An International Study on the Diagnostic Accuracy of the Japan Narrow-Band Imaging Expert Team Classification for Colorectal Polyps Observed with Blue Laser Imaging.

BACKGROUND: The Japan narrow-band imaging Expert Team (JNET) classification of colorectal polyps based on magnifying endoscopy is used in Japan, but not worldwide. The objective of this study was to clarify differences of diagnostic accuracy between JNET users in Japan and non-JNET users in other countries. METHODS: A total of 185 colorectal tumors were assessed. Six endoscopists (3 each from Japan and Taiwan) participated in the study. The Japanese endoscopists normally used the JNET classification and the Taiwanese endoscopists normally used the narrow-band imaging International Colorectal Endoscopic classification for diagnosis of colorectal tumors. After receiving a lecture on the JNET classification, they all observed one blue laser imaging magnified image per lesion and performed diagnosis based on the JNET classification. RESULTS: Diagnostic ability was equivalent for Type 1, Type 2A, and Type 2B. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value of Type 3 for deep submucosal invasive carcinoma was, respectively, 44.4, 98.3, 57.1, and 97.2% in Group J and 70.0, 94.7, 40.4, and 98.4% in Group T. The PPV for diagnosis of Type 3 with a high confidence was significantly higher in Group J than in Group T (81.8% [55.4-94.6] vs. 44.4% [33.6-50.9], p < 0.05). CONCLUSIONS: The PPV for Type 3 differed between the 2 groups, suggesting the need to become familiar with differentiation between Type 2B and Type 3.

Accuracies of Endoscopic Diagnosis of Helicobacter pylori-Gastritis: Multicenter Prospective Study Using White Light Imaging and Linked Color Imaging.

INTRODUCTION: The diagnosis of Helicobacter pylori infection status with white light imaging (WLI) is difficult. We evaluated the accuracies of using WLI and linked color imaging (LCI) for diagnosing H. pylori-active gastritis in a multicenter prospective study setting. METHODS: Patients who underwent esophagogastroduodenoscopy were prospectively included. The image collection process was randomized and anonymous, and the image set included 4 images with WLI or 4 images with LCI in the corpus that 5 reviewers separately evaluated. Active gastritis was defined as positive when there was diffuse redness in WLI and crimson coloring in LCI. The H. pylori infection status was determined by the urea breath test and the serum antibody test. Cases in which both test results were negative but atrophy or intestinal metaplasia was histologically confirmed were defined as past infections. The primary endpoint was the diagnostic accuracies of WLI and LCI, and the secondary endpoint was inter-observer agreement. RESULTS: Data for 127 patients were analyzed. The endoscopic diagnostic accuracy for active gastritis was 79.5 (sensitivity of 84.4 and specificity of 74.6) with WLI and 86.6 (sensitivity of 84.4 and specificity of 88.9) with LCI (p = 0.029). LCI significantly improved the accuracy in patients with past infections over WLI (36.8 in WLI and 78.9 in LCI, p < 0.01). The κ values were 0.59 in WLI and 0.70 in LCI. CONCLUSIONS: LCI is useful for endoscopic diagnosis of H. pylori-active or inactive gastritis, and it is advantageous for patients with past infections of inactive gastritis.

Prospective evaluation of the performances of narrow-band imaging flexible videoscopy relative to white-light imaging flexible videoscopy, in patients scheduled for transurethral resection of a primary NMIBC.

PURPOSE: To evaluate on a lesion-by-lesion basis Narrow-Band Imaging flexible videoscopy (NBI-FV) in the detection of cancer compared to White-Light Imaging flexible videoscopy (WLI-FV). METHODS: WLI-FV and NBI-FV were sequentially performed in patients scheduled for TURBT for primary bladder cancer. Suspicious findings were individually harvested and characterized under WLI-FV (suspicious/non-suspicious) and NBI-FV (5-point Likert scale) and pathology. The primary objective was to determine if NBI-FV informed at least 20% more cancer lesions than WLI-FV (Relative true-positive rate > 1.19). A minimum of 120 specimens was to be analyzed to reach 90% power. RESULTS: Of 147 specimens taken in 68 patients, 101 were found suspicious under WLI-FV and 64 (64/101, 63.4%) confirmed as cancer. Of the 46 lesions undetected by WLI-VF, 16 were found positive for cancer (16/46, 34.8%). For NBI-FV, a significant increase in positive samples was observed with increments in Likert scale (p < 0.0002). Relative true-positive rate was 1.22 (95% CI 1.12-1.39)-NBI-FV detected 22% more cancer lesions compared to WLI-FV. Relative false-positive rate was 1.35 (95% CI 1.19-1.59). CONCLUSION: Researching alterations in mucosa and microvasculature by narrow-band imaging flexible videoscopy augmented by 22% the detection of cancer foci and contributed to the objective of complete resection of all visible lesions. Conversely, it entailed a 35% increase in false-positive results compared to white-light imaging, although the structured analysis of narrow-band imaging findings might be used to grade suspicion according to the Likert scale and balance the risk of a false-positive result to the benefit of demonstrating cancer.

