Accuracy of Colorectal Surveillance Interval Assignment Based on In-vivo Predictions of Pathology in Patients with Colorectal Polyps

2011 ◽  
Vol 106 ◽  
pp. S579-S580
Author(s):  
Susan Coe ◽  
Julia Crook ◽  
Michael Wallace
Keyword(s):  
Colorectal Polyps ◽  
Surveillance Interval

scholarly journals Post-polypectomy surveillance interval based on flexible spectral color imaging enhancement (FICE) with magnifying zoom imaging for optical biopsy

2018 ◽  
Vol 06 (08) ◽  
pp. E1051-E1058
Author(s):  
Rodrigo de Rezende Zago ◽  
Pedro Popoutchi ◽  
Lucas Santana Nova da Costa ◽  
Marcelo Averbach
Keyword(s):  
Task Force ◽  
Colorectal Polyps ◽  
Optical Biopsy ◽  
Intraobserver Agreement ◽  
High Confidence ◽  
Color Imaging ◽  
Neoplastic Lesions ◽  
Surveillance Interval ◽  
Pathological Assessment

Abstract Background and study aims Post-polypectomy surveillance interval (SI) is determined based on the number, size, and histology of colorectal polyps. Electronic chromoendoscopy in association with magnifying imaging colonoscopy allows “in vivo” polyp histology prediction. Colorectal polyps ≤ 5 mm can be resected and discarded without pathologic assessment if the endoscopic technology when used with high confidence provides ≥ 90 % agreement between the post-polypectomy SI and the SI based on pathological assessment. The aim of this study was to evaluate the agreement between the post-polypectomy SI based on flexible spectral color imaging enhancement (FICE) chromoendoscopy in association with magnified imaging and the pathology-based SI. Patients and methods Each diagnosed colorectal polyp received a histology prediction (neoplastic or non-neoplastic) based on the FICE capillary-vessel pattern classification. Each prediction was classified as high or low confidence. SI based on the FICE prediction was compared to the pathology-based SI recommendation according to the US Multi-Society Task Force on Colorectal Cancer guideline. Sensitivity, specificity and accuracy of FICE in diagnosing neoplastic lesions were compared with the pathology assessment. Interobserver and intraobserver agreement for FICE-based SI predictions was evaluated using the kappa coefficient. Results A total of 267 polyps had histology prediction assessed with high confidence in 136 patients. Sensitivity of FICE was 98.7 % (95 % CI: 93.5 – 99.3) and specificity was 62.5 % (95 % CI: 43.6 – 78.9). Prediction accuracy was 94.4 % (95 % CI: 88.6 – 96 – 1) in differentiating between neoplastic and non-neoplastic lesions. Therefore, magnifying FICE colonoscopy-based SI recommendation was consistent with pathological assessment in 88.3 % of general cases (95 % CI: 82.1 – 92.6) and in 89.7 % (95 % CI: 83 – 94.5) of the high-confidence evaluation cases. The intraobserver agreement value for FICE-based SI predictions was 0.87 (high-confidence evaluations), and the interobserver agreement values were 0.78 (high- and low-confidence evaluations) and 0.82 (high-confidence evaluations) (95 % CI: 0.79 – 0.95). Conclusions FICE-based SI demonstrated 89.7 % concordance with the pathology-based SI.

scholarly journals A118 POLYP SIZE CUT-OFF LEVEL TO IMPLEMENT OPTICAL POLYP DIAGNOSIS

2021 ◽  
Vol 4 (Supplement_1) ◽  
pp. 98-99
Author(s):  
M Taghiakbari ◽  
R Djinbachian ◽  
D von Renteln
Keyword(s):  
Colorectal Polyps ◽  
Optical Diagnosis ◽  
Clinical Implementation ◽  
Polyp Size ◽  
Funding Agencies ◽  
Size Groups ◽  
Surveillance Interval ◽  
High Reduction ◽  
Advanced Adenomas ◽  
Post Hoc

