For Publishers
DiscoveryMetadataPeer reviewHostingPublishing
For Researchers
JoinPublishReviewCollect
Register
Blog
About
Search
Advanced search
My ScienceOpen
Search
For Publishers
For Researchers
Blog
About
3
views
37
references
 Top references
cited by
2
    
0 reviews
 Review
0
comments
 Comment
0
recommends
+1 Recommend
0 collections
    0
    shares
      532
      similar
       All similar
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study

      research-article
      Author(s): a , b , c , d , 1 , a , 1 , e , b , f , a , b , c , d , a , b , c , d , a , b , c , d , g , a , b , c , d , f , a , b , c , d , a , b , c , d , a , c , d , h , *
      Publication date (Electronic):
      Journal: NeuroImage : Clinical
      Publisher: Elsevier
      Keywords: ICH, intracerebral hemorrhage, PHE, perihematomal edema, NCCT, non-contrast computed tomography, mRS, modified Rankin Scale, GCS, Glasgow Coma Scale, AUC, area under the receiver operating characteristic curve, ROC, receiver operating characteristic, IDI, integrated discrimination improvement, NRI, net reclassification improvement, Intracerebral hemorrhage, Radiomics, Non-contrast computed tomography, Perihematomal edema, Outcome

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Highlights

          • •

            Age, hemorrhage volume and location, and Glasgow Coma Scale score were independently associated with intracerebral hemorrhage outcomes.

          • •

            Radiomics features can quantitatively analyze morphological features and the internal heterogeneity of the hematoma and edema area.

          • •

            The radiomics features of hemorrhage and perihematomal edema areas providing additional value in prognostic prediction and risk stratification.

          Abstract

          Background

          Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH.

          Methods

          This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their outcomes at 3 months were recorded based on the modified Rankin Scale (good, 0–3; poor, 4–6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts.

          Results

          Among the 1098 ICH patients evaluated (mean age, 60 ± 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 ( P < 0.001), and integrated discrimination improvement, 0.050 ( P < 0.001).

          Conclusions

          The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy.

          Related collections

          Most cited references37

          • Record: found
          • Abstract: found
          • Article: not found

          The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

          Alex Zwanenburg, Martin Vallières, Mahmoud A. Abdalah … (2020)
          Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.
          Article 0 comments Cited 984 times – based on 0 reviews     Review now
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Prognosis of cerebral vein and dural sinus thrombosis: results of the International Study on Cerebral Vein and Dural Sinus Thrombosis (ISCVT).

            José M. Ferro, Patrícia Canhão, Jan Stam … (2004)
            The natural history and long-term prognosis of cerebral vein and dural sinus thrombosis (CVT) have not been examined previously by adequately powered prospective studies. We performed a multinational (21 countries), multicenter (89 centers), prospective observational study. Patients were followed up at 6 months and yearly thereafter. Primary outcome was death or dependence as assessed by modified Rankin Scale (mRS) score >2 at the end of follow-up. From May 1998 to May 2001, 624 adult patients with CVT were registered. At the end of follow-up (median 16 months), 356 patients (57.1%) had no symptom or signs (mRS=0), 137 (22%) had minor residual symptoms (mRS=1), and 47 (7.5%) had mild impairments (mRS=2). Eighteen (2.9%) were moderately impaired (mRS=3), 14 (2.2%) were severely handicapped (mRS=4 or 5), and 52 (8.3%) had died. Multivariate predictors of death or dependence were age >37 years (hazard ratio [HR]=2.0), male sex (HR=1.6), coma (HR=2.7), mental status disorder (HR=2.0), hemorrhage on admission CT scan (HR=1.9), thrombosis of the deep cerebral venous system (HR=2.9), central nervous system infection (HR=3.3), and cancer (HR=2.9). Fourteen patients (2.2%) had a recurrent sinus thrombosis, 27 (4.3%) had other thrombotic events, and 66 (10.6%) had seizures. The prognosis of CVT is better than reported previously. A subgroup (13%) of clinically identifiable CVT patients is at increased risk of bad outcome. These high-risk patients may benefit from more aggressive therapeutic interventions, to be studied in randomized clinical trials.
            Article 0 comments Cited 503 times – based on 0 reviews     Review now
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Hemorrhagic and ischemic strokes compared: stroke severity, mortality, and risk factors.

