Item


Acute and sub-acute stroke lesion segmentation from multimodal MRI

Background and 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. 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 sym- metry 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. The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Le- sion 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. 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

This work has been partially supported by Retos de Inves- tigación TIN2015-73563-JIN and DPI2017-86696-R from the Minis- terio de Ciencia, Innovación y Universidades

Elsevier

Manager: Ministerio de Economía y Competitividad (Espanya)
Author: Clèrigues, Albert
Oliver, Arnau
Lladó, Xavier
Valverde Valverde, Sergi
Bernal, Jose
Freixenet i Bosch, Jordi
Oliver i Malagelada, Arnau
Date: 2020 October 1
Abstract: Background and 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. 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 sym- metry 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. The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Le- sion 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. 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
This work has been partially supported by Retos de Inves- tigación TIN2015-73563-JIN and DPI2017-86696-R from the Minis- terio de Ciencia, Innovación y Universidades
Format: application/pdf
Document access: http://hdl.handle.net/10256/18453
Language: eng
Publisher: Elsevier
Collection: info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cmpb.2020.105521
info:eu-repo/semantics/altIdentifier/issn/0169-2607
info:eu-repo/semantics/altIdentifier/eissn/1872-7565
info:eu-repo/grantAgreement/MINECO//TIN2015-73563-JIN/ES/SEGMENTACION AUTOMATICA DE LAS ESTRUCTURAS CEREBRALES PARA SU USO COMO BIOMARCADORES DE IMAGEN/
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/DPI2017-86696-R/ES/MODELOS PREDICTIVOS PARA LA ESCLEROSIS MULTIPE USANDO BIOMARCADORES DE RESONANCIA MAGNETICA DEL CEREBRO/
Rights: Tots els drets reservats
Subject: Imatgeria per ressonància magnètica
Magnetic resonance imaging
Isquèmia cerebral -- Imatgeria per ressonància magnètica
Cerebral ischemia -- Magnetic resonance imaging
Imatgeria per al diagnòstic
Diagnostic imaging
Title: Acute and sub-acute stroke lesion segmentation from multimodal MRI
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors