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

By Xiaomeng Li, Lequan Yu, Hao Chen, Chi-Wing Fu, P. Heng. IEEE Transactions on Neural Networks and Learning Systems, 2019

495 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/51b422ca6fe84342918458fe399cdf24eb675fcf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Semi-supervised Medical Image Segmentation through Dual-task Consistency (2020, methodology): “To be specific, they can either add small perturbations to the unlabeled samples and enforce the consistency between the model predictions on the original data and the perturbed data (Yu et al. 2019; Li et al. 2020), or just directly enforce the similar prediction distributions on the entire unlabel”
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization (2021, methodology): “…approach against several state-of-the-art SLL methods for segmentation that have code available: the mean teacher model with transformation-consistency ( MT ) [87, 53], the adversarial training-based method [37] ( AdvSSL ), and also the recently proposed Guided Collaborative Training ( GCT ) [47].”
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation (2019, background): “Liskowski and Krawiec (2016) apply gamma correction of saturation and value of the HSV color space prior to segmenting retinal blood vessels.”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, methodology): “There are some commonly used input perturbations, such as Gaussian noise, Gaussian blurring, randomly rotation, scaling and contrast variations, and the segmentation network is encouraged to be transformation-consistent for unlabeled data [35].”
Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer (2021, background): “…al., 2017; Hu et al., 2020), few-shot learning (Tang et al., 2021a), mean teacher and its extensions (Tarvainen and Valpola, 2017; Yu et al., 2019; Li et al., 2020; Reiß et al., 2021; You et al., 2021a,b), multi-task learning (Luo et al., 2021a; Kervadec et al., 2019; Chen et al., 2019),…”
Efficient Semi-supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency (2020, methodology): “After that, the perturbation-based methods have achieved increasing attentions in semi-supervised learning [2,4,12,19].”
Recent advances and clinical applications of deep learning in medical image analysis (2021, background): “The mean teacher model can also be improved by the transformation-consistent strategy (Li et al., 2020b).”
SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation (2021, background): “have achieved much stronger performance in recent years with huge advances in representation learning [6], [7], [8], [9], [10], [11], [12], [13].”