Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions

Improving the endoscopic recognition of early colorectal carcinoma using artificial intelligence: current evidence and future directions

Background and study aims Artificial intelligence (AI) has great potential to improve endoscopic recognition of early stage colorectal carcinoma (CRC). This scoping review aimed to summarize current evidence on this topic, provide an overview of the methodologies currently used, and guide future research. Methods A systematic search was performed following the PRISMA-Scr guideline. PubMed (including Medline), Scopus, Embase, IEEE Xplore, and ACM Digital Library were searched up to January 2024. Studies were eligible for inclusion when using AI for distinguishing CRC from colorectal polyps on endoscopic imaging, using histopathology as gold standard, reporting sensitivity, specificity, or accuracy as outcomes. Results Of 5024 screened articles, 26 were included. Computer-aided diagnosis (CADx) system classification categories ranged from two categories, such as lesions suitable or unsuitable for endoscopic resection, to five categories, such as hyperplastic polyp, sessile serrated lesion, adenoma, cancer, and other. The number of images used in testing databases varied from 69 to 84,585. Diagnostic performances were divergent, with sensitivities varying from 55.0% to 99.2%, specificities from 67.5% to 100% and accuracies from 74.4% to 94.4%. Conclusions This review highlights that using AI to improve endoscopic recognition of early stage CRC is an upcoming research field. We introduced a suggestions list of essential subjects to report in research regarding the development of endoscopy CADx systems, aiming to facilitate more complete reporting and better comparability between studies. There is a knowledge gap regarding real-time CADx system performance during multicenter external validation. Future research should focus on development of CADx systems that can differentiate CRC from premalignant lesions, while providing an indication of invasion depth.

Association between colonic adenoma size and proliferative zone in the crypt

BACKGROUND

We previously reported unusual adenomas with proliferative zones confined to the lower two-thirds of the crypt. The proliferative zones of colorectal adenomas have three patterns: 'lower,' 'superficial' and 'entire'. This study aimed to clarify the characteristics of each adenoma pattern.

METHODS

We investigated 2925 consecutive patients who underwent colonoscopy at our institute. All polyps that were removed were histologically examined using hematoxylin and eosin staining. The location of the proliferative zone was assessed for adenomas. Data were compared using Dunn's and Kruskal-Wallis tests.

RESULTS

Colorectal adenomas with 'lower' proliferative zone often appeared similar to hyperplastic polyps (42.8%), and the frequency was significantly higher than that of adenomas with 'superficial' and 'entire' proliferative zones (p < 0.001). The mean sizes of adenomas were 2.4, 3.0 and 3.9 mm for 'lower,' 'superficial' and 'entire' proliferative zones, respectively. A significant gradual increase was observed. Regarding morphology, the proportion of type 0-I in adenomas with an 'entire' proliferative zone was significantly higher than that in adenomas with 'superficial' proliferative zone (p < 0.001).

CONCLUSION

While colorectal adenomas develop and increase in size, the proliferative zone appears to shift upward and become scattered.

Role of artificial intelligence in colorectal cancer

The sphere of artificial intelligence (AI) is ever expanding. Applications for clinical practice have been emerging over recent years. Although its uptake has been most prominent in endoscopy, this represents only one aspect of holistic patient care. There are a multitude of other potential avenues in which gastrointestinal care may be involved. We aim to review the role of AI in colorectal cancer as a whole. We performed broad scoping and focused searches of the applications of AI in the field of colorectal cancer. All trials including qualitative research were included from the year 2000 onwards. Studies were grouped into pre-operative, intra-operative and post-operative aspects. Pre-operatively, the major use is with endoscopic recognition. Colonoscopy has embraced the use for human derived classifications such as Narrow-band Imaging International Colorectal Endoscopic, Japan Narrow-band Imaging Expert Team, Paris and Kudo. However, novel detection and diagnostic methods have arisen from advances in AI classification. Intra-operatively, adjuncts such as image enhanced identification of structures and assessment of perfusion have led to improvements in clinical outcomes. Post-operatively, monitoring and surveillance have taken strides with potential socioeconomic and environmental savings. The uses of AI within the umbrella of colorectal surgery are multiple. We have identified existing technologies which are already augmenting cancer care. The future applications are exciting and could at least match, if not surpass human standards.

A Semi-Supervised Learning Framework for Classifying Colorectal Neoplasia Based on the NICE Classification

Labelling medical images is an arduous and costly task that necessitates clinical expertise and large numbers of qualified images. Insufficient samples can lead to underfitting during training and poor performance of supervised learning models. In this study, we aim to develop a SimCLR-based semi-supervised learning framework to classify colorectal neoplasia based on the NICE classification. First, the proposed framework was trained under self-supervised learning using a large unlabelled dataset; subsequently, it was fine-tuned on a limited labelled dataset based on the NICE classification. The model was evaluated on an independent dataset and compared with models based on supervised transfer learning and endoscopists using accuracy, Matthew's correlation coefficient (MCC), and Cohen's kappa. Finally, Grad-CAM and t-SNE were applied to visualize the models' interpretations. A ResNet-backboned SimCLR model (accuracy of 0.908, MCC of 0.862, and Cohen's kappa of 0.896) outperformed supervised transfer learning-based models (means: 0.803, 0.698, and 0.742) and junior endoscopists (0.816, 0.724, and 0.863), while performing only slightly worse than senior endoscopists (0.916, 0.875, and 0.944). Moreover, t-SNE showed a better clustering of ternary samples through self-supervised learning in SimCLR than through supervised transfer learning. Compared with traditional supervised learning, semi-supervised learning enables deep learning models to achieve improved performance with limited labelled endoscopic images.

Colon polyps: updates in classification and management

PURPOSE OF REVIEW

Colon polyps are potential precursors to colorectal cancer (CRC), which remains one of the most common causes of cancer-associated death. The proper identification and management of these colorectal polyps is an important quality measure for colonoscopy outcomes. Here, we review colon polyp epidemiology, their natural history, and updates in endoscopic classification and management.

RECENT FINDINGS

Colon polyps that form from not only the adenoma, but also the serrated polyp pathway have significant risk for future progression to CRC. Therefore, correct identification and management of sessile serrated lesions can improve the quality of screening colonoscopy. Malignant polyp recognition continues to be heavily reliant on well established endoscopic classification systems and plays an important role in intraprocedural management decisions. Hot snare remains the gold standard for pedunculated polyp resection. Nonpedunculated noninvasive lesions can be effectively removed by large forceps if diminutive, but cold snare is preferred for colon polyps 3-20 mm in diameter. Larger lesions at least 20 mm require endoscopic mucosal resection. Polyps with the endoscopic appearance of submucosal invasion require surgical referral or advanced endoscopic resection in select cases. Advances in artificial intelligence may revolutionize endoscopic polyp classification and improve both patient and cost-related outcomes of colonoscopy.

SUMMARY

Clinicians should be aware of the most recent updates in colon polyp classification and management to provide the best care to their patients initiating screening colonoscopy.

Computer-aided diagnosis in predicting the invasion depth of early colorectal cancer: a systematic review and meta-analysis of diagnostic test accuracy

BACKGROUND

Endoscopic resection (ER) is widely applied to treat early colorectal cancer (CRC). Predicting the invasion depth of early CRC is critical in determining treatment strategies. The use of computer-aided diagnosis (CAD) algorithms could theoretically make accurate and objective predictions regarding the suitability of lesions for ER indication based on invasion depth. This study aimed to assess diagnostic test accuracy of CAD algorithms in predicting the invasion depth of early CRC and to compare the performance between the CAD algorithms and endoscopists.

METHODS

Multiple databases were searched until June 30, 2022 for studies that evaluated the diagnostic performance of CAD algorithms for invasion depth of CRC. Meta-analysis of diagnostic test accuracy using a bivariate mixed-effects model was performed.