Abstract Background Optical polyp diagnosis can be used for real-time pathology prediction of colorectal polyps ≤10 mm. However, the risk of misdiagnosing a polyp with advanced pathology potentially increases with increasing polyp size. Aims This study aimed to evaluate different size cut-offs for using optical polyp diagnosis and the associated risk of patients undergoing inadequate follow-up or surveillance. Methods In a post-hoc analysis of two prospective studies, the performance of optical diagnosis was evaluated in three polyp size groups: 1–3 mm, 1–5 mm, and 1–10 mm. The primary outcome was the proportion of patients with advanced adenomas and delayed or inappropriate surveillance. Secondary outcomes included percentage of polyps with advanced pathology, agreement between surveillance intervals based on high-confidence optical diagnosis and pathology outcomes, reduction in histopathological examinations, and proportion of patients who could receive an immediate surveillance interval recommendation. Results We included 1525 patients with complete colonoscopies (mean age 62.9 years, 50.2% male). The percentage of patients with advanced adenomas and delayed or inappropriate surveillance was 0.7%, 1.7%, and 1.8% when using optical diagnosis for patients with polyps of 1–3, 1–5, and 1–10 mm, respectively. The percentage of polyps with advanced pathology was 0.5%, 1.4%, and 1.9%, respectively. Surveillance interval agreement between pathology and optical diagnosis was 99%, 98%, and 97.8%, respectively. Total reduction in pathology examinations was 33.9%, 53.5%, and 69.0%, respectively. Conclusions A 3-mm cut-off for clinical implementation of optical polyp diagnosis yielded high surveillance interval agreement with pathology and a high reduction in pathology examinations while minimizing the risk of inappropriate management for polyps with advanced pathology. Funding Agencies None

i-Scan Optical Enhancement Technology Significantly Improves In vivo Optical Diagnostic Yield of Small (< 5 mm) Colorectal Polyps

2017 ◽  
Vol 112 ◽  
pp. S53
Author(s):  
Kirtipal Bhatia ◽  
Bijun S. Kannadath ◽  
Paaras Kohli ◽  
Julie Guider ◽  
Nancy Behazin ◽  
...  
Keyword(s):  
Diagnostic Yield ◽  
Colorectal Polyps ◽  
Optical Diagnostic ◽  
Enhancement Technology

scholarly journals Quantitative analysis of in vivo high-resolution microendoscopic images for the detection of neoplastic colorectal polyps

2018 ◽  
Vol 23 (11) ◽  
pp. 1 ◽  
Author(s):  
Yubo Tang ◽  
Alexandros D. Polydorides ◽  
Sharmila Anandasabapathy ◽  
Rebecca R. Richards-Kortum
Keyword(s):  
Quantitative Analysis ◽  
High Resolution ◽  
Colorectal Polyps

scholarly journals Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks

2020 ◽  
Vol 13 ◽  
pp. 175628482091065 ◽  
Author(s):  
Tsuyoshi Ozawa ◽  
Soichiro Ishihara ◽  
Mitsuhiro Fujishiro ◽  
Youichi Kumagai ◽  
Satoki Shichijo ◽  
...  
Keyword(s):  
White Light ◽  
Colorectal Polyps ◽  
Future Application ◽  
Single Shot ◽  
Still Images ◽  
Promising Application ◽  
American Society ◽  
Measure Of Performance

Background: Recently the American Society for Gastrointestinal Endoscopy addressed the ‘resect and discard’ strategy, determining that accurate in vivo differentiation of colorectal polyps (CP) is necessary. Previous studies have suggested a promising application of artificial intelligence (AI), using deep learning in object recognition. Therefore, we aimed to construct an AI system that can accurately detect and classify CP using stored still images during colonoscopy. Methods: We used a deep convolutional neural network (CNN) architecture called Single Shot MultiBox Detector. We trained the CNN using 16,418 images from 4752 CPs and 4013 images of normal colorectums, and subsequently validated the performance of the trained CNN in 7077 colonoscopy images, including 1172 CP images from 309 various types of CP. Diagnostic speed and yields for the detection and classification of CP were evaluated as a measure of performance of the trained CNN. Results: The processing time of the CNN was 20 ms per frame. The trained CNN detected 1246 CP with a sensitivity of 92% and a positive predictive value (PPV) of 86%. The sensitivity and PPV were 90% and 83%, respectively, for the white light images, and 97% and 98% for the narrow band images. Among the correctly detected polyps, 83% of the CP were accurately classified through images. Furthermore, 97% of adenomas were precisely identified under the white light imaging. Conclusions: Our CNN showed promise in being able to detect and classify CP through endoscopic images, highlighting its high potential for future application as an AI-based CP diagnosis support system for colonoscopy.

scholarly journals Clinical validation of the SIMPLE classification for optical diagnosis of colorectal polyps

2021 ◽  
Vol 09 (05) ◽  
pp. E684-E692
Author(s):  
Ahmed Amine Alaoui ◽  
Kussil Oumedjbeur ◽  
Roupen Djinbachian ◽  
Étienne Marchand ◽  
Paola N. Marques ◽  
...  
Keyword(s):  
Primary Outcome ◽  
Colorectal Polyps ◽  
Clinical Validation ◽  
Optical Diagnosis ◽  
Clinical Cohort ◽  
Simple Classification ◽  
Surveillance Interval ◽  
Colonoscopy Surveillance ◽  
Secondary Outcomes ◽  
Diagnosis Classification

