Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation

TLDR

Medical imaging deep learning suffers from scarce labeled data, which is costly and time‑consuming to obtain. The study proposes a semisupervised segmentation method that optimizes a weighted combination of supervised loss on labeled data and a regularization loss on both labeled and unlabeled data. The method enforces transformation‑consistent predictions via a self‑ensembling framework that applies perturbations and scaling, uses a teacher model averaging student weights, and is evaluated on skin‑lesion, optic‑disk, and liver segmentation tasks. It achieves superior performance compared with state‑of‑the‑art methods on challenging 2‑D and 3‑D medical image segmentation.

Abstract

A common shortfall of supervised deep learning for medical imaging is the lack of labeled data, which is often expensive and time consuming to collect. This article presents a new semisupervised method for medical image segmentation, where the network is optimized by a weighted combination of a common supervised loss only for the labeled inputs and a regularization loss for both the labeled and unlabeled data. To utilize the unlabeled data, our method encourages consistent predictions of the network-in-training for the same input under different perturbations. With the semisupervised segmentation tasks, we introduce a transformation-consistent strategy in the self-ensembling model to enhance the regularization effect for pixel-level predictions. To further improve the regularization effects, we extend the transformation in a more generalized form including scaling and optimize the consistency loss with a teacher model, which is an averaging of the student model weights. We extensively validated the proposed semisupervised method on three typical yet challenging medical image segmentation tasks: 1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 data set; 2) optic disk (OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) data set; and 3) liver segmentation from volumetric CT scans in the Liver Tumor Segmentation Challenge (LiTS) data set. Compared with state-of-the-art, our method shows superior performance on the challenging 2-D/3-D medical images, demonstrating the effectiveness of our semisupervised method for medical image segmentation.