Meta Corrupted Pixels Mining for Medical Image Segmentation
This addresses the costly and error-prone annotation process in medical image segmentation, offering a solution for handling corrupted labels, though it is incremental as it builds on existing methods for noisy annotations.
The paper tackles the problem of training deep segmentation models on medical images with corrupted pixel-level annotations by proposing a Meta Corrupted Pixels Mining method that automatically estimates a weighting map to prioritize important pixels, achieving state-of-the-art performance on LIDC-IDRI and LiTS datasets.
Deep neural networks have achieved satisfactory performance in piles of medical image analysis tasks. However the training of deep neural network requires a large amount of samples with high-quality annotations. In medical image segmentation, it is very laborious and expensive to acquire precise pixel-level annotations. Aiming at training deep segmentation models on datasets with probably corrupted annotations, we propose a novel Meta Corrupted Pixels Mining (MCPM) method based on a simple meta mask network. Our method is targeted at automatically estimate a weighting map to evaluate the importance of every pixel in the learning of segmentation network. The meta mask network which regards the loss value map of the predicted segmentation results as input, is capable of identifying out corrupted layers and allocating small weights to them. An alternative algorithm is adopted to train the segmentation network and the meta mask network, simultaneously. Extensive experimental results on LIDC-IDRI and LiTS datasets show that our method outperforms state-of-the-art approaches which are devised for coping with corrupted annotations.