Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentation
This work addresses the challenge of limited labeled data in medical imaging, offering an incremental improvement for lesion segmentation tasks.
The paper tackles the problem of data scarcity in medical lesion segmentation by proposing a semi-supervised method using cut-paste augmentation and consistency regularization, achieving superior performance over existing methods on two public datasets.
Semi-supervised learning has the potential to improve the data-efficiency of training data-hungry deep neural networks, which is especially important for medical image analysis tasks where labeled data is scarce. In this work, we present a simple semi-supervised learning method for lesion segmentation tasks based on the ideas of cut-paste augmentation and consistency regularization. By exploiting the mask information available in the labeled data, we synthesize partially labeled samples from the unlabeled images so that the usual supervised learning objective (e.g., binary cross entropy) can be applied. Additionally, we introduce a background consistency term to regularize the training on the unlabeled background regions of the synthetic images. We empirically verify the effectiveness of the proposed method on two public lesion segmentation datasets, including an eye fundus photograph dataset and a brain CT scan dataset. The experiment results indicate that our method achieves consistent and superior performance over other self-training and consistency-based methods without introducing sophisticated network components.