Endoscopic versus histological characterisation of polyps during screening colonoscopy

Schachschal, Guido; Mayr, Michael; Treszl, András; Balzer, K.; Wegscheider, Karl; Aschenbeck, Jens; Aminalai, A; Drossel, R; Schröder, Andreas; Scheel, Mathias; Bothe, Carl-Hermann; Bruhn, Jens-Peter; Burmeister, Wolfgang; Stange, G; Bähr, Christina; Kießlich, Ralf; Rösch, Thomas

doi:10.1136/gutjnl-2013-304562

Cited by 66 publications

(60 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3 Various studies have shown that using modern endoscopic technology, such as narrow-band imaging, endoscopists can predict neoplastic polyps with high accuracy and apply the resect and discard strategy for diminutive polyps. [13][14][15] However, a recent study evaluating the ability of community endoscopists to diagnose in vivo polyp type showed an accuracy of only 76.6%, 16 lower than ASGE-PIVI standards.…”

Section: Discussionmentioning

confidence: 96%

Diminutive polyps among black and Latino populations undergoing screening colonoscopy: evidence supporting a resect and discard approach

Lee

Jandorf

Itzkowitz

2015

Gastrointestinal Endoscopy

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 96%

Diminutive polyps among black and Latino populations undergoing screening colonoscopy: evidence supporting a resect and discard approach

Lee

Jandorf

Itzkowitz

2015

Gastrointestinal Endoscopy

View full text Add to dashboard Cite

“…All colonic hyperplastic polyps were selected from a previously published study [18] on the endoscopic differential diagnosis of colonic polyps, which had been originally interpreted as hyperplastic polyps by private practice pathologists. Out of these, hyperplastic polyps that were distally located (below the splenic flexure) and were ≤5 mm in size were excluded: This was done because such small whitish polyps can usually be recognized at endoscopy as hyperplastic and are almost always histologically confirmed as such if resected or removed under biopsy.…”

Section: Case Selection and Reassessmentmentioning

confidence: 99%

Impact of reassessment of colonic hyperplastic polyps by expert GI pathologists

Schachschal

Sehner

Choschzick

et al. 2016

Int J Colorectal Dis

Self Cite

View full text Add to dashboard Cite

BACKGROUND: Recommended follow-up intervals after endoscopic removal of hyperplastic polyps (HP) and sessile serrated adenomas (SSA) differ because of assumed differences in biological behaviour. However, histopathologic differentiation is difficult, with higher SSA rates reported from specialist GI histopathologists. OBJECTIVE: The objective of this study was to clarify the relevance of histologic reassessment of HP. DESIGN AND SETTING: From a prospective screening colonoscopy study relevant serrated lesions (excluding distal small HP 5 mm) diagnosed by private practice pathologists were reassessed by four specialized GI pathologists PATIENTS: One thousand sixty-nine screening colonoscopies were performed in patients. MAIN OUTCOME MEASUREMENTS: In terms of main outcome measurements, there is a likelihood of changes of the HP diagnosis on reassessment, as well as interrater variability. RESULTS: SSA were initially diagnosed in 7 cases (0.7 %) and relevant HP in 83 (7.8 %; 101 lesions). Of the latter, the chance of a change in diagnosis from HP to SSA by any of the four specialist histopathologists was higher for larger (>5 mm) and right-sided lesions (19.1 vs 1.3 %, OR 18.4, p = 0.04) including a higher likelihood to change recommended follow-up intervals (32.1 vs 3.3 %, p < 0.01). However, follow-up intervals were determined by concomitant adenomas in 41 %. Interrater variability was also higher for these lesions (p = 0.04), with an overall kappa value of 0.48. However, this issue related to only 1.2 % of the 1069 study cases. LIMITATION: The limitations this study are the limited case number as well as limited retrospective assessment. CONCLUSIONS: Right-sided HP >5 mm had a higher chance of change in diagnosis to SSA; therefore, they should probably be treated like adenomas and be removed. However, reliable data for recommendations on follow-up intervals of HP or SSA will require follow-up studies. Abstract Background Recommended follow-up intervals after endoscopic removal of hyperplastic polyps (HP) and sessile serrated adenomas (SSA) differ because of assumed differences in biological behaviour. However, histopathologic differentiation is difficult, with higher SSA rates reported from specialist GI histopathologists.Objective The objective of this study was to clarify the relevance of histologic reassessment of HP.Design and setting From a prospective screening colonoscopy study relevant serrated lesions (excluding distal small HP ≤5 mm) diagnosed by private practice pathologists were reassessed by four specialized GI pathologists Patients One thousand sixty-nine screening colonoscopies were performed in patients.Main outcome measurements In terms of main outcome measurements, there is a likelihood of changes of the HP diagnosis on reassessment, as well as interrater variability.Results SSA were initially diagnosed in 7 cases (0.7 %) and relevant HP in 83 (7.8 %; 101 lesions). Of the latter, the chance of a change in diagnosis from HP to SSA by any of the four specialist histopathologists was hig...

show abstract

“…Moreover, under conventional white light observation with 0.1% indigo carmine application, the sensitivity, specificity, and correct diagnosis rates in the diagnosis of cT1b cancer requiring surgical resection are 66.0, 95.8, and 86.3%, respectively [15]. However, there is pressure on endoscopy physicians in general clinical hospitals to perform accurate depth of invasion diagnoses when performing endoscopic diagnoses as part of screening colon endoscopies in busy clinical settings [16].…”

Section: Introductionmentioning

confidence: 99%

Endoscopic Diagnostic Support System for cT1b Colorectal Cancer Using Deep Learning

Ito

Kawahira

Nakashima³

et al. 2018

Oncology

View full text Add to dashboard Cite

Objective: This study aimed to use convolutional neural network (CNN), a deep learning software, to assist in cT1b diagnosis. Methods: This retrospective study used 190 colon lesion images from 41 cases of colon endoscopies performed between February 2015 and October 2016. Unenhanced colon endoscopy images (520 × 520 pixels) with white light were used. Images included 14 cTis cases with endoscopic resection and 14 cT1a and 13 cT1b cases with surgical resection. Protruding, flat, and recessed lesions were analyzed. AlexNet and Caffe were used for machine learning. Fine tuning of data to increase image numbers was performed. Oversampling for the training images was conducted to avoid impartiality in image numbers, and learning was carried out. The 3-fold cross-validation method was used. Sensitivity, specificity, accuracy, and area under the curve (AUC) values in the receiver operating characteristic curve were calculated for each group. Results: The results were the average of obtained values. With CNN learning, cT1b sensitivity, specificity, and accuracy were 67.5, 89.0, and 81.2%, respectively, and AUC was 0.871. Conclusion: Quantitative diagnosis is possible using an endoscopic diagnostic support system with machine learning, without relying on the skill and experience of endoscopists. Moreover, this system could be used to objectively evaluate endoscopic diagnoses.

show abstract

Endoscopic versus histological characterisation of polyps during screening colonoscopy

Abstract: NCT01297712.

Cited by 66 publications

References 35 publications

Diminutive polyps among black and Latino populations undergoing screening colonoscopy: evidence supporting a resect and discard approach

Diminutive polyps among black and Latino populations undergoing screening colonoscopy: evidence supporting a resect and discard approach

Impact of reassessment of colonic hyperplastic polyps by expert GI pathologists

Endoscopic Diagnostic Support System for cT1b Colorectal Cancer Using Deep Learning

Contact Info

Product

Resources

About