgorithm evaluation

0 comments

The pith

BraTS 2021 supplies a standardized benchmark of 2040 multi-institutional mpMRI cases for evaluating algorithms on glioma sub-region segmentation and MGMT methylation classification.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents the tenth edition of the BraTS challenge, now jointly run by RSNA, ASNR, and MICCAI, which supplies a large curated collection of pre-operative multi-parametric MRI scans from 2040 patients. Its two explicit tasks are to segment the histologically distinct tumor compartments and to predict the tumor's MGMT promoter methylation status directly from imaging. These tasks address core clinical needs in neuro-oncology because gliomas vary widely in aggressiveness and treatment response, and non-invasive imaging markers could reduce reliance on biopsy. The evaluation is split across the Synapse platform for segmentation and Kaggle for classification, with cash prizes for the top entries.

Core claim

The paper establishes a common benchmarking venue that supplies well-curated multi-institutional mpMRI data from 2040 patients so that algorithms can be compared on identical tasks of tumor sub-region segmentation and MGMT promoter methylation classification.

What carries the argument

The curated multi-parametric MRI dataset annotated for tumor sub-regions and MGMT methylation status, hosted for public algorithm evaluation on Synapse and Kaggle.

If this is right

Segmentation algorithms can be ranked on a common, large-scale test set for glioma compartmentalization.
Imaging-based MGMT classifiers can be compared without the need for separate biopsy-derived labels.
Top-performing methods receive public visibility and monetary incentives to refine their approaches.
Future challenges can build on the same data distribution for additional molecular targets.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Widespread adoption of the top segmentation models could shorten pre-operative planning time for neurosurgeons.
The radiogenomic task may encourage development of imaging biomarkers that generalize across scanner vendors.
Similar benchmark structures could be applied to other CNS tumors or to longitudinal treatment-response monitoring.

Load-bearing premise

The tumor sub-region boundaries and MGMT labels have been annotated consistently and accurately across all 2040 cases from multiple institutions.

What would settle it

Re-annotation of a random subset by independent neuroradiologists showing substantial disagreement on tumor boundaries or MGMT status would undermine the reliability of the benchmark rankings.

read the original abstract

The BraTS 2021 challenge celebrates its 10th anniversary and is jointly organized by the Radiological Society of North America (RSNA), the American Society of Neuroradiology (ASNR), and the Medical Image Computing and Computer Assisted Interventions (MICCAI) society. Since its inception, BraTS has been focusing on being a common benchmarking venue for brain glioma segmentation algorithms, with well-curated multi-institutional multi-parametric magnetic resonance imaging (mpMRI) data. Gliomas are the most common primary malignancies of the central nervous system, with varying degrees of aggressiveness and prognosis. The RSNA-ASNR-MICCAI BraTS 2021 challenge targets the evaluation of computational algorithms assessing the same tumor compartmentalization, as well as the underlying tumor's molecular characterization, in pre-operative baseline mpMRI data from 2,040 patients. Specifically, the two tasks that BraTS 2021 focuses on are: a) the segmentation of the histologically distinct brain tumor sub-regions, and b) the classification of the tumor's O[6]-methylguanine-DNA methyltransferase (MGMT) promoter methylation status. The performance evaluation of all participating algorithms in BraTS 2021 will be conducted through the Sage Bionetworks Synapse platform (Task 1) and Kaggle (Task 2), concluding in distributing to the top ranked participants monetary awards of $60,000 collectively.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

BraTS 2021 is a scaled-up challenge announcement that organizes 2040 cases for segmentation and MGMT classification but adds no new methods or findings.

read the letter

This paper announces the tenth BraTS challenge with a dataset of 2040 pre-operative mpMRI cases across institutions. The two tasks are segmenting tumor sub-regions and classifying MGMT promoter methylation status, with evaluation on Synapse and Kaggle plus cash prizes for top entries. It does a practical job of documenting the data scale and task rules in one place, which can help standardize how groups test algorithms on glioma imaging. The multi-institutional collection and dual-task setup represent steady growth from prior years. The main gap is the missing detail on annotation. The text calls the data well-curated but gives no numbers on inter-rater agreement, how labels were reconciled across sites, or exclusion criteria. For a benchmark paper that will be used to rank algorithms, that information matters for judging whether comparisons will be fair. Readers who work on brain tumor segmentation or radiogenomics will find the task definitions and data volume useful when deciding whether to enter the challenge or download the data later. I would send this to peer review. These descriptive benchmark papers still serve the field by locking down evaluation protocols, and the size here is large enough to justify referee time even without novel technical claims.

