Dataset Information

The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions.

ABSTRACT: This article analyses the literature regarding the value of computer-assisted systems in esogastroduodenoscopy-quality monitoring and the assessment of gastric lesions. Current data show promising results in upper-endoscopy quality control and a satisfactory detection accuracy of gastric premalignant and malignant lesions, similar or even exceeding that of experienced endoscopists. Moreover, artificial systems enable the decision for the best treatment strategies in gastric-cancer patient care, namely endoscopic vs surgical resection according to tumor depth. In so doing, unnecessary surgical interventions would be avoided whilst providing a better quality of life and prognosis for these patients. All these performance data have been revealed by numerous studies using different artificial intelligence (AI) algorithms in addition to white-light endoscopy or novel endoscopic techniques that are available in expert endoscopy centers. It is expected that ongoing clinical trials involving AI and the embedding of computer-assisted diagnosis systems into endoscopic devices will enable real-life implementation of AI endoscopic systems in the near future and at the same time will help to overcome the current limits of the computer-assisted systems leading to an improvement in performance. These benefits should lead to better diagnostic and treatment strategies for gastric-cancer patients. Furthermore, the incorporation of AI algorithms in endoscopic tools along with the development of large electronic databases containing endoscopic images might help in upper-endoscopy assistance and could be used for telemedicine purposes and second opinion for difficult cases.

SUBMITTER: Lazar DC

PROVIDER: S-EPMC8309682 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions.

Lazăr Daniela Cornelia DC Avram Mihaela Flavia MF Faur Alexandra Corina AC Romoşan Ioan I Goldiş Adrian A

Gastroenterology report 20210312 3

This article analyses the literature regarding the value of computer-assisted systems in esogastroduodenoscopy-quality monitoring and the assessment of gastric lesions. Current data show promising results in upper-endoscopy quality control and a satisfactory detection accuracy of gastric premalignant and malignant lesions, similar or even exceeding that of experienced endoscopists. Moreover, artificial systems enable the decision for the best treatment strategies in gastric-cancer patient care, ...[more]

PMID: 34316369

Similar Datasets

Project description:AimTo analyse the clinical features of patients with the serrated lesions in the upper gastrointestinal tract (UPGI) tract.MethodsPatients who underwent routine esophagogastroduodenoscopy (EGD) at the Digestive Endoscopy Centre of General Hospital, Tianjin Medical University between January 2011 and December 2015 were consecutively recruited. Patients with UPGI serrated lesions were consecutively identified. The patients' demographics and histopathology were recorded. The colorectal findings for patients who underwent colonoscopy simultaneously or within six months were also extracted from the colonoscopy database. In addition, we analysed differences in colorectal neoplasia detection between the study patients and randomly selected patients matched for age and gender who did not exhibit serrated lesions and who also underwent colonoscopy in the same period.ResultsA total of 21 patients out of 98746 patients (0.02%) who underwent EGD were confirmed to have serrated lesions with predominantly crenated, sawtooth-like configurations. The mean age of the 21 patients was (55.3 ± 17.2) years, and 11 patients were male (52.4%). In terms of the locations of the serrated lesions, 17 were found in the stomach (including 3 in the cardia, 9 in the corpus and 5 in the antrum), 3 were found in the duodenum, and 1 was found in the esophagus. Serrated lesions were found in different mucosal lesions, with 14 lesions were detected in polyps (8 hyperplastic polyps and 6 serrated adenomas with low grade dysplasia), 3 detected in Ménétrier gastropathy, 3 detected in an area of inflammation or ulcer, and 1 detected in the intramucosal carcinoma of the duodenum. In addition, colonoscopy data were available for 18 patients, and a significantly higher colorectal adenoma detection rate was observed in the UPGI serrated lesions group than in the randomly selected age- and gender-matched group without serrated lesions who also underwent colonoscopy in the same period (38.9% vs 11.1%, OR = 5.091, 95%CI: 1.534-16.890, P = 0.010). The detection rate of advanced adenoma was also higher in the UPGI serrated lesions group (22.2% vs 4.2%, OR = 6.571, 95%CI: 1.322-32.660, P = 0.028).ConclusionSerrated lesions in the UPGI were detected in various mucosal lesions with different pathological morphologies. Moreover colonoscopy is recommended for the detection of concurrent colorectal adenoma for these patients.

Project description:BackgroundPreimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy.ObjectiveComputer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment.Study designImage processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm.ResultsAn efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84.ConclusionThis research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model.

Project description:Computer-Assisted Semen Analysis (CASA) enables reliable analysis of semen images, and is designed to process large number of images with high consistency, accuracy, and repeatability. Design and testing of CASA algorithms can be accelerated greatly if reliable simulations of semen images under a variety of conditions and sample quality modes are available. Using life-like simulation of semen images can quantify the performance of existing and proposed CASA algorithms, since the parameters of the simulated image are known and controllable. We present simulation models for sperm cell image and swimming modes observed in real 2D (top-down) images of sperm cells in laboratory specimen. The models simulate human sperm using four (4) types of swimming, namely linear mean, circular, hyperactive, and immotile (or dead). The simulation models are used in studying algorithms for segmentation, localization, and tracking of sperm cells. Several segmentation and localization algorithms were tested under varying levels of noise, and then compared using precision, recall, and the optimal subpattern assignment (OSPA) metric. Images of real human semen sample were used to validate the segmentation and localization observations obtained from simulations. An example is given of sperm cell tracking on simulated semen images of cells using the different tracking algorithms (nearest neighbor (NN), global nearest neighbor (GNN), probabilistic data association filter (PDAF), and joint probabilistic data association filter (JPDAF)). Tracking performance was evaluated through multi-object tracking precision (MOTP) and multi-object tracking accuracy (MOTA). Simulation models enable objective assessments of semen image processing algorithms. We demonstrate the use of a new simulation tool to assess and compare segmentation, localization, and tracking methods. The simulation software allows testing along a large spectrum of parameter values that control the appearance and behavior of simulated semen images. Users can generate scenarios of different characteristics and assess the effectiveness of different CASA algorithms in these environments. The simulation was used to assess and compare algorithms for segmentation and tracking of sperm cells in semen images.

Project description:BackgroundThe quality of gastrointestinal (GI) endoscopy has been recently identified as a major priority being associated with many outcomes and patient's experience.ObjectiveTo assess adherence of endoscopists to the European Society of Gastrointestinal Endoscopy (ESGE) quality performance measures for upper and lower GI endoscopy in Italy.MethodsAll endoscopist members of the Italian Society of Digestive Endoscopy (SIED) were invited from October 2018 to December 2018 to participate to a self-administered questionnaire-based survey. The questionnaire included questions on demographics and professional characteristics, and the recent ESGE quality performance measures for upper and lower GI endoscopy.ResultsA total of 392 endoscopists participated in the study. Only a minority (18.2%) of participants recorded the duration of esophagogastroduodenoscopy (EGD) and 51% provided accurate photo documentation in the minimum standard of 90% of cases. Almost all endoscopists correctly used Prague and Los Angeles classifications (87.8% and 98.2%, respectively), as well as Seattle and Management of precancerous conditions and lesions in the stomach (MAPS) biopsy protocols (86.5% and 91.4%, respectively). However, only 52.8% of participants monitored complications after therapeutic EGD, and 40.8% recorded patients with a diagnosis of Barrett's esophagus (BE). With regard to colonoscopy, almost all endoscopists (93.9%) used the Boston Bowel Preparation Scale for measuring bowel preparation quality and reported a cecal intubation rate ≥90%. However, about a quarter (26.2%) of participants reported an adenoma detection rate of <25%, only 52.8% applied an appropriate polypectomy technique, 48% monitored complications after the procedure, and 12.4% measured patient's experience.ConclusionThe adherence of endoscopists to ESGE performance measures for GI endoscopy is sub-optimal in Italy. There is a need to disseminate and implement performance measures and endorse educational and scientific interventions on the quality of endoscopy.

Dataset Information

The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions.

Publications

The role of computer-assisted systems for upper-endoscopy quality monitoring and assessment of gastric lesions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets