EUVIMEDEUVIMED entdecken
Crossref

Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features

Phattanun Thabarsa, Papangkorn Inkeaw, Chakri Madla, Withawat Vuthiwong, Kittisak Unsrisong, Natipat Jitmahawong, Thanwa Sudsang, Chaisiri Angkurawaranon, Salita Angkurawaranon

Neuroradiology · 2025

DOI: 10.1007/s00234-024-03481-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neuroradiology, 2025. Verfasst von Phattanun Thabarsa und 8 weiteren Autor:innen. Beteiligte Einrichtung: Master's Degree Program in Data Science, Faculty of Engineering, Chiang Mai University, Chiang Mai, 50200, Thailand. Hauptthemen laut MEDLINE: Machine Learning, Tomography, X-Ray Computed, Intracranial Hemorrhages. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Chiang Mai University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To assess the efficacy of radiomics features extracted from non-contrast computed tomography (NCCT) scans in differentiating multiple etiologies of spontaneous intracerebral hemorrhage (ICH). METHODS: CT images and clinical data from 141 ICH patients from 2010 to 2022 were collected. The cohort comprised primary (n = 57), tumorous (n = 46), and vascular malformation-related ICH (n = 38). Radiomics features were extracted from the initial brain NCCT scans and identified potential features using mutual information. A hierarchical classification with AdaBoost classifiers was employed to classify the multiple etiologies of ICH. Age of the patient and ICH's location were examined alongside radiomics features. The accuracy, area under the curve (AUC), sensitivity, and specificity were used to evaluate classification performance. RESULTS: The proposed method achieved an accuracy of 0.79. For identifying primary ICH, the model achieved a sensitivity of 0.86 and specificity of 0.87. Meanwhile, the sensitivity and specificity for identifying tumoral causes were 0.78 and 0.93, respectively. For vascular malformation, the model reached a sensitivity and specificity of 0.72 and 0.89, respectively. The AUCs for primary, tumorous, and vascular malformation were 0.86, 0.85, and 0.82, respectively. The findings further highlight the importance of texture-based variables in ICH classification. The age and location of the ICH can enhance the classification performance. CONCLUSION: The use of a machine learning model with radiomics features has the potential in classifying the three types of non-traumatic ICH. It may help the radiologist decide on an appropriate further examination plan to arrive at a correct diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTomography, X-Ray ComputedIntracranial HemorrhagesHumansMaleFemaleMiddle AgedSensitivity and SpecificityAdultAgedDiagnosis, DifferentialRadiographic Image Interpretation, Computer-AssistedRetrospective StudiesAged, 80 and overRadiomics

Stichwörter der Autor:innen

Machine learningNon-contrast enhanced CTRadiomicsSpontaneous intracerebral hemorrhage

Autor:innen und Institutionen

  • Master's Degree Program in Data Science, Faculty of Engineering, Chiang Mai University, Chiang Mai, 50200, Thailand.
  • Data Science Research Center, Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand.
  • Global Health and Chronic Conditions Research Group, Chiang Mai University, Chiang Mai, 50200, Thailand.
  • Department of Radiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand.
  • Department of Radiology, Ramathibodi Hospital, Mahidol University, Bangkok, 10400, Thailand.
  • Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand.

Förderung

  • Chiang Mai University

Zitieren

APA

Thabarsa, P., Inkeaw, P., Madla, C., Vuthiwong, W., Unsrisong, K., Jitmahawong, N., Sudsang, T., Angkurawaranon, C., & Angkurawaranon, S. (2025). Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features. Neuroradiology. https://doi.org/10.1007/s00234-024-03481-1

Vancouver

Thabarsa P, Inkeaw P, Madla C, Vuthiwong W, Unsrisong K, Jitmahawong N, et al. Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features. Neuroradiology. 2025. doi:10.1007/s00234-024-03481-1

BibTeX
@article{Thabarsa2025,
  author = {Thabarsa, Phattanun and Inkeaw, Papangkorn and Madla, Chakri and Vuthiwong, Withawat and Unsrisong, Kittisak and Jitmahawong, Natipat and Sudsang, Thanwa and Angkurawaranon, Chaisiri and Angkurawaranon, Salita},
  title = {Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features},
  journal = {Neuroradiology},
  year = {2025},
  doi = {10.1007/s00234-024-03481-1}
}
Kostenlos starten →