Computer-Aided Diagnosis of Diminutive Colorectal Polyps in Endoscopic Images: Systematic Review and Meta-analysis of Diagnostic Test Accuracy

Use of Artificial Intelligence in Lower Gastrointestinal and Small Bowel Disorders: An Update Beyond Polyp Detection

Machine learning and its specialized forms, such as Artificial Neural Networks and Convolutional Neural Networks, are increasingly being used for detecting and managing gastrointestinal conditions. Recent advancements involve using Artificial Neural Network models to enhance predictive accuracy for severe lower gastrointestinal (LGI) bleeding outcomes, including the need for surgery. To this end, artificial intelligence (AI)-guided predictive models have shown promise in improving management outcomes. While much literature focuses on AI in early neoplasia detection, this review highlights AI's role in managing LGI and small bowel disorders, including risk stratification for LGI bleeding, quality control, evaluation of inflammatory bowel disease, and video capsule endoscopy reading. Overall, the integration of AI into routine clinical practice is still developing, with ongoing research aimed at addressing current limitations and gaps in patient care.

Artificial intelligence and early cancer of the digestive tract: New challenges and new futures

Early gastrointestinal tumors have a good prognosis, but they have insidious onset and no specific manifestations, making their diagnosis difficult. With the rapid development of artificial intelligence technology in the medical field, it has shown great potential in clinical work such as diagnosis and prognosis prediction of early gastrointestinal cancer. In this paper, we systematically review the relevant studies on AI in early esophageal cancer, early gastric cancer, early colon cancer, and hepatobiliary pancreatic cancer, and discuss the challenges and futures of AI application in early gastrointestinal cancer.

Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review

Background

Some research has already reported the diagnostic value of artificial intelligence (AI) in different endoscopy outcomes. However, the evidence is confusing and of varying quality.

Objective

This review aimed to comprehensively evaluate the credibility of the evidence of AI's diagnostic accuracy in endoscopy.

Methods

Before the study began, the protocol was registered on PROSPERO (CRD42023483073). First, 2 researchers searched PubMed, Web of Science, Embase, and Cochrane Library using comprehensive search terms. Then, researchers screened the articles and extracted information. We used A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR2) to evaluate the quality of the articles. When there were multiple studies aiming at the same result, we chose the study with higher-quality evaluations for further analysis. To ensure the reliability of the conclusions, we recalculated each outcome. Finally, the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) was used to evaluate the credibility of the outcomes.

Results

A total of 21 studies were included for analysis. Through AMSTAR2, it was found that 8 research methodologies were of moderate quality, while other studies were regarded as having low or critically low quality. The sensitivity and specificity of 17 different outcomes were analyzed. There were 4 studies on esophagus, 4 studies on stomach, and 4 studies on colorectal regions. Two studies were associated with capsule endoscopy, two were related to laryngoscopy, and one was related to ultrasonic endoscopy. In terms of sensitivity, gastroesophageal reflux disease had the highest accuracy rate, reaching 97%, while the invasion depth of colon neoplasia, with 71%, had the lowest accuracy rate. On the other hand, the specificity of colorectal cancer was the highest, reaching 98%, while the gastrointestinal stromal tumor, with only 80%, had the lowest specificity. The GRADE evaluation suggested that the reliability of most outcomes was low or very low.

Conclusions

AI proved valuabe in endoscopic diagnoses, especially in esophageal and colorectal diseases. These findings provide a theoretical basis for developing and evaluating AI-assisted systems, which are aimed at assisting endoscopists in carrying out examinations, leading to improved patient health outcomes. However, further high-quality research is needed in the future to fully validate AI's effectiveness.

Optical diagnosis in still images of colorectal polyps: comparison between expert endoscopists and PolyDeep, a Computer-Aided Diagnosis system

Background

PolyDeep is a computer-aided detection and classification (CADe/x) system trained to detect and classify polyps. During colonoscopy, CADe/x systems help endoscopists to predict the histology of colonic lesions.

Objective

To compare the diagnostic performance of PolyDeep and expert endoscopists for the optical diagnosis of colorectal polyps on still images.

Methods

PolyDeep Image Classification (PIC) is an in vitro diagnostic test study. The PIC database contains NBI images of 491 colorectal polyps with histological diagnosis. We evaluated the diagnostic performance of PolyDeep and four expert endoscopists for neoplasia (adenoma, sessile serrated lesion, traditional serrated adenoma) and adenoma characterization and compared them with the McNemar test. Receiver operating characteristic curves were constructed to assess the overall discriminatory ability, comparing the area under the curve of endoscopists and PolyDeep with the chi- square homogeneity areas test.

