Detecting blindspots in colonoscopy by modelling curvature

Abrahams, George; Hervé, Anthony; Bernth, Julius E.; Yvon, Marc; Hayee, Bu; Liu, Hongbin

doi:10.1109/icra48506.2021.9561966

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [51] and Mathew et al [52] utilized preprocedure CT scans for reconstruction of 3D colon segments. Abrahams et al [53] proposed to predict blindspots at acute bends in the colon assuming a known colon centerline, the camera's pose relative to the model, and a torus colon model with fixed-diameter circular cross-sections and straight or bent centerline. Lastly, Ma et al [54] made available a Colon10K dataset for evaluation of methods for finding the region in the colon in the current colonoscopy given an image taken from the same patient in a previous colonoscopy.…”

Section: B Bowel Preparation and Cleansingmentioning

confidence: 99%

Artificial Intelligence for Colonoscopy: Past, Present, and Future

Tavanapong

Riegler

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

During the past decades, many automated image analysis methods have been developed for colonoscopy. Realtime implementation of the most promising methods during colonoscopy has been tested in clinical trials, including several recent multi-center studies. All trials have shown results that may contribute to prevention of colorectal cancer. We summarize the past and present development of colonoscopy video analysis methods, focusing on two categories of artificial intelligence (AI) technologies used in clinical trials. These are (1) analysis and feedback for improving colonoscopy quality and (2) detection of abnormalities. Our survey includes methods that use traditional machine learning algorithms on carefully designed hand-crafted features as well as recent deep-learning methods. Lastly, we present the gap between current state-of-the-art technology and desirable clinical features and conclude with future directions of endoscopic AI technology development that will bridge the current gap.

show abstract

Section: B Bowel Preparation and Cleansingmentioning

confidence: 99%

Artificial Intelligence for Colonoscopy: Past, Present, and Future

Tavanapong

Riegler

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Although widely used, a colonoscopy has certain limitations that narrow the diagnostic value of the method [ 3 ]. The proper diagnosis relies on a complete colonoscopy procedure where the colonoscope must reach the cecal valve.…”

Section: Introductionmentioning

confidence: 99%

High Concordance of CT Colonography and Colonoscopy Allows for the Distinguishing and Diagnosing of Intestinal Diseases

Chervenkov,

Sirakov,

Georgiev

et al. 2023

Life

View full text Add to dashboard Cite

(1) Although new imaging methods for examining the GIT with high diagnostic capabilities were introduced, the improvement and implementation of safe, efficient, and cost-effective approaches continue, and GIT diseases are still challenging to diagnose; (2) Methods: We aim to show the possibilities of computed tomography (CT) colonography for early diagnosis of colon diseases using a multidetector 32-channel CT scanner after appropriate preparation; (3) Results: After a colonoscopy was performed earlier, 140 patients were examined with CT colonography. Complete colonoscopy was performed in 80 patients (57.1%) out of 140 who underwent CT colonography. Incomplete colonoscopy was observed in 52 patients (37.2%); in 5 patients (3.6%), it was contraindicated, and in 3 patients (2.1%), it was not performed because of patients’ refusal. We determined that in cases of complete FCS in 95% of patients, CT colonography established the same clinical diagnosis as FCS. In cases of incomplete, refused, or contraindicated FCS in 32.7% (17 patients), FCS failed to diagnose correctly. The main reasons for incomplete colonoscopy were: intraluminal obturation of tumor nature-17 patients (33%), extraluminal obturation (compression) from a tumor formation-4 patients (8%), stenotic changes of non-tumor nature-11 patients (21%), congenital diseases with changes in the length of the lumen of the intestinal loops-7 patients (13%), and subjective factors (pain, poor preparation, contraindications) in 13 patients (25%); (4) Conclusions: Our results confirmed that CT colonography is a method of choice in cases of negative FCS results accompanied by clinical data for the neoplastic process and in cases of incomplete and contraindicated FCS. Also, the insufflation system we developed optimizes the method by improving the quality of the obtained images and ensuring good patient tolerance.

show abstract

Detecting blindspots in colonoscopy by modelling curvature

Cited by 2 publications

References 21 publications

Artificial Intelligence for Colonoscopy: Past, Present, and Future

Artificial Intelligence for Colonoscopy: Past, Present, and Future

High Concordance of CT Colonography and Colonoscopy Allows for the Distinguishing and Diagnosing of Intestinal Diseases

Contact Info

Product

Resources

About