Referee Report

2 major / 0 minor

Summary. The manuscript announces the RSNA-ASNR-MICCAI BraTS 2021 challenge, which provides a benchmark for segmenting histologically distinct brain tumor sub-regions and classifying MGMT promoter methylation status from pre-operative multi-parametric MRI scans of 2,040 patients. It specifies the two tasks, the multi-institutional data scale, and the evaluation platforms (Sage Bionetworks Synapse for Task 1 and Kaggle for Task 2), with monetary awards for top performers.

Significance. If the underlying annotations prove reliable, the release of this large, multi-institutional dataset would establish a standardized, reproducible benchmark for glioma segmentation and radiogenomic classification, enabling fair algorithmic comparisons and potentially accelerating clinical translation in neuro-oncology.

major comments (2)

Abstract: the statement that the data are 'well-curated' is not accompanied by any description of annotation protocols, inter-rater variability metrics, exclusion criteria, or quality-control procedures for the 2,040 cases; these details are load-bearing for claims of benchmark fairness and reproducibility.
Abstract (Task 2 description): no information is given on how MGMT promoter methylation status was determined (e.g., assay type, threshold, or central review), leaving the ground-truth reliability for the classification task unverified.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the positive summary and recommendation of minor revision. We address each major comment below and have updated the abstract to include appropriate references and brief clarifications.

read point-by-point responses

Referee: Abstract: the statement that the data are 'well-curated' is not accompanied by any description of annotation protocols, inter-rater variability metrics, exclusion criteria, or quality-control procedures for the 2,040 cases; these details are load-bearing for claims of benchmark fairness and reproducibility.

Authors: We agree that the abstract would be strengthened by explicit pointers to the curation details. The annotation and quality-control procedures follow the standardized BraTS protocol established in prior iterations and are documented in full in the dataset release notes hosted on the Synapse platform (including multi-expert annotation, consensus review, and exclusion criteria for incomplete or artifact-laden scans). We have revised the abstract to reference these resources and added a concise summary sentence. revision: yes
Referee: Abstract (Task 2 description): no information is given on how MGMT promoter methylation status was determined (e.g., assay type, threshold, or central review), leaving the ground-truth reliability for the classification task unverified.

Authors: We accept this observation. The MGMT labels originate from the contributing institutions' clinical records and are described in the dataset metadata on the Kaggle platform. We have revised the abstract to direct readers to that documentation for assay specifics and any institutional thresholds applied. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The manuscript is a purely descriptive challenge announcement that defines the BraTS 2021 tasks (tumor sub-region segmentation and MGMT promoter methylation classification), the 2,040-patient multi-institutional mpMRI dataset, evaluation platforms, and award structure. No derivations, equations, predictions, fitted parameters, or load-bearing claims are advanced; the text only specifies organizational and logistical details. Consequently there are no steps that reduce by construction to the paper's own inputs, and the document is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical derivations or empirical claims are made; the document is an announcement of a data challenge.

pith-pipeline@v0.9.0 · 6103 in / 1108 out tokens · 34846 ms · 2026-05-14T21:25:10.247147+00:00 · methodology

discussion (0)

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark
cs.CV 2026-04 conditional novelty 9.0

DyABD is the first benchmark dataset for abdominal muscle segmentation in dynamic MRIs featuring exercise-induced anatomical changes and pre/post-surgery scans, where existing models achieve an average Dice score of 0.82.
SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
cs.CV 2026-05 unverdicted novelty 7.0

SEMIR replaces dense voxel computation with a learned topology-preserving graph minor that supports exact decoding and GNN-based inference for small-structure segmentation in large medical images.
AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
cs.CV 2026-05 conditional novelty 7.0

AnomalyClaw turns single-step VLM anomaly judgments into a multi-round tool-grounded refutation process, delivering consistent macro-AUROC gains of 3.5-7.9 percentage points over direct inference across 12 cross-domai...
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
cs.CV 2026-04 unverdicted novelty 7.0

Introduces VietPET-RoI dataset with fine-grained RoI annotations for Vietnamese 3D PET/CT and HiRRA graph framework that improves report generation by modeling region dependencies, claiming large gains over prior models.
Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis
cs.CV 2026-04 unverdicted novelty 7.0

Agentic LLMs autonomously execute complex neuro-radiological workflows like glioma segmentation and multi-timepoint response assessment by directing off-the-shelf tools, without any model training.
Cross Modality Image Translation In Medical Imaging Using Generative Frameworks
cs.CV 2026-05 accept novelty 6.0

A uniform benchmark across 77 experiments finds SRGAN superior to latent diffusion models for 3D medical image translation, with synthetic volumes indistinguishable from real ones in a 17-physician Turing test.
LARGO: Low-Rank Hypernetwork for Handling Missing Modalities
cs.CV 2026-05 unverdicted novelty 6.0

LARGO uses a low-rank hypernetwork with CP decomposition to unify 2^N-1 missing-modality models into one, ranking first in 47 of 52 configurations on BraTS and ISLES with small Dice gains over baselines.
BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning
cs.LG 2026-04 unverdicted novelty 6.0

BrainDINO delivers a single self-supervised brain MRI representation that generalizes to tumor segmentation, disease classification, brain age estimation, and other tasks without volumetric pretraining or full fine-tuning.
Diffusion Model as a Generalist Segmentation Learner
cs.CV 2026-04 unverdicted novelty 6.0

DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation
cs.CV 2026-04 unverdicted novelty 6.0

VS-DDPM accelerates 3D diffusion models for medical modality translation, reaching SOTA Dice scores of 0.80-0.88 and SSIM 0.95 on missing MRI synthesis in BraTS2025 while remaining competitive on tumor removal and sCT tasks.
WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis
cs.CV 2026-04 unverdicted novelty 6.0

WFM achieves near-diffusion quality for all four BraTS MRI modalities with one 82M model in 1-2 steps by flowing from the mean of conditioning modalities in wavelet space, running 250-1000x faster.
MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
cs.CV 2026-04 unverdicted novelty 6.0

MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while impr...
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
cs.CV 2026-04 accept novelty 6.0

Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details a...
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
cs.CV 2026-04 unverdicted novelty 6.0

LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation
cs.CV 2026-04 unverdicted novelty 6.0

GCNV-Net achieves state-of-the-art accuracy on multiple 3D medical segmentation benchmarks while cutting FLOPs by 56% and inference latency by 68% through dynamic nonvoid voxelization and geometric attention.
Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks
cs.CV 2026-04 unverdicted novelty 6.0

LLaBIT is a single instruction-finetuned LLM that performs report generation, VQA, segmentation, and translation on brain MRI images while outperforming task-specific models.
Fairboard: a quantitative framework for equity assessment of healthcare models
cs.LG 2026-03 unverdicted novelty 6.0

Patient identity and clinical features predict brain tumor segmentation accuracy more strongly than model choice, with localized spatial biases consistent across models and no formal fairness guarantees in any.
Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection
cs.CV 2026-03 unverdicted novelty 6.0

A single model trained on one normal sample per dataset from nine heterogeneous medical sources achieves state-of-the-art anomaly detection in one-shot universal, full-shot universal, one-shot specialized, and full-sh...
SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
cs.CV 2026-05 unverdicted novelty 5.0

SynerMedGen introduces generation-aligned understanding tasks and a two-stage training strategy that enables strong zero-shot medical image synthesis performance and outperforms specialized models when generation trai...
VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation
cs.CV 2026-04 unverdicted novelty 5.0

VS-DDPM accelerates 3D diffusion-based medical image translation, achieving SOTA Dice scores of 0.80-0.88 and SSIM 0.95 on missing MRI synthesis while remaining competitive on other modality tasks.
RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation
cs.CV 2026-04 unverdicted novelty 5.0

