Acute and sub-acute stroke lesion segmentation from multimodal MRI.

Automatic lesion segmentation Brain Convolutional neural networks Deep learning Ischemic stroke MRI

Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Oct 2020
Historique:
received: 25 04 2019
revised: 30 03 2020
accepted: 23 04 2020
pubmed: 21 5 2020
medline: 15 5 2021
entrez: 21 5 2020
Statut: ppublish

Résumé

Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed time-critical treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered the gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment. We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. We pre-process the data to facilitate learning features based on the symmetry of brain hemispheres. The issue of class imbalance is tackled using small patches with a balanced training patch sampling strategy and a dynamically weighted loss function. Moreover, a combination of whole patch predictions, using a U-Net based CNN architecture, and high degree of overlapping patches reduces the need for additional post-processing. The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from multiple diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59 ± 0.31) and SPES sub-tasks (DSC=0.84 ± 0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance. Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without hyper-parameter tuning. In order to promote the reproducibility of our results, a public version of the proposed method has been released to the scientific community.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed time-critical treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered the gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment.
METHODS METHODS
We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. We pre-process the data to facilitate learning features based on the symmetry of brain hemispheres. The issue of class imbalance is tackled using small patches with a balanced training patch sampling strategy and a dynamically weighted loss function. Moreover, a combination of whole patch predictions, using a U-Net based CNN architecture, and high degree of overlapping patches reduces the need for additional post-processing.
RESULTS RESULTS
The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from multiple diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59 ± 0.31) and SPES sub-tasks (DSC=0.84 ± 0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance.
CONCLUSIONS CONCLUSIONS
Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without hyper-parameter tuning. In order to promote the reproducibility of our results, a public version of the proposed method has been released to the scientific community.

Identifiants

pubmed: 32434099
pii: S0169-2607(19)30589-9
doi: 10.1016/j.cmpb.2020.105521
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

105521

Informations de copyright

Copyright © 2020 Elsevier B.V. All rights reserved.

Auteurs

Albert Clèrigues (A)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain. Electronic address: albert.clerigues@udg.edu.

Sergi Valverde (S)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.

Jose Bernal (J)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.

Jordi Freixenet (J)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.

Arnau Oliver (A)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.

Xavier Lladó (X)

Institute of Computer Vision and Robotics, University of Girona, P-IV, Campus Montilivi, 17003 Girona Spain.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH