Classification of Hyperspectral Endocrine Tissue Images Using Support Vector Machines

Abstract

Background: Thyroidectomy is one of the most commonly performed surgical procedures. The region of the neck has a very complex structural organization. It would be beneficial to introduce a tool that can assist the surgeon in tissue discrimination during the procedure. One such solution is the noninvasive and contactless technique, called hyperspectral imaging (HSI).

Methods: To interpret the HSI data, we implemented a supervised classification method to automatically discriminate the parathyroid, the thyroid, and the recurrent laryngeal nerve from surrounding tissue(muscle, skin) and materials (instruments, gauze). A leave-one-patient-out cross-validation was performed.

Results: The best performance was obtained using support vector machine (SVM) with a classification and visualization in less than 1.4 seconds. A mean patient accuracy of 68% ± 23% was obtained for all tissues and material types.

Conclusions: The proposed method showed promising results and have to be confirmed on a larger cohort of patient data.

Keywords: computer assisted surgery; head and neck; imaged guided surgery; intraoperative imaging; surgery; thyroidectomy.

© 2020 The Authors. The International Journal of Medical Robotics and Computer Assisted Surgery published by John Wiley & Sons Ltd.

Download