RF-HiT uses rectified flow and a multi-scale hierarchical transformer to reach 91.27% Dice on ACDC and 87.40% on BraTS 2021 with only 10.14 GFLOPs, 13.6M parameters, and three inference steps.
Improved Anomaly Detection in Medical Images via Mean Shift Density Enhancement
cs.CV 2026-04 unverdicted novelty 5.0

A new Mean Shift Density Enhancement procedure applied to self-supervised embeddings yields state-of-the-art anomaly detection AUC and average precision on seven medical imaging datasets.
CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation
cs.CV 2026-04 unverdicted novelty 4.0

CoRE aligns image tokens to a hierarchical concept library to simulate clinical reasoning for expert routing and demand-based growth in continual brain lesion segmentation, achieving SOTA on 12 tasks.

Reference graph

Works this paper leans on

47 extracted references · 47 canonical work pages · cited by 22 Pith papers · 1 internal anchor

[1]

cimpact-now: a practical summary of diagnostic points from round 1 updates,

D. N. Louis, D. W. Ellison, D. J. Brat, K. Aldape, D. Capper, C. Hawkins, W. Paulus, A. Perry, G. Reifenberger, D. Figarella-Branger, et al., “cimpact-now: a practical summary of diagnostic points from round 1 updates,” Brain Pathology, vol. 29, no. 4, pp. 469–472, 2019

work page 2019
[2]

cimpact-now update 1: not otherwise speciﬁed (nos) and not elsewhere classiﬁed (nec),

D. N. Louis, P. Wesseling, W. Paulus, C. Giannini, T. T. Batchelor, J. G. Cairn- cross, D. Capper, D. Figarella-Branger, M. B. Lopes, W. Wick,et al., “cimpact-now update 1: not otherwise speciﬁed (nos) and not elsewhere classiﬁed (nec),” Acta neuropathologica, vol. 135, no. 3, pp. 481–484, 2018

work page 2018
[3]

cimpact-now update 2: diagnostic clariﬁcations for diﬀuse midline glioma, h3 k27m-mutant and diﬀuse astrocytoma/anaplastic astrocytoma, idh-mutant,

D. N. Louis, C. Giannini, D. Capper, W. Paulus, D. Figarella-Branger, M. B. Lopes, T. T. Batchelor, J. G. Cairncross, M. van den Bent, W. Wick, et al., “cimpact-now update 2: diagnostic clariﬁcations for diﬀuse midline glioma, h3 k27m-mutant and diﬀuse astrocytoma/anaplastic astrocytoma, idh-mutant,” Acta neuropathologica, vol. 135, no. 4, pp. 639–642, 2018

work page 2018
[4]

cimpact- now update 3: recommended diagnostic criteria for “diﬀuse astrocytic glioma, idh-wildtype, with molecular features of glioblastoma, who grade iv

D. J. Brat, K. Aldape, H. Colman, E. C. Holland, D. N. Louis, R. B. Jenkins, B. Kleinschmidt-DeMasters, A. Perry, G. Reifenberger, R. Stupp, et al., “cimpact- now update 3: recommended diagnostic criteria for “diﬀuse astrocytic glioma, idh-wildtype, with molecular features of glioblastoma, who grade iv”,” Acta neu- ropathologica, vol. 136, no. 5, pp. 805–...

work page 2018
[5]

cimpact-now update 4: diﬀuse gliomas characterized by myb, mybl1, or fgfr1 alterations or braf v600e mutation,

D. W. Ellison, C. Hawkins, D. T. Jones, A. Onar-Thomas, S. M. Pﬁster, G. Reifen- berger, and D. N. Louis, “cimpact-now update 4: diﬀuse gliomas characterized by myb, mybl1, or fgfr1 alterations or braf v600e mutation,” Acta neuropathologica, vol. 137, no. 4, pp. 683–687, 2019

work page 2019
[6]

cimpact-now update 5: recommended grading criteria and terminologies for idh- mutant astrocytomas,