RESULTS

Ten studies consisting of 13 arms (13,918 images from 1472 lesions) were included. Due to significant heterogeneity, studies were stratified into Japan/Korea-based or China-based studies. For the former, the area under the curve (AUC), sensitivity, and specificity of the CAD algorithms were 0.89 (95% CI 0.86-0.91), 62% (95% CI 50-72%), and 96% (95% CI 93-98%), respectively. For the latter, AUC, sensitivity, and specificity were 0.94 (95% CI 0.92-0.96), 88% (95% CI 78-94%), and 88% (95% CI 80-93%), respectively. The performance of the CAD algorithms in Japan/Korea-based studies was not significantly different from that of all endoscopists (0.88 vs. 0.91, P = 0.10) but was inferior to that of expert endoscopists (0.88 vs. 0.92, P = 0.03). The performance of the CAD algorithms in China-based studies was better than that of all endoscopists (0.94 vs. 0.90, P = 0.01).

CONCLUSION

The CAD algorithms showed comparable accuracy for prediction of invasion depth of early CRC compared to all endoscopists, which was still lower than expert endoscopists in diagnostic accuracy; more improvements should be achieved before it can be extensively applied to clinical practice.

Updates in narrow-band imaging for colorectal polyps: Narrow-band imaging generations, detection, diagnosis, and artificial intelligence

Narrow-band imaging (NBI) is an optical digital enhancement method that allows the observation of vascular and surface structures of colorectal lesions. Its usefulness in the detection and diagnosis of colorectal polyps has been demonstrated in several clinical trials and the diagnostic algorithms have been simplified after the establishment of endoscopic classifications such as the Japan NBI Expert Team classification. However, there were issues including lack of brightness in the earlier models, poor visibility under insufficient bowel preparation, and the incompatibility of magnifying endoscopes in certain endoscopic platforms, which had impeded NBI from becoming standardized globally. Nonetheless, NBI continued its evolution and the newest endoscopic platform launched in 2020 offers significantly brighter and detailed images. Enhanced visualization is expected to improve the detection of polyps while universal compatibility across all scopes including magnifying endoscopy will promote the global standardization of magnifying diagnosis. Therefore, knowledge related to magnifying colonoscopy will become essential as magnification becomes standardly equipped in future models, although the advent of computer-aided diagnosis and detection may greatly assist endoscopists to ensure quality of practice. Given that most endoscopic departments will be using both old and new models, it is important to understand how each generation of endoscopic platforms differ from each other. We reviewed the advances in the endoscopic platforms, artificial intelligence, and evidence related to NBI essential for the next generation of endoscopic practice.

Real-Time Artificial Intelligence-Based Histologic Classifications of Colorectal Polyps Using Narrow-Band Imaging

Background and Aims

With the development of artificial intelligence (AI), we have become capable of applying real-time computer-aided detection (CAD) in clinical practice. Our aim is to develop an AI-based CAD-N and optimize its diagnostic performance with narrow-band imaging (NBI) images.

Methods

We developed the CAD-N model with ResNeSt using NBI images for real-time assessment of the histopathology of colorectal polyps (type 1, hyperplastic or inflammatory polyps; type 2, adenomatous polyps, intramucosal cancer, or superficial submucosal invasive cancer; type 3, deep submucosal invasive cancer; and type 4, normal mucosa). We also collected 116 consecutive polyp videos to validate the accuracy of the CAD-N.

Results

A total of 10,573 images (7,032 images from 650 polyps and 3,541 normal mucous membrane images) from 478 patients were finally chosen for analysis. The sensitivity, specificity, PPV, NPV, and accuracy for each type of the CAD-N in the test set were 89.86%, 97.88%, 93.13%, 96.79%, and 95.93% for type 1; 93.91%, 95.49%, 91.80%, 96.69%, and 94.94% for type 2; 90.21%, 99.29%, 90.21%, 99.29%, and 98.68% for type 3; and 94.86%, 97.28%, 94.73%, 97.35%, and 96.45% for type 4, respectively. The overall accuracy was 93%. We also built models for polyps ≤5 mm, and the sensitivity, specificity, PPV, NPV, and accuracy for them were 96.81%, 94.08%, 95%, 95.97%, and 95.59%, respectively. Video validation results showed that the sensitivity, specificity, and accuracy of the CAD-N were 84.62%, 86.27%, and 85.34%, respectively.

Conclusions

We have developed real-time AI-based histologic classifications of colorectal polyps using NBI images with good accuracy, which may help in clinical management and documentation of optical histology results.