Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm.
| Autor: | Saba L; Department of Radiology, A.O.U., Cagliari, Italy., Biswas M; Department of Computer Science and Engineering, JIS University, Agarpara, Kolkata, India., Suri HS; Brown University, Providence, Rhode Island, USA., Viskovic K; Department of Radiology and Ultrasound University Hospital for Infectious Diseases, Zagreb, Croatia., Laird JR; Heart and Vascular Institute, Adventist, St. Helena Hospital, Napa Valley, CA, USA., Cuadrado-Godia E; Department of Neurology, IMIM-Hospital del Mar, Barcelona, Spain., Nicolaides A; Vascular Screening and Diagnostic Centre, London, UK.; Department of Biological Sciences, University of Cyprus, Nicosia, Cyprus., Khanna NN; Cardiology Department, Indraprastha Apollo Hospitals, New Delhi, India., Viswanathan V; MV Hospital for Diabetes and Professor M Viswanathan Diabetes Research Centre, Chennai, India., Suri JS; Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Cardiovascular diagnosis and therapy [Cardiovasc Diagn Ther] 2019 Oct; Vol. 9 (5), pp. 439-461. |
| DOI: | 10.21037/cdt.2019.09.01 |
| Abstrakt: | Background: Stroke is in the top three leading causes of death worldwide. Non-invasive monitoring of stroke can be accomplished via stenosis measurements. The current conventional image-based methods for these measurements are not accurate and reliable. They do not incorporate shape and intelligent learning component in their design. Methods: In this study, we propose a deep learning (DL)-based methodology for accurate measurement of stenosis in common carotid artery (CCA) ultrasound (US) scans using a class of AtheroEdge system from AtheroPoint, USA. Three radiologists manually traced the lumen-intima (LI) for the near and the far walls, respectively, which served as a gold standard (GS) for training the DL-based model. Three DL-based systems were developed based on three types of GS. Results: IRB approved (Toho University, Japan) 407 US scans from 204 patients were collected. The risk was characterized into three classes: low, moderate, and high-risk. The area-under-curve (AUC) corresponding to three DL systems using receiver operating characteristic (ROC) analysis computed were: 0.90, 0.94 and 0.86, respectively. Conclusions: Novel DL-based strategy showed reliable, accurate and stable stenosis severity index (SSI) measurements. Competing Interests: Conflicts of Interest: The authors have no conflicts of interest to declare. (2019 Cardiovascular Diagnosis and Therapy. All rights reserved.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|