Size and Smoothness Aware Adaptive Focal Loss for Small Tumor Segmentation

TL;DR

This paper introduces an Adaptive Focal Loss that considers object boundary smoothness and size to enhance small tumor segmentation in medical images, outperforming traditional loss functions on multiple datasets.

Contribution

The novel A-FL dynamically adjusts based on object surface smoothness, size, and class ratio, improving segmentation accuracy for intricate anatomical regions.

Findings

A-FL outperforms regular Focal Loss in IoU and DSC scores.

A-FL surpasses conventional loss functions by large margins in multiple metrics.

Achieved state-of-the-art results on PICAI 2022 and BraTS 2018 datasets.

Abstract

Deep learning has achieved remarkable accuracy in medical image segmentation, particularly for larger structures with well-defined boundaries. However, its effectiveness can be challenged by factors such as irregular object shapes and edges, non-smooth surfaces, small target areas, etc. which complicate the ability of networks to grasp the intricate and diverse nature of anatomical regions. In response to these challenges, we propose an Adaptive Focal Loss (A-FL) that takes both object boundary smoothness and size into account, with the goal to improve segmentation performance in intricate anatomical regions. The proposed A-FL dynamically adjusts itself based on an object's surface smoothness, size, and the class balancing parameter based on the ratio of targeted area and background. We evaluated the performance of the A-FL on the PICAI 2022 and BraTS 2018 datasets. In the PICAI 2022 dataset, the A-FL achieved an Intersection over Union (IoU) score of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular Focal Loss (FL) by 5.5% and 5.4% respectively. It also surpassed the best baseline by 2.0% and 1.2%. In the BraTS 2018 dataset, A-FL achieved an IoU score of 0.883 and a DSC score of 0.931. Our ablation experiments also show that the proposed A-FL surpasses conventional losses (this includes Dice Loss, Focal Loss, and their hybrid variants) by large margin in IoU, DSC, and other metrics. The code is available at https://github.com/rakibuliuict/AFL-CIBM.git.