Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study
Abstract To develop and validate non-contrast computed tomography (NCCT)-based radiomics method combines machine learning (ML) to investigate invisible microscopic acute ischaemic stroke (AIS) lesions. We retrospectively analyzed 1122 patients from August 2015 to July 2022, whose were later confirme...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88016-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571869610377216 |
|---|---|
| author | Kui Sun Rongchao Shi Xinxin Yu Ying Wang Wei Zhang Xiaoxia Yang Mei Zhang Jian Wang Shu Jiang Haiou Li Bing Kang Tong Li Shuying Zhao Yu Ai Jianfeng Qiu Haiyan Wang Ximing Wang |
| author_facet | Kui Sun Rongchao Shi Xinxin Yu Ying Wang Wei Zhang Xiaoxia Yang Mei Zhang Jian Wang Shu Jiang Haiou Li Bing Kang Tong Li Shuying Zhao Yu Ai Jianfeng Qiu Haiyan Wang Ximing Wang |
| author_sort | Kui Sun |
| collection | DOAJ |
| description | Abstract To develop and validate non-contrast computed tomography (NCCT)-based radiomics method combines machine learning (ML) to investigate invisible microscopic acute ischaemic stroke (AIS) lesions. We retrospectively analyzed 1122 patients from August 2015 to July 2022, whose were later confirmed AIS by diffusion-weighted imaging (DWI). However, receiving a negative result was reported by radiologists according to the NCCT images. Patients in five institutions (n = 592) were combined to generate training and internal validation sets, remaining in three institutions as external validation sets (n = 204, 53 and 273). Through a series of procedures: head alignment, co-registration of NCCT and DWI, the volume of interest delineation and feature extraction. Multiple ML models (random forest, RF; support vector machine, SVM; logistic regression, LR; multilayer perceptron, MLP) were used to discriminate microscopic AIS and non-AIS. Among 1122 patients included (760 men [67.7%]; median [range] age, 64 [21–96] years). After least absolute shrinkage and selection operator (LASSO) algorithm, 44 optimal features were remained. The radiomics combined ML models were yielded similar mean areas under the receiver operating characteristic curve of 0.808 (95% CI 0.754 to 0.861) for RF, 0.802 (95% CI 0.748 to 0.856) for radial basis kernel function-based SVM, 0.792 (95% CI 0.737 to 0.847) for MLP, 0.792 (95% CI 0.736 to 0.848) for Linear-SVM and 0.787 (95% CI 0.730 to 0.844) for LR, respectively. Combining radiomics with ML models can be an efficient, noninvasive, economical, and reliable technique for evaluating invisible microscopic AIS on NCCT and assisting radiologists to make clinical decisions. |
| format | Article |
| id | doaj-art-8575f13c7b1a4983b2de66906afc4dcc |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8575f13c7b1a4983b2de66906afc4dcc2025-02-02T12:15:53ZengNature PortfolioScientific Reports2045-23222025-01-0115111210.1038/s41598-025-88016-1Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective studyKui Sun0Rongchao Shi1Xinxin Yu2Ying Wang3Wei Zhang4Xiaoxia Yang5Mei Zhang6Jian Wang7Shu Jiang8Haiou Li9Bing Kang10Tong Li11Shuying Zhao12Yu Ai13Jianfeng Qiu14Haiyan Wang15Ximing Wang16Department of General Surgery, Peking University Third HospitalDepartment of Radiology, Beijing Friendship Hospital, Capital Medical UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityDepartment of Radiology, Wangjing Hospital of CACMSDepartment of Radiology, The Third People’s Hospital of DatongDepartment of Radiology, Shandong First Medical University & Shandong Academy of Medical SciencesDepartment of Radiology, Jinan Central Hospital Affiliated to Shandong UniversityDepartment of Radiology, The First Affiliated Hospital of Shandong First Medical University, Shandong Provincial Qianfoshan HospitalDepartment of Radiology, Cheeloo College of Medicine, Qilu Hospital, Shandong UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityThe National Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders, Beijing Anding Hospital, Capital Medical UniversityDepartment of Otolaryngology-Head and Neck Surgery, Cheeloo College of Medicine, Shandong Provincial ENT Hospital, Shandong UniversityMedical Science and Technology Innovation Center, Shandong First Medical University, Shandong Academy of Medical SciencesDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityAbstract To develop and validate non-contrast computed tomography (NCCT)-based radiomics method combines machine learning (ML) to investigate invisible microscopic acute ischaemic stroke (AIS) lesions. We retrospectively analyzed 1122 patients from August 2015 to July 2022, whose were later confirmed AIS by diffusion-weighted imaging (DWI). However, receiving a negative result was reported by radiologists according to the NCCT images. Patients in five institutions (n = 592) were combined to generate training and internal validation sets, remaining in three institutions as external validation sets (n = 204, 53 and 273). Through a series of procedures: head alignment, co-registration of NCCT and DWI, the volume of interest delineation and feature extraction. Multiple ML models (random forest, RF; support vector machine, SVM; logistic regression, LR; multilayer perceptron, MLP) were used to discriminate microscopic AIS and non-AIS. Among 1122 patients included (760 men [67.7%]; median [range] age, 64 [21–96] years). After least absolute shrinkage and selection operator (LASSO) algorithm, 44 optimal features were remained. The radiomics combined ML models were yielded similar mean areas under the receiver operating characteristic curve of 0.808 (95% CI 0.754 to 0.861) for RF, 0.802 (95% CI 0.748 to 0.856) for radial basis kernel function-based SVM, 0.792 (95% CI 0.737 to 0.847) for MLP, 0.792 (95% CI 0.736 to 0.848) for Linear-SVM and 0.787 (95% CI 0.730 to 0.844) for LR, respectively. Combining radiomics with ML models can be an efficient, noninvasive, economical, and reliable technique for evaluating invisible microscopic AIS on NCCT and assisting radiologists to make clinical decisions.https://doi.org/10.1038/s41598-025-88016-1RadiomicsComputed tomographyMagnetic resonanceAcute ischaemic strokeMachine learningRandom Forest |
| spellingShingle | Kui Sun Rongchao Shi Xinxin Yu Ying Wang Wei Zhang Xiaoxia Yang Mei Zhang Jian Wang Shu Jiang Haiou Li Bing Kang Tong Li Shuying Zhao Yu Ai Jianfeng Qiu Haiyan Wang Ximing Wang Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study Scientific Reports Radiomics Computed tomography Magnetic resonance Acute ischaemic stroke Machine learning Random Forest |
| title | Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study |
| title_full | Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study |
| title_fullStr | Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study |
| title_full_unstemmed | Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study |
| title_short | Noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke (≤ 24 h): a multicentre retrospective study |
| title_sort | noninvasive imaging biomarker reveals invisible microscopic variation in acute ischaemic stroke ≤ 24 h a multicentre retrospective study |
| topic | Radiomics Computed tomography Magnetic resonance Acute ischaemic stroke Machine learning Random Forest |
| url | https://doi.org/10.1038/s41598-025-88016-1 |
| work_keys_str_mv | AT kuisun noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT rongchaoshi noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT xinxinyu noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT yingwang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT weizhang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT xiaoxiayang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT meizhang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT jianwang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT shujiang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT haiouli noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT bingkang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT tongli noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT shuyingzhao noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT yuai noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT jianfengqiu noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT haiyanwang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy AT ximingwang noninvasiveimagingbiomarkerrevealsinvisiblemicroscopicvariationinacuteischaemicstroke24hamulticentreretrospectivestudy |