Journal of Medical Imaging 2025

16 papers
The 2025 edition of the Journal of Medical Imaging features 14 papers focused on automated segmentation and diagnostic differentiation across diverse clinical domains. A primary research trend involves the optimization of foundation models, such as Segment Anything 2 (SA2), for specialized tasks like depth-aware brain tumor segmentation in sub-Saharan populations. Research also emphasizes weakly supervised learning, including scribble-supervised cardiac tissue segmentation and the differentiation of primary central nervous system lymphoma from glioblastoma using multi-site whole slide images. Additional studies provide comparative analyses of deep learning frameworks like nnU-Net and Auto3Dseg for breast tissue segmentation, alongside the development of a multi-contrast computed tomography atlas for the healthy pancreas. The volume also explores semantic and instance segmentation for Mpox lesion counting. Prolific contributors to this year's edition include Bennett Allan Landman, Lucas W. Remedios, and Yuankai Huo. Collectively, these works demonstrate a focus on adapting segmentation models to varied demographic contexts and utilizing temporal or contrastive information to improve diagnostic accuracy.

Top Research Directions

The 21 research directions with Journal of Medical 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
1Cross Dataset Validation for Robust Model Generalization2112.5%4.8%6
2Addressing Demographic Representation Gaps in Clinical AI106.2%0.0%—
3Architectural Heterogeneity in Model Ensembles106.2%0.0%—
4Architectural Strategies for Multimodal Data Fusion106.2%0.0%—
5Decoupling Visceral Adiposity from Total Body Mass106.2%0.0%—
6Deep Learning on Large Scale Histopathology Datasets106.2%0.0%—
7Delineating Ambiguous Boundaries in Low-Contrast Images106.2%0.0%—
8Explainable Machine Learning for Clinical Trust106.2%0.0%—
9Harmonizing Multi Site Neuroimaging Datasets126.2%9.5%1
10Hierarchical Spatial Alignment for Deformable Image Registration106.2%0.0%—
11High-Accuracy Deformable Image Registration106.2%0.0%—
12Instance Segmentation for Densely Packed and Overlapping Objects106.2%0.0%—
13Model Ensembling for Robustness and Generalization106.2%0.0%—
14No Reference Image Quality Assessment106.2%0.0%—
15Normalizing Intensity and Spatial Distributions in Medical Imaging106.2%0.0%—
16Self-Configuring Frameworks for Medical Image Segmentation106.2%0.0%—
17Synergizing Convolutions and Transformers for Visual Representation106.2%0.0%—
18The Decoupling of Muscle Quantity and Quality106.2%0.0%—
19The Hidden Pitfalls of Single Institution Datasets106.2%0.0%—
20Transferring Natural Image Representations to Specialized Medical Domains116.2%4.8%31
21Unified Representations via Multimodal Feature Fusion106.2%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Journal of Medical Imaging 2025 papers: a paper credits every institution named in its affiliations, once. 19 institutions share 8 credited papers.

#InstitutionPapersShare20242024 rank
1Vanderbilt University 675.0%61
2Vanderbilt University Medical Center 562.5%43
301c9rqr26 225.0%0—
4DELL (United States) 225.0%0—
5Johns Hopkins University 225.0%42
6The University of Texas at Austin 225.0%0—
7006zn3t30 112.5%0—
803qyfje32 112.5%0—
904m219c69 112.5%0—
10Champalimaud Foundation 112.5%0—
11Frederick National Laboratory for Cancer Research 112.5%0—
12Instituto Superior Técnico 112.5%0—
13National Institutes of Health 112.5%24
14Nvidia (United States) 112.5%121
15United States Department of Veterans Affairs 112.5%0—
16University of Kentucky 112.5%0—
17University of Latvia 112.5%0—
18University of Lisbon 112.5%0—
19University of Maryland School of Medicine 112.5%0—

Download all institutions as CSV

About this data

Papers. Journal of Medical Imaging 2025 lists 16 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 21 to 16 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 8 of 16 papers (50.0%) 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 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of Medical Imaging 2025”, https://lacuna.tiptreesystems.com/venue/journal-of-medical-imaging/2025.

Top Authors

AuthorPapers
Bennett Allan Landman7
Abdullah-Al-Zubaer Imran1
Cynthia Rudin1
Kazi Ramisa Rifa1

Papers

Title
Comparative analysis of nnU-Net and Auto3Dseg for fat and fibroglandular tissue segmentation in MRI
Data-driven abdominal phenotypes of type 2 diabetes in lean, overweight, and obese cohorts from computed tomography
DCEF-AVNet: multi-scale feature fusion and attention mechanism-guided brain tumor segmentation network
Improving annotation efficiency for fully labeling a breast mass segmentation dataset
Influence of early through late fusion on pancreas segmentation from imperfectly registered multimodal magnetic resonance imaging
JMI’s Special Issues and Shared Journeys
Learning disentangled representations to harmonize connectome network measures
MD-SA2: optimizing Segment Anything 2 for multimodal, depth-aware brain tumor segmentation in sub-Saharan populations
Mpox lesion counting with semantic and instance segmentation methods
Multi-contrast computed tomography atlas of healthy pancreas with dense displacement sampling registration
New Growth, New Opportunities
Scribble-supervised method for cardiac tissue segmentation using position and temporal contrastive information
Summer of Ideas, Community, and Recognition
Synthetic multi-inversion time magnetic resonance images for visualization of subcortical structures
TFKT V2: task-focused knowledge transfer from natural images for computed tomography perceptual image quality assessment
Weakly supervised pathological differentiation of primary central nervous system lymphoma and glioblastoma on multi-site whole slide images