MyoPath: A deep learning pipeline for objective morphometric assessment of skeletal muscle biopsies.
4 affiliations
- 1Huashan Rare Disease Centre, Department of Neurology, Huashan Hospital, Fudan University, Shanghai, China.
- 2Shanghai Key Laboratory of Gene Editing and Cell Therapy for Rare Diseases, Fudan University, Shanghai, China.
- 3Department of Pathology, Huashan Hospital, Fudan University, Shanghai, China.
- 4Department of Neurology, Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
Abstract
Muscle biopsy assessment relies on descriptive features that are difficult to compare across samples. We developed MyoPath to quantify these features and examined their usefulness in clinical biopsies and population-based autopsy material. MyoPath combines Cellpose-SAM and conventional image analysis within QuPath to segment myofibers, fat, nuclei, and connective tissue. We analyzed 478 hematoxylin and eosin images from HuashanMuscle (79 snap-frozen biopsies) and GTEx (399 formalin-fixed, paraffin-embedded autopsy samples). Thirty-seven features were summarized by seven pathology indicators. A composite model trained on GTEx healthy and wasting strata was transferred to HuashanMuscle without retraining. Segmentation Dice coefficients ranged from 0.87 to 0.95 on annotated cryosections. Nuclear centralization index (NCI) and fiber size coefficient of variation (fiber CV) discriminated myopathy from controls in HuashanMuscle (AUC 0.85 and 0.79) and wasting from healthy donors in GTEx (0.74 and 0.74). Their GTEx associations changed little after age and sex adjustment. The composite achieved AUC 0.788 (95% CI 0.71-0.85) in GTEx and 0.873 (0.78-0.94) in HuashanMuscle. In the latter cohort, mean predicted probability was 0.49 compared with an observed myopathy proportion of 0.79. NCI and fiber CV provide interpretable measures of muscle pathology in two distinct tissue settings. MyoPath supports quantitative comparison between groups; clinical severity grading and interpretation of absolute scores require further validation.
Related
- A Batch-Aware, Subject-Grouped Pipeline to Prioritize HIIT-Associated DNA Methylation Candidates with Cross-Cohort Evaluation in Skeletal Muscle
- MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
- A Two-Stage ESM-Based Machine Learning Pipeline for Robust Hierarchically Evaluated Enzyme Function Prediction
- AutoWrinkleID: a machine learning pipeline for biofilm wrinkle identification and quantitative analysis
- Label-free morphometric profiling reveals early drug responses in 3D tumor spheroids
BibTeX
@article{zhong2026myopath,
title = {{MyoPath: A deep learning pipeline for objective morphometric assessment of skeletal muscle biopsies.}},
author = {Huahua Zhong and Mingshi Gao and Shang Ma and Wenhan Zhang and Nachuan Cheng and Kexin Jiao and Bochen Zhu and Jie Song and Chong Yan and Dongyue Yue and Jianying Xi and Zunguo Du and Wenhua Zhu and Chongbo Zhao and Sushan Luo},
journal = {Journal of pathology informatics},
year = {2026},
month = oct,
doi = {10.1016/j.jpi.2026.100747},
url = {https://europepmc.org/article/MED/42997577},
note = {CC BY},
}
RIS
TY - JOUR
TI - MyoPath: A deep learning pipeline for objective morphometric assessment of skeletal muscle biopsies.
AU - Huahua Zhong
AU - Mingshi Gao
AU - Shang Ma
AU - Wenhan Zhang
AU - Nachuan Cheng
AU - Kexin Jiao
AU - Bochen Zhu
AU - Jie Song
AU - Chong Yan
AU - Dongyue Yue
AU - Jianying Xi
AU - Zunguo Du
AU - Wenhua Zhu
AU - Chongbo Zhao
AU - Sushan Luo
PY - 2026
DA - 2026/10/06
JO - Journal of pathology informatics
DO - 10.1016/j.jpi.2026.100747
UR - https://europepmc.org/article/MED/42997577
AB - Muscle biopsy assessment relies on descriptive features that are difficult to compare across samples. We developed MyoPath to quantify these features and examined their usefulness in clinical biopsies and population-based autopsy material. MyoPath combines Cellpose-SAM and conventional image analysis within QuPath to segment myofibers, fat, nuclei, and connective tissue. We analyzed 478 hematoxylin and eosin images from HuashanMuscle (79 snap-frozen biopsies) and GTEx (399 formalin-fixed, paraffin-embedded autopsy samples). Thirty-seven features were summarized by seven pathology indicators. A composite model trained on GTEx healthy and wasting strata was transferred to HuashanMuscle without retraining. Segmentation Dice coefficients ranged from 0.87 to 0.95 on annotated cryosections. Nuclear centralization index (NCI) and fiber size coefficient of variation (fiber CV) discriminated myopathy from controls in HuashanMuscle (AUC 0.85 and 0.79) and wasting from healthy donors in GTEx (0.74 and 0.74). Their GTEx associations changed little after age and sex adjustment. The composite achieved AUC 0.788 (95% CI 0.71-0.85) in GTEx and 0.873 (0.78-0.94) in HuashanMuscle. In the latter cohort, mean predicted probability was 0.49 compared with an observed myopathy proportion of 0.79. NCI and fiber CV provide interpretable measures of muscle pathology in two distinct tissue settings. MyoPath supports quantitative comparison between groups; clinical severity grading and interpretation of absolute scores require further validation.
SN - 2229-5089
SN - 2153-3539
ER -