Incorrect placement of the needle causes medical complications in the epidural block, such as dural puncture or spinal cord injury. This study proposes a system which combines an optical coherence tomography (OCT) imaging probe with an automatic identification (AI) system to objectively identify the position of the epidural needle tip. The automatic identification system uses three features as image parameters to distinguish the different tissue by three classifiers. Finally, we found that the support vector machine (SVM) classifier has highest accuracy, specificity, and sensitivity, which reached to 95%, 98%, and 92%, respectively.

Date Published: 12 February 2018
PDF: 7 pages
Proc. SPIE 10484, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XVI, 104840D (12 February 2018); doi: 10.1117/12.2289750

Published in SPIE Proceedings Vol. 10484:
Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XVI
Tuan Vo-Dinh; Anita Mahadevan-Jansen; Warren S. Grundfest M.D., Editor(s)