Computer aided detection for laterally spreading tumors and sessile serrated adenomas during colonoscopy

Zhou, Guanyu; Xiao, Xincai; Tu, Mengtian; Liu, Peixi; Yang, Dexin; Liu, Xiaogang; Zhang, Renyi; Li, Liangping; Lei, Shan; Wang, Han; Song, Yan; Wang, Pu

doi:10.1371/journal.pone.0231880

Cited by 22 publications

(28 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An exclusive study demonstrated the perimage sensitivity of this CADe system on small SSAs/Ps was 80%, which is <94%, the per-image sensitivity of the conventional adenomas and non-neoplastic polyps. 34 Future improvement in CADe should be directed to sensitively and specifically detect hard-to-detect SSAs/Ps collected among more extensive sources. Further studies should also look at AMR for advanced adenoma and SSAs/Ps, with a larger sample size aimed at detecting a statistically significant difference.…”

Section: Discussionmentioning

confidence: 99%

Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

See Covering the Cover synopsis on page 1193. BACKGROUND AND AIMS: Up to 30% of adenomas might be missed during screening colonoscopy-these could be polyps that appear on-screen but are not recognized by endoscopists or polyps that are in locations that do not appear on the screen at all. Computer-aided detection (CADe) systems, based on deep learning, might reduce rates of missed adenomas by displaying visual alerts that identify precancerous polyps on the endoscopy monitor in real time. We compared adenoma miss rates of CADe colonoscopy vs routine white-light colonoscopy. METHODS: We performed a prospective study of patients, 18-75 years old, referred for diagnostic, screening, or surveillance colonoscopies at a single endoscopy center of Sichuan Provincial People's Hospital from June 3, 2019 through September 24, 2019. Same day, tandem colonoscopies were performed for each participant by the same endoscopist. Patients were randomly assigned to groups that received either CADe colonoscopy (n¼184) or routine colonoscopy (n¼185) first, followed immediately by the other procedure. Endoscopists were blinded to the group each patient was assigned to until immediately before the start of each colonoscopy. Polyps that were missed by the CADe system but detected by endoscopists were classified as missed polyps. False polyps were those continuously traced by the CADe system but then determined not to be polyps by the endoscopists. The primary endpoint was adenoma miss rate, which was defined as the number of adenomas detected in the second-pass colonoscopy divided by the total number of adenomas detected in both passes. RESULTS: The adenoma miss rate was significantly lower with CADe colonoscopy (13.89%; 95% CI, 8.24%-19.54%) than with routine colonoscopy (40.00%; 95% CI, 31.23%-48.77%, P<.0001). The polyp miss rate was significantly lower with CADe colonoscopy (12.98%; 95% CI, 9.08%-16.88%) than with routine colonoscopy (45.90%; 95% CI, 39.65%-52.15%) (P<.0001). Adenoma miss rates in ascending, transverse, and descending colon were significantly lower with CADe colonoscopy than with routine colonoscopy (ascending colon 6.67% vs 39.13%; P¼.0095; transverse colon 16.33% vs 45.16%; P¼.0065; and descending colon 12.50% vs 40.91%, P¼.0364). CONCLUSIONS: CADe colonoscopy reduced the overall miss rate of adenomas by endoscopists using white-light endoscopy. Routine use of CADe might reduce the incidence of interval colon cancers. chictr.org.cn study no: ChiCTR1900023086

show abstract

Section: Discussionmentioning

confidence: 99%

Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…These findings provide new understanding for the preoperative diagnosis and evaluation of LSTs. New breakthroughs in endoscopic technology, such as artificial intelligence (AI), may also support diagnosis; Zhou 20 et al report using AI technology to help diagnose LST.…”

Section: Discussionmentioning

confidence: 99%

Pathological Analysis and Endoscopic Characteristics of Colorectal Laterally Spreading Tumors

Li¹,

Liu²,

Huang³

et al. 2021

CMAR

View full text Add to dashboard Cite

Objective This study aims to analyze the endoscopic and pathological characteristics of colorectal laterally spreading tumors (LSTs) to assist malignant risk stratification to inform selection of the appropriate treatment strategy. Methods Patients with colorectal LST were selected as retrospective study objects. Characteristics, including endoscopic findings and the most common site of LSTs of different diameters and histological types, were analyzed. The risk factors for malignancy in colorectal LST were explored by multivariate logistic regression analysis. Results LSTs with diameters of ≥20 mm were found mainly in the rectum and mainly with granular-mixed (G-M) morphology (36% and 44.6%, respectively; p < 0.05), while LSTs with diameters of <20 mm were found mainly in the ascending colon and mainly with granular-homogenous (G-H) morphology (40.9% and 46.2%, respectively; p < 0.05). Adenoma was the main histological type in patients with tumors of all diameters. However, the cancerization rate of LSTs was 31% in patients with tumor diameter ≥20 mm, while there was no invasive cancer in patients with tumor diameter < 20 mm. In the low-grade dysphasia (adenoma) group, most of the lesions were located in the ascending colon and most had the morphology LST-G-H (35.8% and 39.2%, respectively; p < 0.05). In the cancerization group, most of the lesions were located in the rectum, with the morphology LST-G-M (51.6% and 67.2%, respectively; p < 0.05), and the diameter was larger than that of the adenoma group (33.84 ± 17.99 mm vs 21.68 ± 8.99 mm). Conclusion The rectum was the most common site for an LST with a diameter ≥20 mm and cancerization, of which the morphology was mainly LST-G-M (endoscopic submucosal dissection is the preferred treatment for this type of LST). LST malignancy was found to be correlated with lesion diameter, location, and morphological appearance.

show abstract

“…1) 24 This said, can AI reduce the miss rate of flat advanced neoplasia? This will depend on two main factors, namely the intrinsic accuracy of AI in flat lesion detection and the AI‐human interaction in real‐time endoscopy 12,24 …”

Section: Miss Rate Of Flat Neoplasiamentioning

confidence: 99%

“…22,23 For sure, it is much simpler to recognize a welldemarcated small lesion in a single frame than the subtle contrast between a large flat and surrounding mucosa when only a fraction of the margin may be appreciated in a single frame ( Fig. 1) 24 This said, can AI reduce the miss rate of flat advanced neoplasia? This will depend on two main factors, namely the intrinsic accuracy of AI in flat lesion detection and the AI-human interaction in real-time endoscopy.…”

Section: Introductionmentioning

confidence: 99%

“…This will depend on two main factors, namely the intrinsic accuracy of AI in flat lesion detection and the AI-human interaction in real-time endoscopy. 12,24 AI AND FLAT LESIONS R EAL -time applications of AI for colorectal neoplasia detection (CADe) depend on deep learning algorithms. 25 According to such algorithms, the matrix that will be applied to real-time endoscopy is automatically extracted after a supervised training with putative lesions.…”

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

Computer aided detection for laterally spreading tumors and sessile serrated adenomas during colonoscopy

Cited by 22 publications

References 35 publications

Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

Pathological Analysis and Endoscopic Characteristics of Colorectal Laterally Spreading Tumors

Artificial intelligence for non‐polypoid colorectal neoplasms

Contact Info

Product

Resources

About