A novel intelligent chromo capsule endoscope for the diagnosis of neoplastic lesions in the gastrointestinal tract.

Background: Chromoendoscopy has not been fully integrated into capsule endoscopy. This study aimded to develop and validate a novel intelligent chromo capsule endoscope (ICCE). Methods: The ICCE has two modes: a white-light imaging (WLI) mode and an intelligent chromo imaging (ICI) mode. The performance of the ICCE in observing colors, animal tissues, and early gastrointestinal (GI) neoplastic lesions in humans was evaluated. Images captured by the ICCE were analysed using variance of Laplacian (VoL) values or image contrast evaluation. Results: For color observation, conventional narrow-band imaging endoscopes and the ICI mode of the ICCE have similar spectral distributions. Compared with the WLI mode, the ICI mode had significantly higher VoL values for animal tissues (2.154 ± 1.044 vs 3.800 ± 1.491, P = 0.003), gastric precancerous lesions and early gastric cancers (2.242 ± 0.162 vs 6.642 ± 0.919, P < 0.001), and colon tumors (3.896 ± 1.430 vs 11.882 ± 7.663, P < 0.001), and significantly higher contrast for differentiating tumor and non-tumor areas (0.069 ± 0.046 vs 0.144 ± 0.076, P = 0.005). More importantly, the sensitivity, specificity, and accuracy of the ICI mode for early GI tumors were 95.83%, 91.67%, and 94.64%, respectively, which were significantly higher than the values of the WLI mode (78.33% [P < 0.001], 77.08% [P = 0.01], and 77.98% [P < 0.001], respectively). Conclusions: We successfully integrated ICI into the capsule endoscope. The ICCE is an innovative and useful tool for differential diagnosis based on contrast-enhanced images and thus has great potential as a superior diagnostic tool for early GI tumor detection.

Artificial intelligence-based diagnosis of abnormalities in small-bowel capsule endoscopy.

BACKGROUND : Further development of deep learning-based artificial intelligence (AI) technology to automatically diagnose multiple abnormalities in small-bowel capsule endoscopy (SBCE) videos is necessary. We aimed to develop an AI model, to compare its diagnostic performance with doctors of different experience levels, and to further evaluate its auxiliary role for doctors in diagnosing multiple abnormalities in SBCE videos. METHODS : The AI model was trained using 280 426 images from 2565 patients, and the diagnostic performance was validated in 240 videos. RESULTS : The sensitivity of the AI model for red spots, inflammation, blood content, vascular lesions, protruding lesions, parasites, diverticulum, and normal variants was 97.8 %, 96.1 %, 96.1 %, 94.7 %, 95.6 %, 100 %, 100 %, and 96.4 %, respectively. The specificity was 86.0 %, 75.3 %, 87.3 %, 77.8 %, 67.7 %, 97.5 %, 91.2 %, and 81.3 %, respectively. The accuracy was 95.0 %, 88.8 %, 89.2 %, 79.2 %, 80.8 %, 97.5 %, 91.3 %, and 93.3 %, respectively. For junior doctors, the assistance of the AI model increased the overall accuracy from 85.5 % to 97.9 % (P  < 0.001, Bonferroni corrected), comparable to that of experts (96.6 %, P > 0.0125, Bonferroni corrected). CONCLUSIONS : This well-trained AI diagnostic model automatically diagnosed multiple small-bowel abnormalities simultaneously based on video-level recognition, with potential as an excellent auxiliary system for less-experienced endoscopists.

Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: A retrospective multicentre study.

BACKGROUND: To reduce the high incidence and mortality of gastric cancer (GC), we aimed to develop deep learning-based models to assist in predicting the diagnosis and overall survival (OS) of GC patients using pathological images. METHODS: 2333 hematoxylin and eosin-stained pathological pictures of 1037 GC patients were collected from two cohorts to develop our algorithms, Renmin Hospital of Wuhan University (RHWU) and the Cancer Genome Atlas (TCGA). Additionally, we gained 175 digital pictures of 91 GC patients from National Human Genetic Resources Sharing Service Platform (NHGRP), served as the independent external validation set. Two models were developed using artificial intelligence (AI), one named GastroMIL for diagnosing GC, and the other named MIL-GC for predicting outcome of GC. FINDINGS: The discriminatory power of GastroMIL achieved accuracy 0.920 in the external validation set, superior to that of the junior pathologist and comparable to that of expert pathologists. In the prognostic model, C-indices for survival prediction of internal and external validation sets were 0.671 and 0.657, respectively. Moreover, the risk score output by MIL-GC in the external validation set was proved to be a strong predictor of OS both in the univariate (HR = 2.414, P < 0.0001) and multivariable (HR = 1.803, P = 0.043) analyses. The predicting process is available at an online website (https://baigao.github.io/Pathologic-Prognostic-Analysis/). INTERPRETATION: Our study developed AI models and contributed to predicting precise diagnosis and prognosis of GC patients, which will offer assistance to choose appropriate treatment to improve the survival status of GC patients. FUNDING: Not applicable.

Novel scheme for non-invasive gut bioinformation acquisition with a magnetically controlled sampling capsule endoscope.

OBJECTIVE: Intestinal flora and metabolites are associated with multiple systemic diseases. Current approaches for acquiring information regarding microbiota/metabolites have limitations. We aimed to develop a precise magnetically controlled sampling capsule endoscope (MSCE) for the convenient, non-invasive and accurate acquisition of digestive bioinformation for disease diagnosis and evaluation. DESIGN: The MSCE and surgery were both used for sampling both jejunal and ileal GI content in the control and antibiotic-induced diarrhoea groups. The GI content was then used for microbiome profiling and metabolomics profiling. RESULTS: Compared with surgery, our data showed that the MSCE precisely acquired data regarding the intestinal flora and metabolites, which was effectively differentiated in different intestinal regions and disease models. Using MSCE, we detected a dramatic decrease in the abundance of Bacteroidetes, Patescibacteria and Actinobacteria and hippuric acid levels, as well as an increase in the abundance of Escherichia-Shigella and the 2-pyrrolidinone levels were detected in the antibiotic-induced diarrhoea model by MSCE. MSCE-mediated sampling revealed specific gut microbiota/metabolites including Enterococcus, Lachnospiraceae, acetyl-L-carnitine and succinic acid, which are related to metabolic diseases, cancers and nervous system disorders. Additionally, the MSCE exhibited good sealing characteristics with no contamination after sampling. CONCLUSIONS: We present a newly developed MSCE that can non-invasively and accurately acquire intestinal bioinformation via direct visualization under magnetic control, which may further aid in disease prevention, diagnosis, prognosis and treatment.

Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model.

BACKGROUND & AIMS: Capsule endoscopy has revolutionized investigation of the small bowel. However, this technique produces a video that is 8-10 hours long, so analysis is time consuming for gastroenterologists. Deep convolutional neural networks (CNNs) can recognize specific images among a large variety. We aimed to develop a CNN-based algorithm to assist in the evaluation of small bowel capsule endoscopy (SB-CE) images. METHODS: We collected 113,426,569 images from 6970 patients who had SB-CE at 77 medical centers from July 2016 through July 2018. A CNN-based auxiliary reading model was trained to differentiate abnormal from normal images using 158,235 SB-CE images from 1970 patients. Images were categorized as normal, inflammation, ulcer, polyps, lymphangiectasia, bleeding, vascular disease, protruding lesion, lymphatic follicular hyperplasia, diverticulum, parasite, and other. The model was further validated in 5000 patients (no patient was overlap with the 1970 patients in the training set); the same patients were evaluated by conventional analysis and CNN-based auxiliary analysis by 20 gastroenterologists. If there was agreement in image categorization between the conventional analysis and CNN model, no further evaluation was performed. If there was disagreement between the conventional analysis and CNN model, the gastroenterologists re-evaluated the image to confirm or reject the CNN categorization. RESULTS: In the SB-CE images from the validation set, 4206 abnormalities in 3280 patients were identified after final consensus evaluation. The CNN-based auxiliary model identified abnormalities with 99.88% sensitivity in the per-patient analysis (95% CI, 99.67-99.96) and 99.90% sensitivity in the per-lesion analysis (95% CI, 99.74-99.97). Conventional reading by the gastroenterologists identified abnormalities with 74.57% sensitivity (95% CI, 73.05-76.03) in the per-patient analysis and 76.89% in the per-lesion analysis (95% CI, 75.58-78.15). The mean reading time per patient was 96.6 ± 22.53 minutes by conventional reading and 5.9 ± 2.23 minutes by CNN-based auxiliary reading (P < .001). CONCLUSIONS: We validated the ability of a CNN-based algorithm to identify abnormalities in SB-CE images. The CNN-based auxiliary model identified abnormalities with higher levels of sensitivity and significantly shorter reading times than conventional analysis by gastroenterologists. This algorithm provides an important tool to help gastroenterologists analyze SB-CE images more efficiently and more accurately.