A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy

A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer

BACKGROUND

We developed an artificial intelligence (AI)-based endoscopic ultrasonography (EUS) system for diagnosing the invasion depth of early gastric cancer (EGC), and we evaluated the performance of this system.

METHODS

A total of 8280 EUS images from 559 EGC cases were collected from 11 institutions. Within this dataset, 3451 images (285 cases) from one institution were used as a development dataset. The AI model consisted of segmentation and classification steps, followed by the CycleGAN method to bridge differences in EUS images captured by different equipment. AI model performance was evaluated using an internal validation dataset collected from the same institution as the development dataset (1726 images, 135 cases). External validation was conducted using images collected from the other 10 institutions (3103 images, 139 cases).

RESULTS

The area under the curve (AUC) of the AI model in the internal validation dataset was 0.870 (95% CI: 0.796-0.944). Regarding diagnostic performance, the accuracy/sensitivity/specificity values of the AI model, experts (n = 6), and nonexperts (n = 8) were 82.2/63.4/90.4%, 81.9/66.3/88.7%, and 68.3/60.9/71.5%, respectively. The AUC of the AI model in the external validation dataset was 0.815 (95% CI: 0.743-0.886). The accuracy/sensitivity/specificity values of the AI model (74.1/73.1/75.0%) and the real-time diagnoses of experts (75.5/79.1/72.2%) in the external validation dataset were comparable.

CONCLUSIONS

Our AI model demonstrated a diagnostic performance equivalent to that of experts.

Building and validating an artificial intelligence model to identify tracheobronchopathia osteochondroplastica by using bronchoscopic images

BACKGROUND

Given the rarity of tracheobronchopathia osteochondroplastica (TO), many young doctors in primary hospitals are unable to identify TO based on bronchoscopy findings.

OBJECTIVES

To build an artificial intelligence (AI) model for differentiating TO from other multinodular airway diseases by using bronchoscopic images.

DESIGN

We designed the study by comparing the imaging data of patients undergoing bronchoscopy from January 2010 to October 2022 by using EfficientNet. Bronchoscopic images of 21 patients with TO at Anhui Chest Hospital from October 2019 to October 2022 were collected for external validation.

METHODS

Bronchoscopic images of patients with multinodular airway lesions (including TO, amyloidosis, tumors, and inflammation) and without airway lesions in the First Affiliated Hospital of Guangzhou Medical University were collected. The images were randomized (4:1) into training and validation groups based on different diseases and utilized for deep learning by convolutional neural networks (CNNs).

RESULTS

We enrolled 201 patients with multinodular airway disease (38, 15, 75, and 73 patients with TO, amyloidosis, tumors, and inflammation, respectively) and 213 without any airway lesions. To find multinodular lesion images for deep learning, we utilized 2183 bronchoscopic images of multinodular lesions (including TO, amyloidosis, tumor, and inflammation) and compared them with images without any airway lesions (1733). The accuracy of multinodular lesion identification was 98.9%. Further, the accuracy of TO detection based on the bronchoscopic images of multinodular lesions was 89.2%. Regarding external validation (using images from 21 patients with TO), all patients could be diagnosed with TO; the accuracy was 89.8%.

CONCLUSION

We built an AI model that could differentiate TO from other multinodular airway diseases (mainly amyloidosis, tumors, and inflammation) by using bronchoscopic images. The model could help young physicians identify this rare airway disease.

Deep Learning and Gastric Cancer: Systematic Review of AI-Assisted Endoscopy

BACKGROUND

Gastric cancer (GC), a significant health burden worldwide, is typically diagnosed in the advanced stages due to its non-specific symptoms and complex morphological features. Deep learning (DL) has shown potential for improving and standardizing early GC detection. This systematic review aims to evaluate the current status of DL in pre-malignant, early-stage, and gastric neoplasia analysis.

METHODS

A comprehensive literature search was conducted in PubMed/MEDLINE for original studies implementing DL algorithms for gastric neoplasia detection using endoscopic images. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The focus was on studies providing quantitative diagnostic performance measures and those comparing AI performance with human endoscopists.

RESULTS

Our review encompasses 42 studies that utilize a variety of DL techniques. The findings demonstrate the utility of DL in GC classification, detection, tumor invasion depth assessment, cancer margin delineation, lesion segmentation, and detection of early-stage and pre-malignant lesions. Notably, DL models frequently matched or outperformed human endoscopists in diagnostic accuracy. However, heterogeneity in DL algorithms, imaging techniques, and study designs precluded a definitive conclusion about the best algorithmic approach.

CONCLUSIONS

The promise of artificial intelligence in improving and standardizing gastric neoplasia detection, diagnosis, and segmentation is significant. This review is limited by predominantly single-center studies and undisclosed datasets used in AI training, impacting generalizability and demographic representation. Further, retrospective algorithm training may not reflect actual clinical performance, and a lack of model details hinders replication efforts. More research is needed to substantiate these findings, including larger-scale multi-center studies, prospective clinical trials, and comprehensive technical reporting of DL algorithms and datasets, particularly regarding the heterogeneity in DL algorithms and study designs.

Distinguishing bronchoscopically observed anatomical positions of airway under by convolutional neural network

Background

Artificial intelligence (AI) technology has been used for finding lesions via gastrointestinal endoscopy. However, there were few AI-associated studies that discuss bronchoscopy.

Objectives

To use convolutional neural network (CNN) to recognize the observed anatomical positions of the airway under bronchoscopy.

Design

We designed the study by comparing the imaging data of patients undergoing bronchoscopy from March 2022 to October 2022 by using EfficientNet (one of the CNNs) and U-Net.

Methods

Based on the inclusion and exclusion criteria, 1527 clear images of normal anatomical positions of the airways from 200 patients were used for training, and 475 clear images from 72 patients were utilized for validation. Further, 20 bronchoscopic videos of examination procedures in another 20 patients with normal airway structures were used to extract the bronchoscopic images of normal anatomical positions to evaluate the accuracy for the model. Finally, 21 respiratory doctors were enrolled for the test of recognizing corrected anatomical positions using the validating datasets.

Results

In all, 1527 bronchoscopic images of 200 patients with nine anatomical positions of the airway, including carina, right main bronchus, right upper lobe bronchus, right intermediate bronchus, right middle lobe bronchus, right lower lobe bronchus, left main bronchus, left upper lobe bronchus, and left lower lobe bronchus, were used for supervised machine learning and training, and 475 clear bronchoscopic images of 72 patients were used for validation. The mean accuracy of recognizing these 9 positions was 91% (carina: 98%, right main bronchus: 98%, right intermediate bronchus: 90%, right upper lobe bronchus: 91%, right middle lobe bronchus 92%, right lower lobe bronchus: 83%, left main bronchus: 89%, left upper bronchus: 91%, left lower bronchus: 76%). The area under the curves for these nine positions were >0.98. In addition, the accuracy of extracting the images via the video by the trained model was 94.7%. We also conducted a deep learning study to segment 10 segment bronchi in right lung, and 8 segment bronchi in Left lung. Because of the problem of radial depth, only segment bronchi distributions below right upper bronchus and right middle bronchus could be correctly recognized. The accuracy of recognizing was 84.33 ± 7.52% by doctors receiving interventional pulmonology education in our hospital over 6 months.

Conclusion

Our study proved that AI technology can be used to distinguish the normal anatomical positions of the airway, and the model we trained could extract the corrected images via the video to help standardize data collection and control quality.

Computer-aided demarcation of early gastric cancer: a pilot comparative study with endoscopists

BACKGROUND

Precise area diagnosis of early gastric cancer (EGC) is critical for reliable endoscopic resection. Computer-aided diagnosis (CAD) shows strong potential for detecting EGC and reducing cancer-care disparities caused by differences in endoscopists' skills. To be used in clinical practice, CAD should enable both the detection and the demarcation of lesions. This study proposes a scheme for the detection and delineation of EGC under white-light endoscopy and validates its performance using 1-year consecutive cases.

METHODS

Only 300 endoscopic images randomly selected from 68 consecutive cases were used for training a convolutional neural network. All cases were treated with endoscopic submucosal dissection, enabling the accumulation of a training dataset in which the extent of lesions was precisely determined. For validation, 462 cancer images and 396 normal images from 137 consecutive cases were used. From the validation results, 38 randomly selected images were compared with those delineated by six endoscopists.

RESULTS

Successful detections of EGC in 387 cancer images (83.8%) and the absence of lesions in 307 normal images (77.5%) were achieved. Positive and negative predictive values were 81.3% and 80.4%, respectively. Successful detection was achieved in 130 cases (94.9%). We achieved precise demarcation of EGC with a mean intersection over union of 66.5%, showing the extent of lesions with a smooth boundary; the results were comparable to those achieved by specialists.

CONCLUSIONS

Our scheme, validated using 1-year consecutive cases, shows potential for demarcating EGC. Its performance matched that of specialists; it might therefore be suitable for clinical use in the future.

The Role of Artificial Intelligence in Gastric Cancer: Surgical and Therapeutic Perspectives: A Comprehensive Review

Stomach cancer has a high annual mortality rate worldwide necessitating early detection and accurate treatment. Even experienced specialists can make erroneous judgments based on several factors. Artificial intelligence (AI) technologies are being developed rapidly to assist in this field. Here, we aimed to determine how AI technology is used in gastric cancer diagnosis and analyze how it helps patients and surgeons. Early detection and correct treatment of early gastric cancer (EGC) can greatly increase survival rates. To determine this, it is important to accurately determine the diagnosis and depth of the lesion and the presence or absence of metastasis to the lymph nodes, and suggest an appropriate treatment method. The deep learning algorithm, which has learned gastric lesion endoscopyimages, morphological characteristics, and patient clinical information, detects gastric lesions with high accuracy, sensitivity, and specificity, and predicts morphological characteristics. Through this, AI assists the judgment of specialists to help select the correct treatment method among endoscopic procedures and radical resections and helps to predict the resection margins of lesions. Additionally, AI technology has increased the diagnostic rate of both relatively inexperienced and skilled endoscopic diagnosticians. However, there were limitations in the data used for learning, such as the amount of quantitatively insufficient data, retrospective study design, single-center design, and cases of non-various lesions. Nevertheless, this assisted endoscopic diagnosis technology that incorporates deep learning technology is sufficiently practical and future-oriented and can play an important role in suggesting accurate treatment plans to surgeons for resection of lesions in the treatment of EGC.

The relationship between the esophageal endoscopic submucosal dissection technical difficulty and its intraoperative process

BACKGROUND

Estimating the esophageal endoscopic submucosal dissection (ESD) technical difficulty is important to reduce complications. Endoscopic duration is one of the related factors to a technical difficulty. The relationship between the esophageal ESD technical difficulty and its intraoperative process was analyzed as a first step toward automatic technical difficulty recognition using artificial intelligence.

METHODS

This study enrolled 75 patients with superficial esophageal cancer who underwent esophageal ESD. The technical difficulty score was established, which consisted of three factors, including total procedure duration, en bloc resection, and complications. Additionally, technical difficulty-related factors, which were perioperative factors that included the intraoperative process, were investigated.

RESULTS

Eight (11%) patients were allocated to high difficulty, whereas 67 patients (89%) were allocated to low difficulty. The intraoperative process, which was shown as the extension of each endoscopic phase, was significantly related to a technical difficulty. The area under the curve (AUC) values were higher at all the phase duration than at the clinical characteristics. Submucosal dissection phase (AUC 0.902; 95% confidence intervals (CI) 0.752-1.000), marking phase (AUC 0.827; 95% CI 0.703-0.951), and early phase which was defined as the duration from the start of marking to the end of submucosal injection (AUC 0.847; 95% CI 0.701-0.992) were significantly related to technical difficulty.

CONCLUSIONS

The intraoperative process, particularly early phase, was strongly associated with esophageal ESD technical difficulty. This study demonstrated the potential for automatic evaluation of esophageal ESD technical difficulty when combined with an AI-based automatic phase evaluation system.

Deep learning for pancreatic diseases based on endoscopic ultrasound: A systematic review

BACKGROUND AND AIMS

Endoscopic ultrasonography (EUS) is one of the main examinations in pancreatic diseases. A series of the studies reported the application of deep learning (DL)-assisted EUS in the diagnosis of pancreatic diseases. This systematic review is to evaluate the role of DL algorithms in assisting EUS diagnosis of pancreatic diseases.

METHODS

Literature search were conducted in PubMed and Semantic Scholar databases. Studies that developed DL models for pancreatic diseases based on EUS were eligible for inclusion. This review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and quality assessment of the included studies was performed according to the IJMEDI checklist.

RESULTS

A total of 23 studies were enrolled into this systematic review, which could be categorized into three groups according to computer vision tasks: classification, detection and segmentation. Seventeen studies focused on the classification task, among which five studies developed simple neural network (NN) models while twelve studies constructed convolutional NN (CNN) models. Three studies were concerned the detection task and five studies were the segmentation task, all based on CNN architectures. All models presented in the studies performed well based on EUS images, videos or voice. According to the IJMEDI checklist, six studies were recognized as high-grade quality, with scores beyond 35 points.

CONCLUSIONS

DL algorithms show great potential in EUS images/videos/voice for pancreatic diseases. However, there is room for improvement such as sample sizes, multi-center cooperation, data preprocessing, model interpretability, and code sharing.

A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video)

BACKGROUND

White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data.

METHODS

WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability.

RESULTS

Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159).

CONCLUSIONS

The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.

Application of artificial intelligence in the endoscopic diagnosis of early gastric cancer, atrophic gastritis, and Helicobacter pylori infection

Gastric cancer (GC) is one of the most serious health problems worldwide. Chronic atrophic gastritis (CAG) is most commonly caused by Helicobacter pylori (H. pylori) infection. Currently, endoscopic detection of early gastric cancer (EGC) and CAG remains challenging for endoscopists, and the diagnostic accuracy of H. pylori infection by endoscopy is approximately 70%. Artificial intelligence (AI) can assist endoscopic diagnosis including detection, prediction of depth of invasion, boundary delineation, and anatomical location of EGC, and has achievable diagnostic ability even comparable to experienced endoscopists. In this review we summarized various AI-assisted systems in the diagnosis of EGC, CAG, and H. pylori infection.

Artificial intelligence for diagnosing gastric lesions under white-light endoscopy

BACKGROUND

The ability of endoscopists to identify gastric lesions is uneven. Even experienced endoscopists may miss or misdiagnose lesions due to heavy workload or fatigue or subtle changes in lesions under white-light endoscopy (WLE). This study aimed to develop an artificial intelligence (AI) system that could diagnose six common gastric lesions under WLE and to explore its role in assisting endoscopists in diagnosis.

METHODS

Images of early gastric cancer, advanced gastric cancer, submucosal tumor, polyp, peptic ulcer, erosion, and lesion-free gastric mucosa were retrospectively collected to train and test the system. The performance of the system was compared with that of 12 endoscopists. The performance of endoscopists with or without referring to the system was also evaluated.

RESULTS

A total of 29,809 images from 8947 patients and 1579 images from 496 patients were used to train and test the system, respectively. For per-lesion analysis, the overall accuracy of the system was 85.7%, which was comparable to that of senior endoscopists (85.1%, P = 0.729) and significantly higher than that of junior endoscopists (78.8%, P < 0.001). With system assistance, the overall accuracies of senior and junior endoscopists increased to 89.3% (4.2%, P < 0.001) and 86.2% (7.4%, P < 0.001), respectively. Senior and junior endoscopists achieved varying degrees of improvement in the diagnostic performance of other types of lesions except for polyp. The diagnostic times of senior (3.8 vs 3.2 s per image, P = 0.500) and junior endoscopists (6.2 vs 4.6 s per image, P = 0.144) assisted by the system were both slightly shortened, despite no significant differences.

CONCLUSIONS

The proposed AI system could be applied as an auxiliary tool to reduce the workload of endoscopists and improve the diagnostic accuracy of gastric lesions.

Artificial intelligence in gastric cancer: applications and challenges

Gastric cancer (GC) is one of the most common malignant tumors with high mortality. Accurate diagnosis and treatment decisions for GC rely heavily on human experts' careful judgments on medical images. However, the improvement of the accuracy is hindered by imaging conditions, limited experience, objective criteria, and inter-observer discrepancies. Recently, the developments of machine learning, especially deep-learning algorithms, have been facilitating computers to extract more information from data automatically. Researchers are exploring the far-reaching applications of artificial intelligence (AI) in various clinical practices, including GC. Herein, we aim to provide a broad framework to summarize current research on AI in GC. In the screening of GC, AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological confirmation. In the diagnosis of GC, AI can support tumor-node-metastasis (TNM) staging and subtype classification. For treatment decisions, AI can help with surgical margin determination and prognosis prediction. Meanwhile, current approaches are challenged by data scarcity and poor interpretability. To tackle these problems, more regulated data, unified processing procedures, and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.

Alotaibi S, Marzouk R, S. Salama A, Rizwanullah M, Zamani AS, Atta Abdelmageed A, I. Eldesouki M. Manta Ray Foraging Optimization Transfer Learning-Based Gastric Cancer Diagnosis and Classification on Endoscopic Images

Gastric cancer (GC) diagnoses using endoscopic images have gained significant attention in the healthcare sector. The recent advancements of computer vision (CV) and deep learning (DL) technologies pave the way for the design of automated GC diagnosis models. Therefore, this study develops a new Manta Ray Foraging Optimization Transfer Learning technique that is based on Gastric Cancer Diagnosis and Classification (MRFOTL-GCDC) using endoscopic images. For enhancing the quality of the endoscopic images, the presented MRFOTL-GCDC technique executes the Wiener filter (WF) to perform a noise removal process. In the presented MRFOTL-GCDC technique, MRFO with SqueezeNet model is used to derive the feature vectors. Since the trial-and-error hyperparameter tuning is a tedious process, the MRFO algorithm-based hyperparameter tuning results in enhanced classification results. Finally, the Elman Neural Network (ENN) model is utilized for the GC classification. To depict the enhanced performance of the presented MRFOTL-GCDC technique, a widespread simulation analysis is executed. The comparison study reported the improvement of the MRFOTL-GCDC technique for endoscopic image classification purposes with an improved accuracy of 99.25%.

Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)

The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ² = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ² = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ² = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ² = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ² = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings.

Artificial Intelligence in Endoscopy

Artificial intelligence (AI) is rapidly developing in various medical fields, and there is an increase in research performed in the field of gastrointestinal (GI) endoscopy. In particular, the advent of convolutional neural network, which is a class of deep learning method, has the potential to revolutionize the field of GI endoscopy, including esophagogastroduodenoscopy (EGD), capsule endoscopy (CE), and colonoscopy. A total of 149 original articles pertaining to AI (27 articles in esophagus, 30 articles in stomach, 29 articles in CE, and 63 articles in colon) were identified in this review. The main focuses of AI in EGD are cancer detection, identifying the depth of cancer invasion, prediction of pathological diagnosis, and prediction of Helicobacter pylori infection. In the field of CE, automated detection of bleeding sites, ulcers, tumors, and various small bowel diseases is being investigated. AI in colonoscopy has advanced with several patient-based prospective studies being conducted on the automated detection and classification of colon polyps. Furthermore, research on inflammatory bowel disease has also been recently reported. Most studies of AI in the field of GI endoscopy are still in the preclinical stages because of the retrospective design using still images. Video-based prospective studies are needed to advance the field. However, AI will continue to develop and be used in daily clinical practice in the near future. In this review, we have highlighted the published literature along with providing current status and insights into the future of AI in GI endoscopy.

Usefulness of artificial intelligence in early gastric cancer

Gastric cancer (GC) is a major cancer worldwide, with high mortality and morbidity. Endoscopy, important for the early detection of GC, requires trained skills, high-quality technologies, surveillance and screening programs. Early diagnosis allows a better prognosis, through surgical or curative endoscopic therapy. Magnified endoscopy with virtual chromoendoscopy remarkably improve the detection of early gastric cancer (EGC) when endoscopy is performed by expert endoscopists. Artificial intelligence (AI) has also been introduced to GC diagnostics to increase diagnostic efficiency. AI improves the early detection of gastric lesions because it supports the non-expert and experienced endoscopist in defining the margins of the tumor and the depth of infiltration. AI increases the detection rate of EGC, reduces the rate of missing tumors, and characterizes EGCs, allowing clinicians to make the best therapeutic decision, that is, one that ensures curability. AI has had a remarkable evolution in medicine in recent years, moving from the research phase to clinical practice. In addition, the diagnosis of GC has markedly progressed. We predict that AI will allow great evolution in the diagnosis and treatment of EGC by overcoming the variability in performance that is currently a limitation of chromoendoscopy.

Prediction of pouchitis after ileal pouch-anal anastomosis in patients with ulcerative colitis using artificial intelligence and deep learning

BACKGROUND

Pouchitis is one of the major postoperative complications of ulcerative colitis (UC), and it is still difficult to predict the development of pouchitis after ileal pouch-anal anastomosis (IPAA) in UC patients. In this study, we examined whether a deep learning (DL) model could predict the development of pouchitis.

