Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information

In developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imagi...

Full description

Bibliographic Details
Main Authors: Adriano Pinto, Richard Mckinley, Victor Alves, Roland Wiest, Carlos A. Silva, Mauricio Reyes
Format: Article
Language:English
Published: Frontiers Media S.A. 2018-12-01
Series:Frontiers in Neurology
Subjects:
MRI
Online Access:https://www.frontiersin.org/article/10.3389/fneur.2018.01060/full
id doaj-737a287e2c33493cbb0299c2c62fa5e9
record_format Article
spelling doaj-737a287e2c33493cbb0299c2c62fa5e92020-11-24T20:54:41ZengFrontiers Media S.A.Frontiers in Neurology1664-22952018-12-01910.3389/fneur.2018.01060384549Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical InformationAdriano Pinto0Adriano Pinto1Richard Mckinley2Victor Alves3Roland Wiest4Carlos A. Silva5Mauricio Reyes6CMEMS-UMinho Research Unit, University of Minho, Guimarães, PortugalCentro Algoritmi, University of Minho, Braga, PortugalSupport Center for Advanced Neuroimaging, University Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Bern, SwitzerlandCentro Algoritmi, University of Minho, Braga, PortugalSupport Center for Advanced Neuroimaging, University Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Bern, SwitzerlandCMEMS-UMinho Research Unit, University of Minho, Guimarães, PortugalInstitute for Surgical Technology and Biomechanics, University of Bern, Bern, SwitzerlandIn developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imaging captures blood flow dynamics that guides the physician in evaluating the risks and benefits of the reperfusion procedure. However, the decision process is an intricate task due to the variability of lesion size, shape, and location, as well as the complexity of the underlying cerebral hemodynamic process. Therefore, an automatic method that predicts the stroke lesion outcome, at a 3-month follow-up, would provide an important support to the physicians' decision process. In this work, we propose an automatic deep learning-based method for stroke lesion outcome prediction. Our main contribution resides in the combination of multi-modal Magnetic Resonance Imaging maps with non-imaging clinical meta-data: the thrombolysis in cerebral infarction scale, which categorizes the success of recanalization, achieved through mechanical thrombectomy. In our proposal, this clinical information is considered at two levels. First, at a population level by embedding the clinical information in a custom loss function used during training of our deep learning architecture. Second, at a patient-level through an extra input channel of the neural network used at testing time for a given patient case. By merging imaging with non-imaging clinical information, we aim to obtain a model aware of the principal and collateral blood flow dynamics for cases where there is no perfusion beyond the point of occlusion and for cases where the perfusion is complete after the occlusion point.https://www.frontiersin.org/article/10.3389/fneur.2018.01060/fullstrokemachine learningdeep learningMRIprediction
collection DOAJ
language English
format Article
sources DOAJ
author Adriano Pinto
Adriano Pinto
Richard Mckinley
Victor Alves
Roland Wiest
Carlos A. Silva
Mauricio Reyes
spellingShingle Adriano Pinto
Adriano Pinto
Richard Mckinley
Victor Alves
Roland Wiest
Carlos A. Silva
Mauricio Reyes
Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
Frontiers in Neurology
stroke
machine learning
deep learning
MRI
prediction
author_facet Adriano Pinto
Adriano Pinto
Richard Mckinley
Victor Alves
Roland Wiest
Carlos A. Silva
Mauricio Reyes
author_sort Adriano Pinto
title Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
title_short Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
title_full Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
title_fullStr Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
title_full_unstemmed Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information
title_sort stroke lesion outcome prediction based on mri imaging combined with clinical information
publisher Frontiers Media S.A.
series Frontiers in Neurology
issn 1664-2295
publishDate 2018-12-01
description In developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imaging captures blood flow dynamics that guides the physician in evaluating the risks and benefits of the reperfusion procedure. However, the decision process is an intricate task due to the variability of lesion size, shape, and location, as well as the complexity of the underlying cerebral hemodynamic process. Therefore, an automatic method that predicts the stroke lesion outcome, at a 3-month follow-up, would provide an important support to the physicians' decision process. In this work, we propose an automatic deep learning-based method for stroke lesion outcome prediction. Our main contribution resides in the combination of multi-modal Magnetic Resonance Imaging maps with non-imaging clinical meta-data: the thrombolysis in cerebral infarction scale, which categorizes the success of recanalization, achieved through mechanical thrombectomy. In our proposal, this clinical information is considered at two levels. First, at a population level by embedding the clinical information in a custom loss function used during training of our deep learning architecture. Second, at a patient-level through an extra input channel of the neural network used at testing time for a given patient case. By merging imaging with non-imaging clinical information, we aim to obtain a model aware of the principal and collateral blood flow dynamics for cases where there is no perfusion beyond the point of occlusion and for cases where the perfusion is complete after the occlusion point.
topic stroke
machine learning
deep learning
MRI
prediction
url https://www.frontiersin.org/article/10.3389/fneur.2018.01060/full
work_keys_str_mv AT adrianopinto strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT adrianopinto strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT richardmckinley strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT victoralves strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT rolandwiest strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT carlosasilva strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
AT mauricioreyes strokelesionoutcomepredictionbasedonmriimagingcombinedwithclinicalinformation
_version_ 1716793699350872064