Distribution-aware Margin Calibration for Medical Image Segmentation
This addresses a key challenge in medical image segmentation for practitioners, offering a method to enhance segmentation accuracy, though it appears incremental as it builds on prior work on mIoU optimization.
The paper tackles the problem of optimizing mean Intersection-over-Union (mIoU) for medical image segmentation by proposing a distribution-aware margin calibration method, which improves IoU scores on two datasets with substantial gains over existing schemes.
The Jaccard index, also known as Intersection-over-Union (IoU score), is one of the most critical evaluation metrics in medical image segmentation. However, directly optimizing the mean IoU (mIoU) score over multiple objective classes is an open problem. Although some algorithms have been proposed to optimize its surrogates, there is no guarantee provided for their generalization ability. In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound. This scheme ensures a better segmentation performance in terms of IoU scores in practice. We evaluate the effectiveness of the proposed margin calibration method on two medical image segmentation datasets, showing substantial improvements of IoU scores over other learning schemes using deep segmentation models.