D. J. Brat, K. Aldape, H. Colman, D. Figrarella-Branger, G. N. Fuller, C. Gian- nini, E. C. Holland, R. B. Jenkins, B. Kleinschmidt-DeMasters, T. Komori, et al., “cimpact-now update 5: recommended grading criteria and terminologies for idh- mutant astrocytomas,” Acta neuropathologica, vol. 139, no. 3, pp. 603–608, 2020

work page 2020
[7]

cimpact-now update 6: new entity and diagnostic principle recommendations of the cimpact-utrecht meeting on future cns tumor classiﬁcation and grading,

D. N. Louis, P. Wesseling, K. Aldape, D. J. Brat, D. Capper, I. A. Cree, C. Eber- hart, D. Figarella-Branger, M. Fouladi, G. N. Fuller, et al., “cimpact-now update 6: new entity and diagnostic principle recommendations of the cimpact-utrecht meeting on future cns tumor classiﬁcation and grading,” 2020

work page 2020
[8]

Bakas, G

S. Bakas, G. Shukla, H. Akbari, G. Erus, A. Sotiras, S. Rathore, C. Sako, S. Min Ha, M. Rozycki, R. T. Shinohara, M. Bilello, and C. Davatzikos, “Overall survival pre- diction in glioblastoma patients using structural magnetic resonance imaging (mri): advanced radiomic features may compensate for lack of advanced mri modalities,” Journal of medical imagin...

work page 2020
[9]

The 2016 world health organization classiﬁcation of tumors of the central nervous sys- tem: a summary,

D. N. Louis, A. Perry, G. Reifenberger, A. Von Deimling, D. Figarella-Branger, W. K. Cavenee, H. Ohgaki, O. D. Wiestler, P. Kleihues, and D. W. Ellison, “The 2016 world health organization classiﬁcation of tumors of the central nervous sys- tem: a summary,” Acta neuropathologica, vol. 131, no. 6, pp. 803–820, 2016

work page 2016
[10]

MGMT promoter methylation is predictive of response to radiotherapy and prognostic in the absence of adjuvant alkylating chemotherapy for glioblastoma,

A. L. Rivera, C. E. Pelloski, M. R. Gilbert, H. Colman, C. De La Cruz, E. P. Sul- man, B. N. Bekele, and K. D. Aldape, “MGMT promoter methylation is predictive of response to radiotherapy and prognostic in the absence of adjuvant alkylating chemotherapy for glioblastoma,” Neuro-Oncology, vol. 12, pp. 116–121, 12 2009. The RSNA-ASNR-MICCAI BraTS 2021 Benchmark 17

work page 2009
[11]

The multimodal brain tumor image segmentation benchmark (brats),

B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, Y. Burren, N. Porz, J. Slotboom, R. Wiest, et al., “The multimodal brain tumor image segmentation benchmark (brats),” IEEE transactions on medical imaging , vol. 34, no. 10, pp. 1993–2024, 2014

work page 1993
[12]

Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features,

S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. Farahani, and C. Davatzikos, “Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features,” Scientiﬁc data, vol. 4, no. 1, pp. 1–13, 2017

work page 2017
[13]

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempﬂer, A. Crimi, R. T. Shinohara, C. Berger, S. M. Ha, M. Rozycki, et al. , “Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall sur- vival prediction in the brats challenge,” arXiv preprint arXiv:1811.02629 , 2018

work page internal anchor Pith review Pith/arXiv arXiv 2018
[14]

Segmentation labels for the pre-operative scans of the tcga-gbm collection.,

S. Bakas, H. Akbari, A. Sotiras, et al., “Segmentation labels for the pre-operative scans of the tcga-gbm collection.,” The cancer imaging archive , 2017

work page 2017
[15]

Segmentation labels and radiomic features for the pre-operative scans of the tcga-lgg collection,

S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. Kirby, J. Freymann, K. Farahani, and C. Davatzikos, “Segmentation labels and radiomic features for the pre-operative scans of the tcga-lgg collection,” The cancer imaging archive , vol. 286, 2017

work page 2017
[16]

The university of california san francisco preop- erative diﬀuse glioma (ucsf-pdgm) mri dataset,