              Tom Olsen, Kell K. Andersen, Lars Kammersgaard … (2009)
              Stroke patients with hemorrhagic (HS) and ischemic strokes were compared with regard to stroke severity, mortality, and cardiovascular risk factors. A registry started in 2001, with the aim of registering all hospitalized stroke patients in Denmark, now holds information for 39,484 patients. The patients underwent an evaluation including stroke severity (Scandinavian Stroke Scale), CT, and cardiovascular risk factors. They were followed-up from admission until death or censoring in 2007. Independent predictors of death were identified by means of a survival model based on 25,123 individuals with a complete data set. Of the patients 3993 (10.1%) had HS. Stroke severity was almost linearly related to the probability of having HS (2% in patients with the mildest stroke and 30% in those with the most severe strokes). Factors favoring ischemic strokes vs HS were diabetes, atrial fibrillation, previous myocardial infarction, previous stroke, and intermittent arterial claudication. Smoking and alcohol consumption favored HS, whereas age, sex, and hypertension did not herald stroke type. Compared with ischemic strokes, HS was associated with an overall higher mortality risk (HR, 1.564; 95% CI, 1.441-1.696). The increased risk was, however, time-dependent; initially, risk was 4-fold, after 1 week it was 2.5-fold, and after 3 weeks it was 1.5-fold. After 3 months stroke type did not correlate to mortality. Strokes are generally more severe in patients with HS. Within the first 3 months after stroke, HS is associated with a considerable increase of mortality, which is specifically associated with the hemorrhagic nature of the lesion.
              Article 0 comments Cited 162 times – based on 0 reviews     Review now
                Bookmark
                All references

                Author and article information

                Contributors
                Junlin Zhou
                Journal
                Journal ID (nlm-ta): Neuroimage Clin
                Journal ID (iso-abbrev): Neuroimage Clin
                Title: NeuroImage : Clinical
                Publisher: Elsevier
                ISSN (Electronic): 2213-1582
                Publication date PMC-release: 19 October 2022
                Publication date Collection: 2022
                Publication date (Electronic): 19 October 2022
                Volume: 36
                Electronic Location Identifier: 103242
                Affiliations
                [a ]Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China
                [b ]Second Clinical School, Lanzhou University, Lanzhou 730030, China
                [c ]Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China
                [d ]Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China
                [e ]Department of Radiology, Xi’an Central Hospital, Xi An 710000, China
                [f ]Department of Radiology, Gansu Provincial Hospital, Lanzhou 730030, China
                [g ]GE Healthcare, Beijing 100176, China
                [h ]Department of Neurosurgery, Lanzhou University Second Hospital Lanzhou 730030, China
                Author notes
                [* ]Corresponding author at: Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China. ery_zhoujl@ 123456lzu.edu.cn
                [1]

                Xiaoyu Huang and Dan Wang contributed equally to this work.

                Article
                Publisher Item ID: S2213-1582(22)00307-2 Publisher ID: 103242
                DOI: 10.1016/j.nicl.2022.103242
                PMC ID: 9668657
                PubMed ID: 36279754
                SO-VID: 46f2db7e-6e3d-433e-8bcd-b35b0363fd2e
                Copyright © © 2022 The Authors
                License:

                This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

                History
                Date received : 25 August 2022
                Date revision received : 15 October 2022
                Date accepted : 18 October 2022
                Categories
                Subject: Regular Article

                Keywords: ich, intracerebral hemorrhage,phe, perihematomal edema,ncct, non-contrast computed tomography,mrs, modified rankin scale,gcs, glasgow coma scale,auc, area under the receiver operating characteristic curve,roc, receiver operating characteristic,idi, integrated discrimination improvement,nri, net reclassification improvement,intracerebral hemorrhage,radiomics,non-contrast computed tomography,perihematomal edema,outcome
                Data availability:
                Keywords: ich, intracerebral hemorrhage, phe, perihematomal edema, ncct, non-contrast computed tomography, mrs, modified rankin scale, gcs, glasgow coma scale, auc, area under the receiver operating characteristic curve, roc, receiver operating characteristic, idi, integrated discrimination improvement, nri, net reclassification improvement, intracerebral hemorrhage, radiomics, non-contrast computed tomography, perihematomal edema, outcome

                Comments

                Comment on this article

                scite_

                Similar content532

                See all similar

                Cited by2

                See all cited by

                Most referenced authors686

                See all reference authors