Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation

Abstract

Deep convolutional neural networks have achieved remarkable progress on a variety of medical image computing tasks. A common problem when applying supervised deep learning methods to medical images is the lack of labeled data, which is very expensive and time-consuming to be collected. In this paper, we present a novel semi-supervised method for medical image segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data. To utilize the unlabeled data, our method encourages the consistent predictions of the network-in-training for the same input under different regularizations. Aiming for the semi-supervised segmentation problem, we enhance the effect of regularization for pixel-level predictions by introducing a transformation, including rotation and flipping, consistent scheme in our self-ensembling model. With the aim of semi-supervised segmentation tasks, we introduce a transformation consistent strategy in our self-ensembling model to enhance the regularization effect for pixel-level predictions. We have extensively validated the proposed semi-supervised method on three typical yet challenging medical image segmentation tasks: (i) skin lesion segmentation from dermoscopy images on International Skin Imaging Collaboration (ISIC) 2017 dataset, (ii) optic disc segmentation from fundus images on Retinal Fundus Glaucoma Challenge (REFUGE) dataset, and (iii) liver segmentation from volumetric CT scans on Liver Tumor Segmentation Challenge (LiTS) dataset. Compared to the state-of-the-arts, our proposed method shows superior segmentation performance on challenging 2D/3D medical images, demonstrating the effectiveness of our semi-supervised method for medical image segmentation.

arXiv commentAccept at IEEE Transactions on Neural Networks and Learning Systems

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• The Liver Tumor Segmentation Benchmark (LiTS)
• Applications of Deep Learning and Reinforcement Learning to Biological Data
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• Group Equivariant Convolutional Networks
• Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• Lesion Border Detection in Dermoscopy Images Using Ensembles of Thresholding Methods
• Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
• Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• ISIC 2017 - Skin Lesion Analysis Towards Melanoma Detection
• Automatic Skin Lesion Segmentation using Semi-supervised Learning Technique
• Deeply Supervised Rotation Equivariant Network for Lesion Segmentation in Dermoscopy Images

Cited by in corpus (5)

• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
• Total-Body Low-Dose CT Image Denoising using Prior Knowledge Transfer Technique with Contrastive Regularization Mechanism
• Extreme Consistency: Overcoming Annotation Scarcity and Domain Shifts
• Belief function-based semi-supervised learning for brain tumor segmentation