E. Calabrese, J. Villanueva-Meyer, J. Rudie, A. Rauschecker, U. Baid, S. Bakas, J. Mongan, C. Hess, and S. Cha, “The university of california san francisco preop- erative diﬀuse glioma (ucsf-pdgm) mri dataset,” 2021

work page 2021
[17]

A (sort of) new image data format standard: Nifti-1: We 150,

R. Cox, J. Ashburner, H. Breman, K. Fissell, C. Haselgrove, C. Holmes, J. Lan- caster, D. Rex, S. Smith, J. Woodward, et al., “A (sort of) new image data format standard: Nifti-1: We 150,” Neuroimage, vol. 22, 2004

work page 2004
[18]

The sri24 multichan- nel atlas of normal adult human brain structure,

T. Rohlﬁng, N. M. Zahr, E. V. Sullivan, and A. Pfeﬀerbaum, “The sri24 multichan- nel atlas of normal adult human brain structure,” Human brain mapping , vol. 31, no. 5, pp. 798–819, 2010

work page 2010
[19]

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

C. Davatzikos, S. Rathore, S. Bakas, S. Pati, M. Bergman, R. Kalarot, P. Sridharan, A. Gastounioti, N. Jahani, E. Cohen, et al. , “Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome,” Journal of medical imaging , vol. 5, no. 1, p. 011018, 2018

work page 2018
[20]

Brain cancer imaging phenomics toolkit (brain-captk): an interactive platform for quantitative analysis of glioblastoma,

S. Rathore, S. Bakas, S. Pati, H. Akbari, R. Kalarot, P. Sridharan, M. Rozycki, M. Bergman, B. Tunc, R. Verma, et al., “Brain cancer imaging phenomics toolkit (brain-captk): an interactive platform for quantitative analysis of glioblastoma,” in International MICCAI Brainlesion Workshop , pp. 133–145, Springer, 2017

work page 2017
[21]

The cancer imaging phenomics toolkit (captk): Technical overview,

S. Pati, A. Singh, S. Rathore, A. Gastounioti, M. Bergman, P. Ngo, S. M. Ha, D. Bounias, J. Minock, G. Murphy, et al., “The cancer imaging phenomics toolkit (captk): Technical overview,” in International MICCAI Brainlesion Workshop , pp. 380–394, Springer, 2019

work page 2019
[22]

Identiﬁcation of anonymous mri research participants with face- recognition software,

C. G. Schwarz, W. K. Kremers, T. M. Therneau, R. R. Sharp, J. L. Gunter, P. Vemuri, A. Arani, A. J. Spychalla, K. Kantarci, D. S. Knopman, R. C. Petersen, and C. R. Jack, “Identiﬁcation of anonymous mri research participants with face- recognition software,” New England Journal of Medicine, vol. 381, no. 17, pp. 1684– 1686, 2019. PMID: 31644852

work page 2019
[23]

Identiﬁcation from mri with face-recognition software,

C. G. Schwarz, W. K. Kremers, T. M. Therneau, R. R. Sharp, J. L. Gunter, P. Vemuri, A. Arani, A. J. Spychalla, K. Kantarci, D. S. Knopman, R. C. Petersen, and C. R. Jack, “Identiﬁcation from mri with face-recognition software,” New England Journal of Medicine , vol. 382, no. 5, pp. 489–490, 2020. PMID: 31995706

work page 2020
[24]

Thakur, J

S. Thakur, J. Doshi, S. Pati, S. Rathore, C. Sako, M. Bilello, S. M. Ha, G. Shukla, A. Flanders, A. Kotrotsou, et al., “Brain extraction on mri scans in presence of dif- 18 Baid et al. fuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training,” NeuroImage, vol. 220, p. 117081, 2020

work page 2020
[25]

Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation,

S. K. Warﬁeld, K. H. Zou, and W. M. Wells, “Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation,” IEEE transactions on medical imaging , vol. 23, no. 7, pp. 903–921, 2004

work page 2004
[26]

nnu-net: a self-conﬁguring method for deep learning-based biomedical image segmentation,

