Analysis of Factors Related to Recurrence of Colorectal Adenomatous Polyps After Endoscopic Treatment

Objective: To study and analyze the related factors of recurrence after endoscopic treatment of colorectal adenomatous polyps. Methods: From March 2017 to March 2018, a total of 600 colorectal adenomatous polyps treated with endoscopy in our hospital were selected as the study objects. The clinical data of all patients were analyzed retrospectively, including gender, age, occupation, income, drinking history, smoking history, whether they were infected with Helicobacter pylori, polyp location, polyp number, adenoma type, adenoma base, gland Tumor diameter, atypical hyperplasia, history of diabetes mellitus, history of hypertension, dyslipidemia (cholesteremia, low-density lipoprotein, hypertriglyceridemia), treatment methods, the relationship between the above risk factors and recurrence were analyzed, and the relevant factors of recurrence of colorectal adenomatous polyps were screened. Result: Age, occupation, income, drinking, smoking, polyp type, polyp diameter, Helicobacter pylori infection, treatment, diabetes, hypertension, adenoma type, adenoma base, atypical hyperplasia and dyslipidemia were all related factors (P < 0.05). Conclusion: Patients with colorectal adenomatous polyps undergo recurrence after endoscopic treatment with age, occupation, income, alcohol consumption, smoking, polyp type, Helicobacter pylori infection, treatment, diabetes, hypertension, adenoma type, adenoma base, A typical hyperplasia and dyslipidemia are associated. The more the above factors occur, the greater the chance of recurrence. The corresponding preventive measures should be taken for the above factors.

Value of Magnifying Chromoendoscopy and Magnifying Optical Enhancement Technology in Classifying Colorectal Polyps: A Prospective Controlled Study

Background and Aims. Magnifying chromoendoscopy (ME-CE) through the observation of pit patterns is a productive way to distinguish between neoplastic and nonneoplastic polyps. Magnifying optical enhancement technology (ME-OE) is an emerging virtual chromoendoscopy imaging technology and appeared to be a promising approach. However, this information is currently not available. This study is aimed at comparing the differential diagnostic value of ME-CE and OE for neoplastic and nonneoplastic polyps. Patients and Methods. Consecutive patients undergoing colonoscopy were randomized (1 : 1) into examination by ME-OE or ME-CE. Histopathological findings were utilized as the reference standard. Accuracy, sensitivity, specificity, and positive and negative predictive values of two endoscopy methods were compared using ME-OE (were classified according to the JNET classification) and ME-CE (were classified according to the Kudo pit pattern classification), respectively, and the time to predict the histological polyp type was compared. And the agreements between the pathological and clinical diagnosis by ME-OE or ME-CE were analyzed. Results. A total of 365 polyps were found in the 220 patients included (ME-OE: 185; ME-CE: 180.202 had nonneoplastic polyps, 163 had neoplastic polyps). The diagnostic accuracy of ME-OE was higher than that of ME-CE (93% vs. 92%, p > 0.05 ). The average diagnosis time was lower in ME-OE than ME-CE ( 83 ± 26.4 s vs. 194 ± 17.7 s , p < 0.001 ). The agreements between the pathological and clinical diagnosis were at least substantial in both groups. Conclusion. ME-OE was superlative to ME-CE in predicting the histology of polyps. OE devoted classification would possibly similarly enhance the endoscopist performance. The trial is registered with ChiCT2000032075.

Computer-Aided Colon Polyp Detection on High Resolution Colonoscopy Using Transfer Learning Techniques

Colonoscopies reduce the incidence of colorectal cancer through early recognition and resecting of the colon polyps. However, the colon polyp miss detection rate is as high as 26% in conventional colonoscopy. The search for methods to decrease the polyp miss rate is nowadays a paramount task. A number of algorithms or systems have been developed to enhance polyp detection, but few are suitable for real-time detection or classification due to their limited computational ability. Recent studies indicate that the automated colon polyp detection system is developing at an astonishing speed. Real-time detection with classification is still a yet to be explored field. Newer image pattern recognition algorithms with convolutional neuro-network (CNN) transfer learning has shed light on this topic. We proposed a study using real-time colonoscopies with the CNN transfer learning approach. Several multi-class classifiers were trained and mAP ranged from 38% to 49%. Based on an Inception v2 model, a detector adopting a Faster R-CNN was trained. The mAP of the detector was 77%, which was an improvement of 35% compared to the same type of multi-class classifier. Therefore, our results indicated that the polyp detection model could attain a high accuracy, but the polyp type classification still leaves room for improvement.

Overtreatment of Nonneoplastic Gallbladder Polyps due to Inadequate Routine Ultrasound Assessment

<b><i>Background:</i></b> The primary aim was to assess the diagnostic accuracy of routine ultrasound assessment for gallbladder polyps. The secondary aim was to identify the characteristics that differentiate neoplastic polyps from nonneoplastic polyps. <b><i>Methods:</i></b> A total of 156 patients with histopathologically proven gallbladder polyps in 4 Dutch hospitals between 2003 and 2013 were included. Sensitivity and specificity of ultrasound for polyp size, number of polyps, and polyp type were assessed using histopathological findings as a reference standard. In addition, diagnostic accuracy of sonographic size ≥1 cm for neoplasia was assessed. Subgroup analysis for patients with polyps as primary indication for cholecystectomy was performed. The sonographic polyp characteristics on preoperative routine ultrasound were described. <b><i>Results:</i></b> Fifty-six percent of gallbladder polyps were preoperatively identified on ultrasound, of which 31% were neoplastic. Sensitivity and specificity of ultrasound to estimate polyp size were 93 and 43% (subgroup; 92 and 33%). Sensitivity and specificity of sonographic polyp size ≥1 cm for neoplasia were 86 and 32% (subgroup; 94 and 26%). No specific sonographic characteristics for neoplastic polyps could be established due to lack of reporting. <b><i>Conclusion:</i></b> Routine ultrasound assessment of polyps is associated with overestimation of polyp size and low specificity of sonographic size ≥1 cm for neoplasia, which contributes to surgical overtreatment of nonneoplastic polyps.