Automatic Segmentation of Vestibular Schwannoma from T2-Weighted MRI by Deep Spatial Attention with Hardness-Weighted Loss

by   Guotai Wang, et al.

Automatic segmentation of vestibular schwannoma (VS) tumors from magnetic resonance imaging (MRI) would facilitate efficient and accurate volume measurement to guide patient management and improve clinical workflow. The accuracy and robustness is challenged by low contrast, small target region and low through-plane resolution. We introduce a 2.5D convolutional neural network (CNN) able to exploit the different in-plane and through-plane resolutions encountered in standard of care imaging protocols. We use an attention module to enable the CNN to focus on the small target and propose a supervision on the learning of attention maps for more accurate segmentation. Additionally, we propose a hardness-weighted Dice loss function that gives higher weights to harder voxels to boost the training of CNNs. Experiments with ablation studies on the VS tumor segmentation task show that: 1) the proposed 2.5D CNN outperforms its 2D and 3D counterparts, 2) our supervised attention mechanism outperforms unsupervised attention, 3) the voxel-level hardness-weighted Dice loss can improve the performance of CNNs. Our method achieved an average Dice score and ASSD of 0.87 and 0.43 mm respectively. This will facilitate patient management decisions in clinical practice.


page 2

page 6


A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging

We propose a novel automatic method for accurate segmentation of the pro...

Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRI

Background and Objective: Accurate and reliable segmentation of the pros...

Angular Visual Hardness

Although convolutional neural networks (CNNs) are inspired by the mechan...

Meningioma segmentation in T1-weighted MRI leveraging global context and attention mechanisms

Meningiomas are the most common type of primary brain tumor, accounting ...

A Generative Adversarial Model for Right Ventricle Segmentation

The clinical management of several cardiovascular conditions, such as pu...

Automatic Segmentation and Location Learning of Neonatal Cerebral Ventricles in 3D Ultrasound Data Combining CNN and CPPN

Preterm neonates are highly likely to suffer from ventriculomegaly, a di...

Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Ability

This work employs a pre-trained, multi-view Convolutional Neural Network...

Please sign up or login with your details

Forgot password? Click here to reset