%0 Journal Article %1 Maktabi2020-fk %A Maktabi, Marianne %A Köhler, Hannes %A Ivanova, Magarita %A Neumuth, Thomas %A Rayes, Nada %A Seidemann, Lena %A Sucher, Robert %A Jansen-Winkeln, Boris %A Gockel, Ines %A Barberio, Manuel %A Chalopin, Claire %D 2020 %I Wiley %J Int. J. Med. Robot. %K and assisted computer guided head imaged imaging; intraoperative neck; surgery; thyroidectomy %N 5 %P 1--10 %T Classification of hyperspectral endocrine tissue images using support vector machines %V 16 %X 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\% $\pm$ 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.

@article{Maktabi2020-fk, 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\% $\pm$ 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.}, added-at = {2024-09-10T11:54:51.000+0200}, author = {Maktabi, Marianne and K{\"o}hler, Hannes and Ivanova, Magarita and Neumuth, Thomas and Rayes, Nada and Seidemann, Lena and Sucher, Robert and Jansen-Winkeln, Boris and Gockel, Ines and Barberio, Manuel and Chalopin, Claire}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/25a5f1758ecc38c4c6b4a26664d80cb18/scadsfct}, copyright = {http://creativecommons.org/licenses/by-nc/4.0/}, interhash = {286852a1e027aa07962543539cc016df}, intrahash = {5a5f1758ecc38c4c6b4a26664d80cb18}, journal = {Int. J. Med. Robot.}, keywords = {and assisted computer guided head imaged imaging; intraoperative neck; surgery; thyroidectomy}, language = {en}, month = oct, number = 5, pages = {1--10}, publisher = {Wiley}, timestamp = {2024-09-10T11:54:51.000+0200}, title = {Classification of hyperspectral endocrine tissue images using support vector machines}, volume = 16, year = 2020 }