Development and validation of an artificial intelligence-based system for predicting colorectal cancer invasion depth using multi-modal data.

OBJECTIVES: Accurate endoscopic optical prediction of the depth of cancer invasion is critical for guiding an optimal treatment approach of large sessile colorectal polyps but was hindered by insufficient endoscopists expertise and inter-observer variability. We aimed to construct a clinically applicable artificial intelligence (AI) system for the identification of presence of cancer invasion in large sessile colorectal polyps. METHODS: A deep learning-based colorectal cancer invasion calculation (CCIC) system was constructed. Multi-modal data including clinical information, white light (WL) and image-enhanced endoscopy (IEE) were included for training. The system was trained using 339 lesions and tested on 198 lesions across three hospitals. Man-machine contest, reader study and video validation were further conducted to evaluate the performance of CCIC. RESULTS: The overall accuracy of CCIC system using image and video validation was 90.4% and 89.7%, respectively. In comparison with 14 endoscopists, the accuracy of CCIC was comparable with expert endoscopists but superior to all the participating senior and junior endoscopists in both image and video validation set. With CCIC augmentation, the average accuracy of junior endoscopists improved significantly from 75.4% to 85.3% (P = 0.002). CONCLUSIONS: This deep learning-based CCIC system may play an important role in predicting the depth of cancer invasion in colorectal polyps, thus determining treatment strategies for these large sessile colorectal polyps.

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.).

Real-time automated diagnosis of colorectal cancer invasion depth using a deep learning model with multimodal data (with video).

BACKGROUND AND AIMS: The optical diagnosis of colorectal cancer (CRC) invasion depth with white light (WL) and image-enhanced endoscopy (IEE) remains challenging. We aimed to construct and validate a 2-modal deep learning-based system, incorporated with both WL and IEE images (named Endo-CRC) in estimating the invasion depth of CRC. METHODS: Samples were retrospectively obtained from 3 hospitals in China. We combined WL and IEE images into image pairs. Altogether, 337,278 image pairs from 268 noninvasive and superficial CRC and 181,934 image pairs from 82 deep CRC were used for training. A total of 296,644 and 4528 image pairs were used for internal and external tests and for comparison with endoscopists. Thirty-five videos were used for evaluating the real-time performance of the Endo-CRC system. Two deep learning models, solely using either WL (model W) or IEE images (model I), were constructed to compare with Endo-CRC. RESULTS: The accuracies of Endo-CRC in internal image tests with and without advanced CRC were 91.61% and 93.78%, respectively, and 88.65% in the external test, which did not include advanced CRC. In an endoscopist-machine competition, Endo-CRC achieved an expert comparable accuracy of 88.11% and the highest sensitivity compared with all endoscopists. In a video test, Endo-CRC achieved an accuracy of 100.00%. Compared with model W and model I, Endo-CRC had a higher accuracy (per image pair: 91.61% vs 88.27% compared with model I and 91.61% vs 81.32% compared with model W). CONCLUSIONS: The Endo-CRC system has great potential for assisting in CRC invasion depth diagnosis and may be well applied in clinical practice.

Multi-step validation of a deep learning-based system for the quantification of bowel preparation: a prospective, observational study.

BACKGROUND: Inadequate bowel preparation is associated with a decrease in adenoma detection rate (ADR). A deep learning-based bowel preparation assessment system based on the Boston bowel preparation scale (BBPS) has been previously established to calculate the automatic BBPS (e-BBPS) score (ranging 0-20). The aims of this study were to investigate whether there was a statistically inverse relationship between the e-BBPS score and the ADR, and to determine the threshold of e-BBPS score for adequate bowel preparation in colonoscopy screening. METHODS: In this prospective, observational study, we trained and internally validated the e-BBPS system using retrospective colonoscopy images and videos from the Endoscopy Center of Wuhan University, annotated by endoscopists. We externally validated the system using colonoscopy images and videos from the First People's Hospital of Yichang and the Third Hospital of Wuhan. To prospectively validate the system, we recruited consecutive patients at Renmin Hospital of Wuhan University aged between 18 and 75 years undergoing colonoscopy. The exclusion criteria included: contraindication to colonoscopy, family polyposis syndrome, inflammatory bowel disease, history of surgery for colorectal or colorectal cancer, known or suspected bowel obstruction or perforation, patients who were pregnant or lactating, inability to receive caecal intubation, and lumen obstruction. We did colonoscopy procedures and collected withdrawal videos, which were reviewed and the e-BBPS system was applied to all colon segments. The primary outcome of this study was ADR, defined as the proportion of patients with one or more conventional adenomas detected during colonoscopy. We calculated the ADR of each e-BBPS score and did a correlation analysis using Spearman analysis. FINDINGS: From May 11 to Aug 10, 2020, 616 patients underwent screening colonoscopies, which evaluated. There was a significant inverse correlation between the e-BBPS score and ADR (Spearman's rank -0·976, p<0·010). The ADR for the e-BBPS scores 1-8 was 28·57%, 28·68%, 26·79%, 19·19%, 17·57%, 17·07%, 14·81%, and 0%, respectively. According to the 25% ADR standard for screening colonoscopy, an e-BBPS score of 3 was set as a threshold to guarantee an ADR of more than 25%, and so high-quality endoscopy. Patients with scores of more than 3 had a significantly lower ADR than those with a score of 3 or less (ADR 15·93% vs 28·03%, p<0·001, 95% CI 0·28-0·66, odds ratio 0·43). INTERPRETATION: The e-BBPS system has potential to provide a more objective and refined threshold for the quantification of adequate bowel preparation. FUNDING: Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision and Hubei Province Major Science and Technology Innovation Project.

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.

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

BACKGROUND: Accurate delineation of cancer margins is critical for endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks for delineating the resection margin of early gastric cancer (EGC) under indigo carmine chromoendoscopy (CE) or white light endoscopy (WLE), and evaluated its performance and that of magnifying endoscopy with narrow-band imaging (ME-NBI). METHODS: We collected CE and WLE images of EGC lesions to train fully convolutional networks ENDOANGEL. ENDOANGEL was tested both on stationary images and endoscopic submucosal dissection (ESD) videos. The accuracy and reliability of ENDOANGEL and NBI-dependent delineation were further evaluated by a novel endoscopy-pathology point-to-point marking. RESULTS: ENDOANGEL had an accuracy of 85.7% in the CE images and 88.9% in the WLE images under an overlap ratio threshold of 0.60 in comparison with the manual markers labeled by the experts. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancers. The minimum distance between the margins predicted by ENDOANGEL and the histological cancer boundary was 3.44 ± 1.45 mm which outperformed the resection margin based on ME-NBI. CONCLUSIONS: ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGC under CE or WLE during ESD.

Interference of P-REX2a may inhibit proliferation and reverse the resistance of SGC7901 cells to doxorubicin.

Drug resistance inhibits the efficacy of doxorubicin in gastric cancer. Phosphatidylinositol 3,4,5-trisphosphate RAC exchanger 2a (P-REX2a) activates the phosphatidylinositol-3-kinase (PI3K)/protein kinase B (Akt) signaling pathway by binding to and inactivating phosphatase and tensin homolog (PTEN), which functions as a tumor promoter in a number of types of cancer. However, there is no research concerning the association between P-REX2a expression and drug resistance in gastric cancer. In the present study, the expression of P-REX2a in clinical gastric cancer tissues was detected, and the mechanism of doxorubicin resistance in the gastric cancer cell line SGC7901 was investigated. Using reverse transcription-quantitative polymerase chain reaction and western blotting, it was demonstrated that the mRNA and protein expression of P-REX2a was increased in gastric cancer tissues. MTT assays were also used to determine proliferation, and proliferation was revealed to be reduced following transfection of P-REX2a small interfering (si)RNA. When the cells were treated with 0.3 µM doxorubicin for 24 h, the rate of apoptosis in the siRNA-transfected groups significantly increased and no marked changes in of PTEN and Akt expression were observed. By contrast, the activity of PTEN increased, and the expression of p-Akt (S473) decreased in the P-REX2a siRNA-transfected group compared with the control. The detection of PTEN enzymatic activity in the present study was based on phosphatidylinositol-3,4,5-trisphosphate. Therefore, it was concluded that P-REX2a may participate in the generation of resistance to doxorubicin in gastric cancer, and this may be associated with the upregulation of the PI3K/Akt signaling pathway via inactivation of PTEN.

Diagnostic accuracy of the 14C-urea breath test in Helicobacter pylori infections: a meta-analysis.

OBJECTIVES: To summarize and appraise the available literature regarding the use of the 14C-urea breath test in the diagnosis of Helicobacter pylori infections in adult patients with dyspepsia and to calculate pooled diagnostic accuracy measures. METHODS: We systematically searched the PubMed, EMBASE, Cochrane Library, Chinese Journals Full-text (CNKI) and CBMDisc databases to identify published data regarding the sensitivity, specificity, and other measures of diagnostic accuracy of the 14C-urea breath test in the diagnosis of Helicobacter pylori infections in adult patients with dyspeptic symptoms. Risk of bias was assessed using the QUADAS (Quality Assessment of Diagnostic Accuracy Studies)-2 tool. Statistical analyses were performed using Meta-Disc 1.4 software and STATA. RESULTS: Eighteen studies met the inclusion criteria. Pooled results indicated that the 14C-urea breath test showed a diagnostic sensitivity of 0.96 (95% CI 0.95 to 0.96) and specificity of 0.93 (95% CI 0.91 to 0.94). The positive like ratio (PLR) was 12.27 (95% CI 8.17 to 18.44), the negative like ratio (NLR) was 0.05 (95% CI 0.04 to 0.07), and the area under the curve was 0.985. The DOR was 294.95 (95% CI 178.37 to 487.70). The 14C-urea breath test showed sufficient sensitivity and specificity for diagnosing Helicobacter pylori infection, but unexplained heterogeneity after meta-regression and several subgroup analyses remained. CONCLUSIONS: The UBT has high accuracy for diagnosing H. pylori infections in adult patients with dyspepsia. However, the reliability of these diagnostic meta-analytic estimates is limited by significant heterogeneity due to unknown factors.