Abstract Background and study aims A novel endoscopic optical diagnosis classification system (SIMPLE) has recently been developed. This study aimed to evaluate the SIMPLE classification in a clinical cohort. Patients and methods All diminutive and small colorectal polyps found in a cohort of individuals undergoing screening, diagnostic, or surveillance colonoscopies underwent optical diagnosis using image-enhanced endoscopy (IEE) and the SIMPLE classification. The primary outcome was the agreement of surveillance intervals determined by optical diagnosis compared with pathology-based results for diminutive polyps. Secondary outcomes included the negative predictive value (NPV) for rectosigmoid adenomas, the percentage of pathology exams avoided, and the percentage of immediate surveillance interval recommendations. Analysis of optical diagnosis for polyps ≤ 10 mm was also performed. Results 399 patients (median age 62.6 years; 55.6 % female) were enrolled. For patients with at least one polyp ≤ 5 mm undergoing optical diagnosis, agreement with pathology-based surveillance intervals was 93.5 % (95 % confidence interval [CI] 91.4–95.6). The NPV for rectosigmoid adenomas was 86.7 % (95 %CI 77.5–93.2). When using optical diagnosis, pathology analysis could be avoided in 61.5 % (95 %CI 56.9–66.2) of diminutive polyps, and post-colonoscopy surveillance intervals could be given immediately to 70.9 % (95 %CI 66.5–75.4) of patients. For patients with at least one ≤ 10 mm polyp, agreement with pathology-based surveillance intervals was 92.7 % (95 %CI 89.7–95.1). NPV for rectosigmoid adenomas ≤ 10 mm was 85.1 % (95 %CI CI 76.3–91.6). Conclusions IEE with the SIMPLE classification achieved the quality benchmark for the resect and discard strategy; however, the NPV for rectosigmoid polyps requires improvement.

scholarly journals A119 THE LOCATION-BASED RESECT AND DISCARD STRATEGY FOR DIMINUTIVE COLORECTAL POLYPS: A PROSPECTIVE CLINICAL STUDY

2021 ◽  
Vol 4 (Supplement_1) ◽  
pp. 99-101
Author(s):  
M Taghiakbari ◽  
H Pohl ◽  
R Djinbachian ◽  
A N Barkun ◽  
P Marques ◽  
...  
Keyword(s):  
Task Force ◽  
A Priori ◽  
Cost Effective ◽  
Colorectal Polyps ◽  
Prospective Clinical Study ◽  
Colon Polyps ◽  
Optical Diagnosis ◽  
Cost Effective Approach ◽  
Surveillance Interval ◽  
Task Force Guideline

Abstract Background Replacing histopathology evaluation of diminutive polyps with optical polyp diagnosis is considered a cost-effective approach. However, the widespread use of optical diagnosis is limited due to concerns about making incorrect optical diagnoses and the requirements of training, credentialing and auditing of performance. Aims This prospective study aimed to evaluate a simplified resect and discard strategy that is not operator dependent. Methods The study evaluated a resect and discard strategy that uses anatomical polyp location to classify colon polyps into non-neoplastic or low-risk neoplastic. All rectosigmoid diminutive polyps were considered hyperplastic and all polyps located proximally to the sigmoid colon were considered neoplastic. Surveillance interval assignments based on these a priori assumptions were compared with those based on actual pathology results and optical diagnosis, respectively. The primary outcome was ≥90% agreement with pathology in surveillance interval assignment. Results Overall, 1117 patients undergoing complete colonoscopy were included and 482 (43.1%) had at least one diminutive polyp. Surveillance interval agreement between the location-based resect and discard strategy and pathological findings using the 2020 US Multi-Society Task Force guideline was 97.0% (95% CI = 0.96 - 0.98), surpassing the ≥90% benchmark. Optical diagnoses using NICE and Sano classifications reached 89.1% and 90.01% agreement, respectively (p &lt;0.0001), and were inferior to the location-based strategy. The location-based resect and discard strategy allowed a 69.7% (95% CI = 0.67 - 0.72) reduction in pathology examinations compared with 55.3% (95% CI = 0.52 - 0.58) (NICE and Sano) and 41.9% (95% CI = 0.39 - 0.45) (WASP) with optical diagnosis. Conclusions The location-based resect and discard strategy achieved very high surveillance interval agreement with pathology-based surveillance interval assignment, surpassing the ≥90% quality benchmark and outperforming optical diagnosis in surveillance interval agreement and the number of pathology examinations avoided. Funding Agencies None

Sign in / Sign up

Export Citation Format

Share Document