Background and Aim
To examine whether our convolutional neural network (CNN) system based on deep learning can reduce the reading time of endoscopists without oversight of abnormalities in the ...capsule‐endoscopy reading process.
Methods
Twenty videos of the entire small‐bowel capsule endoscopy procedure were prepared, each of which included 0–5 lesions of small‐bowel mucosal breaks (erosions or ulcerations). At another institute, two reading processes were compared: (A) endoscopist‐alone readings and (B) endoscopist readings after the first screening by the proposed CNN. In process B, endoscopists read only images detected by CNN. Two experts and four trainees independently read 20 videos each (10 for process A and 10 for process B). Outcomes were reading time and detection rate of mucosal breaks by endoscopists. Gold standard was findings at the original institute by two experts.
Results
Mean reading time of small‐bowel sections by endoscopists was significantly shorter during process B (expert, 3.1 min; trainee, 5.2 min) compared to process A (expert, 12.2 min; trainee, 20.7 min) (P < 0.001). For 37 mucosal breaks, detection rate by endoscopists did not significantly decrease in process B (expert, 87%; trainee, 55%) compared to process A (expert, 84%; trainee, 47%). Experts detected all eight large lesions (>5 mm), but trainees could not, even when supported by the CNN.
Conclusions
Our CNN‐based system for capsule endoscopy videos reduced the reading time of endoscopists without decreasing the detection rate of mucosal breaks. However, the reading level of endoscopists should be considered when using the system.
Abstract Background and Aims Endoscopic submucosal dissection (ESD) is an effective procedure for en bloc resection of superficial colorectal tumors regardless of tumor size or location. However, ...there are few reports on long-term outcomes for superficial colorectal tumor patients post-ESD. We therefore aimed to evaluate long-term outcomes after ESD for superficial colorectal tumors. Methods ESD was performed on 257 consecutive colorectal tumors in 255 patients at Hiroshima University Hospital between June 2003 and July 2010. We investigated the following variables: patients’ characteristics, the American Society of Anesthesiologists score, tumor location, tumor size, growth type, histology, en bloc resection rate, achievement of curative resection, procedure time, and adverse events. The 5-year overall survival (OS), 5-year disease-specific survival (DSS), local recurrence, and metachronous tumor occurrence were also analyzed. Results We identified 224 tumors in 222 patients who were confirmed dead or had follow-up data longer than 5 years. After a median follow-up of 79 months, 5-year OS and DSS rates were 94.6% and 100%, respectively. The local recurrence rate (1.5%) was significantly higher in patients undergoing piecemeal resection (9.1%) compared to en bloc resection (0.6%), in histological incomplete resection patients compared to complete resection, and in non-R0 resection patients compared to R0 resection. The rates of total (≥6 mm) and carcinoma metachronous tumors after ESD without additional surgical resection were 18.9% (38/201) and 4.0% (8/201), respectively. Conclusions Long-term outcomes after ESD for superficial colorectal tumors are favorable. Patients should be surveyed for both local recurrence and metachronous tumors after ESD.
Background
Recently in Japan, the morbidity of colorectal polyp has been increasing. As a result, a large number of cases of colorectal polyps that are diagnosed and treated using colonoscopy has now ...increased, and clinical guidelines are needed for endoscopic management and surveillance after treatment.
Methods
Three committees the professional committee for making clinical questions (CQs) and statements by Japanese specialists, the expert panelist committee for rating statements by the modified Delphi method, and the evaluating committee by moderators were organized. Ten specialists for colorectal polyp management extracted the specific clinical statements from articles published between 1983 and September 2011 obtained from PubMed and a secondary database, and developed the CQs and statements. Basically, statements were made according to the GRADE system. The expert panel individually rated the clinical statements using a modified Delphi approach, in which a clinical statement receiving a median score greater than seven on a nine-point scale from the panel was regarded as valid.
Results
The professional committee created 91CQs and statements for the current concept and diagnosis/treatment of various colorectal polyps including epidemiology, screening, pathophysiology, definition and classification, diagnosis, treatment/management, practical treatment, complications and surveillance after treatment, and other colorectal lesions (submucosal tumors, nonneoplastic polyps, polyposis, hereditary tumors, ulcerative colitis-associated tumor/carcinoma).
Conclusions
After evaluation by the moderators, evidence-based clinical guidelines for management of colorectal polyps have been proposed for 2014.
Hepatocellular carcinoma (HCC) is one of the most common malignancies worldwide and its incidence is still increasing. While the primary curative treatment for HCC is surgical resection, a major ...obstacle for the treatment of HCC is the high frequency of tumor recurrence even after curative resection. Effective palliative treatment is hindered by the evidence that HCC is frequently resistant to conventional chemotherapy and radiotherapy. Targeted therapy which specifically inhibits molecular abnormalities has emerged as a novel approach for the innovative and effective medical treatment of malignancies. In order to fulfill this promise there is an urgent need to identify the optimal targets for the treatment of HCC. A multi-kinase angiogenesis inhibitor, sorafenib, has been revealed as the first agent to show favorable overall survival in patients with advanced HCC. A new era of HCC treatment has arrived, but there has been limited improvement in survival benefits with the status quo. This review summarizes molecular targeted therapy for HCC, with a focus on angiogenesis, growth signaling, and mitosis, as well as a promising concept, “cancer stemness” for the current and potential next strategies of HCC treatment.
