The Journal of Machine Learning for Biomedical Imaging 2025

12 papers
The 2025 edition of The Journal of Machine Learning for Biomedical Imaging comprises twelve papers focusing on medical image segmentation, federated learning, and dataset development. Research themes include the mitigation of hierarchical bias in neural networks and the use of cross-architecture knowledge distillation to prevent shortcut learning. Several studies address technical challenges in segmentation, such as volume bias and imbalanced data, through hybrid loss functions and latent trajectory alignment. Federated learning is a central topic, with papers examining robust aggregation for Byzantine resilience and methods to balance local and global fairness in multi-site medical analysis. The volume features results from several benchmarks, including the BraTS 2023 challenges for meningioma and brain metastasis segmentation, the FeTS 2024 challenge, and the LNQ 2023 challenge for lymph node quantification. Additionally, the year saw the introduction of CTSpine1K, a large-scale dataset for spinal vertebrae segmentation. Prolific authors contributing to these developments include Ivan Ezhov, Rachit Saluja, and Ujjwal Baid.

Top Research Directions

The 34 research directions with The Journal of Machine Learning for Biomedical Imaging 2025 papers, ranked by paper count, next to 2024. Share is the fraction of the edition’s papers in the direction.

#Direction20252024Share 2025Share 20242024 rank
1Amortized Optimization for Real-Time Deformable Image Registration118.3%11.1%1
2Bilateral Symmetry Priors for Medical Anomaly Detection108.3%0.0%—
3Bridging the Conditional Coverage Gap in Conformal Prediction108.3%0.0%—
4Bridging the Local-Global Fairness Gap in Federated Learning108.3%0.0%—
5Bridging the Weakly Supervised Localization Gap108.3%0.0%—
6Collaborative Learning Across Isolated Data Silos108.3%0.0%—
7Cross-Modality Generalization in Medical Artificial Intelligence108.3%0.0%—
8Delineating Ambiguous Boundaries in Low-Contrast Images108.3%0.0%—
9Diagnosing and Mitigating Bias via Feature Attribution108.3%0.0%—
10Fairness for Intersecting Demographic Subgroups108.3%0.0%—
11Generalizing Deep Networks Across Diverse Imaging Hardware108.3%0.0%—
12Hierarchical Annotation Pipelines for High Fidelity Datasets108.3%0.0%—
13Hybrid Loss Functions for Image Segmentation108.3%0.0%—
14Hybrid Supervision for Scalable Machine Learning108.3%0.0%—
15Inter Organ Spatial Constraints for Medical Image Segmentation108.3%0.0%—
16Iterative Model Assisted Labeling and Refinement108.3%0.0%—
17Knowledge Distillation via Internal Representation Alignment108.3%0.0%—
18Localizing Bias within Neural Network Architectures108.3%0.0%—
19Mitigating Metal Artifacts in Medical Imaging108.3%0.0%—
20Mitigating Overfitting in Small Sample Clinical Machine Learning108.3%0.0%—
21Model Calibration Under Distribution Shift108.3%0.0%—
22Multi Metric Evaluation for Image Segmentation108.3%0.0%—
23Overcoming Cross-Institutional Domain Shift in Medical AI118.3%11.1%17
24Overcoming Local Minima in Iterative Point Registration108.3%0.0%—
25Preserving Anatomical Structure in Image Translation108.3%0.0%—

Download all directions as CSV

Institutions

Institutions credited by The Journal of Machine Learning for Biomedical Imaging 2025 papers: a paper credits every institution named in its affiliations, once. 119 institutions share 12 credited papers.

#InstitutionPapersShare20242024 rank
1Technical University of Munich 541.7%32
2Cornell University 433.3%23
3Helmholtz Munich 433.3%19
4Massachusetts General Hospital 433.3%15
5Sage Bionetworks 433.3%147
6University of Zurich 433.3%125
7Booz Allen Hamilton (United States) 325.0%155
8Children's Hospital of Philadelphia 325.0%123
9Duke Medical Center 325.0%137
10Duke University 325.0%111
11German Cancer Research Center 325.0%149
12Harvard Medical School 325.0%140
13Indiana University Indianapolis 325.0%133
14Indiana University School of Medicine 325.0%126
15Mayo Clinic 325.0%129
16McGill University 325.0%120
17Montreal Neurological Institute and Hospital 325.0%158
18National Cancer Institute 325.0%142
19National Institutes of Health 325.0%117
20Technical University of Denmark 325.0%153
21United States Food and Drug Administration 325.0%131
22University of Pennsylvania 325.0%17
23Weill Cornell Medicine 325.0%0—
2401k05jx47 216.7%118
2505sdzff81 216.7%160
26Allen Institute for Artificial Intelligence 216.7%161
27Athinoula A. Martinos Center for Biomedical Imaging 216.7%0—
28Brigham and Women's Hospital 216.7%148
29Children's National 216.7%0—
30George Washington University 216.7%114

Download all institutions as CSV

About this data

Papers. The Journal of Machine Learning for Biomedical Imaging 2025 lists 12 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2024 use shares, since the edition went from 9 to 12 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 12 of 12 papers (100.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-21 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “The Journal of Machine Learning for Biomedical Imaging 2025”, https://lacuna.tiptreesystems.com/venue/the-journal-of-machine-learning-for-biomedical-imaging/2025.

Top Authors

AuthorPapers
bjoern menze3
Adrian V Dalca1
Carlos Fernandez-Granda1
Ce Wang1
Johannes C. Paetzold1
Kaveri A. Thakoor1
Klaus Maier-Hein1
Mert R. Sabuncu1
Reuben Dorent1
Suprosanna Shit1

Impactful Papers

Papers from The Journal of Machine Learning for Biomedical Imaging 2025 that shaped research clusters.

Influential

Papers

Title
AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge
BrainMorph: A Foundational Keypoint Model for Robust and Flexible Brain MRI Registration
BraTS-PEDs: Results of the Multi-Consortium International Pediatric Brain Tumor Segmentation Challenge 2023
ContourDiff: Unpaired Medical Image Translation with Structural Consistency
CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography
LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantification
On the Role of Calibration in Benchmarking Algorithmic Fairness for Skin Cancer Detection
Preventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI
The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods
Understanding differences in applying DETR to natural and medical images