Myofibre segmentation in H&E stained adult skeletal muscle images using coherence-enhancing diffusion filtering.

Harry Strange,Reyer Zwiggelaar,Ian Scott

doi:10.1186/1471-2342-14-38

Abstract

BackgroundThe correct segmentation of myofibres in histological muscle biopsy images is a critical step in the automatic analysis process. Errors occurring as a result of incorrect segmentations have a compounding effect on latter morphometric analysis and as such it is vital that the fibres are correctly segmented. This paper presents a new automatic approach to myofibre segmentation in H&E stained adult skeletal muscle images that is based on Coherence-Enhancing Diffusion filtering.MethodsThe procedure can be broadly divided into four steps: 1) pre-processing of the images to extract only the eosinophilic structures, 2) performing of Coherence-Enhancing Diffusion filtering to enhance the myofibre boundaries whilst smoothing the interior regions, 3) morphological filtering to connect unconnected boundary regions and remove noise, and 4) marker controlled watershed transform to split touching fibres.ResultsThe method has been tested on a set of adult cases with a total of 2,832 fibres. Evaluation was done in terms of segmentation accuracy and other clinical metrics.ConclusionsThe results show that the proposed approach achieves a segmentation accuracy of 89% which is a significant improvement over existing methods.

Highlights

The correct segmentation of myofibres in histological muscle biopsy images is a critical step in the automatic analysis process
There are numerous existing approaches to automatic myofibre segmentation ranging from simple thresholding [4] to more advanced methods that use deformable models [5]
This paper presents a method for myofibre segmentation based on CoherenceEnhancing Diffusion (CED) filtering [14] that is robust to noise and weak fibre boundaries, and provides a side by side comparison with the main approaches to the segmentation problem

Summary

Introduction

The correct segmentation of myofibres in histological muscle biopsy images is a critical step in the automatic analysis process. There are numerous existing approaches to automatic myofibre segmentation ranging from simple thresholding [4] to more advanced methods that use deformable models [5]. These approaches either identify the pixels in the image associated with the fibres themselves or identify the boundaries of the fibres — the perimysium and endomysium (see Figure 1). These methods may fail in cases where there are weak fibre boundaries or an increased presence of noise due to inconsistencies in the staining process

Methods

Results

Conclusion