Cross-Modal Self-Attention Distillation for Prostate Cancer Segmentation

TL;DR

This paper introduces a novel cross-modal self-attention distillation network that effectively leverages multi-modal MRI features for improved prostate cancer segmentation, achieving state-of-the-art results.

Contribution

The work proposes a new network architecture with self-attention distillation and a spatial correlated feature fusion module for better multi-modal feature integration.

Findings

Achieves state-of-the-art segmentation accuracy.

Demonstrates effective utilization of multi-modal MRI features.

Outperforms existing methods in prostate cancer segmentation.

Abstract

Automatic segmentation of the prostate cancer from the multi-modal magnetic resonance images is of critical importance for the initial staging and prognosis of patients. However, how to use the multi-modal image features more efficiently is still a challenging problem in the field of medical image segmentation. In this paper, we develop a cross-modal self-attention distillation network by fully exploiting the encoded information of the intermediate layers from different modalities, and the extracted attention maps of different modalities enable the model to transfer the significant spatial information with more details. Moreover, a novel spatial correlated feature fusion module is further employed for learning more complementary correlation and non-linear information of different modality images. We evaluate our model in five-fold cross-validation on 358 MRI with biopsy confirmed. Extensive experiment results demonstrate that our proposed network achieves state-of-the-art performance.