Development of a Research Testbed for Intraoperative Optical Spectroscopy Tumor Margin Assessment

Abstract

Surgical intervention is a primary treatment option for early-stage cancers. However, the difficulty of intraoperative tumor margin assessment contributes to a high rate of incomplete tumor resection, necessitating revision surgery. This work aims to develop and evaluate a prototype of a tracked tissue sensing research testbed for navigated tumor margin assessment. Our testbed employs diffuse reflection broadband optical spectroscopy for tissue characterization and electromagnetic tracking for navigation. Spectroscopy data and a trained classifier are used to predict tissue types. Navigation allows these predictions to be superimposed on the scanned tissue, creating a spatial classification map. We evaluate the real-time operation of our testbed using an ex vivo tissue phantom. Furthermore, we use the testbed to interrogate ex vivo human kidney tissue and establish a modeling pipeline to classify cancerous and non-neoplastic tissue. The testbed recorded latencies of 125 ± 11 ms and 167 ± 26 ms for navigation and classification respectively. The testbed achieved a Dice similarity coefficient of 93%, and an accuracy of 94% for the spatial classification. These results demonstrated the capabilities of our testbed for the real-time interrogation of an arbitrary tissue volume. Our modeling pipeline attained a balanced accuracy of 91% ± 4% on the classification of cancerous and non-neoplastic human kidney tissue. Our tracked tissue sensing research testbed prototype shows potential for facilitating the development and evaluation of intraoperative tumor margin assessment technologies across tissue types. The capacity to assess tumor margin status intraoperatively has the potential to increase surgeon confidence in complete tumor resection, thereby reducing the rates of revision surgeries.