Training CNN Classifiers for Semantic Segmentation using Partially Annotated Images: with Application on Human Thigh and Calf MRI

TL;DR

This paper introduces presence masking strategies to train a single CNN classifier for semantic segmentation across heterogeneously annotated medical images, achieving comparable or better results than multiple classifiers with reduced training time and resources.

Contribution

The study proposes presence masking methods enabling training one classifier on partially annotated datasets without semi-supervised learning, improving efficiency and performance across modalities.

Findings

Presence masking enables training class-generic classifiers effectively.

Class-generic classifiers match or outperform multiple class-specific classifiers.

Method reduces training time and annotation costs.

Abstract

Objective: Medical image datasets with pixel-level labels tend to have a limited number of organ or tissue label classes annotated, even when the images have wide anatomical coverage. With supervised learning, multiple classifiers are usually needed given these partially annotated datasets. In this work, we propose a set of strategies to train one single classifier in segmenting all label classes that are heterogeneously annotated across multiple datasets without moving into semi-supervised learning. Methods: Masks were first created from each label image through a process we termed presence masking. Three presence masking modes were evaluated, differing mainly in weightage assigned to the annotated and unannotated classes. These masks were then applied to the loss function during training to remove the influence of unannotated classes. Results: Evaluation against publicly available CT datasets shows that presence masking is a viable method for training class-generic classifiers. Our class-generic classifier can perform as well as multiple class-specific classifiers combined, while the training duration is similar to that required for one class-specific classifier. Furthermore, the class-generic classifier can outperform the class-specific classifiers when trained on smaller datasets. Finally, consistent results are observed from evaluations against human thigh and calf MRI datasets collected in-house. Conclusion: The evaluation outcomes show that presence masking is capable of significantly improving both training and inference efficiency across imaging modalities and anatomical regions. Improved performance may even be observed on small datasets. Significance: Presence masking strategies can reduce the computational resources and costs involved in manual medical image annotations. All codes are publicly available at https://github.com/wong-ck/DeepSegment.