Cross-Modal Self-Attention Distillation for Prostate Cancer Segmentation
This work addresses the challenge of multi-modal image segmentation for prostate cancer, which is critical for patient staging and prognosis, but it appears incremental as it builds on existing attention and fusion methods.
The paper tackles the problem of efficiently using multi-modal MRI features for prostate cancer segmentation by developing a cross-modal self-attention distillation network, achieving state-of-the-art performance in experiments on 358 biopsy-confirmed MRI images.
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.