MyGO: Make your Goals Obvious, Avoiding Semantic Confusion in Prostate Cancer Lesion Region Segmentation

TL;DR

This paper introduces a novel segmentation method for prostate cancer lesions that uses a Pixel Anchor Module, self-attention, and focal loss to improve semantic understanding and achieve state-of-the-art accuracy.

Contribution

The paper proposes a Pixel Anchor Module with a self-attention-based selection strategy and focal loss to enhance lesion segmentation accuracy in prostate cancer images.

Findings

Achieved 69.73% IoU and 74.32% Dice scores on PI-CAI dataset.

Significantly improved prostate cancer lesion detection accuracy.

Enhanced semantic comprehension in lesion segmentation.

Abstract

Early diagnosis and accurate identification of lesion location and progression in prostate cancer (PCa) are critical for assisting clinicians in formulating effective treatment strategies. However, due to the high semantic homogeneity between lesion and non-lesion areas, existing medical image segmentation methods often struggle to accurately comprehend lesion semantics, resulting in the problem of semantic confusion. To address this challenge, we propose a novel Pixel Anchor Module, which guides the model to discover a sparse set of feature anchors that serve to capture and interpret global contextual information. This mechanism enhances the model's nonlinear representation capacity and improves segmentation accuracy within lesion regions. Moreover, we design a self-attention-based Top_k selection strategy to further refine the identification of these feature anchors, and incorporate a focal loss function to mitigate class imbalance, thereby facilitating more precise semantic interpretation across diverse regions. Our method achieves state-of-the-art performance on the PI-CAI dataset, demonstrating 69.73% IoU and 74.32% Dice scores, and significantly improving prostate cancer lesion detection.