Purpose: Esophageal carcinoma is the eighth most common cancer worldwide. Esophageal resection with gastric pull-up is a potentially curative therapeutic option. After this procedure, the specimen is examined by the pathologist to confirm complete removal of the cancer. An intraoperative analysis of the resectate would be less time-consuming and therefore improve patient safety.
Methods: Hyperspectral imaging (HSI) is a relatively new modality, which has shown promising results for the detection of tumors. Automatic approaches could support the surgeon in the visualization of tumor margins. Therefore, we evaluated four supervised classification algorithms: random forest, support vector machines (SVM), multilayer perceptron, and k-nearest neighbors to differentiate malignant from healthy tissue based on HSI recordings of esophago-gastric resectates in 11 patients.
Results: The best performances were obtained with a cancerous tissue detection of 63% sensitivity and 69% specificity with the SVM. In a leave-one patient-out cross-validation, the classification showed larger performance differences according to the patient data used. In less than 1 s, data classification and visualization was shown.
Conclusion: In this work, we successfully tested several classification algorithms for the automatic detection of esophageal carcinoma in resected tissue. A larger data set and a combination of several methods would probably increase the performance. Moreover, the implementation of software tools for intraoperative tumor boundary visualization will further support the surgeon during oncologic operations.
Keywords: Cancer detection; Hyperspectral imaging (HSI); Machine learning; Visceral surgery.