Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning

Abstract

(1) Background: Clinicians demand new tools for early diagnosis and improved detection of colon lesions that are vital for patient prognosis. Optical coherence tomography (OCT) allows microscopical inspection of tissue and might serve as an optical biopsy method that could lead to in-situ diagnosis and treatment decisions; (2) Methods: A database of murine (rat) healthy, hyperplastic and neoplastic colonic samples with more than 94,000 images was acquired. A methodology that includes a data augmentation processing strategy and a deep learning model for automatic classification (benign vs. malignant) of OCT images is presented and validated over this dataset. Comparative evaluation is performed both over individual B-scan images and C-scan volumes; (3) Results: A model was trained and evaluated with the proposed methodology using six different data splits to present statistically significant results. Considering this, 0.9695 (±0.0141) sensitivity and 0.8094 (±0.1524) specificity were obtained when diagnosis was performed over B-scan images. On the other hand, 0.9821 (±0.0197) sensitivity and 0.7865 (±0.205) specificity were achieved when diagnosis was made considering all the images in the whole C-scan volume; (4) Conclusions: The proposed methodology based on deep learning showed great potential for the automatic characterization of colon polyps and future development of the optical biopsy paradigm.

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)(58)(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.…”

“…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 ).…”

Extended continuous similarity indices: theory and application for QSAR descriptor selection

“…and ii) cross-validation [40]. It is a generally applicable multicriteria decision making tool [41], whose applications were demonstrated in a wide range of fields from food chemistry [42] to medical applications [43], as well as politics [44] and sports [45]. The sum of ranking differences (SRDs) is calculated as the city block (Manhattan) distance (dkj) between the rank values of the gold standard and the rank values of the original data.…”

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

“…Recent advances in convolutional neural networks (CNN) have enabled clinical application in ophthalmology and cardiology malignancy detection [4][5][6] Moreover, CNN has also been applied to esophageal and colorectal tissues as an image classification tool for automatic diagnosis. [7][8][9][10][11][12] Specifically, C. L. Saratxaga et al applied transfer learning using a pretrained Xception classification model for automatic classification (benign vs. malignant) of OCT images of murine (rat) colon, 13 achieving 97% sensitivity and 81% specificity for tumor detection.…”