Efficacy of Magnifying Narrow Band Imaging for Delineating Horizontal Margins of Early Gastric Cancer.

BACKGROUND/AIMS: The aim of this study was to evaluate the diagnostic accuracy of magnifying narrow-band imaging (M-NBI) with histopathological confirmation in identifying the demarcation line (DL) of early gastric cancer (EGC). METHODS: EGCs resected by endoscopic submucosal dissection after identifying the DL using M-NBI following histopathological confirmation were included. After determining the DL for the entire EGC lesion using M-NBI, at least 4 biopsies were taken from non-cancerous tissues outside the EGC lesion for histopathological confirmation. RESULTS: A total of 330 EGCs were analyzed in this study. The rate of biopsy-negative and negative horizontal margin were 96.7% (319/330) and 97.9% (323/330) in EGC respectively. Tumors larger than 20 mm showed a higher risk for showing remnant cancer cells on biopsies taken outside the DL. Risk factors for a positive horizontal resection margin were tumor size > 20 mm and moderately or poorly differentiated adenocarcinomas. CONCLUSION: The assessment of demarcation of EGC using M-NBI was excellent in well-differentiated (WD) adenocarcinoma and lesions below 20 mm in size. However, histopathological confirmation is needed to assess the demarcation of non-WD adenocarcinomas and EGC over 20 mm in size.

Novel endoscopic visualization techniques for bladder cancer detection: a review of the contemporary literature.

PURPOSE OF REVIEW: To describe the principles of photodynamic diagnosis (PDD), narrow-band imaging (NBI) and Storz Professional Image Enhancement System (SPIES) techniques for the endoscopic management of nonmuscle-invasive bladder cancer (BCa) and to report their impact on clinical practice. RECENT FINDINGS: PDD is associated with an increased sensitivity for detecting BCa specifically carcinoma in situ (CIS). Moreover, PDD has been shown to lower recurrence rate in comparison with white-light cystoscopy. The impact on progression-free survival is still unclear yet. NBI and, more recently, SPIES are two novel imaging techniques that do not require preoperative instillation of photosensitizing agents. NBI seems to be associated with lower recurrence rates. Nevertheless, further trials are necessary to confirm these results, in particular in high-risk lesions and CIS. Randomized clinical trials addressing the clinical impact of SPIES are ongoing. SUMMARY: Novel endoscopic imaging techniques are useful diagnostic tools for evaluating BCa during cystoscopic diagnostic surveillance as well as during transurethral resection of the bladder. Although the standard of care remains white-light cystoscopy, these techniques provide higher sensitivity in detecting BCa especially CIS. The continued evidence also suggests that this increased detection leads to lower recurrence rates. The impact on progression and the cost-efficacy as well as selection remains to be refined.

Usefulness of close observation with non-magnified blue laser imaging for determining cold polypectomy indications.

PURPOSE: To examine the usefulness of non-magnified close observation with blue laser imaging (BLI) using a colonoscope with close observation capability in determining indications for cold polypectomy. METHODS: We conducted an image evaluation study on 100 consecutive colorectal lesions of 10 mm or less which were observed endoscopically without magnification using BLI mode prior to treatment. Two experts and two non-experts reviewed the images using the Japan NBI expert team (JNET) classification and the diagnostic accuracy was analyzed. RESULTS: The final pathological diagnoses of the 100 lesions were hyperplastic/sessile serrated polyp (HP/SSP), low grade dysplasia (LGD), high grade dysplasia (HGD) and deep submucosal invasive cancer (dSM), respectively, in 12, 79, 9 and 0 lesions. When JNET classification type 1 corresponds to HP/SSP; 2A to LGD; 2B to HGD; and 3 to dSM; the overall diagnostic accuracy was 84.3%. Accuracy was 90.5% for experts and 78.0% for non-experts. High confidence rate was 67.5% for experts and 48.0% for non-experts. In diagnostic accuracy for HGD, the sensitivity, specificity, PPV and NPV were, respectively, 77.8%, 98.9%, 87.5% and 97.8% for experts; and 66.6%, 92.3%, 46.2% and 96.6% for non-experts. CONCLUSIONS: The diagnostic accuracy of unmagnified close observation with BLI using a colonoscope with close observation capability is similar to that reported for magnifying endoscopy and is useful in predicting the histological diagnosis of colorectal polyps of 10 mm or less although the effectiveness may be limited for non-experts. This modality is a potentially useful tool in deciding indications for cold polypectomy.

Linked color imaging improves the visibility of various featured colorectal polyps in an endoscopist's visibility and color difference value.

PURPOSE: Linked color imaging (LCI) by laser endoscopy is a novel narrow band light observation. In this study, we analyzed the efficacy of LCI for improving the various featured colorectal polyp's visibility utilizing a subjective endoscopist's visibility scoring and objective color difference (CD) value. METHODS: We retrospectively reviewed two pictures both with white light (WL) and LCI for 54 consecutive neoplastic polyps 2-20 mm in size. All pictures were evaluated by four endoscopists according to a published polyp visibility score from four (excellent visibility) to one (poor visibility). Additionally, we calculated CD value between each polyp and surrounding mucosa in LCI and WL using an original software. RESULTS: The mean polyp visibility scores of LCI (3.11 ± 1.05) were significantly higher than those of WL (2.50 ± 1.09, P < 0.001). The ratio of an endoscopist's poor visibility (polyp visibility scores 1 and 2) was significantly lower in LCI (27.9%) than WL (55.6%, P < 0.001). With respect to the CD analysis, the CD value of LCI was significantly higher than that of WL (33.3 ± 13.9 vs. 20.7 ± 13.6, P < 0.001). In a subgroup analysis, the polyp visibility scores and CD values of LCI about 24 diminutive polyps (≤5 mm) were higher than those of WL (3.29 ± 0.99 vs. 2.12 ± 0.99, P < 0.001; 31.6 ± 12.8 vs. 14.7 ± 7.6, P < 0.001). Additionally, the polyp visibility scores and CD values of LCI for polyps with any location, size, histology, and morphology were significantly higher than those of WL. CONCLUSIONS: LCI improved the various featured polyp's visibility compared to WL in both polyp visibility scores and CD value.

Usefulness of Non-magnifying Narrow Band Imaging in EVIS EXERA III Video Systems and High-Definition Endoscopes to Diagnose Dysplasia in Barrett's Esophagus Using the Barrett International NBI Group (BING) Classification.

BACKGROUND: Narrow band imaging (NBI) allows identification of abnormal areas of Barrett's esophagus (BE) and could facilitate targeted biopsies. AIMS: We evaluated the diagnostic accuracy for dysplasia prediction using non-magnifying NBI in Evis Exera III processors and high-definition endoscopes using the Barrett International NBI Group (BING) classification, as well as inter/intraobserver agreement for dysplasia prediction and mucosal/vascular patterns. METHODS: Eight observers (4 staff endoscopists and 4 trainee endoscopists) evaluated 100 images selected from an anonymized bank of 470 photographs using the BING classification. Observers were to assign their individual assessment of the mucosal and vascular pattern, and prediction for dysplasia. Accuracy for dysplasia prediction and intra/interobserver agreement was calculated. RESULTS: Dysplasia prediction had an accuracy of 81.1%, sensitivity of 48.4%, and a specificity of 91%. Positive predictive value and negative predictive value (NPV) were 61.4 and 85.5%, respectively. Dysplasia prediction done with a high degree of confidence (vs. low degree of confidence) had better diagnostic accuracy (85.8 vs. 70.7%). Interobserver concordance for dysplasia was weak: Κ = 0.40. Agreement for mucosal and vascular patterns was 0.39 and 0.30, respectively. Intraobserver concordance (assessed 6 months after initial test) for mucosal pattern, vascular pattern, and dysplasia prediction was moderate: Κ = 0.56, Κ = 0.47 and Κ = 0.60, respectively. CONCLUSIONS: Our results showed that NBI had a significant accuracy in BE assessment for dysplasia prediction, high specificity (>90%), and NPV (>85%), with suboptimal sensitivity. NBI could be a useful additional tool for BE inspection and targeted biopsies, but cannot avoid the need for biopsies following the Seattle protocol.

Narrow band imaging: clinical applications in oral and oropharyngeal cancer.

