Background
The Japanese Society of Gastroenterology (JSGE) published ‘‘Daicho Polyp Shinryo Guideline 2014′’ in Japanese and a part of this guideline was published in English as “Evidence-based ...clinical practice guidelines for management of colorectal polyps” in the
Journal of Gastroenterology
in 2015. A revised version of the Japanese-language guideline was published in 2020, and here we introduce a part of the contents of revised version.
Methods
The guideline committee discussed and drew up a series of clinical questions (CQs). Recommendation statements for the CQs were limited to items with multiple therapeutic options. Items with established conclusions that had 100% agreement with previous guidelines (background questions) and items with no (or old) evidence that are topics for future research (future research questions: FRQs) were given descriptions only. To address the CQs and FRQs, PubMed, ICHUSHI, and other sources were searched for relevant articles published in English from 1983 to October 2018 and articles published in Japanese from 1983 to November 2018. The Japan Medical Library Association was also commissioned to search for relevant materials. Manual searches were performed for questions with insufficient online references.
Results
The professional committee created 18 CQs and statements concerning the current concept and diagnosis/treatment of various colorectal polyps, including their epidemiology, screening, pathophysiology, definition and classification, diagnosis, management, practical treatment, complications, and surveillance after treatment, and other colorectal lesions (submucosal tumors, nonneoplastic polyps, polyposis, hereditary tumors, ulcerative colitis-associated tumors/carcinomas).
Conclusions
After evaluation by the moderators, evidence-based clinical practice guidelines for management of colorectal polyps were proposed for 2020. This report addresses the therapeutic related CQs introduced when formulating these guidelines.
Although erosions and ulcerations are the most common small-bowel abnormalities found on wireless capsule endoscopy (WCE), a computer-aided detection method has not been established. We aimed to ...develop an artificial intelligence system with deep learning to automatically detect erosions and ulcerations in WCE images.
We trained a deep convolutional neural network (CNN) system based on a Single Shot Multibox Detector, using 5360 WCE images of erosions and ulcerations. We assessed its performance by calculating the area under the receiver operating characteristic curve and its sensitivity, specificity, and accuracy using an independent test set of 10,440 small-bowel images including 440 images of erosions and ulcerations.
The trained CNN required 233 seconds to evaluate 10,440 test images. The area under the curve for the detection of erosions and ulcerations was 0.958 (95% confidence interval CI, 0.947-0.968). The sensitivity, specificity, and accuracy of the CNN were 88.2% (95% CI, 84.8%-91.0%), 90.9% (95% CI, 90.3%-91.4%), and 90.8% (95% CI, 90.2%-91.3%), respectively, at a cut-off value of 0.481 for the probability score.
We developed and validated a new system based on CNN to automatically detect erosions and ulcerations in WCE images. This may be a crucial step in the development of daily-use diagnostic software for WCE images to help reduce oversights and the burden on physicians.
Display omitted
Background and Aim
Although small‐bowel angioectasia is reported as the most common cause of bleeding in patients and frequently diagnosed by capsule endoscopy (CE) in patients with obscure ...gastrointestinal bleeding, a computer‐aided detection method has not been established. We developed an artificial intelligence system with deep learning that can automatically detect small‐bowel angioectasia in CE images.
Methods
We trained a deep convolutional neural network (CNN) system based on Single Shot Multibox Detector using 2237 CE images of angioectasia. We assessed its diagnostic accuracy by calculating the area under the receiver operating characteristic curve (ROC‐AUC), sensitivity, specificity, positive predictive value, and negative predictive value using an independent test set of 10 488 small‐bowel images, including 488 images of small‐bowel angioectasia.
Results
The AUC to detect angioectasia was 0.998. Sensitivity, specificity, positive predictive value, and negative predictive value of CNN were 98.8%, 98.4%, 75.4%, and 99.9%, respectively, at a cut‐off value of 0.36 for the probability score.
Conclusions
We developed and validated a new system based on CNN to automatically detect angioectasia in CE images. This may be well applicable to daily clinical practice to reduce the burden of physicians as well as to reduce oversight.
