Clinically Acceptable Segmentation of Organs at Risk in Cervical Cancer Radiation Treatment from Clinically Available Annotations

TL;DR

This paper introduces a semi-supervised deep learning approach for automatic segmentation of organs at risk in cervical cancer radiation therapy, effectively handling data inhomogeneity, label noise, and missing annotations, resulting in clinically acceptable contours.

Contribution

It presents a novel semi-supervised learning method with automatic data cleaning and annotation imputation for improved segmentation in challenging clinical datasets.

Findings

Significant performance improvement on test data

Contours are clinically acceptable and comparable to manual contours

Effective handling of missing annotations in large datasets

Abstract

Deep learning models benefit from training with a large dataset (labeled or unlabeled). Following this motivation, we present an approach to learn a deep learning model for the automatic segmentation of Organs at Risk (OARs) in cervical cancer radiation treatment from a large clinically available dataset of Computed Tomography (CT) scans containing data inhomogeneity, label noise, and missing annotations. We employ simple heuristics for automatic data cleaning to minimize data inhomogeneity and label noise. Further, we develop a semi-supervised learning approach utilizing a teacher-student setup, annotation imputation, and uncertainty-guided training to learn in presence of missing annotations. Our experimental results show that learning from a large dataset with our approach yields a significant improvement in the test performance despite missing annotations in the data. Further, the contours generated from the segmentation masks predicted by our model are found to be equally clinically acceptable as manually generated contours.