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

Automatic and consistent meningioma segmentation in T1-weighted magnetic resonance (MR) imaging volumes and corresponding volumetric assessment is of use for diagnosis, treatment planning, and tumor growth evaluation. We optimized the segmentation and processing speed performances using a large numb...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medical imaging (Bellingham, Wash.) Vol. 8; no. 2; p. 024002
Main Authors: Bouget, David, Pedersen, André, Hosainey, Sayied Abdol Mohieb, Vanel, Johanna, Solheim, Ole, Reinertsen, Ingerid
Format: Journal Article
Language:English
Published: United States 01.03.2021
Subjects:
clinical diagnosis
meningioma
deep learning
magnetic resonance imaging
three-dimensional segmentation
ISSN:2329-4302
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic and consistent meningioma segmentation in T1-weighted magnetic resonance (MR) imaging volumes and corresponding volumetric assessment is of use for diagnosis, treatment planning, and tumor growth evaluation. We optimized the segmentation and processing speed performances using a large number of both surgically treated meningiomas and untreated meningiomas followed at the outpatient clinic. We studied two different three-dimensional (3D) neural network architectures: (i) a simple encoder-decoder similar to a 3D U-Net, and (ii) a lightweight multi-scale architecture [Pulmonary Lobe Segmentation Network (PLS-Net)]. In addition, we studied the impact of different training schemes. For the validation studies, we used 698 T1-weighted MR volumes from St. Olav University Hospital, Trondheim, Norway. The models were evaluated in terms of detection accuracy, segmentation accuracy, and training/inference speed. While both architectures reached a similar Dice score of 70% on average, the PLS-Net was more accurate with an -score of up to 88%. The highest accuracy was achieved for the largest meningiomas. Speed-wise, the PLS-Net architecture tended to converge in about 50 h while 130 h were necessary for U-Net. Inference with PLS-Net takes less than a second on GPU and about 15 s on CPU. Overall, with the use of mixed precision training, it was possible to train competitive segmentation models in a relatively short amount of time using the lightweight PLS-Net architecture. In the future, the focus should be brought toward the segmentation of small meningiomas ( ) to improve clinical relevance for automatic and early diagnosis and speed of growth estimates.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2329-4302
DOI:10.1117/1.JMI.8.2.024002