FAU-Net: An Attention U-Net Extension with Feature Pyramid Attention for Prostate Cancer Segmentation

TL;DR

This paper introduces FAU-Net, an enhanced U-Net model with feature pyramid attention for improved prostate cancer segmentation in MRI images, demonstrating superior performance over several existing models.

Contribution

The paper presents FAU-Net, a novel attention-based extension of U-Net that incorporates feature pyramid attention modules for better prostate zone segmentation.

Findings

Achieved a mean DSC of 84.15% and IoU of 76.9% on test data.

Outperformed most compared U-Net variants in segmentation accuracy.

Demonstrated potential to improve prostate cancer detection workflows.

Abstract

This contribution presents a deep learning method for the segmentation of prostate zones in MRI images based on U-Net using additive and feature pyramid attention modules, which can improve the workflow of prostate cancer detection and diagnosis. The proposed model is compared to seven different U-Net-based architectures. The automatic segmentation performance of each model of the central zone (CZ), peripheral zone (PZ), transition zone (TZ) and Tumor were evaluated using Dice Score (DSC), and the Intersection over Union (IoU) metrics. The proposed alternative achieved a mean DSC of 84.15% and IoU of 76.9% in the test set, outperforming most of the studied models in this work except from R2U-Net and attention R2U-Net architectures.