Narrow Band Imaging (NBI) is an endoscopic optical imaging enhancement technology that improves the contrast of mucosal surface texture, and enhances visualisation of mucosal and submucosal vasculature. White light is filtered to emit two 30-nm narrow bands of blue (415 nm) and green light (540 nm) light simultaneously, the former corresponding to the main peak absorption spectrum of haemoglobin, and the latter allowing visualisation of blood vessels in the deeper mucosal and submucosal layers. NBI has been used to better assess oral potentially malignant disorders (OPMD), identify oral and oropharyngeal squamous cell carcinoma (SCC), and to define surgical margins of head and neck malignancies. NBI shows great potential in improving detection rates of OPMD, facilitating better assessment of oral and oropharyngeal SCC, and reducing the risk of recurrence for oral SCC. Although further research is required to better understand and define intrapapillary capillary loop (IPCL) patterns and to relate these with clinical, histopathological and molecular parameters especially for early mucosal changes, there is building evidence to recommend its use as the new gold standard for endoscopic assessment in head and neck oncology.

A computer system to be used with laser-based endoscopy for quantitative diagnosis of early gastric cancer.

GOALS: To evaluate the usefulness of a newly devised computer system for use with laser-based endoscopy in differentiating between early gastric cancer, reddened lesions, and surrounding tissue. BACKGROUND: Narrow-band imaging based on laser light illumination has come into recent use. We devised a support vector machine (SVM)-based analysis system to be used with the newly devised endoscopy system to quantitatively identify gastric cancer on images obtained by magnifying endoscopy with blue-laser imaging (BLI). We evaluated the usefulness of the computer system in combination with the new endoscopy system. STUDY: We evaluated the system as applied to 100 consecutive early gastric cancers in 95 patients examined by BLI magnification at Hiroshima University Hospital. We produced a set of images from the 100 early gastric cancers; 40 flat or slightly depressed, small, reddened lesions; and surrounding tissues, and we attempted to identify gastric cancer, reddened lesions, and surrounding tissue quantitatively. RESULTS: The average SVM output value was 0.846 ± 0.220 for cancerous lesions, 0.381 ± 0.349 for reddened lesions, and 0.219 ± 0.277 for surrounding tissue, with the SVM output value for cancerous lesions being significantly greater than that for reddened lesions or surrounding tissue. The average SVM output value for differentiated-type cancer was 0.840 ± 0.207 and for undifferentiated-type cancer was 0.865 ± 0.259. CONCLUSIONS: Although further development is needed, we conclude that our computer-based analysis system used with BLI will identify gastric cancers quantitatively.

Diagnostic accuracy of Narrow Band Imaging for the detection of oral potentially malignant disorders.

OBJECTIVE: To determine the clinical diagnostic accuracy of Narrow Band Imaging(™) for the detection of oral potentially malignant disorders in a prospective series of patients. MATERIALS AND METHODS: New and existing patients referred to an oral medicine and pathology specialist clinic for assessment of at least one white, red or red-white oral mucosal lesion underwent conventional oral examination, followed by examination with the white light mode and then narrow band imaging mode of a Narrow Band Imaging(™) system. The clinical presentation, microvascular architecture and relevant histopathology of all lesions were recorded. RESULTS: A total of 272 lesions from 95 patients were observed. The sensitivity, specificity, positive predictive value, negative predictive value and accuracy for the detection of oral potentially malignant disorders or worse by Narrow Band Imaging(™) were 100%, 74.63%, 92.38%, 100% and 93.77%, respectively, when compared with conventional oral examination. Narrow Band Imaging(™) aided the detection of 24 lesions undetected by conventional oral examination and 13 lesions undetected by white light endoscopy. CONCLUSION: Narrow Band Imaging(™) demonstrates great utility as a visualisation adjunct for detecting and monitoring oral potentially malignant diseases, particularly lesions not identified by conventional oral examination or white light examination alone.

Diagnostic and therapeutic cholangiopancreatoscopy: performance of a new digital cholangioscope.