F. Isensee, P. F. Jaeger, S. A. Kohl, J. Petersen, and K. H. Maier-Hein, “nnu-net: a self-conﬁguring method for deep learning-based biomedical image segmentation,” Nature Methods, pp. 1–9, 2020

work page 2020
[27]

Ensembles of densely-connected cnns with label-uncertainty for brain tumor segmentation,

R. McKinley, R. Meier, and R. Wiest, “Ensembles of densely-connected cnns with label-uncertainty for brain tumor segmentation,” in International MICCAI Brain- lesion Workshop, pp. 456–465, Springer, 2018

work page 2018
[28]

Eﬃcient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation,

K. Kamnitsas, C. Ledig, V. F. Newcombe, J. P. Simpson, A. D. Kane, D. K. Menon, D. Rueckert, and B. Glocker, “Eﬃcient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation,” Medical image analysis, vol. 36, pp. 61–78, 2017

work page 2017
[29]

Itk: enabling repro- ducible research and open science,

M. McCormick, X. Liu, L. Ibanez, J. Jomier, and C. Marion, “Itk: enabling repro- ducible research and open science,” Frontiers in Neuroinformatics , vol. 8, p. 13, 2014

work page 2014
[30]

The cancer imaging archive (tcia): main- taining and operating a public information repository,

K. Clark, B. Vendt, K. Smith, J. Freymann, J. Kirby, P. Koppel, S. Moore, S. Phillips, D. Maﬃtt, M. Pringle, et al., “The cancer imaging archive (tcia): main- taining and operating a public information repository,” Journal of digital imaging , vol. 26, no. 6, pp. 1045–1057, 2013

work page 2013
[31]

Radiology data from the cancer genome atlas glioblastoma multiforme [tcga-gbm] collection,

L. Scarpace, L. Mikkelsen, T. Cha, S. Rao, S. Tekchandani, S. Gutman, and D. Pierce, “Radiology data from the cancer genome atlas glioblastoma multiforme [tcga-gbm] collection,” The Cancer Imaging Archive , vol. 11, no. 4, p. 1, 2016

work page 2016
[32]

Radiology data from the cancer genome atlas low grade glioma [tcga-lgg] collection,

N. Pedano, A. E. Flanders, L. Scarpace, T. Mikkelsen, J. M. Eschbacher, B. Her- mes, and Q. Ostrom, “Radiology data from the cancer genome atlas low grade glioma [tcga-lgg] collection,” Cancer Imaging Arch, vol. 2, 2016

work page 2016
[33]

An anatomic transcrip- tional atlas of human glioblastoma,

R. B. Puchalski, N. Shah, J. Miller, R. Dalley, S. R. Nomura, J.-G. Yoon, K. A. Smith, M. Lankerovich, D. Bertagnolli, K. Bickley, et al., “An anatomic transcrip- tional atlas of human glioblastoma,” Science, vol. 360, no. 6389, pp. 660–663, 2018

work page 2018
[34]

Data from ivy gap,

N. Shah, X. Feng, M. Lankerovich, R. B. Puchalski, and B. Keogh, “Data from ivy gap,” The Cancer Imaging Archive , vol. 10, p. K9, 2016

work page 2016
[35]

Radiology data from the clinical proteomic tumor analysis consortium glioblastoma multiforme [cptac-gbm] collection,

TCIA, “Radiology data from the clinical proteomic tumor analysis consortium glioblastoma multiforme [cptac-gbm] collection,” The Cancer Imaging Archive , vol. 10, p. K9, 2016

work page 2016
[36]

Proteogenomic and metabolomic characterization of human glioblastoma,

L.-B. Wang, A. Karpova, M. A. Gritsenko, J. E. Kyle, S. Cao, Y. Li, D. Rykunov, A. Colaprico, J. H. Rothstein, R. Hong, et al., “Proteogenomic and metabolomic characterization of human glioblastoma,” Cancer cell, vol. 39, no. 4, pp. 509–528, 2021

work page 2021
[37]

Data from acrin-fmiso-brain,

P. Kinahan, M. Muzi, B. Bialecki, and L. Coombs, “Data from acrin-fmiso-brain,” 2018

work page 2018
[38]