METHODS

UC patients who underwent two-stage restorative proctocolectomy with IPAA at Keio University Hospital were included in this retrospective analysis. The modified pouchitis disease activity index (mPDAI) was evaluated by the clinical and endoscopic findings. Pouchitis was defined as an mPDAI ≥ 5.860; endoscopic pouch images before ileostomy closure were collected. A convolutional neural network was used as the DL model, and the prediction rates of pouchitis after ileostomy closure were evaluated by fivefold cross-validation.

RESULTS

A total of 43 patients were included (24 males and 19 females, mean age 39.2 ± 13.2 years). Pouchitis occurred in 14 (33%) patients after ileostomy closure. In less than half of the patients, mPDAI scores matched before and after ileostomy closure. Most of patients whose mPDAI scores did not match before and after ileostomy closure had worse mPDAI scores after than before. The prediction rate of pouchitis calculated by the area under the curve using the DL model was 84%. Conversely, the prediction rate of pouchitis using mPDAI before ileostomy closure was 62%.

CONCLUSION

The prediction rate of pouchitis using the DL model was more than 20% higher than that using mPDAI, suggesting the utility of the DL model as a prediction model for the development of pouchitis. It could also be used to determine early interventions for pouchitis.

Identification of gastric cancer with convolutional neural networks: a systematic review

The identification of diseases is inseparable from artificial intelligence. As an important branch of artificial intelligence, convolutional neural networks play an important role in the identification of gastric cancer. We conducted a systematic review to summarize the current applications of convolutional neural networks in the gastric cancer identification. The original articles published in Embase, Cochrane Library, PubMed and Web of Science database were systematically retrieved according to relevant keywords. Data were extracted from published papers. A total of 27 articles were retrieved for the identification of gastric cancer using medical images. Among them, 19 articles were applied in endoscopic images and 8 articles were applied in pathological images. 16 studies explored the performance of gastric cancer detection, 7 studies explored the performance of gastric cancer classification, 2 studies reported the performance of gastric cancer segmentation and 2 studies analyzed the performance of gastric cancer delineating margins. The convolutional neural network structures involved in the research included AlexNet, ResNet, VGG, Inception, DenseNet and Deeplab, etc. The accuracy of studies was 77.3 - 98.7%. Good performances of the systems based on convolutional neural networks have been showed in the identification of gastric cancer. Artificial intelligence is expected to provide more accurate information and efficient judgments for doctors to diagnose diseases in clinical work.

Deep learning for gastroscopic images: computer-aided techniques for clinicians

Gastric disease is a major health problem worldwide. Gastroscopy is the main method and the gold standard used to screen and diagnose many gastric diseases. However, several factors, such as the experience and fatigue of endoscopists, limit its performance. With recent advancements in deep learning, an increasing number of studies have used this technology to provide on-site assistance during real-time gastroscopy. This review summarizes the latest publications on deep learning applications in overcoming disease-related and nondisease-related gastroscopy challenges. The former aims to help endoscopists find lesions and characterize them when they appear in the view shed of the gastroscope. The purpose of the latter is to avoid missing lesions due to poor-quality frames, incomplete inspection coverage of gastroscopy, etc., thus improving the quality of gastroscopy. This study aims to provide technical guidance and a comprehensive perspective for physicians to understand deep learning technology in gastroscopy. Some key issues to be handled before the clinical application of deep learning technology and the future direction of disease-related and nondisease-related applications of deep learning to gastroscopy are discussed herein.

Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos)

BACKGROUND AND AIMS

White-light endoscopy (WLE) is the most pivotal tool to detect gastric cancer in an early stage. However, the skill among endoscopists varies greatly. Here, we aim to develop a deep learning-based system named ENDOANGEL-LD (lesion detection) to assist in detecting all focal gastric lesions and predicting neoplasms by WLE.

METHODS

Endoscopic images were retrospectively obtained from Renmin Hospital of Wuhan University (RHWU) for the development, validation, and internal test of the system. Additional external tests were conducted in 5 other hospitals to evaluate the robustness. Stored videos from RHWU were used for assessing and comparing the performance of ENDOANGEL-LD with that of experts. Prospective consecutive patients undergoing upper endoscopy were enrolled from May 6, 2021 to August 2, 2021 in RHWU to assess clinical practice applicability.

