Maktabi Marianne, Köhler Hannes, Ivanova Magarita, Neumuth Thomas, Rayes Nada, Seidemann Lena, Sucher Robert, Jansen-Winkeln Boris, Gockel Ines, Barberio Manuel, Chalopin Claire
Innovation Center Computer Assisted Surgery (ICCAS), University of Leipzig, Leipzig, Germany.
Department of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, Leipzig, Germany.
Int J Med Robot. 2020 Oct;16(5):1-10. doi: 10.1002/rcs.2121. Epub 2020 May 29.
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).
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.
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.
The proposed method showed promising results and have to be confirmed on a larger cohort of patient data.
甲状腺切除术是最常施行的外科手术之一。颈部区域具有非常复杂的结构组织。引入一种能够在手术过程中协助外科医生进行组织辨别的工具将大有裨益。一种这样的解决方案是名为高光谱成像（HSI）的非侵入性且非接触式技术。
为了解释高光谱成像数据，我们实施了一种监督分类方法，以自动从周围组织（肌肉、皮肤）和材料（器械、纱布）中辨别甲状旁腺、甲状腺和喉返神经。进行了留一患者交叉验证。
使用支持向量机（SVM）在不到1.4秒内进行分类和可视化时获得了最佳性能。所有组织和材料类型的平均患者准确率为68%±23%。
所提出的方法显示出有前景的结果，并且必须在更大的患者数据集上得到证实。
