Human colorectal cancer tissue assessment using optical coherence tomography catheter and deep learning

Abstract

Optical coherence tomography (OCT) can differentiate normal colonic mucosa from neoplasia, potentially offering a new mechanism of endoscopic tissue assessment and biopsy targeting, with a high optical resolution and an imaging depth of ~1 mm. Recent advances in convolutional neural networks (CNN) have enabled application in ophthalmology, cardiology, and gastroenterology malignancy detection with high sensitivity and specificity. Here, we describe a miniaturized OCT catheter and a residual neural network (ResNet)‐based deep learning model manufactured and trained to perform automatic image processing and real‐time diagnosis of the OCT images. The OCT catheter has an outer diameter of 3.8 mm, a lateral resolution of ~7 μm, and an axial resolution of ~6 μm. A customized ResNet is utilized to classify OCT catheter colorectal images. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.975 is achieved to distinguish between normal and cancerous colorectal tissue images.

Towards targeted colorectal cancer biopsy based on tissue morphology assessment by compression optical coherence elastography

“…The characteristic qualitative features, such as the absence of serrated architectonics and the disappearance of layering, were inextricably linked with the pathological processes of the colon, as was previously shown in the OCT examination of the colon by our research group ( 31 ) and others ( 56 ). However, in order to optimize qualitative diagnostic parameters of the OCT method for detecting cancer in benign and normal colon tissue, quantitative analysis parameters by deep learning-based pattern recognition were developed and applied recently ( 57 – 59 ). In these cases, machine learning relied on the disappearance of “teeth” structures ( 57 ), loss of layering ( 58 ) in hyperplastic or neoplastic processes of the colon.…”

“…In addition, it is also worth noting the high efficiency of combining OCT with machine learning in the differentiation of colorectal liver metastases from liver parenchyma ex vivo , which is very important in the intraoperative examination of resection margins during liver surgery ( 60 ). Subsequently, significant progress has been achieved in colonoscopy of colorectal cancer using OCT and machine learning, which was demonstrated in a recent publication ( 59 ), where high sensitivity and specificity (~93%) were achieved in the detection of colorectal cancer. However, as the authors noted, such studies did not assess the OCT ability to distinguish other colorectal pathologies, such as mucosal adenoma, which, based on the characteristics of OCT detection and adenoma morphology, are likely to be erroneously assigned to cancerous areas of the colon.…”

High-resolution rectoscopy using MHz optical coherence tomography: a step towards real time 3D endoscopy

“…The efficacy of EUS in assessing infiltration depths in rectal cancer contextually underscores the importance of our findings 37 , which align with Luo et al's comprehensive analysis on colorectal specimens. This analysis demonstrated our endoscope's capability to distinguish between normal and cancerous tissues accurately 38 , enhancing the clinical utility of OCT technology.…”

Extracting Morphological and Sub-Resolution Features from Optical Coherence Tomography Images, a Review with Applications in Cancer Diagnosis

“…The proposed framework takes advantage of pixel classification and adversarial learning, thus generating human-like segmentation results [198,199]. H. Luo et al, constructed a miniaturized OCT catheter and combined it with a residual neural network (ResNet)-based DL model to perform automatic image processing and real-time classification of normal and cancerous colorectal OCT images with 0.975 AUC (Figure 16) [200]. ML and DL have also been applied to OCT images of various other tissues.…”