Improving Segmentation of Objects with Varying Sizes in Biomedical Images using Instance-wise and Center-of-Instance Segmentation Loss Function

TL;DR

This paper introduces a novel loss function called ICI loss for biomedical image segmentation, which effectively addresses instance imbalance and improves detection of small objects, outperforming existing loss functions in stroke lesion segmentation.

Contribution

The paper proposes the ICI loss, combining instance-wise and center-of-instance components, as a new solution to the instance imbalance problem in biomedical segmentation tasks.

Findings

ICI loss outperforms Dice and blob losses in Dice similarity coefficient.

ICI loss provides more balanced segmentation results.

Significant improvement in small instance detection.

Abstract

In this paper, we propose a novel two-component loss for biomedical image segmentation tasks called the Instance-wise and Center-of-Instance (ICI) loss, a loss function that addresses the instance imbalance problem commonly encountered when using pixel-wise loss functions such as the Dice loss. The Instance-wise component improves the detection of small instances or ``blobs" in image datasets with both large and small instances. The Center-of-Instance component improves the overall detection accuracy. We compared the ICI loss with two existing losses, the Dice loss and the blob loss, in the task of stroke lesion segmentation using the ATLAS R2.0 challenge dataset from MICCAI 2022. Compared to the other losses, the ICI loss provided a better balanced segmentation, and significantly outperformed the Dice loss with an improvement of $1.7-3.7\%$ and the blob loss by $0.6-5.0\%$ in terms of the Dice similarity coefficient on both validation and test set, suggesting that the ICI loss is a potential solution to the instance imbalance problem.