RESULTS

Over 10,000 patients undergoing upper endoscopy were enrolled in this study. The sensitivities were 96.9% and 95.6% for detecting gastric lesions and 92.9% and 91.7% for diagnosing neoplasms in internal and external patients, respectively. In 100 videos, ENDOANGEL-LD achieved superior sensitivity and negative predictive value for detecting gastric neoplasms from that of experts (100% vs 85.5% ± 3.4% [P = .003] and 100% vs 86.4% ± 2.8% [P = .002], respectively). In 2010 prospective consecutive patients, ENDOANGEL-LD achieved a sensitivity of 92.8% for detecting gastric lesions with 3.04 ± 3.04 false positives per gastroscopy and a sensitivity of 91.8% and specificity of 92.4% for diagnosing neoplasms.

CONCLUSIONS

Our results show that ENDOANGEL-LD has great potential for assisting endoscopists in screening gastric lesions and suspicious neoplasms in clinical work. (Clinical trial registration number: ChiCTR2100045963.).

Impact of Computer-Assisted System on the Learning Curve and Quality in Esophagogastroduodenoscopy: Randomized Controlled Trial

Background and Aims: To investigate the impact of the computer-assisted system on esophagogastroduodenoscopy (EGD) training for novice trainees in a prospective randomized controlled trial. Methods: We have constructed a computer-aided system (CAD) using retrospective images based on deep learning which could automatically monitor the 26 anatomical landmarks of the upper digestive tract and document standard photos. Six novice trainees were allocated and grouped into the CAD group and control group. Each of them took the training course, pre and post-test, and EGD examination scored by two experts. The CAD group was trained with the assistance of the CAD system and the control group without. Results: Both groups achieved great improvements in EGD skills. The CAD group received a higher examination grading score in the EGD examination (72.83 ± 16.12 vs. 67.26 ± 15.64, p = 0.039), especially in the mucosa observation (26.40 ± 6.13 vs. 24.11 ± 6.21, p = 0.020) and quality of collected images (7.29 ± 1.09 vs. 6.70 ± 1.05). The CAD showed a lower blind spot rate (2.19 ± 2.28 vs. 3.92 ± 3.30, p = 0.008) compared with the control group. Conclusion: The artificial intelligence assistant system displayed assistant capacity on standard EGD training, and assisted trainees in achieving a learning curve with high operation quality, which has great potential for application. Clinical Trial Registration: This trial is registered at https:/clinicaltrials.gov/, number NCT04682821.

Advances in the Aetiology & Endoscopic Detection and Management of Early Gastric Cancer

Simple Summary

Gastric adenocarcinoma has remained a highly lethal disease. Awareness and recognition of preneoplastic conditions (including gastric atrophy and intestinal metaplasia) using high-resolution white-light endoscopy as well as chromoendoscopy is therefore essential. Helicobacter pylori, a class I carcinogen, remains the main contributor to the development of sporadic distal gastric neoplasia. Management of early gastric neoplasia with endoscopic resections should be in line with standard indications. A multidisciplinary approach to any case of an early gastric neoplasia is imperative. Hereditary forms of gastric cancer require a tailored approach and individua-lized surveillance.

Abstract

The mortality rates of gastric carcinoma remain high, despite the progress in research and development in disease mechanisms and treatment. Therefore, recognition of gastric precancerous lesions and early neoplasia is crucial. Two subtypes of sporadic gastric cancer have been recognized: cardia subtype and non-cardia (distal) subtype, the latter being more frequent and largely associated with infection of Helicobacter pylori, a class I carcinogen. Helicobacter pylori initiates the widely accepted Correa cascade, describing a stepwise progression through precursor lesions from chronic inflammation to gastric atrophy, gastric intestinal metaplasia and neoplasia. Our knowledge on He-licobacter pylori is still limited, and multiple questions in the context of its contribution to the pathogenesis of gastric neoplasia are yet to be answered. Awareness and recognition of gastric atrophy and intestinal metaplasia on high-definition white-light endoscopy, image-enhanced endoscopy and magnification endoscopy, in combination with histology from the biopsies taken accurately according to the protocol, are crucial to guiding the management. Standard indications for endoscopic resections (endoscopic mucosal resection and endoscopic submucosal dissection) of gastric dysplasia and intestinal type of gastric carcinoma have been recommended by multiple societies. Endoscopic evaluation and surveillance should be offered to individuals with an inherited predisposition to gastric carcinoma.