BACKGROUND: High-definition cholangioscopes provide excellent images of the pancreatobiliary ductal system and may play a significant role in diagnosis and treatment of various pancreatobiliary disorders. OBJECTIVE: To assess the performance of a new digital cholangioscope for diagnosis and treatment of pancreatobiliary disorders in clinical practice. DESIGN: Prospective study. SETTING: Academic hospital, tertiary-care referral center. PATIENTS: Consecutive patients with suspected pancreatobiliary disorders. INTERVENTION: Diagnostic or therapeutic high-definition digital cholangiopancreatoscopy. MAIN OUTCOME MEASUREMENTS: Satisfactory visualization of the ductal mucosa and lumen and treatment of pancreatobiliary disorders when indicated. RESULTS: A total of 28 cholangioscopy and 4 pancreatoscopy procedures were completed before breakdown of the cholangioscope. Excellent views of the ductal lumen and mucosa were obtained in all patients. In the 18 patients with indeterminate biliary strictures, high-definition cholangioscopy identified all cholangiocarcinomas but labeled as malignant only 1 of 4 strictures caused by pancreatic cancer (sensitivity 73%). All benign strictures were correctly labeled (specificity 100%). Cholangioscopy proved helpful in evaluation of various biliary disorders and lithotripsy of pancreatic stones under direct vision. LIMITATIONS: Single center, small number of patients. CONCLUSION: High-definition cholangioscopy is a useful adjunct to ERCP in the diagnosis and treatment of pancreatobiliary disorders. Although fragility of the cholangioscope remains a problem, the changes made in the construction of this prototype digital cholangioscope have significantly increased its durability.

New colonoscope technology: impact on image capture and quality and on confidence and accuracy of endoscopy-based polyp discrimination.

BACKGROUND AND STUDY AIMS: A newer colonoscope series has optical magnification and improvement in image freezing function. We aimed to assess the impact on image capture, image quality, and polyp discrimination. PATIENTS AND METHODS: In consecutive patients undergoing outpatient colonoscopy images of colorectal polyps were taken with Olympus 190 or 180 series instruments. The number of image captures needed to obtain an adequate image, quality of stored images, proportion of polyps with a high confidence estimate of likely histology, and accuracy of interpretations were compared. RESULTS: An acceptable image at the first attempt was obtained in 97.3 % of photos with the 190 device vs. 83.8 % with the 180 instrument (P < 0.001). In the 190 group narrowband imaging (NBI) provided high confidence readings in 9 % more cases than in the 180 group, but did not improve accuracy of polyp categorization. The quality of the stored images was judged better for the 190 device. However, when images that had provided high confidence estimates of polyp histology were re-interpreted later by the original endoscopist, there was agreement with the original interpretation for > 98 % of polyps in both the 180 group and the 190 group. A second endoscopist agreed with the original high confidence interpretations for 90 % of polyps imaged with either the 180 or the 190 scope. CONCLUSION: The new colonoscope had less image blurring, improved subjective quality of stored images, and increased the proportion of high confidence endoscopic estimates of polyp histology, but did not improve accuracy in estimating polyp histology.

Evaluation of a new image-enhanced endoscopic technology using band-limited light for detection of esophageal squamous cell carcinoma.

BACKGROUND: The aim of the present study was to evaluate the clinical utility of a new image-enhanced endoscopy (IEE) technology called optical enhancement imaging (OEI-1, -2, -3) by quantitatively evaluating diagnostic performance in superficial esophageal squamous cell carcinoma (SCC) in order to facilitate detection and characterization of gastrointestinal tumors. PATIENTS AND METHODS: The study involved 10 esophageal SCC resected endoscopically at our hospital. Ex vivo observation of the boundary area between normal and SCC was done using each mode (white light image [WLI], OEI-1, OEI-2, and OEI-3) with and without magnification. The additional effect of OEI on WLI was evaluated by calculating the color difference (expressed as ΔE94 ) between SCC and normal epithelium, and that between the intraepithelial papillary capillary loop (IPCL) and inter-vascular background coloration (IVBC). RESULTS: Mean ΔE94 values between SCC and normal epithelium for WLI, OEI-1, OEI-2, and OEI-3 were 9.37 ± 4.64, 13.82 ± 4.46,13.26 ± 4.73, and 16.44 ± 4.83, respectively; the corresponding values between IPCL and IVBC were 17.57 ± 10.17, 29.32 ± 9.95, 25.41 ± 11.72, and 23.71 ± 11.58, respectively. Compared with WLI, all OEI exhibited significant additional effect on ΔE94 . Furthermore, we found significant additional effect of OEI-3 in observing SCC and normal epithelium, and of OEI-1 in observing IPCL and IVBC, compared with other OEI. CONCLUSION: These results suggest that OEI improves endoscopic detection and characterization of esophageal SCC compared with WLI. Moreover, the data indicate that OEI-3 is useful for detection and OEI-1 is useful for characterization of esophageal SCC.

