Artificial intelligence−enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth

Luo, Xin; Wang, Jiahao; Han, Zelong; Yu, Hanry; Chen, Zhenyu; Huang, Feiyang; Xu, Yumeng; Cai, Jianqun; Zhang, Qiang; Qiao, Weiguang; Ng, Inn Chuan; Tan, Robby T.; Liu, Side; Yu, Hanry

doi:10.1016/j.gie.2021.03.936

Cited by 28 publications

(24 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last decade, several studies focused on the development of these tools for application to conventional esophagogastroduodenoscopy and colonoscopy. These works have mainly focused on the development of algorithms for the detection and characterization of premalignant or malignant lesions [21][22][23]. The first commercial AI solution for automatic identification of colorectal polyps received clearance by the U.S. Food and Drug Administration [24].…”

Section: Discussionmentioning

confidence: 99%

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

et al. 2021

View full text Add to dashboard Cite

Background and Objectives: Device-assisted enteroscopy (DAE) allows deep exploration of the small bowel and combines diagnostic and therapeutic capacities. Suspected mid-gastrointestinal bleeding is the most frequent indication for DAE, and vascular lesions, particularly angioectasia, are the most common etiology. Nevertheless, the diagnostic yield of DAE for the detection of these lesions is suboptimal. Deep learning algorithms have shown great potential for automatic detection of lesions in endoscopy. We aimed to develop an artificial intelligence (AI) model for the automatic detection of angioectasia DAE images. Materials and Methods: A convolutional neural network (CNN) was developed using DAE images. Each frame was labeled as normal/mucosa or angioectasia. The image dataset was split for the constitution of training and validation datasets. The latter was used for assessing the performance of the CNN. Results: A total of 72 DAE exams were included, and 6740 images were extracted (5345 of normal mucosa and 1395 of angioectasia). The model had a sensitivity of 88.5%, a specificity of 97.1% and an AUC of 0.988. The image processing speed was 6.4 ms/frame. Conclusions: The application of AI to DAE may have a significant impact on the management of patients with suspected mid-gastrointestinal bleeding.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It showed an overall accuracy of 91.1% with a sensitivity of 91.2% and a specificity of 91.0%. 68 Although technical limitations remain with respect to clinical application and such AI models cannot outperform experienced endoscopists, these tools are expected to aid the clinical decision-making process in the treatment of ECC in the future.…”

Section: Artificial Intelligence-aided Clinical Decision-mentioning

confidence: 99%

“…Recently, an AI-enhanced attention-guided whitelight colonoscopy system was developed to differentiate noninvasive or superficially invasive neoplasms from deeply invasive colorectal cancer. It showed an overall accuracy of 91.1% with a sensitivity of 91.2% and a specificity of 91.0% [ 68 ]. Although technical limitations remain with respect to clinical application and such AI models cannot outperform experienced endoscopists, these tools are expected to aid the clinical decision-making process in the treatment of ECC in the future.…”

Section: Unmet Needs In Ecc and Latest Researchmentioning

confidence: 99%

Endoscopic diagnosis and treatment of early colorectal cancer

Hong

Byeon

2022

Intest Res

View full text Add to dashboard Cite

Early colorectal cancer refers to cancer in the colorectum that is confined to the mucosa or submucosa and does not invade the muscularis propria, irrespective of lymph node or distant metastasis. As the number of persons undergoing screening colonoscopy increases, the proportion of patients diagnosed with precancerous colorectal lesions and early colorectal cancer also increases. In the last decade, innovative optical technologies for endoscopic diagnosis have been introduced and endoscopic treatment techniques such as endoscopic submucosal dissection have provided major breakthroughs in the management of early colorectal cancer. With these remarkable developments, endoscopic treatment has established itself as an alternative to surgical resection in the treatment of early colorectal cancer. This review will discuss the endoscopic diagnosis and treatment of early colorectal cancer. Furthermore, the unmet needs in this field and the latest research addressing those issues will be summarized.

show abstract

“…(82)(83)(84) It is, therefore, unsurprising that AI is also being studied in these areas. (85)(86)(87)…”

Section: Other Examples Of Research In the Use Of Ai In Colonoscopymentioning

confidence: 99%

Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications

Li¹,

Lm²

2022

smedj

View full text Add to dashboard Cite

Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.

show abstract

Artificial intelligence−enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth

Cited by 28 publications

References 31 publications

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

Endoscopic diagnosis and treatment of early colorectal cancer

Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications

Contact Info

Product

Resources

About