Background and Aims The Japan NBI Expert Team (JNET) was established in 2011 and has proposed a universal narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors. The aim ...of this study was to evaluate the clinical usefulness of the JNET classification for colorectal lesions. Methods We analyzed 2933 colorectal lesions, which were diagnosed by NBI magnifying observation before endoscopic treatment or surgery. The colorectal lesions consisted of 136 hyperplastic polyps/sessile serrated polyps (HPs/SSPs), 1926 low-grade dysplasia (LGD), 571 high-grade dysplasia (HGD), 87 superficial submucosal invasive (SM-s) carcinomas, and 213 deep submucosal invasive (SM-d) carcinomas. We evaluated the relationship between the JNET classification and the histologic findings of these lesions. Results The sensitivity, specificity, positive and negative predictive values, and accuracy of Type 1 lesions for the diagnosis of HP/SSP were, respectively, 87.5%, 99.9%, 97.5%, 99.4%, and 99.3%; of Type 2A lesions for the diagnosis of LGD were 74.3%, 92.7%, 98.3%, 38.7%, and 77.1%; of Type 2B lesions for the diagnosis of HGD/SM-s carcinoma were 61.9%, 82.8%, 50.9%, 88.2%, and 78.1%; for Type 3 lesions for the diagnosis of SM-d carcinoma were 55.4%, 99.8%, 95.2%, 96.6%, and 96.6%, respectively. Conclusions Type 1, 2A, and 3 of the JNET classification were very reliable indicators for HP/SSP, LGD, and SM-d carcinoma, respectively. However, the specificity and positive predictive value of Type 2B were relatively lower than those of others. Therefore, an additional examination such as pit pattern diagnosis using chromoagents is necessary for accurate diagnosis of Type 2B lesions.
Background
The current status of colorectal endoscopic submucosal dissection (ESD) performed by endoscopists without colorectal ESD experience is unknown. This study evaluated the quality of ...colorectal ESD performed by endoscopists without colorectal ESD experience.
Methods
We retrospectively examined the outcomes of 420 consecutive patients with 427 superficial colorectal tumors (male/female, 251/169; mean age, 69 years) who underwent ESD. The procedures were performed by 31 endoscopists without colorectal ESD experience using needle knife-type devices at 13 hospitals from October 2008 to June 2017. Cases were divided into the first and second phases according to the experience of the endoscopist: the first phase included the first 20 cases and the second phase included case 21 and beyond. We also identified factors associated with en bloc resection failure.
Results
Rates of colonic tumors, laterally spreading tumors of the non-granular type, poor scope operability, and severe submucosal fibrosis for the first phase were significantly lower than those for the second phase. The en bloc resection rates for the first and second phases were 93% and 96%, respectively. The factors associated with en bloc resection failure were poor scope operability (odds ratio OR 2.6; 95% confidence interval CI 1.0–6.5), severe submucosal fibrosis (OR 6.5; 95% CI 2.6–15.9), and the first 20 cases (OR 3.4; 95% CI 1.2–10.1).
Conclusion
Inexperienced endoscopists should initially perform colorectal ESD for tumors without severe submucosal fibrosis under good scope operability for at least 20 cases.
The number of deaths from colorectal cancer in Japan continues to increase. Colorectal cancer deaths exceeded 50,000 in 2016. In the 2019 edition, revision of all aspects of treatments was performed, ...with corrections and additions made based on knowledge acquired since the 2016 version (drug therapy) and the 2014 version (other treatments). The Japanese Society for Cancer of the Colon and Rectum guidelines 2019 for the treatment of colorectal cancer (JSCCR guidelines 2019) have been prepared to show standard treatment strategies for colorectal cancer, to eliminate disparities among institutions in terms of treatment, to eliminate unnecessary treatment and insufficient treatment and to deepen mutual understanding between healthcare professionals and patients by making these guidelines available to the general public. These guidelines have been prepared by consensuses reached by the JSCCR Guideline Committee, based on a careful review of the evidence retrieved by literature searches and in view of the medical health insurance system and actual clinical practice settings in Japan. Therefore, these guidelines can be used as a tool for treating colorectal cancer in actual clinical practice settings. More specifically, they can be used as a guide to obtaining informed consent from patients and choosing the method of treatment for each patient. Controversial issues were selected as clinical questions, and recommendations were made. Each recommendation is accompanied by a classification of the evidence and a classification of recommendation categories based on the consensus reached by the Guideline Committee members. Here, we present the English version of the JSCCR guidelines 2019.
Macrophages are an essential component of antitumor activity; however, the role of tumor‐associated macrophages (TAMs) in colorectal cancer (CRC) remains controversial. Here, we elucidated the role ...of TAMs in CRC progression, especially at the early stage. We assessed the TAM number, phenotype, and distribution in 53 patients with colorectal neoplasia, including intramucosal neoplasia, submucosal invasive colorectal cancer (SM‐CRC), and advanced cancer, using double immunofluorescence for CD68 and CD163. Next, we focused on the invasive front in SM‐CRC and association between TAMs and clinicopathological features including lymph node metastasis, which were evaluated in 87 SM‐CRC clinical specimens. The number of M2 macrophages increased with tumor progression and dynamic changes were observed with respect to the number and phenotype of TAMs at the invasive front, especially at the stage of submucosal invasion. A high M2 macrophage count at the invasive front was correlated with lymphovascular invasion, low histological differentiation, and lymph node metastasis; a low M1 macrophage count at the invasive front was correlated with lymph node metastasis. Furthermore, receiver operating characteristic curve analysis revealed that the M2/M1 ratio was a better predictor of the risk of lymph node metastasis than the pan‐, M1, or M2 macrophage counts at the invasive front. These results suggested that TAMs at the invasive front might play a role in CRC progression, especially at the early stages. Therefore, evaluating the TAM phenotype, number, and distribution may be a potential predictor of metastasis, including lymph node metastasis, and TAMs may be a potential CRC therapeutic target.
We identified dynamic changes in the number and phenotype of tumor‐associated macrophages (TAMs) at the invasive front in colorectal cancer (CRC), especially at the stage of submucosal invasion. Furthermore, TAMs at the invasive front may play a role in CRC progression, especially in early stage CRC, ie, M1 macrophages at the invasive front may inhibit CRC progression, while M2 macrophages may promote CRC progression via EMT. Therefore, a marker comprising the phenotype, number, and distribution of TAMs may serve as a potential predictor of metastasis, including lymph node metastasis, and TAMs may be a potential therapeutic target in CRC.
Protruding lesions of the small bowel vary in wireless capsule endoscopy (WCE) images, and their automatic detection may be difficult. We aimed to develop and test a deep learning–based system to ...automatically detect protruding lesions of various types in WCE images.
We trained a deep convolutional neural network (CNN), using 30,584 WCE images of protruding lesions from 292 patients. We evaluated CNN performance by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, using an independent set of 17,507 test images from 93 patients, including 7507 images of protruding lesions from 73 patients.
The developed CNN analyzed 17,507 images in 530.462 seconds. The AUC for detection of protruding lesions was 0.911 (95% confidence interval Cl, 0.9069–0.9155). The sensitivity and specificity of the CNN were 90.7% (95% CI, 90.0%–91.4%) and 79.8% (95% CI, 79.0%–80.6%), respectively, at the optimal cut-off value of 0.317 for probability score. In a subgroup analysis of the category of protruding lesions, the sensitivities were 86.5%, 92.0%, 95.8%, 77.0%, and 94.4% for the detection of polyps, nodules, epithelial tumors, submucosal tumors, and venous structures, respectively. In individual patient analyses (n = 73), the detection rate of protruding lesions was 98.6%.
We developed and tested a new computer-aided system based on a CNN to automatically detect various protruding lesions in WCE images. Patient-level analyses with larger cohorts and efforts to achieve better diagnostic performance are necessary in further studies.
PDF
