Search

Background: To improve the diagnosis of early gastric cancer (EGC), a train-the-trainer (TTT) course was developed. This trial aimed to investigate whether TTT courses from trained trainers could improve trainees' EGC detection. Methods: In this multi-center, retrospective study, the training was carried out 8 times in one year. Clinical records one year before ("2016"), during ("2017"), and after ("2018") the course were collected. The primary endpoint was the improvement of EGC detection rate after TTT courses. Results: Twenty-four trainees from 17 hospitals were included in this study. A total of 123,416 esophagogastroduodenoscopy and 65,570 colonoscopy procedures were analyzed. The early gastric cancer detection rate (EDR) was 0.101% in 2016, which significantly increased to 0.338% in 2018 (p = 0.015). The early gastric cancer ratio (ECR, ratio of newly detected EGCs to all newly detected gastric cancers) in 2016 was 8.440%, which consistently increased to 11.853% and 19.778% in 2017 and 2018 (p = 0.006), respectively. In contrast, the advanced gastric cancer detection rate (ADR) was similar before, during, or after the course (p = 0.987). The 3-year EDR, ECR, and ADR in esophageal and colorectal cancer were not significantly different. Conclusions: The systematic training course can improve EGC detection rate and may be an effective educational strategy to reduce gastrointestinal cancers mortality. [ABSTRACT FROM AUTHOR]

Benign ulcerative colorectal diseases (UCDs) such as ulcerative colitis, Crohn's disease, ischemic colitis, and intestinal tuberculosis share similar phenotypes with different etiologies and treatment strategies. To accurately diagnose closely related diseases like UCDs, we hypothesize that contextual learning is critical in enhancing the ability of the artificial intelligence models to differentiate the subtle differences in lesions amidst the vastly divergent spatial contexts. White-light colonoscopy datasets of patients with confirmed UCDs and healthy controls were retrospectively collected. We developed a Multiclass Contextual Classification (MCC) model that can differentiate among the mentioned UCDs and healthy controls by incorporating the tissue object contexts surrounding the individual lesion region in a scene and spatial information from other endoscopic frames (video-level) into a unified framework. Internal and external datasets were used to validate the model's performance. Training datasets included 762 patients, and the internal and external testing cohorts included 257 patients and 293 patients, respectively. Our MCC model provided a rapid reference diagnosis on internal test sets with a high averaged area under the receiver operating characteristic curve (image-level: 0.950 and video-level: 0.973) and balanced accuracy (image-level: 76.1% and video-level: 80.8%), which was superior to junior endoscopists (accuracy: 71.8%, P <.0001) and similar to experts (accuracy: 79.7%, P =.732). The MCC model achieved an area under the receiver operating characteristic curve of 0.988 and balanced accuracy of 85.8% using external testing datasets. These results enable this model to fit in the routine endoscopic workflow, and the contextual framework to be adopted for diagnosing other closely related diseases. [Display omitted] The study developed an artificial intelligence model that can differentiate among various ulcerative benign colorectal diseases including ulcerative colitis, Crohn's disease, ischemic colitis, and intestinal tuberculosis from colonoscopy still images and videos. [ABSTRACT FROM AUTHOR]

Background and aims: Improving the rate of polyp detection is an important measure to prevent colorectal cancer (CRC). Real-time automatic polyp detection systems, through deep learning methods, can learn and perform specific endoscopic tasks previously performed by endoscopists. The purpose of this study was to explore whether a high-performance, real-time automatic polyp detection system could improve the polyp detection rate (PDR) in the actual clinical environment. Methods: The selected patients underwent same-day, back-to-back colonoscopies in a random order, with either traditional colonoscopy or artificial intelligence (AI)-assisted colonoscopy performed first by different experienced endoscopists (> 3000 colonoscopies). The primary outcome was the PDR. It was registered with clinicaltrials.gov. (NCT047126265). Results: In this study, we randomized 150 patients. The AI system significantly increased the PDR (34.0% vs 38.7%, p < 0.001). In addition, AI-assisted colonoscopy increased the detection of polyps smaller than 6 mm (69 vs 91, p < 0.001), but no difference was found with regard to larger lesions. Conclusions: A real-time automatic polyp detection system can increase the PDR, primarily for diminutive polyps. However, a larger sample size is still needed in the follow-up study to further verify this conclusion. Trial Registration: clinicaltrials.gov Identifier: NCT047126265 [ABSTRACT FROM AUTHOR]

Endoscopic submucosal dissection (ESD) and EMR are applied in treating superficial colorectal neoplasms but are contraindicated by deeply invasive colorectal cancer (CRC). The invasion depth of neoplasms can be examined by an automated artificial intelligence (AI) system to determine the applicability of ESD and EMR. A deep convolutional neural network with a tumor localization branch to guide invasion depth classification was constructed on the GoogLeNet architecture. The model was trained using 7734 nonmagnified white-light colonoscopy (WLC) images supplemented by image augmentation from 657 lesions labeled with histopathologic analysis of invasion depth. An independent testing dataset consisting of 1634 WLC images from 156 lesions was used to validate the model. For predicting noninvasive and superficially invasive neoplasms, the model achieved an overall accuracy of 91.1% (95% confidence interval [CI], 89.6%-92.4%), with 91.2% sensitivity (95% CI, 88.8%-93.3%) and 91.0% specificity (95% CI, 89.0%-92.7%) at an optimal cutoff of.41 and the area under the receiver operating characteristic (AUROC) curve of.970 (95% CI,.962-.978). Inclusion of the advanced CRC data significantly increased the sensitivity in differentiating superficial neoplasms from deeply invasive early CRC to 65.3% (95% CI, 61.9%-68.8%) with an AUROC curve of.729 (95% CI,.699-.759), similar to experienced endoscopists (.691; 95% CI,.624-.758). We have developed an AI-enhanced attention-guided WLC system that differentiates noninvasive or superficially submucosal invasive neoplasms from deeply invasive CRC with high accuracy, sensitivity, and specificity. [Display omitted] [ABSTRACT FROM AUTHOR]

The loss-of-function mutation of AT-rich interactive domain 1A (ARID1A) frequently occurs in various types of cancer, making it a promising therapeutic target. In the present study, we performed a screening of an FDA-approved drug library in ARID1A isogenic colorectal cancer (CRC) cells and discovered that ARID1A loss sensitizes CRC cells to floxuridine (FUDR), an antineoplastic agent used for treating hepatic metastases from CRC, both in vivo and in vitro. As a pyrimidine analogue, FUDR induces DNA damage by inhibiting thymidylate synthase (TS) activity. ARID1A, as a regulator of DNA damage repair, when lost, exacerbates FUDR-induced DNA damage, leading to increased cell apoptosis. Specifically, ARID1A deficiency impairs DNA damage repair by downregulating Chk2 phosphorylation, thereby sensitizing cancer cells to FUDR. Notably, we found that FUDR exhibited increased sensitivity in ARID1A-deficient cells compared to 5-fluorouracil (5-FU), a commonly used anticancer drug for CRC. This suggests that FUDR is superior to 5-FU in treating ARID1A-deficient CRC. In conclusion, ARID1A loss significantly heightens sensitivity to FUDR by promoting FUDR-induced DNA damage in CRC. These findings offer a novel therapeutic approach for the treatment of CRC characterized by ARID1A loss-of-function mutations. [ABSTRACT FROM AUTHOR]