Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke
While the penumbra zone is traditionally assessed based on perfusion–diffusion mismatch, it can be assessed based on machine learning (ML) prediction of infarct growth. The purpose of this work was to develop and validate an ML method for the prediction of infarct growth distribution and volume, in...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/9/6/1977 |
| _version_ | 1797564302645788672 |
|---|---|
| author | Yoon-Chul Kim Hyung Jun Kim Jong-Won Chung In Gyeong Kim Min Jung Seong Keon Ha Kim Pyoung Jeon Hyo Suk Nam Woo-Keun Seo Gyeong-Moon Kim Oh Young Bang |
| author_facet | Yoon-Chul Kim Hyung Jun Kim Jong-Won Chung In Gyeong Kim Min Jung Seong Keon Ha Kim Pyoung Jeon Hyo Suk Nam Woo-Keun Seo Gyeong-Moon Kim Oh Young Bang |
| author_sort | Yoon-Chul Kim |
| collection | DOAJ |
| description | While the penumbra zone is traditionally assessed based on perfusion–diffusion mismatch, it can be assessed based on machine learning (ML) prediction of infarct growth. The purpose of this work was to develop and validate an ML method for the prediction of infarct growth distribution and volume, in cases of successful (SR) and unsuccessful recanalization (UR). Pre-treatment perfusion-weighted, diffusion-weighted imaging (DWI) data, and final infarct lesions annotated from day-7 DWI from patients with middle cerebral artery occlusion were utilized to develop and validate two ML models for prediction of tissue fate. SR and UR models were developed from data in patients with modified treatment in cerebral infarction (mTICI) scores of 2b–3 and 0–2a, respectively. When compared to manual infarct annotation, ML-based infarct volume predictions resulted in an intraclass correlation coefficient (ICC) of 0.73 (95% CI = 0.31–0.91, <i>p</i> < 0.01) for UR, and an ICC of 0.87 (95% CI = 0.73–0.94, <i>p</i> < 0.001) for SR. Favorable outcomes for mismatch presence and absence in SR were 50% and 36%, respectively, while they were 61%, 56%, and 25%, respectively, for the low, intermediate, and high infarct growth groups. The presented method can offer novel and alternative insights into selecting patients for recanalization therapy and predicting functional outcome. |
| first_indexed | 2024-03-10T18:55:24Z |
| format | Article |
| id | doaj.art-822df29406134475b321ca13b4d68ed6 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T18:55:24Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-822df29406134475b321ca13b4d68ed62023-11-20T04:50:00ZengMDPI AGJournal of Clinical Medicine2077-03832020-06-0196197710.3390/jcm9061977Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic StrokeYoon-Chul Kim0Hyung Jun Kim1Jong-Won Chung2In Gyeong Kim3Min Jung Seong4Keon Ha Kim5Pyoung Jeon6Hyo Suk Nam7Woo-Keun Seo8Gyeong-Moon Kim9Oh Young Bang10Clinical Research Institute, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Radiology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Radiology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Radiology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Yonsei University, Seoul 03722, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Seoul 06351, KoreaWhile the penumbra zone is traditionally assessed based on perfusion–diffusion mismatch, it can be assessed based on machine learning (ML) prediction of infarct growth. The purpose of this work was to develop and validate an ML method for the prediction of infarct growth distribution and volume, in cases of successful (SR) and unsuccessful recanalization (UR). Pre-treatment perfusion-weighted, diffusion-weighted imaging (DWI) data, and final infarct lesions annotated from day-7 DWI from patients with middle cerebral artery occlusion were utilized to develop and validate two ML models for prediction of tissue fate. SR and UR models were developed from data in patients with modified treatment in cerebral infarction (mTICI) scores of 2b–3 and 0–2a, respectively. When compared to manual infarct annotation, ML-based infarct volume predictions resulted in an intraclass correlation coefficient (ICC) of 0.73 (95% CI = 0.31–0.91, <i>p</i> < 0.01) for UR, and an ICC of 0.87 (95% CI = 0.73–0.94, <i>p</i> < 0.001) for SR. Favorable outcomes for mismatch presence and absence in SR were 50% and 36%, respectively, while they were 61%, 56%, and 25%, respectively, for the low, intermediate, and high infarct growth groups. The presented method can offer novel and alternative insights into selecting patients for recanalization therapy and predicting functional outcome.https://www.mdpi.com/2077-0383/9/6/1977strokeischemiamachine learningcerebral infarction |
| spellingShingle | Yoon-Chul Kim Hyung Jun Kim Jong-Won Chung In Gyeong Kim Min Jung Seong Keon Ha Kim Pyoung Jeon Hyo Suk Nam Woo-Keun Seo Gyeong-Moon Kim Oh Young Bang Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke Journal of Clinical Medicine stroke ischemia machine learning cerebral infarction |
| title | Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke |
| title_full | Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke |
| title_fullStr | Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke |
| title_full_unstemmed | Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke |
| title_short | Novel Estimation of Penumbra Zone Based on Infarct Growth Using Machine Learning Techniques in Acute Ischemic Stroke |
| title_sort | novel estimation of penumbra zone based on infarct growth using machine learning techniques in acute ischemic stroke |
| topic | stroke ischemia machine learning cerebral infarction |
| url | https://www.mdpi.com/2077-0383/9/6/1977 |
| work_keys_str_mv | AT yoonchulkim novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT hyungjunkim novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT jongwonchung novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT ingyeongkim novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT minjungseong novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT keonhakim novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT pyoungjeon novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT hyosuknam novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT wookeunseo novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT gyeongmoonkim novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke AT ohyoungbang novelestimationofpenumbrazonebasedoninfarctgrowthusingmachinelearningtechniquesinacuteischemicstroke |