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

by   David Bouget, et al.

Meningiomas are the most common type of primary brain tumor, accounting for approximately 30 never surgically removed but rather monitored over time. Automatic and precise meningioma segmentation is therefore beneficial to enable reliable growth estimation and patient-specific treatment planning. In this study, we propose the inclusion of attention mechanisms over a U-Net architecture: (i) Attention-gated U-Net (AGUNet) and (ii) Dual Attention U-Net (DAUNet), using a 3D MRI volume as input. Attention has the potential to leverage the global context and identify features' relationships across the entire volume. To limit spatial resolution degradation and loss of detail inherent to encoder-decoder architectures, we studied the impact of multi-scale input and deep supervision components. The proposed architectures are trainable end-to-end and each concept can be seamlessly disabled for ablation studies. The validation studies were performed using a 5-fold cross validation over 600 T1-weighted MRI volumes from St. Olavs University Hospital, Trondheim, Norway. For the best performing architecture, an average Dice score of 81.6 95.6 were occasionally missed hence reaching an overall recall of 93 global context from a 3D MRI volume provided the best performances, even if the native volume resolution could not be processed directly. Overall, near-perfect detection was achieved for meningiomas larger than 3ml which is relevant for clinical use. In the future, the use of multi-scale designs and refinement networks should be further investigated to improve the performance. A larger number of cases with meningiomas below 3ml might also be needed to improve the performance for the smallest tumors.


page 4

page 6

page 9

page 10

page 11


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...

Multiclass MRI Brain Tumor Segmentation using 3D Attention-based U-Net

This paper proposes a 3D attention-based U-Net architecture for multi-re...

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

Automatic segmentation of vestibular schwannoma (VS) tumors from magneti...

Optimized U-Net for Brain Tumor Segmentation

We propose an optimized U-Net architecture for a brain segmentation tas...

3D Global Convolutional Adversarial Network for Prostate MR Volume Segmentation

Advanced deep learning methods have been developed to conduct prostate M...

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

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

Please sign up or login with your details

Forgot password? Click here to reset