SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation
Top Cited Papers
- 31 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (9) , 2228-2237
Abstract
Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present SimCVD, a simple contrastive distillation framework that significantly advances state-of-the-art voxel-wise representation learning. We first describe an unsupervised training strategy, which takes two views of an input volume and predicts their signed distance maps of object boundaries in a contrastive objective, with only two independent dropout as mask. This simple approach works surprisingly well, performing on the same level as previous fully supervised methods with much less labeled data. We hypothesize that dropout can be viewed as a minimal form of data augmentation and makes the network robust to representation collapse. Then, we propose to perform structural distillation by distilling pair-wise similarities. We evaluate SimCVD on two popular datasets: the Left Atrial Segmentation Challenge (LA) and the NIH pancreas CT dataset. The results on the LA dataset demonstrate that, in two types of labeled ratios ( i.e. , 20% and 10%), SimCVD achieves an average Dice score of 90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to previous best results. Our method can be trained in an end-to-end fashion, showing the promise of utilizing SimCVD as a general framework for downstream tasks, such as medical image synthesis, enhancement, and registration.Keywords
This publication has 56 references indexed in Scilit:
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Unsupervised Visual Representation Learning by Context Prediction2015
- Unsupervised Learning of Visual Representations Using Videos2015
- Motion Segmentation of Truncated Signed Distance Function Based Volumetric Surfaces2015
- 3D image segmentation of deformable objects with joint shape-intensity prior models using level setsMedical Image Analysis, 2004
- Neighbor-Constrained Segmentation With Level Set Based 3-D Deformable ModelsIEEE Transactions on Medical Imaging, 2004
- Deformable boundary finding in medical images by integrating gradient and region informationIEEE Transactions on Medical Imaging, 1996
- Model-based deformable surface finding for medical imagesIEEE Transactions on Medical Imaging, 1996
- Boundary finding with parametrically deformable modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992