Acrin 6684: assessment of tumor hypoxia in newly diagnosed glioblastoma using 18f-fmiso pet and mri,

E. R. Gerstner, Z. Zhang, J. R. Fink, M. Muzi, L. Hanna, E. Greco, M. Prah, K. M. Schmainda, A. Mintz, L. Kostakoglu, et al. , “Acrin 6684: assessment of tumor hypoxia in newly diagnosed glioblastoma using 18f-fmiso pet and mri,” Clinical Cancer Research, vol. 22, no. 20, pp. 5079–5086, 2016

work page 2016
[39]

Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data,

M. J. Sheller, B. Edwards, G. A. Reina, J. Martin, S. Pati, A. Kotrotsou, M. Milchenko, W. Xu, D. Marcus, R. R. Colen, et al. , “Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data,” Scientiﬁc reports, vol. 10, no. 1, pp. 1–12, 2020. The RSNA-ASNR-MICCAI BraTS 2021 Benchmark 19

work page 2020
[40]

User-guided 3D active contour segmentation of anatomical struc- tures: Signiﬁcantly improved eﬃciency and reliability,

P. A. Yushkevich, J. Piven, H. Cody Hazlett, R. Gimpel Smith, S. Ho, J. C. Gee, and G. Gerig, “User-guided 3D active contour segmentation of anatomical struc- tures: Signiﬁcantly improved eﬃciency and reliability,” Neuroimage, vol. 31, no. 3, pp. 1116–1128, 2006

work page 2006
[41]

Multi-disease segmentation of gliomas and white mat- ter hyperintensities in the brats data using a 3d convolutional neural network,

J. D. Rudie, D. A. Weiss, R. Saluja, A. M. Rauschecker, J. Wang, L. Sugrue, S. Bakas, and J. B. Colby, “Multi-disease segmentation of gliomas and white mat- ter hyperintensities in the brats data using a 3d convolutional neural network,” Frontiers in Computational Neuroscience, vol. 13, p. 84, 2019

work page 2019
[42]

Isles 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral mri,

O. Maier, B. H. Menze, J. von der Gablentz, L. H¨ ani, M. P. Heinrich, M. Liebrand, S. Winzeck, A. Basit, P. Bentley, L. Chen, et al. , “Isles 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral mri,” Med- ical image analysis , vol. 35, pp. 250–269, 2017

work page 2015
[43]

Hipaa regulations — a new era of medical-record privacy?,

G. J. Annas, “Hipaa regulations — a new era of medical-record privacy?,” New England Journal of Medicine , vol. 348, no. 15, pp. 1486–1490, 2003. PMID: 12686707

work page 2003
[44]

The eu general data protection regulation (gdpr),

P. Voigt and A. Von dem Bussche, “The eu general data protection regulation (gdpr),” A Practical Guide, 1st Ed., Cham: Springer International Publishing , vol. 10, p. 3152676, 2017

work page 2017
[45]

The future of digital health with federated learning,

N. Rieke, J. Hancox, W. Li, F. Milletari, H. R. Roth, S. Albarqouni, S. Bakas, M. N. Galtier, B. A. Landman, K. Maier-Hein, et al., “The future of digital health with federated learning,” NPJ digital medicine , vol. 3, no. 1, pp. 1–7, 2020

work page 2020
[46]

The federated tumor segmentation (fets) challenge,

S. Pati, U. Baid, M. Zenk, B. Edwards, M. Sheller, G. A. Reina, P. Foley, A. Gruzdev, J. Martin, S. Albarqouni, et al., “The federated tumor segmentation (fets) challenge,” arXiv preprint arXiv:2105.05874 , 2021

work page arXiv 2021
[47]

Gandlf: A generally nuanced deep learning framework for scalable end-to-end clinical workﬂows in medical imaging,

S. Pati, S. P. Thakur, M. Bhalerao, U. Baid, C. Grenko, B. Edwards, M. Sheller, J. Agraz, B. Baheti, V. Bashyam,et al., “Gandlf: A generally nuanced deep learning framework for scalable end-to-end clinical workﬂows in medical imaging,” arXiv preprint arXiv:2103.01006, 2021

work page arXiv 2021