Colonoscopy is an effective tool for early screening of colorectal diseases.However,the application of colonoscopy in distinguishing different intestinal diseases still faces great challenges of efficiency and accurac...Colonoscopy is an effective tool for early screening of colorectal diseases.However,the application of colonoscopy in distinguishing different intestinal diseases still faces great challenges of efficiency and accuracy.Here we constructed and evaluated a deep convolution neural network(CNN)model based on 117055 images from 16004 individuals,which achieved a high accuracy of 0.933 in the validation dataset in identifying patients with polyp,colitis,colorectal cancer(CRC)from normal.The proposed approach was further validated onmulti-center real-time colonoscopy videos and images,which achieved accurate diagnostic performance on detecting colorectal diseases with high accuracy and precision to generalize across external validation datasets.The diagnostic performance of the model was further compared to the skilled endoscopists and the novices.In addition,our model has potential in diagnosis of adenomatous polyp and hyperplastic polyp with an area under the receiver operating characteristic curve of 0.975.Our proposed CNN models have potential in assisting clinicians in making clinical decisions with efficiency during application.展开更多
BACKGROUND Preparation for colon capsule endoscopy(CCE)requires a large liquid laxative volume for capsule excretion,which compromises the procedure's tolerability.AIM To assess the safety and utility of castor oi...BACKGROUND Preparation for colon capsule endoscopy(CCE)requires a large liquid laxative volume for capsule excretion,which compromises the procedure's tolerability.AIM To assess the safety and utility of castor oil-boosted bowel preparation.METHODS This prospective cohort study including 20 patients(age range,16-80 years;six men and 14 women)suspected of having colorectal disease was conducted at Kindai University Hospital from September 2017 to August 2019.All patients underwent CCE because of the following inclusion criteria:previous incomplete colonoscopy in other facility(n=20),history of abdominal surgery(n=7),or organ abnormalities such as multiple diverticulum(n=4)and adhesion after surgery(n=6).The exclusion criteria were as follows:Dysphagia,history of allergic reactions to the drugs used in this study(magnesium citrate,polyethylene glycol,metoclopramide,and castor oil),possibility of pregnancy,possibility of bowel obstruction or stenosis based on symptoms,or scheduled magnetic resonance imaging within 2 wk after CCE.The primary outcome was the capsule excretion rate within the battery life,as evaluated by the total large bowel observation rate,large bowel transit time,and bowel creasing level using a fivegrade scale in different colorectal segments.The secondary outcomes were complications,colorectal lesion detection rates,and patients’tolerability.RESULTS The castor oil-based regimen was implemented in 17 patients.Three patients cancelled CCE because they could tolerate castor oil,but not liquid laxatives.The capsule excretion rate within the battery life was 88%(15/17).The mean large bowel transit time was 236 min.Approximately 70%of patients had satisfactory colon cleansing levels.CCE detected colon polyps(14/17,82%)and colonic diverticulum(4/12,33%).The sensitivity,specificity,and diagnostic accuracy rates for detecting colorectal polyps(size≥6 mm)were 76.9%,75.0%,and 76.4%,respectively.The sensitivity,specificity,and diagnostic accuracy rates for detection of diverticulum were 100%each.Twelve patients(71%)rated CCE as more than“good”,confirming the new regimen’s tolerability.No serious adverse events occurred during this study.CONCLUSION The castor oil-based regimen could reduce bowel preparation dose and improve CCE tolerability.展开更多
基金This study was funded by the National Natural Science Foundation of China(Grant No.81902861 to F.Z.and 32000485 to X.H.)“Xinglin Scholars”Scientific Research Project Fund of Chengdu University of Traditional Chinese Medicine(Grant No.YYZX2019012 to F.Z.)+1 种基金the Scientific Research Fund of Technology Bureau in Dazhou(Grant No.17YYJC0004 to F.-W.Z.)the Key Research and Development Project Fund of Science and Technology Bureau in Dazhou,Sichuan Province(Grant No.20ZDYF0001 to F.-W.Z.).We express our deepest appreciation to J.Z,Y.C.for organizing the raw data and G.Y.for the revising the manuscript.
文摘Colonoscopy is an effective tool for early screening of colorectal diseases.However,the application of colonoscopy in distinguishing different intestinal diseases still faces great challenges of efficiency and accuracy.Here we constructed and evaluated a deep convolution neural network(CNN)model based on 117055 images from 16004 individuals,which achieved a high accuracy of 0.933 in the validation dataset in identifying patients with polyp,colitis,colorectal cancer(CRC)from normal.The proposed approach was further validated onmulti-center real-time colonoscopy videos and images,which achieved accurate diagnostic performance on detecting colorectal diseases with high accuracy and precision to generalize across external validation datasets.The diagnostic performance of the model was further compared to the skilled endoscopists and the novices.In addition,our model has potential in diagnosis of adenomatous polyp and hyperplastic polyp with an area under the receiver operating characteristic curve of 0.975.Our proposed CNN models have potential in assisting clinicians in making clinical decisions with efficiency during application.
文摘BACKGROUND Preparation for colon capsule endoscopy(CCE)requires a large liquid laxative volume for capsule excretion,which compromises the procedure's tolerability.AIM To assess the safety and utility of castor oil-boosted bowel preparation.METHODS This prospective cohort study including 20 patients(age range,16-80 years;six men and 14 women)suspected of having colorectal disease was conducted at Kindai University Hospital from September 2017 to August 2019.All patients underwent CCE because of the following inclusion criteria:previous incomplete colonoscopy in other facility(n=20),history of abdominal surgery(n=7),or organ abnormalities such as multiple diverticulum(n=4)and adhesion after surgery(n=6).The exclusion criteria were as follows:Dysphagia,history of allergic reactions to the drugs used in this study(magnesium citrate,polyethylene glycol,metoclopramide,and castor oil),possibility of pregnancy,possibility of bowel obstruction or stenosis based on symptoms,or scheduled magnetic resonance imaging within 2 wk after CCE.The primary outcome was the capsule excretion rate within the battery life,as evaluated by the total large bowel observation rate,large bowel transit time,and bowel creasing level using a fivegrade scale in different colorectal segments.The secondary outcomes were complications,colorectal lesion detection rates,and patients’tolerability.RESULTS The castor oil-based regimen was implemented in 17 patients.Three patients cancelled CCE because they could tolerate castor oil,but not liquid laxatives.The capsule excretion rate within the battery life was 88%(15/17).The mean large bowel transit time was 236 min.Approximately 70%of patients had satisfactory colon cleansing levels.CCE detected colon polyps(14/17,82%)and colonic diverticulum(4/12,33%).The sensitivity,specificity,and diagnostic accuracy rates for detecting colorectal polyps(size≥6 mm)were 76.9%,75.0%,and 76.4%,respectively.The sensitivity,specificity,and diagnostic accuracy rates for detection of diverticulum were 100%each.Twelve patients(71%)rated CCE as more than“good”,confirming the new regimen’s tolerability.No serious adverse events occurred during this study.CONCLUSION The castor oil-based regimen could reduce bowel preparation dose and improve CCE tolerability.