Ability of a novel blue laser imaging system for the diagnosis of colorectal polyps.

BACKGROUND: A new endoscope system with a laser light source, blue laser imaging (BLI), has been developed by Fujifilm that allows for narrow-band light observation. The aim of the present study was to evaluate the utility of BLI for the diagnosis of colorectal polyps. METHODS: We retrospectively analyzed 314 colorectal polyps that were examined with BLI observation at Kyoto Prefectural University of Medicine between September 2011 and January 2013. The surface and vascular patterns of polyps detected by published narrow-band imaging magnification: Hiroshima classification were used. Correlations were determined between the classifications and the histopathological diagnoses. Additionally, the ability of BLI without magnification to differentiate between neoplastic or non-neoplastic polyps was analyzed. RESULTS: A total of 41 hyperplastic polyps, 168 adenomas, 80 intramucosal cancer, 11 shallowly invaded submucosal cancer, and 14 deeply invaded submucosal cancer were analyzed.Hyperplastic polyp was observed in 100% of Type A lesions (39 lesions), adenoma was observed in 89.3% of Type B lesions (159 lesions), intramucosal cancer and shallowly invaded submucosal cancer was observed in 69.6% of Type C1 (92 lesions) and in 84.6% of Type C2 (13 lesions), and deeply invaded submucosal cancer was observed in 81.8% of Type C3 lesions (11 lesions). The overall diagnostic accuracy of BLI with magnification was 84.3%. Additionally, the diagnostic accuracy of BLI without magnification for differentiating between neoplastic and non-neoplastic polyps <10 mm in diameter was 95.2%, which was greater than that of white light (83.2%). CONCLUSION: BLI was useful for the diagnosis of colorectal polyps.

Narrow-band imaging system with magnifying endoscopy for early oral cancer.

It is often difficult to detect early oral cancer due to the specificity of the oral mucosa structure. The aim of this study was to investigate the potential of narrow band imaging (NBI) as an effective and non-invasive diagnostic tool in early oral cancer and other oral diseases. A magnifying endoscopy system manufactured by Olympus Corporation was used. A total of 121 subjects were included in the study. Subepithelial capillary loops were identified and categorized according to the classification of Inoue, with healthy mucosa graded as Type I or II, and that showing evidence of cancer-induced morphological change as Type III or IV. Sensitivity and specificity for the identification of oral cancer were estimated at 92.3% and 88.2%, respectively. Examination under a microscope with H&E staining and immunostaining for CD34 revealed dilation and extension of the capillaries in epithelial dysplasia, in addition to thickening of the epithelial layer. The present results indicate that use of NBI in conjunction with conventional magnifying endoscopy has great potential as an effective and non-invasive diagnostic tool in the early detection of oral cancer.

Narrow-band imaging with dual focus magnification in differentiating colorectal neoplasia.

BACKGROUND: Real-time optical diagnosis of colorectal polyps may lead to substantial time and cost savings and could potentially reduce complications associated with polypectomy. We prospectively assessed the utility of a novel narrow-band imaging (NBI) system with dual focus magnification (DF) in differentiating colorectal polyps in consecutive patients undergoing colonoscopy. PATIENTS AND METHODS: All procedures were carried out with a prototype 190 series Exera III NBI system with Dual Focus capability. Histology of each polyp was predicted in real time with NBI-DF based on the modified Sano's classification with a confidence level (low/high). NBI-DF diagnosis was then compared to the final (blinded) histopathology results. Primary endpoint was the accuracy of endoscopic prediction with the modified Sano's classification of all polyps when they were diagnosed with high confidence. Secondary endpoints were the accuracy of post-polypectomy surveillance intervals for diminutive polyps(≤ 5 mm). A total of 164 polyps in 87 patients (53 males) with a mean age of 63 (range 28-86) years were evaluated. RESULTS: 149 polyps were diagnosed with high confidence on endoscopic prediction, out of which 80 were diminutive, 31 small (6-9 mm) and 38 large (>10 mm). Overall accuracy of NBI-DF compared to final histopathology was 97%. The accuracy for post-polypectomy surveillance interval based on the endoscopic prediction was 97%. The NPV for diminutive rectosigmoid polyps for adenomatous histology was 100%. CONCLUSION: In this preliminary feasibility study, NBI-DF permitted prediction of histology of colorectal polyps with high accuracy. In addition, both of the secondary endpoints exceeded the ASGE PIVI thresholds for the management of diminutive polyps.