Interobserver Agreement Among Pathologists in the Differentiation of Sessile Serrated From Hyperplastic Polyps

Vennelaganti, Sreekar; Cuatrecasas, Míriam; Vennalaganti, Prashanth; Kennedy, Kevin F.; Srinivasan, Sachin; Patil, Deepa T.; Plesec, Thomas; Lanas, Fernando; Hörndler, Carlos; Andraws, Nevene; Cherian, Rachel; Mathur, Sharad C.; Hassan, Cesare; Repici, Alessandro; Klotz, Dagmar; Musulén, Eva; Risio, Mauro; Castells, Antoni; Gupta, Neil; Sharma, Prateek

doi:10.1053/j.gastro.2020.09.015

Cited by 34 publications

(33 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, accurate characterization is challenging and varies markedly even among expert GI pathologists. [9][10][11][12][13][14][15][16]32 We demonstrated that an AI-augmented digital system improved the accuracy of pathologic classification of polyps. Use of this tool might lead to an increased frequency of patients receiving appropriate follow-up surveillance recommendations to prevent subsequent cancer development and reduce colonoscopy overuse.…”

Section: Discussionmentioning

confidence: 84%

“… 4 Variability in pathologists’ histopathologic classification of colorectal polyps can result in considerable inconsistencies in the surveillance recommendations given to patients. 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 Moreover, a shortage of pathologists, which is anticipated to continue through 2030, is likely to cause delays and possibly errors in histopathologic characterization of colorectal polyps, a process that is already labor intensive. 2 , 17 Thus, an image-analysis system that can quickly and reliably classify different types of colorectal polyps on whole-slide images has the potential to address errors in patient surveillance for colorectal cancer through improved efficiency and accuracy in histopathologic characterization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of an Artificial Intelligence–Augmented Digital System for Histologic Classification of Colorectal Polyps

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 84%

Section: Introductionmentioning

confidence: 99%

Evaluation of an Artificial Intelligence–Augmented Digital System for Histologic Classification of Colorectal Polyps

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In a recent report, the overall interobserver agreement for serrated lesions was moderate (κ = 0.44) based on histological assessment. [24] Recent minor changes in the histological criteria for SSL, where some MVHPs are reclassi ed into SSLs, would indicate that the SSL is not a distinct disease entity. Recent evidence has established that MVHP is a precursor to SSL, suggesting that both lesions are along the same disease spectrum.…”

Section: Discussionmentioning

confidence: 99%

Computer-aided diagnosis of serrated colorectal lesions using non-magnified white-light endoscopic images

Nemoto

Guo

Peng

et al. 2022

Int J Colorectal Dis

View full text Add to dashboard Cite

Purpose: Computer-aided diagnosis systems for polyp characterization are commercially available but cannot recognize subtypes of sessile lesions. This study aimed to develop a computer-aided diagnosis system to characterize polyps using non-magni ed white-light endoscopic images.Methods: A total of 2249 non-magni ed white-light images from 1030 lesions including 534 tubular adenomas, 225 sessile serrated adenoma/polyps and 271 hyperplastic polyps in the proximal colon were consecutively extracted from an image library and divided into training and testing datasets (4:1), based on the date of colonoscopy. Using ResNet-50 networks, we developed a classi er (1) to differentiate adenomas from serrated lesions, and another classi er (2) to differentiate sessile serrated adenoma/polyps from hyperplastic polyps. Diagnostic performance was assessed using the testing dataset. The computer-aided diagnosis system generated a probability score for each image, and a probability score for each lesion was calculated as the weighted mean with a log 10 -transformation. Two experts (E1, E2) read the identical testing dataset with a probability score.Results: The area under the curve of classi er (1) for adenomas was equivalent to E1 and superior to E2 (classi er 86%, E1 86%, E2 69%; classi er vs. E2, p<0.001). In contrast, the area under the curve of classi er (2) for sessile serrated adenoma/polyps was inferior to both experts (classi er 55%, E1 68%, E2 79%; classi er vs. E2, p<0.001). Conclusion:The classi er (1) developed using white-light images alone compares favorably with experts in differentiating adenomas from serrated lesions. However, the classi er (2) to identify sessile serrated adenoma/polyps is inferior to experts.

show abstract

“…However, this could create a barrier for the uptake of the PBRD strategy, as assigning longer surveillance intervals to some high risk lesions might be inherent to the strategy. This unavoidable risk by design can also be found in pathology-based surveillance intervals in situations such as unretrieved polyps, polyps crushed with forceps which are then impossible to diagnose, and interobserver disagreement between pathologists for diagnosing SSAs and advanced histology [23][24][25]. However, this problem is common for all optical diagnosis-based resect and discard strategies, as most optical diagnosis classifications such as SIMPLE, WASP, and NICE do not present criteria to distinguish between traditional serrated adenomas and SSA/Ps or between low and high grade dysplasia [26][27][28].…”

Section: Original Articlementioning

confidence: 99%

Evaluation of the polyp-based resect and discard strategy: a retrospective study

et al. 2021

View full text Add to dashboard Cite

Background: Standard colonoscopy practice requires removal and histological characterization of almost all small (<10 mm) and diminutive (≤5 mm) colorectal polyps found. The aim of this study was to test a simplified polyp-based resect and discard (PBRD) strategy that assigns surveillance intervals based only on size and number of small and diminutive polyps, without the need for pathology. Methods: A post hoc analysis was performed on patients enrolled in a prospective colonoscopy study. The primary outcome was surveillance interval agreement of the PBRD strategy compared with pathology-based management according to the 2020 USMSTF guidelines. A chart analysis also evaluated clinician adherence to the pathology-based recommendations for included patients. One-sided testing was performed with a null-hypothesis of 90% agreement with pathology-based surveillance intervals and a two-sided 96.7% CI using correction for multiple testing. Results: 452 patients were included in the study. Surveillance intervals assigned using the PBRD strategy were correct in 97.8% (96.7% CI [96.3% ; 99.3%]) of patients when comparing to pathology-based management. The PBRD strategy reduced pathological examinations by 58.7% while providing 87.8% of patients immediate surveillance interval recommendation on the day of the colonoscopy compared with 47.1% when using pathology-based management. Chart analysis of surveillance interval assignments showed 63.3% adherence to the pathology-based guideline. Conclusion: The PBRD strategy surpassed the 90% agreement with the pathology-based standard for determining subsequent colonoscopy surveillance interval. Furthermore, it reduced the need for pathological examinations and increased the proportion of patients receiving correct surveillance interval recommendations issued on the day of the colonoscopy. The PBRD strategy does not require any expertise in optical diagnosis and may replace any histological characterization of small and diminutive colorectal polyps.

show abstract

Interobserver Agreement Among Pathologists in the Differentiation of Sessile Serrated From Hyperplastic Polyps

Cited by 34 publications

References 7 publications

Evaluation of an Artificial Intelligence–Augmented Digital System for Histologic Classification of Colorectal Polyps

Evaluation of an Artificial Intelligence–Augmented Digital System for Histologic Classification of Colorectal Polyps

Computer-aided diagnosis of serrated colorectal lesions using non-magnified white-light endoscopic images

Evaluation of the polyp-based resect and discard strategy: a retrospective study

Contact Info

Product

Resources

About