Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.
Artificial Intelligence ; Colonic Polyps/diagnosis* ; Colonoscopy/methods* ; Colorectal Neoplasms/diagnosis* ; Diagnosis, Computer-Assisted ; Humans

BACKGROUND: Although routine screening of carcinoembryonic antigen (CEA) is not recommended for the early diagnosis of colorectal cancers, CEA levels are frequently measured in practice and during opportunistic health screening programs. We evaluated the frequency of false-positive results according to CEA level at a health screening center. METHODS: The medical records of 25,786 participants who underwent a general health check-up and CEA testing at the Seoul National University Hospital Healthcare System Gangnam Center from March 2015 to February 2016 were reviewed. CEA levels were measured using the Architect i2000sr (Abbott Laboratories, USA). The cut-off level for elevated CEA was 5.0 ng/mL. RESULTS: Among 25,786 participants who underwent CEA screening, 597 (2.3%) had CEA levels >5.0 ng/mL. Among 597 participants with elevated CEA levels, 12 (2.0%) had actual malignancies with CEA levels of 8.3–155.3 ng/mL. Diabetes, smoking, chronic obstructive pulmonary disease, and colonic polyps were considered as causes of false elevation. The false-positive rates of CEA according to level were as follows: 5.1–10.0 ng/mL, 99.5%; 10.1–15.0 ng/mL, 87.2%; 15.1–20.0 ng/mL, 100.0%; >20.0 ng/mL, 33.3%. A subsequent decrease in the CEA level after a 1-month follow-up was observed in 47.6% of all cases with elevated CEA levels. CONCLUSIONS: False elevation in CEA levels in the range of 5.0–20.0 ng/mL is common in patients who underwent testing at a health screening center. False-positive results above 20.0 ng/mL are less common. These data could provide a guide for the interpretation of elevated CEA level at a health screening center.
Biomarkers ; Carcinoembryonic Antigen ; Colonic Polyps ; Colorectal Neoplasms ; Delivery of Health Care ; Early Diagnosis ; Follow-Up Studies ; Humans ; Mass Screening ; Medical Records ; Pulmonary Disease, Chronic Obstructive ; Seoul ; Smoke ; Smoking

OBJECTIVETo determine the detection rate and distribution characteristics of colorectal adenomas in Ningbo area of China, and to identify the risk factors for colorectal adenoma, in order to provide reference for colorectal cancer screening.

METHODSA cross-sectional study was performed among 8660 subjects undergoing colonoscopy in the Ningbo No.2 Hospital between January and December 2016, using a questionnaire, including demographic data (age, gender, height and weight), history of diseases (diabetes, hypertension, hyperlipidemia, and family history of malignant neoplasm), lifestyle (smoking, alcohol, dietary bias on red meat, dietary bias on fruit and vegetables, dietary frequency of pickled food and physical activities), and intestinal early warning symptoms. All colonoscopically detected polyps were removed for histological examination. Polyps were histologically divided into non-adenomatous (hyperplastic polyps and inflammatory polyps) and adenomatous polyps (tubular, villous, tubulovillous and serrated adenomas). Pathologic features were analyzed according to anatomical site. Multivariate logistic regression analysis was used to identify the risk factors for colorectal adenoma.

RESULTSA total of 7077 subjects who received colonoscopic examination and completed the questionnaire survey were enrolled in this study. There were 3633 males and 3444 females with a median age of 53 (ranged 17 to 83) years. Adenoma detection rate was 15.6% (1103/7077) in all cases, 21.0%(762/3633) for males, and 9.9%(341/3444) for females(P=0.000). Detection rate of 6.2%(29/469) was recorded in individuals aged less than 30 years, 8.0%(87/1086) in those from 30 to 39 years, 12.1%(148/1222) in those from 40 to 49 years, 16.8%(272/1623) in those from 50 to 59 years, 20.4%(326/1601) in those from 60 to 69 years, and 22.4%(241/1076) in those ≥70 years. The detection rate increased according to age(P=0.000). A total of 1521 adenomas were detected in 1103 cases, including 1455 tubular adenomas, 33 tubulovillous adenomas, 9 villous adenomas and 24 serrated adenomas. Among 1521 adenomas, 44.1%(n=671) located in the right hemicolon, 39.0%(n=593) in the left hemicolon, and 16.9%(n=257) in the rectum. Significantly larger number of serrated adenomas and advanced adenomas (advanced adenoma was defined as any adenoma with high-grade intraepithelial neoplasia, diameter ≥10 mm or with villous component) was observed in the right hemicolon compared to left hemicolon and rectum [serrated adenomas: 2.5%(17/671) vs. 0.8% (5/593) and 0.8% (2/257), P=0.029; advanced adenoma: 9.2% (62/671) vs. 5.2% (31/953) and 6.6% (17/257), P=0.021]. Multivariate analysis showed that malely (P=0.003), elderly (P=0.000), obesity (P=0.014), smoking (P=0.001), alcohol (P=0.032), and family history of malignancy (P=0.000) were independent risk factors of colorectal adenoma.

