Key result
MC-Net improves left atrium segmentation over standard semi-supervised methods, achieving a ~90% Dice score.
Why the study?
Most existing semi-supervised methods for left atrium segmentation underestimate the importance of challenging regions during training, limiting model performance.
The proposed MC-Net improves semi-supervised left atrium segmentation from 3D MR images by emphasizing challenging regions through mutual consistency training.
May reduce annotation needs for LA segmentation; leaves open prospective clinical validation before adoption.
Semi-supervised learning has attracted great attention in the field of machine learning, especially for medical image segmentation tasks, since it alleviates the heavy burden of collecting abundant densely annotated data for training. However, most of existing methods underestimate the importance of challenging regions (e.g. small branches or blurred edges) during training. We believe that these unlabeled regions may contain more crucial information to minimize the uncertainty prediction for the model and should be emphasized in the training process. Therefore, in this paper, we propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Particularly, our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss by our designed cycled pseudo label scheme to encourage mutual consistency. Such mutual consistency encourages the two decoders to have consistent and low-entropy predictions and enables the model to gradually capture generalized features from these unlabeled challenging regions. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively. Our MC-Net outperforms six recent semi-supervised methods for left atrium segmentation, and sets the new state-of-the-art performance on the LA database.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2021) studied Left Atrium Segmentation (n=100). Mutual Consistency Network (MC-Net) vs. Standard V-Net and other semi-supervised methods was evaluated on Dice score (%) for left atrium segmentation using 20% labeled data. The proposed Mutual Consistency Network (MC-Net) achieved a Dice score of 90.34% using only 20% labeled data, outperforming the baseline V-Net and other semi-supervised methods for left atrium segmentation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: