Evaluation of a Real-Time Artificial Intelligence System Using a Deep Neural Network for Polyp Detection and Localization in the Lower Gastrointestinal Tract

Seibt, H; Beyer, Albert; Häfner, Michael; Eggert, Christian; Huber, Henry A.; Räth, Timo

doi:10.1055/s-0040-1704078

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study confirms that GI Genius is able to virtually detect all the lesions diagnosed by expert endoscopists with an anticipation of the diagnosis compared with the human reader in the vast majority of cases, with a negligible rate of false-positive cases. Similarly, another system has been designed and is going to be released in the next few months: DISCOVERY (PENTAX Medical, Tokyo, Japan) [ 20 ]. DISCOVERY is intended to support endoscopists in polyp or lesion detection.…”

Section: Computer-aided Polyp Detection In Colonoscopymentioning

confidence: 99%

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

et al. 2021

View full text Add to dashboard Cite

aims to review the history, recent advances, evidence, and challenges of artificial intelligence (AI) in colonoscopy. Although it is mainly focused on polyp detection and characterization, it also considers other potential applications (i.e., inflammatory bowel disease) and future perspectives. Some of the most recent algorithms show promising results that are similar to human expert performance. The integration of AI in routine clinical practice will be challenging, with significant issues to overcome (i.e., regulatory, reimbursement). Medico-legal issues will also need to be addressed. With the exception of an AI system that is already available in selected countries (GI Genius; Medtronic, Minneapolis, MN, USA), the majority of the technology is still in its infancy and has not yet been proven to reach a sufficient diagnostic performance to be adopted in the clinical practice. However, larger players will enter the arena of AI in the next few months. Clin Endosc 2021 Jan 13. [Epub ahead of print]

show abstract

Section: Computer-aided Polyp Detection In Colonoscopymentioning

confidence: 99%

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

et al. 2021

View full text Add to dashboard Cite

show abstract

“…What is the proportion of flat lesions that have been used to train CADe algorithms, and what is the distribution of such flat lesions between <10 mm and LST? Table 1 reports an extract from PubMed of CADe algorithms that have been validated for flat lesion recognition 27–33 . There is a large variability in both the absolute number of lesions used for training and their distribution between polypoid and non‐polypoid categories.…”

Section: Ai and Flat Lesionsmentioning

confidence: 99%

“…Similarly, a lesion identified by AI should be something that the endoscopist is able to recognize as a true lesion. Otherwise, a true positive lesion identified by AI could become false negative if the endoscopist is not experienced enough to recognize it as a true lesion and this is a real possibility when it comes to 28 No NA NA 2018 Wang et al 29 Yes 1208 91.7 2019 Yamada et al 30 Yes 112 ‡ 92.9 2019 Hassan et al 31 Yes 132 99.2 2020 Seibt et al 32 NA NA NA 2020 Wang et al 34 Yes 241 86-99 † † 2020 Weigt et al 33 NA NA NA…”

Section: Ai and Human Interactionmentioning

confidence: 99%

“…Table 1 reports an extract from PubMed of CADe algorithms that have been validated for flat lesion recognition. [27][28][29][30][31][32][33] There is a large variability in both the absolute number of lesions used for training and their distribution between polypoid and nonpolypoid categories. Overall, most studies did not detail the exact proportion of flat lesions included, precluding a definitive comparability of the training datasets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence for non‐polypoid colorectal neoplasms

Hassan

Bhandari

Antonelli

et al. 2020

Digestive Endoscopy

View full text Add to dashboard Cite

The miss rate of flat advanced colorectal neoplasia is still unacceptably high, especially in the Western setting, notwithstanding the widespread implementation of quality improvement programs and training. It is well known that flat morphology is associated with miss rate of colorectal neoplasia, and that this subset of lesions often shows a more aggressive biological behaviour. Artificial intelligence (AI) applied to the detection of colorectal neoplasia has been shown to increase adenoma detection rate, consistently across all lesion sizes and locations in the colon. However, there is still uncertainty whether AI can reduce the miss rate of flat advanced neoplasia, mainly because all published trials report a low number of flat colorectal lesions in their training sets, and this could reduce AI accuracy for this subset of lesions. In addition, flat lesions have different morphologies with variable prevalence and potentially different accuracy in their detection. For example, the subtle appearance and rarer frequency of a non-granular laterally spreading tumor (LST) could be much harder to identify than a granular mixed LST. In this review, we present a summary of the evidence on the role of AI in the identification of colorectal flat neoplasia, with a focus on data regarding presence of LSTs in the training/validation sets of the AI systems currently available on the market.

show abstract

Evaluation of a Real-Time Artificial Intelligence System Using a Deep Neural Network for Polyp Detection and Localization in the Lower Gastrointestinal Tract

Cited by 2 publications

References 0 publications

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective

Artificial intelligence for non‐polypoid colorectal neoplasms

Contact Info

Product

Resources

About