Semi-Supervised Learning With Fact-Forcing for Medical Image Segmentation
Open Access
- 11 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 99413-99425
Abstract
Precise and robust image segmentation is one of the most important steps in supervised deep learning-applied studies. Especially in the medical field, image segmentation requires an enormous time and professionals with clinical knowledge. Although there are constant attempts for automatic and semi-automatic image segmentation algorithm development, acquiring not only clinically accurate but also precise pixel-level annotations for medical images remains insufficient. This article presents a semi-supervised learning method with a novel fact-forcing process, referred to as FFSS, to reduce the labeling cost while improving the prediction accuracy for medical image segmentation. FFSS includes two components: a pre-trained teacher and a student that would be trained, iteratively. In each iteration, the teacher first generates a pseudo-label for each image in an unlabeled set, the student is then trained on the pseudo-labeled set and sends feedback to update the teacher. A fact-forcing process is designed to improve the quality of the student model using a labeled set. We have comprehensively evaluated our method on both three-dimensional binary segmentation and two-dimensional multi-class segmentation. The evaluation results demonstrate significant accuracy improvements of FFSS compared with the state-of-the-art semi-supervised methods. Due to the fact-forcing process, the proposed method consistently outperforms the other ones under various labeled data ratios for all benchmark datasets, including left atrium MRI, pancreas CT, ACDC MRI, and OCT. By refining the quality of student feedback with complementary supervised training, the proposed FFSS shows robustness under labeled data scarcity for diverse types of medical images.Keywords
This publication has 27 references indexed in Scilit:
- A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imagingMedical Image Analysis, 2021
- Shape-Aware Semi-supervised 3D Semantic Segmentation for Medical Images2020
- Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image SegmentationIEEE Transactions on Neural Networks and Learning Systems, 2020
- Soft-Label Guided Semi-Supervised Learning for Bi-Ventricle Segmentation in Cardiac Cine MRI2020
- Uncertainty-Aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation2019
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation2019
- Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiersMedical Image Analysis, 2019
- Deep Co-Training for Semi-Supervised Image Recognition2018
- DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation2015
- Segmentation of retinal blood vessels using the radial projection and semi-supervised approachPattern Recognition, 2011