Artificial intelligence and colonoscopy − enhancements and improvements

Yoo, Byung Soo; D’Souza, Steve M.; Houston, Kevin V.; Patel, Ankit; Lau, James; Elmahdi, Alsiddig; Parekh, Parth J.; Johnson, D. W.

doi:10.37126/aige.v2.i4.157

Cited by 2 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been used to detect and characterize polyps, mucosal healing, and inflammatory bowel dysplasia during colonoscopy. It can also be used to assess the quality of bowel preparation before the examination (Gubatan et al 2021 ; Yang and Bang 2019 ; Yoo et al 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Acute colonic flexures: the basis for developing an artificial intelligence-based tool for predicting the course of colonoscopy

et al. 2022

View full text Add to dashboard Cite

Tortuosity of the colon is an important parameter for predicting the course of colonoscopy. Computed tomography scans of the abdominal cavity were performed in 224 (94 female, 130 male) adult subjects. The number of acute (angle not exceeding 90°) bends between adjacent colonic segments was noted and analyzed. Data were analyzed for correlation with gender, age, height and weight. An artificial intelligence algorithm was proposed to predict the course of colonoscopy. We determined the number of acute flexions in females to be 9.74 ± 2.5 (min–max: 4–15) and in males to be 8.7 ± 2.75 (min–max: 4–20). In addition, more acute flexions were found in women than in men and in older women (after 60 years) and men (after 80 years) than in younger ones. We found the greatest variability in the number of acute flexures in the sigmoid colon (0–9), but no correlation was found between the number of acute flexures and age, gender, height or BMI. In the transverse colon, older and female subjects had more flexures than younger and male subjects, respectively. Older subjects had more acute flexures in the descending colon than younger subjects. There are opportunities to use the number of acute flexures (4–7, 8–12, more than 12 flexures) to classify patients into appropriate risk categories for future incomplete colonoscopy. On this basis, we predicted troublesome colonoscopies in 14.9% female and in 6.1% male subjects.

show abstract

Section: Introductionmentioning

confidence: 99%

Acute colonic flexures: the basis for developing an artificial intelligence-based tool for predicting the course of colonoscopy

et al. 2022

View full text Add to dashboard Cite

show abstract

The imitation game: a review of the use of artificial intelligence in colonoscopy, and endoscopists’ perceptions thereof

Tham¹,

Koh²,

Ladlad³

et al. 2023

Ann Coloproctol

View full text Add to dashboard Cite

The development of deep learning systems in artificial intelligence (AI) has enabled advances in endoscopy, and AI-aided colonoscopy has recently been ushered into clinical practice as a clinical decision-support tool. This has enabled real-time AI-aided detection of polyps with a higher sensitivity than the average endoscopist, and evidence to support its use has been promising thus far. This review article provides a summary of currently published data relating to AI-aided colonoscopy, discusses current clinical applications, and introduces ongoing research directions. We also explore endoscopists’ perceptions and attitudes toward the use of this technology, and discuss factors influencing its uptake in clinical practice.

show abstract

Artificial intelligence and colonoscopy − enhancements and improvements

Cited by 2 publications

References 57 publications

Acute colonic flexures: the basis for developing an artificial intelligence-based tool for predicting the course of colonoscopy

Acute colonic flexures: the basis for developing an artificial intelligence-based tool for predicting the course of colonoscopy

The imitation game: a review of the use of artificial intelligence in colonoscopy, and endoscopists’ perceptions thereof

Contact Info

Product

Resources

About