Computer-aided diagnosis of serrated colorectal lesions using non-magnified white-light endoscopic images

Color-coded parametric imaging support display of vessel hemorrhage-an in vitro experiment and clinical validation study

Background

Digital Subtraction Angiography (DSA) is currently the most effective diagnostic method for vascular diseases, but it is still subject to various factors, resulting in uncertain diagnosis. Therefore, a new technology is needed to help clinical doctors improve diagnostic accuracy and efficiency.

Purpose

The objective of the study was to investigate the effect of utilizing color-coded parametric imaging techniques on the accuracy of identifying active bleeding through DSA, the widely accepted standard for diagnosing vascular disorders.

Methods

Several variables can delay the diagnosis and treatment of active bleeding with DSA. To resolve this, we carried out an in vitro simulation experiment to simulate vascular hemorrhage and utilized five color-coded parameters (area under curve, time to peak, time-of-arrival, transit time, and flow rate of contrast agent) to determine the optimal color coding parameters. We then verified it in a clinical study.

Results

Five different color-coded parametric imaging methods were compared and the time-of-arrival color coding was the most efficient technique for diagnosing active hemorrhage, with a statistically significant advantage (P < 0.001). In clinical study, 135 patients (101 with confirmed bleeding and 34 with confirmed no bleeding) were collected. For patients whose bleeding could not be determined using DSA alone (55/101) and whose no bleeding could not be diagnosed by DSA alone (35/55), the combination of time-of-arrival color parametric imaging was helpful for diagnosis, with a statistically significant difference (P < 0.01 and P = 0.01).

Conclusions

The time-of-arrival color coding imaging method is a valuable tool for detecting active bleeding. When combined with DSA, it improves the visual representation of active hemorrhage and improves the efficiency of diagnosis.

A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart

In this study, we implemented a combination of data augmentation and artificial intelligence (AI) model-Convolutional Neural Network (CNN)-to help physicians classify colonic polyps into traditional adenoma (TA), sessile serrated adenoma (SSA), and hyperplastic polyp (HP). We collected ordinary endoscopy images under both white and NBI lights. Under white light, we collected 257 images of HP, 423 images of SSA, and 60 images of TA. Under NBI light, were collected 238 images of HP, 284 images of SSA, and 71 images of TA. We implemented the CNN-based artificial intelligence model, Inception V4, to build a classification model for the types of colon polyps. Our final AI classification model with data augmentation process is constructed only with white light images. Our classification prediction accuracy of colon polyp type is 94%, and the discriminability of the model (area under the curve) was 98%. Thus, we can conclude that our model can help physicians distinguish between TA, SSA, and HPs and correctly identify precancerous lesions such as TA and SSA.

Impact of computer-aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study

OBJECTIVES

Computer-aided characterization (CADx) may be used to implement optical biopsy strategies into colonoscopy practice; however, its impact on endoscopic diagnosis remains unknown. We aimed to evaluate the additional diagnostic value of CADx when used by endoscopists for assessing colorectal polyps.

METHODS

This was a single-center, multicase, multireader, image-reading study using randomly extracted images of pathologically confirmed polyps resected between July 2021 and January 2022. Approved CADx that could predict two-tier classification (neoplastic or nonneoplastic) by analyzing narrow-band images of the polyps was used to obtain a CADx diagnosis. Participating endoscopists determined if the polyps were neoplastic or not and noted their confidence level using a computer-based, image-reading test. The test was conducted twice with a 4-week interval: the first test was conducted without CADx prediction and the second test with CADx prediction. Diagnostic performances for neoplasms were calculated using the pathological diagnosis as reference and performances with and without CADx prediction were compared.

RESULTS

Five hundred polyps were randomly extracted from 385 patients and diagnosed by 14 endoscopists (including seven experts). The sensitivity for neoplasia was significantly improved by referring to CADx (89.4% vs. 95.6%). CADx also had incremental effects on the negative predictive value (69.3% vs. 84.3%), overall accuracy (87.2% vs. 91.8%), and high-confidence diagnosis rate (77.4% vs. 85.8%). However, there was no significant difference in specificity (80.1% vs. 78.9%).

CONCLUSIONS

Computer-aided characterization has added diagnostic value for differentiating colorectal neoplasms and may improve the high-confidence diagnosis rate.

Artificial intelligence in gastroenterology: A narrative review

Artificial intelligence (AI) is a complex concept, broadly defined in medicine as the development of computer systems to perform tasks that require human intelligence. It has the capacity to revolutionize medicine by increasing efficiency, expediting data and image analysis and identifying patterns, trends and associations in large datasets. Within gastroenterology, recent research efforts have focused on using AI in esophagogastroduodenoscopy, wireless capsule endoscopy (WCE) and colonoscopy to assist in diagnosis, disease monitoring, lesion detection and therapeutic intervention. The main objective of this narrative review is to provide a comprehensive overview of the research being performed within gastroenterology on AI in esophagogastroduodenoscopy, WCE and colonoscopy.