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial

BACKGROUND

Esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). An artificial intelligence system has been shown to monitor blind spots during EGD. In this study, we updated the system (ENDOANGEL), verified its effectiveness in improving endoscopy quality, and pretested its performance in detecting EGC in a multicenter randomized controlled trial.

METHODS

ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD in five hospitals were randomly assigned to the ENDOANGEL-assisted group or to a control group without use of ENDOANGEL. The primary outcome was the number of blind spots. Secondary outcomes included performance of ENDOANGEL in predicting EGC in a clinical setting.

RESULTS

1050 patients were randomized, and 498 and 504 patients in the ENDOANGEL and control groups, respectively, were analyzed. Compared with the control group, the ENDOANGEL group had fewer blind spots (mean 5.38 [standard deviation (SD) 4.32] vs. 9.82 [SD 4.98]; P < 0.001) and longer inspection time (5.40 [SD 3.82] vs. 4.38 [SD 3.91] minutes; P < 0.001). In the ENDOANGEL group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all three EGCs (one mucosal carcinoma and two high grade neoplasias) and two advanced gastric cancers, with a per-lesion accuracy of 84.7 %, sensitivity of 100 %, and specificity of 84.3 % for detecting gastric cancer.

CONCLUSIONS

In this multicenter study, ENDOANGEL was an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.

Tracking cancer lesions on surgical samples of gastric cancer by artificial intelligent algorithms

To quickly locate cancer lesions, especially suspected metastatic lesions after gastrectomy, AI algorithms of object detection and semantic segmentation were established. A total of 509 macroscopic images from 381 patients were collected. The RFB-SSD object detection algorithm and ResNet50-PSPNet semantic segmentation algorithm were used. Another 57 macroscopic images from 48 patients were collected for prospective verification. We used mAP as the metrics of object detection. The best mAP was 95.90% with an average of 89.89% in the test set. The mAP reached 92.60% in validation set. We used mIoU for evaluation of semantic segmentation. The best mIoU was 80.97% with an average of 79.26% in the test set. In addition, 81 out of 92 (88.04%) gastric specimens were accurately predicted for the cancer lesion located at the serosa by ResNet50-PSPNet semantic segmentation model. The positive rate and accuracy of AI prediction were different based on cancer invasive depth. The metastatic lymph nodes were predicted in 24 cases by semantic segmentation model. Among them, 18 cases were confirmed by pathology. The predictive accuracy was 75.00%. Our well-trained AI algorithms effectively identified the subtle features of gastric cancer in resected specimens that may be missed by naked eyes. Taken together, AI algorithms could assist clinical doctors quickly locating cancer lesions and improve their work efficiency.

Deep learning for diagnosis of precancerous lesions in upper gastrointestinal endoscopy: A review

Upper gastrointestinal (GI) cancers are the leading cause of cancer-related deaths worldwide. Early identification of precancerous lesions has been shown to minimize the incidence of GI cancers and substantiate the vital role of screening endoscopy. However, unlike GI cancers, precancerous lesions in the upper GI tract can be subtle and difficult to detect. Artificial intelligence techniques, especially deep learning algorithms with convolutional neural networks, might help endoscopists identify the precancerous lesions and reduce interobserver variability. In this review, a systematic literature search was undertaken of the Web of Science, PubMed, Cochrane Library and Embase, with an emphasis on the deep learning-based diagnosis of precancerous lesions in the upper GI tract. The status of deep learning algorithms in upper GI precancerous lesions has been systematically summarized. The challenges and recommendations targeting this field are comprehensively analyzed for future research.

Artificial Convolutional Neural Network in Object Detection and Semantic Segmentation for Medical Imaging Analysis

In the era of digital medicine, a vast number of medical images are produced every day. There is a great demand for intelligent equipment for adjuvant diagnosis to assist medical doctors with different disciplines. With the development of artificial intelligence, the algorithms of convolutional neural network (CNN) progressed rapidly. CNN and its extension algorithms play important roles on medical imaging classification, object detection, and semantic segmentation. While medical imaging classification has been widely reported, the object detection and semantic segmentation of imaging are rarely described. In this review article, we introduce the progression of object detection and semantic segmentation in medical imaging study. We also discuss how to accurately define the location and boundary of diseases.