MyoPath

Under Development

MyoPath is currently under active development and not yet publicly available.

MyoPath is a deep learning pipeline for objective morphometric assessment of skeletal muscle biopsies from routine H&E-stained whole slide images (WSI).

Live DemoSample: HE_M3405 | M3405

Analysis Summary

Tissue CompositionPercentage of ROI area

48.95%

48.81%

Muscle: 48.95% Fat: 2.24% Connective: 48.81% Nuclei: 8.45%

ROI Region

Total Area:2.25 mm²

Muscle Fibers

Count:522

Area:1.10 mm²

Percentage:48.95%

Fat Regions

Count:61

Area:0.0504 mm²

Percentage:2.24%

Connective Tissue

Area:1.0982 mm²

Percentage:48.81%

Fiber Size Distribution

Mean:2109.9 μm²

Median:1860.1 μm²

Std:1469.4 μm²

CV:0.696

Fiber Shape

Shape Factor (mean):0.561

Shape Factor (std):0.048

Aspect Ratio (mean):1.23

Nuclei Analysis

Total Nuclei:5412

In Muscle:1272

In Connective:4137

Per Fiber (mean):2.86

Multinucleated:330

Centralization Index:0.112

Pathology Indicators

Nuclear-Muscle Ratio:2.44

Inflammatory Infiltration:3767 /mm²

Fiber Size Variability:0.696

Shape Circularity:0.561

Fat Infiltration:2.24%

Fibrosis:48.81%

Nuclear Centralization:0.112

Analysis Detail

Image Comparison

↔

Original

Color Map

Overview

MyoPath implements a four-tissue segmentation pipeline — Cellpose-SAM for myofiber instance segmentation, a pixel classifier for fat infiltration, watershed detection for nuclei, and Boolean subtraction for connective tissue — to extract 37 morphometric features per sample. From these, seven clinically interpretable pathology indicators are derived, with Nuclear Centralization Index (NCI) and Fiber Size Variability Coefficient (Fiber CV) serving as primary biomarkers.

The pipeline has been validated on 478 H&E whole-slide images from two independent cohorts (HuashanMuscle, n = 79; GTEx, n = 399).

Key Features

• Four-tissue segmentation: Myofiber, fat, nucleus, and connective tissue from a single H&E section
• 37 morphometric features across five biological categories (details)
• Seven pathology indicators covering nuclear positioning, fiber size, shape, tissue composition, and cellular reaction
• MyoPath Score: Composite severity measure (AUC = 0.873 on external validation)
• Primary biomarkers: NCI (p = 1.3 x 10⁻⁵) and Fiber CV (p = 2.9 x 10⁻⁴)

Segmentation Pipeline

Layer	Tissue	Method	Dice
1	Myofiber instances	Cellpose-SAM	0.92
2	Fat infiltration	Pixel classifier	0.95
3	Nuclei	Watershed detection	0.87
4	Connective tissue	Boolean subtraction	0.88

Citation

Zhong H*, Gao M*, et al. MyoPath: A Deep Learning Pipeline for Objective Morphometric Assessment of Skeletal Muscle Biopsies. Manuscript in preparation.