In vivo evaluation of complex polyps with endoscopic optical coherence tomography and deep learning during routine colonoscopy - a feasibility study

Sep 21, 2026

Uploaded by Eden

Standard-of-care imaging based on whitelight colonoscopy and narrow-band imaging lacks sufficient accuracy to non-invasively determine invasion depth of complex colorectal polyps during routine colonoscopy. This feasibility pilot study evaluates a custom endoscopic optical coherence tomography (OCT) probe using a side-viewing OCT catheter, capturing OCT images immediately before standard-of-care treatment. A deep learning model is trained to distinguish benign from deeply invasive lesions. Thirty-five polyps from 32 patients are analyzed; OCT adds time without OCT-related complications, correlates with histopathology, and the model attains AUROC 0.984 and Cohen’s kappa 0.845.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Background

Study design and methods

OCT imaging workflow

Deep learning model

Results

Safety and procedure time

Histopathologic correlation

Diagnostic performance

Conclusion

[www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN In vivo evaluation of complex polyps with endoscopic optical coherence tomography and deep learning during routine colonoscopy: a feasibility study Haolin Nie1,7, Hongbo Luo2,7, Vladimir Lamm3,7, Shuying Li1, Sanskar Thakur1,2, Chao Zhou1,2, Thomas Hollander3, Daniel Cho3, Erika Sloan3, Jingxia Liu4, Pooja Navale5, Ahmad N. Bazarbashi3, Juan Pablo Reyes Genere3, Vladimir M. Kushnir3 & Quing Zhu1,2,6􀀍 Standard-of-care (SoC) imaging for assessing colorectal polyps during colonoscopy, based on whitelight colonoscopy (WLC) and narrow-band imaging (NBI), does not have sufficient accuracy to assess the invasion depth of complex polyps non-invasively during colonoscopy. We aimed to evaluate the feasibility of a custom endoscopic optical coherence tomography (OCT) probe for assessing colorectal polyps during routine colonoscopy. Patients referred for endoscopic treatment of large colorectal polyps were enrolled in this pilot clinical study, which used a side-viewing OCT catheter developed for use with an adult colonoscope. OCT images of polyps were captured during colonoscopy immediately before SoC treatment. A deep learning model was trained to differentiate benign from deeply invasive lesions for real-time diagnosis. 35 polyps from 32 patients were included. OCT imaging added on average 3:40 min (range 1:54–8:20) to the total procedure time. No complications due to OCT were observed. OCT revealed distinct subsurface tissue structures that correlated with histological findings, including tubular adenoma (n = 20), tubulovillous adenoma (n = 10), sessile serrated polyps (n = 3), and invasive cancer (n = 2). The deep learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.984 (95%CI 0.972–0.996) and Cohen’s kappa of 0.845 (95%CI 0.774–0.915) when compared to gold standard histopathology. OCT is feasible and safe for polyp assessment during routine colonoscopy. When combined with deep learning, OCT offers clinicians increase confidence in identifying deeply invasive cancers, potentially improving clinical decisionmaking. Compared to previous studies, ours offers a nuanced comparison between not just benign and malignant lesions, but across multiple histological subtypes of polyps. Keywords Optical coherence tomography, Colonoscopy, Colorectal cancer, Polyp, In vivo, Deep learning Colorectal polyps are known precursors to most colorectal cancers (CRCs), a leading cause of cancer-related deaths worldwide1. The invasion of dysplastic elements beyond the mucosa is a critical factor in determining the appropriate treatment strategy. Endoscopic treatments, such as endoscopic mucosal resection (EMR), endoscopic submucosal dissection (ESD), and endoscopic full thickness resection (EFTR), are curative for neoplasms confined to the mucosa or superficial submucosa (<1 mm of submucosal invasion) . However, owing to an increased risk of lymph node metastasis, neoplastic lesions with deeper submucosal invasion (> 1 mm) should be referred for surgical resection2,3. Therefore, the ability to accurately assess, in real-time, the presence and extent of submucosal invasion in colorectal lesions is of clear clinical importance4. 1Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA. 2Department of Electrical & Systems Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA. 3Division of Gastroenterology, Washington University School of Medicine, St. Louis, MO 63110, USA. 4Division of Public Health Science, Division of Biostatistics, Washington University School of Medicine, St. Louis, MO 63110, USA. 5Department of Pathology & Immunology, Washington University School of Medicine, St. Louis, MO 63110, USA. 6Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, USA. 7Haolin Nie, Hongbo Luo and Vladimir Lamm contribu

FAQs

What problem does the study address in colorectal polyp assessment during colonoscopy?

Standard-of-care imaging during colonoscopy does not provide enough accuracy to non-invasively assess the invasion depth of complex polyps. The study targets the feasibility of OCT and deep learning to improve identification of deeply invasive disease.

How was the OCT imaging performed in this pilot study?

Patients undergoing endoscopic treatment of large colorectal polyps were enrolled. OCT images were captured during colonoscopy immediately before standard-of-care treatment using a side-viewing OCT catheter compatible with an adult colonoscope.

How did the deep learning model perform compared with histopathology?

When compared with gold-standard histopathology, the deep learning model achieved an AUROC of 0.984 and a Cohen’s kappa of 0.845, indicating strong diagnostic agreement for distinguishing benign from deeply invasive lesions.

Sep 21, 2026

Uploaded by Eden