Results

The diagnostic performance of the endoscopists and PolyDeep in the characterization of neoplasia is similar in terms of sensitivity (PolyDeep: 89.05%; E1: 91.23%, p=0.5; E2: 96.11%, p<0.001; E3: 86.65%, p=0.3; E4: 91.26% p=0.3) and specificity (PolyDeep: 35.53%; E1: 33.80%, p=0.8; E2: 34.72%, p=1; E3: 39.24%, p=0.8; E4: 46.84%, p=0.2). The overall discriminative ability also showed no statistically significant differences (PolyDeep: 0.623; E1: 0.625, p=0.8; E2: 0.654, p=0.2; E3: 0.629, p=0.9; E4: 0.690, p=0.09). In the optical diagnosis of adenomatous polyps, we found that PolyDeep had a significantly higher sensitivity and a significantly lower specificity. The overall discriminative ability of adenomatous lesions by expert endoscopists is significantly higher than PolyDeep (PolyDeep: 0.582; E1: 0.685, p < 0.001; E2: 0.677, p < 0.0001; E3: 0.658, p < 0.01; E4: 0.694, p < 0.0001).

Conclusion

PolyDeep and endoscopists have similar diagnostic performance in the optical diagnosis of neoplastic lesions. However, endoscopists have a better global discriminatory ability than PolyDeep in the optical diagnosis of adenomatous polyps.

Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps

BACKGROUND

Confusion between high and low confidence decisions in optical diagnosis hinders the implementation of real-time optical diagnosis in clinical practice. We evaluated the effect of a 3-second rule (decision time limited to 3 seconds for a high confidence assignment) in expert and nonexpert endoscopists.

METHODS

This single-center prospective study included eight board-certified gastroenterologists. A 2-month baseline phase used standard real-time optical diagnosis for colorectal polyps < 10 mm and was followed by a 6-month intervention phase using optical diagnosis with the 3-second rule. Performance, including high confidence accuracy, and Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) and Simple Optical Diagnosis Accuracy (SODA) thresholds, was measured.

RESULTS

Real-time optical diagnosis was performed on 1793 patients with 3694 polyps. There was significant improvement in high confidence accuracy between baseline and intervention phases in the nonexpert group (79.2 % vs. 86.3 %; P = 0.01) but not in the expert group (85.3 % vs. 87.5 %; P = 0.53). Using the 3-second rule improved the overall performance of PIVI and SODA in both groups.

CONCLUSIONS

The 3-second rule was effective in improving real-time optical diagnosis performance, especially in nonexperts.

AI in colonoscopy - detection and characterisation of malignant polyps

The medical technological revolution has transformed the nature with which we deliver care. Adjuncts such as artificial intelligence and machine learning have underpinned this. The applications to the field of endoscopy are numerous. Malignant polyps represent a significant diagnostic dilemma as they lie in an area in which mischaracterisation may mean the difference between an endoscopic procedure and a formal bowel resection. This has implications for patients’ oncological outcomes, morbidity and mortality, especially if post-procedure histopathology upstages disease. We have made significant strides with the applications of artificial intelligence to colonoscopic detection. Deep learning algorithms are able to be created from video and image databases. These have been applied to traditional, human-derived, classification methods, such as Paris or Kudo, with up to 93% accuracy. Furthermore, multimodal characterisation systems have been developed, which also factor in patient demographics and colonic location to provide an estimation of invasion and endoscopic resectability with over 90% accuracy. Although the technology is still evolving, and the lack of high-quality randomised controlled trials limits clinical usability, there is an exciting horizon upon us for artificial intelligence-augmented endoscopy.

Real-World Validation of a Computer-Aided Diagnosis System for Prediction of Polyp Histology in Colonoscopy: A Prospective Multicenter Study

INTRODUCTION

Computer-aided diagnosis (CADx) of polyp histology could support endoscopists in clinical decision-making. However, this has not been validated in a real-world setting.

