Classification of hyperspectral endocrine tissue images using support vector machines
Marianne Maktabi, H. Köhler, Magarita Ivanova, Thomas Neumuth, Nada Rayes, Lena Seidemann, Robert Sucher, Boris Jansen‐Winkeln, Ines Gockel, Manuel Barberio, Claire Chalopin
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.