CONCLUSIONSIn view of a higher detection rate of colorectal adenoma in population aged 40 to 49 years especially in male individuals, the starting age of colonoscopy screening may be advanced to 40 years old. People with family history of malignancy, obesity, and habit of smoking or drinking should be regarded as important subjects for colonoscopy screening. During colonoscopy screening, special emphasis should be given to right hemicolon.

Adenoma ; diagnosis ; epidemiology ; Adolescent ; Adult ; Aged ; Aged, 80 and over ; China ; epidemiology ; Colonic Polyps ; Colonoscopy ; Colorectal Neoplasms ; diagnosis ; epidemiology ; Cross-Sectional Studies ; Female ; Humans ; Male ; Middle Aged ; Risk Factors ; Young Adult

OBJECTIVETo summarize the diagnosis and treatment of iatrogenic colonoscopic perforation (ICP).

METHODSClinical data, treatment course and outcome of 17 patients who developed ICP following colonoscopic examination or operation at Department of Colorectal Surgery, Changhai Hospital from January 2000 to December 2013 were retrospectively analyzed.

RESULTSDuring above 13 years, a total of 127 106 patients underwent colonoscopic examination or operation, of whom 17 cases (0.013%) had ICP. There were 8 males and 9 females with an average age of 65.2 (32-85) years. The interval between the onset of ICP and clinically diagnosed ICP was 0 to 6 days after performance. ICP occurred in 8 patients following colonoscopy operations, including simple colonic polyp excision, endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD), while in 9 patients following simple colonoscopy examination. Except for one patient who was immediately diagnosed with ICP through the finding of "yellow adipose tissue visible in the vision field" during operation,7 early cases (41.2%) were diagnosed by abdominal X-ray examination, and 9 later cases were confirmed by abdominal CT examination. The perforation sites included sigmoid colon in 5 cases, caecum in 3 cases, descending colon in 3 cases, descending and sigmoid junction in 2 cases, ileum in 1 case, splenic flexure in 1 case, sigmoid and rectum junction in 1 case, retum in 1 case. One case with ICP following ESD after resection of polyp in caecum was cured successfully with conservative treatment, including fasting, gastrointestinal decompression, fluid infusion, anti-infection and nutritional support. One case with ICP, which was found during colonoscopic operation and the perforation was immediately closed with titanium clip, received conservative treatment, including anti-infection and then was cured. Fifteen patients underwent surgery, including 8 patients with primary intention intestinal perforation repair, 4 patients with primary intention resection of associated intestine and anastomosis, 2 patients with primary intention resection of associated intestine and ostomy, 1 patient with primary intention intestinal perforation repair and ostomy. Postoperative abdominal incision infection occurred in 4 cases, pulmonary infection in 1 case, incision infection with cardiovascular event or urinary tract infection in 1 case each. All the patients were cured and discharged. Average hospital stay was 18.6(3-45) days.

CONCLUSIONSICP should be diagnosed by physical examination and imaging examination as soon as possible. For perforation during colonoscopic performance, colonoscopic titanium clip can be used for closure. Perforation repair is still the main procedure for ICP. If necessary, partial intestinal resection and anastomosis or ostomy can be selected.

Adult ; Aged ; Aged, 80 and over ; Colonic Polyps ; Colonoscopy ; adverse effects ; Female ; Humans ; Iatrogenic Disease ; Intestinal Perforation ; diagnosis ; etiology ; therapy ; Male ; Middle Aged ; Retrospective Studies ; Treatment Outcome

In the last few years, interest in the optical diagnosis of colorectal polyps has increased among gastroenterologists. Several studies have shown that the optical diagnosis of small colorectal polyps is safe and feasible in routine clinical practice and is comparable to histopathology. The Narrow-band Imaging International Colorectal Endoscopic Classification provides a validated criterion for the classification of neoplastic and nonneoplastic polyps as well as polyps with deep submucosal invasion using narrow band imaging during real-time colonoscopy. The aim of the present review is to assess the current evidence for and limitations of optical diagnosis and to propose a systematic approach for transferring research findings to patient care.
Classification ; Colonic Polyps ; Colonoscopy ; Diagnosis* ; Narrow Band Imaging ; Optical Imaging ; Patient Care ; Polyps*

PURPOSE: Virtual colonoscopy is the most recently developed tool for detecting colorectal cancers and polyps, but its effectiveness is limited. In our study, we compared the result of preoperative virtual colonoscopy to result of preoperative and postoperative colonoscopy. We evaluated also the accuracy of preoperative virtual colonoscopy in patients who had obstructive colorectal cancer that did not allow passage of a colonoscope. METHODS: A total of 164 patients who had undergone preoperative virtual colonoscopy and curative surgery after the diagnosis of a colorectal adenocarcinoma between November 2008 and August 2013 were pooled. We compared the result of conventional colonoscopy with that of virtual colonoscopy in the nonobstructive group and the results of preoperative virtual colonoscopy with that of postoperative colonoscopy performed at 6 months after surgery in the obstructive group. RESULTS: Of the 164 patients, 108 were male and 56 were female patients. The mean age was 62.7 years. The average sensitivity, specificity, and accuracy of virtual colonoscopy for all patients were 31.0%, 67.2%, and 43.8%, respectively. In the nonobstructive group, the average sensitivity, specificity, and accuracy were 36.6%, 66.2%, and 48.0%, respectively, whereas in the obstructive group, they were 2%, 72.4%, and 25.4%. Synchronous cancer was detected via virtual colonoscopy in 4 of the 164 patients. CONCLUSION: Virtual colonoscopy may not be an effective method for the detection of proximal colon polyps, but it can be helpful in determining the therapeutic plan when its results are correlated with the results of other studies.
Adenocarcinoma ; Colon* ; Colonic Polyps ; Colonography, Computed Tomographic* ; Colonoscopes ; Colonoscopy ; Colorectal Neoplasms* ; Diagnosis ; Female ; Humans ; Male ; Methods ; Polyps ; Sensitivity and Specificity

PURPOSE: Although there is a consensus about the need for surveillance colonoscopy after endoscopic resection, the interval remains controversial for large sessile colorectal polyps. The aim of this study was to evaluate the long-term outcome and the adequate surveillance colonoscopy interval required for sessile and flat colorectal polyps larger than 20 mm. MATERIALS AND METHODS: A total of 204 patients with large sessile and flat polyps who received endoscopic treatment from May 2005 to November 2011 in a tertiary referral center were included. RESULTS: The mean age was 65.1 years and 62.7% of the patients were male. The mean follow-up duration was 44.2 months and the median tumor size was 25 mm. One hundred and ten patients (53.9%) received a short interval surveillance colonoscopy (median interval of 6.3 months with range of 1-11 months) and 94 patients (46.1%) received a long interval surveillance colonoscopy (median interval of 13.6 months with range of 12-66 months). There were 14 patients (6.9%) who had local recurrence at the surveillance colonoscopy. Using multivariate regression analysis, a polyp size greater than 40 mm was shown to be independent risk factor for local recurrence. However, piecemeal resection and surveillance colonoscopy interval did not significantly influence local recurrence. CONCLUSION: Endoscopic treatment of large sessile colorectal polyps shows a favorable long-term outcome. Further prospective study is mandatory to define an adequate interval of surveillance colonoscopy.
Adult ; Aged ; Colonic Neoplasms/*diagnosis/pathology/surgery ; Colonic Polyps/*diagnosis/pathology/surgery ; *Colonoscopy ; Endoscopic Mucosal Resection ; Female ; Humans ; Male ; Middle Aged ; Neoplasm Recurrence, Local/*diagnosis ; Prospective Studies ; Time Factors ; Watchful Waiting/*methods