METHODS

We performed a prospective, multicenter study comparing CADx and endoscopist predictions of polyp histology in real-time colonoscopy. Optical diagnosis based on visual inspection of polyps was made by experienced endoscopists. After this, the automated output from the CADx support tool was recorded. All imaged polyps were resected for histological assessment. Primary outcome was difference in diagnostic performance between CADx and endoscopist prediction of polyp histology. Subgroup analysis was performed for polyp size, bowel preparation, difficulty of location of the polyps, and endoscopist experience.

RESULTS

A total of 661 eligible polyps were resected in 320 patients aged ≥40 years between March 2021 and July 2022. CADx had an overall accuracy of 71.6% (95% confidence interval [CI] 68.0-75.0), compared with 75.2% (95% CI 71.7-78.4) for endoscopists ( P = 0.023). The sensitivity of CADx for neoplastic polyps was 61.8% (95% CI 56.9-66.5), compared with 70.3% (95% CI 65.7-74.7) for endoscopists ( P < 0.001). The interobserver agreement between CADx and endoscopist predictions of polyp histology was moderate (83.1% agreement, κ 0.661). When there was concordance between CADx and endoscopist predictions, the accuracy increased to 78.1%.

DISCUSSION

The overall diagnostic accuracy and sensitivity for neoplastic polyps was higher in experienced endoscopists compared with CADx predictions, with moderate interobserver agreement. Concordance in predictions increased this diagnostic accuracy. Further research is required to improve the performance of CADx and to establish its role in clinical practice.

Recent advances in devices and technologies that might prove revolutionary for colonoscopy procedures

INTRODUCTION

Colorectal cancer (CRC) is the third most common malignancy and second leading cause of cancer-related mortality in the world. Adenoma detection rate (ADR), a quality indicator for colonoscopy, has gained prominence as it is inversely related to CRC incidence and mortality. As such, recent efforts have focused on developing novel colonoscopy devices and technologies to improve ADR.

AREAS COVERED

The main objective of this paper is to provide an overview of advancements in the fields of colonoscopy mechanical attachments, artificial intelligence-assisted colonoscopy, and colonoscopy optical enhancements with respect to ADR. We accomplished this by performing a comprehensive search of multiple electronic databases from inception to September 2023. This review is intended to be an introduction to colonoscopy devices and technologies.

EXPERT OPINION

Numerous mechanical attachments and optical enhancements have been developed that have the potential to improve ADR and AI has gone from being an inaccessible concept to a feasible means for improving ADR. While these advances are exciting and portend a change in what will be considered standard colonoscopy, they continue to require refinement. Future studies should focus on combining modalities to further improve ADR and exploring the use of these technologies in other facets of colonoscopy.

Artificial intelligence-assisted endoscopic ultrasound in the diagnosis of gastrointestinal stromal tumors: a meta-analysis

BACKGROUND AND AIMS

Endoscopic ultrasonography (EUS) is useful for the diagnosis of gastrointestinal stromal tumors (GISTs), but is limited by subjective interpretation. Studies on artificial intelligence (AI)-assisted diagnosis are under development. Here, we used a meta-analysis to evaluate the diagnostic performance of AI in the diagnosis of GISTs using EUS images.

METHODS

PubMed, Ovid Medline, Embase, Web of science, and the Cochrane Library databases were searched for studies based on the EUS using AI for the diagnosis of GISTs, and a meta-analysis was performed to examine the accuracy.

RESULTS

Overall, 7 studies were included in our meta-analysis. A total of 2431 patients containing more than 36,186 images were used as the overall dataset, of which 480 patients were used for the final testing. The pooled sensitivity, specificity, positive, and negative likelihood ratio (LR) of AI-assisted EUS for differentiating GISTs from other submucosal tumors (SMTs) were 0.92 (95% confidence interval [CI] 0.89-0.95), 0.82 (95% CI 0.75-0.87), 4.55 (95% CI 2.64-7.84), and 0.12 (95% CI 0.07-0.20), respectively. The summary diagnostic odds ratio (DOR) and the area under the curve were 64.70 (95% CI 23.83-175.69) and 0.950 (Q* = 0.891).

CONCLUSIONS

AI-assisted EUS showed high accuracy for the automatic endoscopic diagnosis of GISTs, which could be used as a valuable complementary method for the differentiation of SMTs in the future.

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.

