Perfusion Quantification from Endoscopic Videos: Learning to Read Tumor Signatures

TL;DR

This paper introduces a real-time perfusion quantification technique using multispectral endoscopic videos to differentiate between healthy, benign, and malignant tissues during cancer surgery, leveraging tumor-specific vascular signatures.

Contribution

It presents a novel method for intra-operative tumor identification based on perfusion patterns, enabling real-time discrimination of tissue types during surgery.

Findings

Achieved 95% accuracy in distinguishing tissue types

Demonstrated effectiveness on colorectal cancer endoscopic videos

Introduced a tumor signature based on perfusion patterns

Abstract

Intra-operative identification of malignant versus benign or healthy tissue is a major challenge in fluorescence guided cancer surgery. We propose a perfusion quantification method for computer-aided interpretation of subtle differences in dynamic perfusion patterns which can be used to distinguish between normal tissue and benign or malignant tumors intra-operatively in real-time by using multispectral endoscopic videos. The method exploits the fact that vasculature arising from cancer angiogenesis gives tumors differing perfusion patterns from the surrounding tissue, and defines a signature of tumor which could be used to differentiate tumors from normal tissues. Experimental evaluation of our method on a cohort of colorectal cancer surgery endoscopic videos suggests that the proposed tumor signature is able to successfully discriminate between healthy, cancerous and benign tissue with 95% accuracy.