Machine Learning-Based Prediction of Responsiveness to Neoadjuvant Chemoradiotheapy in Locally Advanced Rectal Cancer Patients from Endomicroscopy

• Published in: Critical reviews in oncogenesis Vol. 29; no. 2; p. 53
• Main Authors: Sabino, Alan U, Safatle-Ribeiro, Adriana V, Lima, Suzylaine S, Marques, Carlos F S, Maluf-Filho, Fauze, Ramos, Alexandre F
• Format: Journal Article
• Language: English
• Published: United States 2024
• Subjects: Colonoscopy - methods; Colorectal Neoplasms - diagnosis; Humans; Microscopy, Confocal - methods; Neoadjuvant Therapy; Neoplasms, Second Primary; Rectal Neoplasms - diagnostic imaging; Rectal Neoplasms - therapy
• ISSN: 0893-9675
• DOI: 10.1615/CritRevOncog.2023050075

The protocol for treating locally advanced rectal cancer consists of the application of chemoradiotherapy (neoCRT) followed by surgical intervention. One issue for clinical oncologists is predicting the efficacy of neoCRT in order to adjust the dosage and avoid treatment toxicity in cases when surgery should be conducted promptly. Biomarkers may be used for this purpose along with in vivo cell-level images of the colorectal mucosa obtained by probe-based confocal laser endomicroscopy (pCLE) during colonoscopy. The aim of this article is to report our experience with Motiro, a computational framework that we developed for machine learning (ML) based analysis of pCLE videos for predicting neoCRT response in locally advanced rectal cancer patients. pCLE videos were collected from 47 patients who were diagnosed with locally advanced rectal cancer (T3/T4, or N+). The patients received neoCRT. Response to treatment by all patients was assessed by endoscopy along with biopsy and magnetic resonance imaging (MRI). Thirty-seven patients were classified as non-responsive to neoCRT because they presented a visible macroscopic neoplastic lesion, as confirmed by pCLE examination. Ten remaining patients were considered responsive to neoCRT because they presented lesions as a scar or small ulcer with negative biopsy, at post-treatment follow-up. Motiro was used for batch mode analysis of pCLE videos. It automatically characterized the tumoral region and its surroundings. That enabled classifying a patient as responsive or non-responsive to neoCRT based on pre-neoCRT pCLE videos. Motiro classified patients as responsive or non-responsive to neoCRT with an accuracy of ~ 0.62 when using images of the tumor. When using images of regions surrounding the tumor, it reached an accuracy of ~ 0.70. Feature analysis showed that spatial heterogeneity in fluorescence distribution within regions surrounding the tumor was the main contributor to predicting response to neoCRT. We developed a computational framework to predict response to neoCRT by locally advanced rectal cancer patients based on pCLE images acquired pre-neoCRT. We demonstrate that the analysis of the mucosa of the region surrounding the tumor provides stronger predictive power.