CAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI

by   Alex Ling Yu Hung, et al.

Prostate cancer is the second leading cause of cancer death among men in the United States. The diagnosis of prostate MRI often relies on the accurate prostate zonal segmentation. However, state-of-the-art automatic segmentation methods often fail to produce well-contained volumetric segmentation of the prostate zones since certain slices of prostate MRI, such as base and apex slices, are harder to segment than other slices. This difficulty can be overcome by accounting for the cross-slice relationship of adjacent slices, but current methods do not fully learn and exploit such relationships. In this paper, we propose a novel cross-slice attention mechanism, which we use in a Transformer module to systematically learn the cross-slice relationship at different scales. The module can be utilized in any existing learning-based segmentation framework with skip connections. Experiments show that our cross-slice attention is able to capture the cross-slice information in prostate zonal segmentation and improve the performance of current state-of-the-art methods. Our method significantly improves segmentation accuracy in the peripheral zone, such that the segmentation results are consistent across all the prostate slices (apex, mid-gland, and base).


page 1

page 6

page 8


Adjacent Slice Feature Guided 2.5D Network for Pulmonary Nodule Segmentation

More and more attention has been paid to the segmentation of pulmonary n...

3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation

We propose a method based on deep learning to perform cardiac segmentati...

Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT

Accurate characterisation of visual attributes such as spiculation, lobu...

SATr: Slice Attention with Transformer for Universal Lesion Detection

Universal Lesion Detection (ULD) in computed tomography plays an essenti...

3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation

We present a novel automated method to segment the myocardium of both le...

Seismic Fault Segmentation via 3D-CNN Training by a Few 2D Slices Labels

Detection faults in seismic data is a crucial step for seismic structura...

Radiotherapy Target Contouring with Convolutional Gated Graph Neural Network

Tomography medical imaging is essential in the clinical workflow of mode...

Please sign up or login with your details

Forgot password? Click here to reset