Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System
Objective: Reliable quantification of white matter hyperintensities (WHMs) resulting from cerebral small vessel diseases (CSVD) is essential for understanding their clinical impact. We aim to develop and clinically validate a deep learning system for automatic segmentation of CSVD-WMH from fluid-att...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Frontiers Media S.A.
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/230212472b924008b293542052464307 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:230212472b924008b293542052464307 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:230212472b924008b2935420524643072021-12-01T02:35:07ZSegmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System2296-858X10.3389/fmed.2021.681183https://doaj.org/article/230212472b924008b2935420524643072021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.681183/fullhttps://doaj.org/toc/2296-858XObjective: Reliable quantification of white matter hyperintensities (WHMs) resulting from cerebral small vessel diseases (CSVD) is essential for understanding their clinical impact. We aim to develop and clinically validate a deep learning system for automatic segmentation of CSVD-WMH from fluid-attenuated inversion recovery (FLAIR) imaging using large multicenter data.Method: A FLAIR imaging dataset of 1,156 patients diagnosed with CSVD associated WMH (median age, 54 years; 653 males) obtained between September 2018 and September 2019 from Beijing Tiantan Hospital was retrospectively analyzed in this study. Locations of CSVD-WMH on the FLAIR scans were manually marked by two experienced neurologists. Using the manually labeled data of 996 patients (development set), a U-shaped novel 2D convolutional neural network (CNN) architecture was trained for automatic segmentation of CSVD-WMH. The segmentation performance of the network was evaluated with per pixel and lesion level dice scores using an independent internal test set (n = 160) and a multi-center external test set (n = 90, three medical centers). The clinical suitability of the segmentation results, classified as acceptable, acceptable with minor revision, acceptable with major revision, and not acceptable, was analyzed by three independent neuroradiologists. The inter-neuroradiologists agreement rate was assessed by the Kendall-W test.Results: On the internal and external test sets, the proposed CNN architecture achieved per pixel and lesion level dice scores of 0.72 (external test set), and they were significantly better than the state-of-the-art deep learning architectures proposed for WMH segmentation. In the clinical evaluation, neuroradiologists observed the segmentation results for 95% of the patients were acceptable or acceptable with a minor revision.Conclusions: A deep learning system can be used for automated, objective, and clinically meaningful segmentation of CSVD-WMH with high accuracy.Wei ShanWei ShanWei ShanYunyun DuanYu ZhengZhenzhou WuShang Wei ChanQun WangQun WangQun WangPeiyi GaoYaou LiuKunlun HeKunlun HeYongjun WangYongjun WangFrontiers Media S.A.articlemasking white matter hyperintensitiesdeep learningneural networksegmentationclinical evaluationMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
masking white matter hyperintensities deep learning neural network segmentation clinical evaluation Medicine (General) R5-920 |
| spellingShingle |
masking white matter hyperintensities deep learning neural network segmentation clinical evaluation Medicine (General) R5-920 Wei Shan Wei Shan Wei Shan Yunyun Duan Yu Zheng Zhenzhou Wu Shang Wei Chan Qun Wang Qun Wang Qun Wang Peiyi Gao Yaou Liu Kunlun He Kunlun He Yongjun Wang Yongjun Wang Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| description |
Objective: Reliable quantification of white matter hyperintensities (WHMs) resulting from cerebral small vessel diseases (CSVD) is essential for understanding their clinical impact. We aim to develop and clinically validate a deep learning system for automatic segmentation of CSVD-WMH from fluid-attenuated inversion recovery (FLAIR) imaging using large multicenter data.Method: A FLAIR imaging dataset of 1,156 patients diagnosed with CSVD associated WMH (median age, 54 years; 653 males) obtained between September 2018 and September 2019 from Beijing Tiantan Hospital was retrospectively analyzed in this study. Locations of CSVD-WMH on the FLAIR scans were manually marked by two experienced neurologists. Using the manually labeled data of 996 patients (development set), a U-shaped novel 2D convolutional neural network (CNN) architecture was trained for automatic segmentation of CSVD-WMH. The segmentation performance of the network was evaluated with per pixel and lesion level dice scores using an independent internal test set (n = 160) and a multi-center external test set (n = 90, three medical centers). The clinical suitability of the segmentation results, classified as acceptable, acceptable with minor revision, acceptable with major revision, and not acceptable, was analyzed by three independent neuroradiologists. The inter-neuroradiologists agreement rate was assessed by the Kendall-W test.Results: On the internal and external test sets, the proposed CNN architecture achieved per pixel and lesion level dice scores of 0.72 (external test set), and they were significantly better than the state-of-the-art deep learning architectures proposed for WMH segmentation. In the clinical evaluation, neuroradiologists observed the segmentation results for 95% of the patients were acceptable or acceptable with a minor revision.Conclusions: A deep learning system can be used for automated, objective, and clinically meaningful segmentation of CSVD-WMH with high accuracy. |
| format |
article |
| author |
Wei Shan Wei Shan Wei Shan Yunyun Duan Yu Zheng Zhenzhou Wu Shang Wei Chan Qun Wang Qun Wang Qun Wang Peiyi Gao Yaou Liu Kunlun He Kunlun He Yongjun Wang Yongjun Wang |
| author_facet |
Wei Shan Wei Shan Wei Shan Yunyun Duan Yu Zheng Zhenzhou Wu Shang Wei Chan Qun Wang Qun Wang Qun Wang Peiyi Gao Yaou Liu Kunlun He Kunlun He Yongjun Wang Yongjun Wang |
| author_sort |
Wei Shan |
| title |
Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| title_short |
Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| title_full |
Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| title_fullStr |
Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| title_full_unstemmed |
Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System |
| title_sort |
segmentation of cerebral small vessel diseases-white matter hyperintensities based on a deep learning system |
| publisher |
Frontiers Media S.A. |
| publishDate |
2021 |
| url |
https://doaj.org/article/230212472b924008b293542052464307 |
| work_keys_str_mv |
AT weishan segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT weishan segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT weishan segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT yunyunduan segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT yuzheng segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT zhenzhouwu segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT shangweichan segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT qunwang segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT qunwang segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT qunwang segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT peiyigao segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT yaouliu segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT kunlunhe segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT kunlunhe segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT yongjunwang segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem AT yongjunwang segmentationofcerebralsmallvesseldiseaseswhitematterhyperintensitiesbasedonadeeplearningsystem |
| _version_ |
1718405890968649728 |