Impact of the Volume and Distribution of Training Datasets in the Development of Deep-Learning Models for the Diagnosis of Colorectal Polyps in Endoscopy Images

Background: Establishment of an artificial intelligence model in gastrointestinal endoscopy has no standardized dataset. The optimal volume or class distribution of training datasets has not been evaluated. An artificial intelligence model was previously created by the authors to classify endoscopic images of colorectal polyps into four categories, including advanced colorectal cancer, early cancers/high-grade dysplasia, tubular adenoma, and nonneoplasm. The aim of this study was to evaluate the impact of the volume and distribution of training dataset classes in the development of deep-learning models for colorectal polyp histopathology prediction from endoscopic images. Methods: The same 3828 endoscopic images that were used to create earlier models were used. An additional 6838 images were used to find the optimal volume and class distribution for a deep-learning model. Various amounts of data volume and class distributions were tried to establish deep-learning models. The training of deep-learning models uniformly used no-code platform Neuro-T. Accuracy was the primary outcome on four-class prediction. Results: The highest internal-test classification accuracy in the original dataset, doubled dataset, and tripled dataset was commonly shown by doubling the proportion of data for fewer categories (2:2:1:1 for advanced colorectal cancer: early cancers/high-grade dysplasia: tubular adenoma: non-neoplasm). Doubling the proportion of data for fewer categories in the original dataset showed the highest accuracy (86.4%, 95% confidence interval: 85.0–97.8%) compared to that of the doubled or tripled dataset. The total required number of images in this performance was only 2418 images. Gradient-weighted class activation mapping confirmed that the part that the deep-learning model pays attention to coincides with the part that the endoscopist pays attention to. Conclusion: As a result of a data-volume-dependent performance plateau in the classification model of colonoscopy, a dataset that has been doubled or tripled is not always beneficial to training. Deep-learning models would be more accurate if the proportion of fewer category lesions was increased.

Artificial intelligence within the small bowel: are we lagging behind?

PURPOSE OF REVIEW

The use of artificial intelligence in small bowel capsule endoscopy is expanding. This review focusses on the use of artificial intelligence for small bowel pathology compared with human data and developments to date.

RECENT FINDINGS

The diagnosis and management of small bowel disease has been revolutionized with the advent of capsule endoscopy. Reading of capsule endoscopy videos however is time consuming with an average reading time of 40 min. Furthermore, the fatigued human eye may miss subtle lesions including indiscreet mucosal bulges. In recent years, artificial intelligence has made significant progress in the field of medicine including gastroenterology. Machine learning has enabled feature extraction and in combination with deep neural networks, image classification has now materialized for routine endoscopy for the clinician.

SUMMARY

Artificial intelligence is in built within the Navicam-Ankon capsule endoscopy reading system. This development will no doubt expand to other capsule endoscopy platforms and capsule endoscopies that are used to visualize other parts of the gastrointestinal tract as a standard. This wireless and patient friendly technique combined with rapid reading platforms with the help of artificial intelligence will become an attractive and viable choice to alter how patients are investigated in the future.

Computer-Aided Diagnosis of Gastrointestinal Protruded Lesions Using Wireless Capsule Endoscopy: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis

Background: Wireless capsule endoscopy allows the identification of small intestinal protruded lesions, such as polyps, tumors, or venous structures. However, reading wireless capsule endoscopy images or movies is time-consuming, and minute lesions are easy to miss. Computer-aided diagnosis (CAD) has been applied to improve the efficacy of the reading process of wireless capsule endoscopy images or movies. However, there are no studies that systematically determine the performance of CAD models in diagnosing gastrointestinal protruded lesions. Objective: The aim of this study was to evaluate the diagnostic performance of CAD models for gastrointestinal protruded lesions using wireless capsule endoscopic images. Methods: Core databases were searched for studies based on CAD models for the diagnosis of gastrointestinal protruded lesions using wireless capsule endoscopy, and data on diagnostic performance were presented. A systematic review and diagnostic test accuracy meta-analysis were performed. Results: Twelve studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of protruded lesions were 0.95 (95% confidence interval, 0.93–0.97), 0.89 (0.84–0.92), 0.91 (0.86–0.94), and 74 (43–126), respectively. Subgroup analyses showed robust results. Meta-regression found no source of heterogeneity. Publication bias was not detected. Conclusion: CAD models showed high performance for the optical diagnosis of gastrointestinal protruded lesions based on wireless capsule endoscopy.

Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis

BACKGROUND

Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models.

OBJECTIVE

To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images.

METHODS

We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed.

RESULTS

Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected.

CONCLUSIONS

CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.