USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets

04/17/2019
by   Leonardo Rundo, et al.
0

Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor's frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks are added after every Encoder (Enc USE-Net) or Encoder-Decoder block (Enc-Dec USE-Net). This study evaluates the generalization ability of CNN-based architectures on three T2-weighted MRI datasets, each one consisting of a different number of patients and heterogeneous image characteristics, collected by different institutions. The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations. USE-Net is compared against three state-of-the-art CNN-based architectures (i.e., U-Net, pix2pix, and Mixed-Scale Dense Network), along with a semi-automatic continuous max-flow model. The results show that training on the union of the datasets generally outperforms training on each dataset separately, allowing for both intra-/cross-dataset generalization. Enc USE-Net shows good overall generalization under any training condition, while Enc-Dec USE-Net remarkably outperforms the other methods when trained on all datasets. These findings reveal that the SE blocks' adaptive feature recalibration provides excellent cross-dataset generalization when testing is performed on samples of the datasets used during training.

READ FULL TEXT
research
03/29/2019

CNN-based Prostate Zonal Segmentation on T2-weighted MR Images: A Cross-dataset Study

Prostate cancer is the most common cancer among US men. However, prostat...
research
10/24/2022

Brain Tumor Segmentation using Enhanced U-Net Model with Empirical Analysis

Cancer of the brain is deadly and requires careful surgical segmentation...
research
06/21/2023

Lumbar spine segmentation in MR images: a dataset and a public benchmark

This paper presents a large publicly available multi-center lumbar spine...
research
10/14/2020

Fast meningioma segmentation in T1-weighted MRI volumes using a lightweight 3D deep learning architecture

Automatic and consistent meningioma segmentation in T1-weighted MRI volu...
research
02/15/2023

Edge-weighted pFISTA-Net for MRI Reconstruction

Deep learning based on unrolled algorithm has served as an effective met...
research
08/24/2023

Learned Local Attention Maps for Synthesising Vessel Segmentations

Magnetic resonance angiography (MRA) is an imaging modality for visualis...

Please sign up or login with your details

Forgot password? Click here to reset