BACKGROUND AND PURPOSE: Radiomics provides a framework for automated extraction of high-dimensional feature sets from medical images. We aimed to determine radiomics signature correlates of admission clinical severity and medium-term outcome from intracerebral hemorrhage (ICH) lesions on baseline head computed tomography (CT). METHODS: We used the ATACH-2 (Antihypertensive Treatment of Acute Cerebral Hemorrhage II) trial dataset. Patients included in this analysis (n = 895) were randomly allocated to discovery (n = 448) and independent validation (n = 447) cohorts. We extracted 1130 radiomics features from hematoma lesions on baseline noncontrast head CT scans and generated radiomics signatures associated with admission Glasgow Coma Scale (GCS), admission National Institutes of Health Stroke Scale (NIHSS), and 3-month modified Rankin Scale (mRS) scores. Spearman's correlation between radiomics signatures and corresponding target variables was compared with hematoma volume. RESULTS: In the discovery cohort, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.47 vs. 0.44, p = 0.008), admission NIHSS (0.69 vs. 0.57, p < 0.001), and 3-month mRS scores (0.44 vs. 0.32, p < 0.001). Similarly, in independent validation, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.43 vs. 0.41, p = 0.02), NIHSS (0.64 vs. 0.56, p < 0.001), and 3-month mRS scores (0.43 vs. 0.33, p < 0.001). In multiple regression analysis adjusted for known predictors of ICH outcome, the radiomics signature was an independent predictor of 3-month mRS in both cohorts. CONCLUSIONS: Limited by the enrollment criteria of the ATACH-2 trial, we showed that radiomics features quantifying hematoma texture, density, and shape on baseline CT can provide imaging correlates for clinical presentation and 3-month outcome. These findings couldtrigger a paradigm shift where imaging biomarkers may improve current modelsfor prognostication, risk-stratification, and treatment triage of ICH patients.
BACKGROUND AND PURPOSE: Radiomics provides a framework for automated extraction of high-dimensional feature sets from medical images. We aimed to determine radiomics signature correlates of admission clinical severity and medium-term outcome from intracerebral hemorrhage (ICH) lesions on baseline head computed tomography (CT). METHODS: We used the ATACH-2 (Antihypertensive Treatment of Acute Cerebral Hemorrhage II) trial dataset. Patients included in this analysis (n = 895) were randomly allocated to discovery (n = 448) and independent validation (n = 447) cohorts. We extracted 1130 radiomics features from hematoma lesions on baseline noncontrast head CT scans and generated radiomics signatures associated with admission Glasgow Coma Scale (GCS), admission National Institutes of Health Stroke Scale (NIHSS), and 3-month modified Rankin Scale (mRS) scores. Spearman's correlation between radiomics signatures and corresponding target variables was compared with hematoma volume. RESULTS: In the discovery cohort, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.47 vs. 0.44, p = 0.008), admission NIHSS (0.69 vs. 0.57, p < 0.001), and 3-month mRS scores (0.44 vs. 0.32, p < 0.001). Similarly, in independent validation, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.43 vs. 0.41, p = 0.02), NIHSS (0.64 vs. 0.56, p < 0.001), and 3-month mRS scores (0.43 vs. 0.33, p < 0.001). In multiple regression analysis adjusted for known predictors of ICH outcome, the radiomics signature was an independent predictor of 3-month mRS in both cohorts. CONCLUSIONS: Limited by the enrollment criteria of the ATACH-2 trial, we showed that radiomics features quantifying hematoma texture, density, and shape on baseline CT can provide imaging correlates for clinical presentation and 3-month outcome. These findings couldtrigger a paradigm shift where imaging biomarkers may improve current modelsfor prognostication, risk-stratification, and treatment triage of ICH patients.
Authors: Zachary Grunwald; Lauren A Beslow; Sebastian Urday; Anastasia Vashkevich; Alison Ayres; Steven M Greenberg; Joshua N Goldstein; Audrey Leasure; Fu-Dong Shi; Kristopher T Kahle; Thomas W K Battey; J Marc Simard; Jonathan Rosand; W Taylor Kimberly; Kevin N Sheth Journal: Neurocrit Care Date: 2017-04 Impact factor: 3.210
Authors: Santosh B Murthy; Sebastian Urday; Lauren A Beslow; Jesse Dawson; Kennedy Lees; W Taylor Kimberly; Costantino Iadecola; Hooman Kamel; Daniel F Hanley; Kevin N Sheth; Wendy C Ziai Journal: J Neurol Neurosurg Psychiatry Date: 2016-07-27 Impact factor: 10.154
Authors: Melissa A LoPresti; Samuel S Bruce; Elvis Camacho; Sudkir Kunchala; Byron G Dubois; Eliza Bruce; Geoff Appelboom; E Sander Connolly Journal: J Neurol Sci Date: 2014-07-05 Impact factor: 3.181
Authors: Stefan P Haider; Kariem Sharaf; Tal Zeevi; Philipp Baumeister; Christoph Reichel; Reza Forghani; Benjamin H Kann; Alexandra Petukhova; Benjamin L Judson; Manju L Prasad; Chi Liu; Barbara Burtness; Amit Mahajan; Seyedmehdi Payabvash Journal: Transl Oncol Date: 2020-10-16 Impact factor: 4.243
Authors: Chad Tang; Brian Hobbs; Ahmed Amer; Xiao Li; Carmen Behrens; Jaime Rodriguez Canales; Edwin Parra Cuentas; Pamela Villalobos; David Fried; Joe Y Chang; David S Hong; James W Welsh; Boris Sepesi; Laurence Court; Ignacio I Wistuba; Eugene J Koay Journal: Sci Rep Date: 2018-01-31 Impact factor: 4.379
Authors: Stefan P Haider; Adnan I Qureshi; Abhi Jain; Hishan Tharmaseelan; Elisa R Berson; Shahram Majidi; Christopher G Filippi; Adrian Mak; David J Werring; Julian N Acosta; Ajay Malhotra; Jennifer A Kim; Lauren H Sansing; Guido J Falcone; Kevin N Sheth; Seyedmehdi Payabvash Journal: Int J Stroke Date: 2021-10-13 Impact factor: 6.948