BACKGROUND/AIMS: Although colonoscopy is not indicated in patients with hematochezia, many surgeons, internists, and physicians are recommending colonoscopy for these patients in Korea. The aim of this study is to evaluate the diagnostic value of colonoscopy for patients with hematochezia. METHODS: We retrospectively reviewed the data of colonoscopy between January 2010 and December 2010. A total of 321 patients among 3,038 colonoscopies (10.6%) underwent colonoscopy to evaluate the cause of hematochezia. The patients with previous colorectal surgery (2) or polypectomy (5) were excluded. We analyzed endoscopic diagnoses. Advanced neoplastic polyps were defined as adenomas with villous histology or high grade dysplasia, or adenomas more than 10 mm in diameter. RESULTS: Hemorrhoid was the most common diagnosis (217 cases, 67.6%). Polyps were detected in 93 patients (29.0%), but advanced neoplastic polyps were found in only 14 cases (4.4%). Colorectal cancers were diagnosed in 18 patients (5.6%) including 14 rectal cancers. There was no cancer located above sigmoid-descending junction. Diverticuli were detected in 41 patients (12.8%) but there was only one case of suspected diverticular bleeding. Colitis was diagnosed in 24 patients (7.5%). Other lesions included acute anal fissure, rectal tumor, stercoral ulcer, and radiation proctitis. CONCLUSIONS: The colonoscopy had little value in patients with hematochezia because the most pathologic lesions were located below sigmoid colon. The first choice of diagnosis in patients with hematochezia is sigmoidoscopy.
Adolescent ; Adult ; Aged ; Aged, 80 and over ; Child ; Colitis/complications/diagnosis ; Colonic Neoplasms/complications/diagnosis ; Colonic Polyps ; *Colonoscopy ; Colorectal Neoplasms/complications/diagnosis ; Female ; Gastrointestinal Hemorrhage/diagnosis/*etiology ; Hemorrhoids/complications/diagnosis ; Humans ; Male ; Middle Aged ; Retrospective Studies ; Young Adult

BACKGROUND/AIMS: The efficacy and safety of endoscopic resection of colorectal cancer derived from sessile serrated adenomas or traditional serrated adenomas are still unknown. The aims of this study were to verify the characteristics and outcomes of endoscopically resected early colorectal cancers developed from serrated polyps. METHODS: Among patients who received endoscopic resection of early colorectal cancers from 2008 to 2011, cancers with documented pre-existing lesions were included. They were classified as adenoma, sessile serrated adenoma, or traditional serrated adenoma according to the baseline lesions. Clinical characteristics, pathologic diagnosis, and outcomes were reviewed. RESULTS: Overall, 208 colorectal cancers detected from 198 patients were included: 198 with adenoma, five with sessile serrated adenoma, and five with traditional serrated adenoma. The sessile serrated adenoma group had a higher prevalence of high-grade dysplasia (40.0% vs. 25.8%, P<0.001) than the adenoma group. During follow-up, local recurrence did not occur after endoscopic resection of early colorectal cancers developed from serrated polyps. In contrast, two cases of metachronous recurrence were detected within a short follow-up period. CONCLUSIONS: Cautious observation and early endoscopic resection are recommended when colorectal cancer from serrated polyp is suspected. Colorectal cancers from serrated polyp can be treated successfully with endoscopy.
Adenoma* ; Colonic Polyps ; Colonoscopy ; Colorectal Neoplasms* ; Diagnosis ; Endoscopy ; Follow-Up Studies ; Humans ; Polyps ; Prevalence ; Recurrence

Colorectal carcinoma is a common lethal disease with signs and symptoms that may be nonspecific. Computed tomography (CT) of the abdomen and pelvis with or without contrast is frequently performed for various general abdominal complaints, but unlike CT colonography, the large bowel may not be optimally prepared for evaluation. As such, careful and diligent assessment of the non-prepared colon in all CT images of the abdomen and pelvis is important, as it ensures that incidental colorectal malignancy is not missed, especially in older patients. This article gives an overview of multidetector CT imaging signs and subtle clues to aid in the diagnosis of colorectal carcinoma, as well as their pitfalls.
Colonic Polyps ; pathology ; Colonography, Computed Tomographic ; Colorectal Neoplasms ; diagnosis ; diagnostic imaging ; Diagnosis, Differential ; Humans ; Incidental Findings ; Pelvis ; diagnostic imaging ; Radiography, Abdominal ; Tomography, X-Ray Computed