Background and Aim
Detecting blood content in the gastrointestinal tract is one of the crucial applications of capsule endoscopy (CE). The suspected blood indicator (SBI) is a conventional tool used ...to automatically tag images depicting possible bleeding in the reading system. We aim to develop a deep learning‐based system to detect blood content in images and compare its performance with that of the SBI.
Methods
We trained a deep convolutional neural network (CNN) system, using 27 847 CE images (6503 images depicting blood content from 29 patients and 21 344 images of normal mucosa from 12 patients). We assessed its performance by calculating the area under the receiver operating characteristic curve (ROC‐AUC) and its sensitivity, specificity, and accuracy, using an independent test set of 10 208 small‐bowel images (208 images depicting blood content and 10 000 images of normal mucosa). The performance of the CNN was compared with that of the SBI, in individual image analysis, using the same test set.
Results
The AUC for the detection of blood content was 0.9998. The sensitivity, specificity, and accuracy of the CNN were 96.63%, 99.96%, and 99.89%, respectively, at a cut‐off value of 0.5 for the probability score, which were significantly higher than those of the SBI (76.92%, 99.82%, and 99.35%, respectively). The trained CNN required 250 s to evaluate 10 208 test images.
Conclusions
We developed and tested the CNN‐based detection system for blood content in CE images. This system has the potential to outperform the SBI system, and the patient‐level analyses on larger studies are required.
At present, there are many narrow band imaging (NBI) magnifying observation classifications for colorectal tumor in Japan. To internationally standardize the NBI observation criteria, a simple ...classification system is required. When a colorectal tumor is closely observed using the recent high‐resolution videocolonoscope, a pit‐like pattern on the tumor can be observed to a certain degree without magnification. In the symposium we could have a consensus that we will name the pit‐like pattern as ‘surface pattern.’ Using the NBI system, the microvessels on the tumor surface can also be recognized to a certain degree. When the NBI system is used, the structure is emphasized, and consequently, the surface pattern can be recognized easily. Recently, an international cooperative group was formed and consists of members from Japan, the USA and Europe, which is named as the Colon Tumor NBI Interest Group. This group has developed a simple category classification (NBI international colorectal endoscopic NICE classification), which classifies colorectal tumors into types 1−3 even by closely observing colorectal tumors using a high‐resolution videocolonoscope (Validation study is now ongoing by Colon Tumor NBI Interest Group.). The key advantage of this is simplification of the NBI classification. Although the magnifying observation is the best for getting detailed NBI findings, both close observation and magnifying observation using the NICE classification might give almost similar results. Of course the NICE classification can be used more precisely with magnification. In this report we also refer the issues on NBI magnification, which should be solved as early as possible.
The interaction between the nervous system and the immune system has recently been well-recognized. Vagus nerve stimulation (VNS) presents potential as an anti-inflammatory therapy through activation ...of neuroimmune pathways. Detailed understanding of the neuroimmune pathways VNS evokes is critical in order to successfully use it in the clinic for the treatment of acute kidney injury, in which inflammation plays an important role. In this review, we describe recent findings regarding VNS-induced neuroimmune pathways responsible for anti-inflammation and tissue protection.
Although advanced high-volume centers have reported good outcomes of colorectal endoscopic submucosal dissection (ESD), a limited number of highly skilled experts in specialized institutions ...performed these procedures. We undertook a retrospective multicenter survey, which included nonspecialized hospitals, to investigate the clinical outcomes of colorectal ESD.
We recruited 1233 consecutive patients with 1259 colorectal tumors resected by ESD at 12 institutions. We evaluated the en bloc resection rate, histologic complete resection rate, curative (R0) resection rate, adverse events, and the long-term prognoses, including local recurrence, metachronous tumor development, and survival rate.
The en bloc, histologic complete, and R0 resection rates were 92.6%, 87.4%, and 83.7%, respectively. The delayed bleeding, intraoperative perforation, and delayed perforation rates were 3.7%, 3.4%, and .4%, respectively. The long-term outcomes analysis included 1091 patients (88.4%). Local recurrences occurred in 1.7%, and metachronous tumors (>5 mm) developed in 11.0% of the patients. The 3- and 5-year overall survival rates were 95.1% and 92.3%, respectively. The number of colonic tumors, severe submucosal fibrosis, and en bloc resection rates were significantly higher in the high-volume centers (Group H) than those in the low-volume centers (Group L). The average tumor size in Group H was significantly larger than that in Group L.
Colorectal ESDs are feasible, have acceptable adverse event risks, and favorable long-term prognoses. (Clinical trial registration number: UMIN000016197.)
Backgrounds and Aims The Japan NBI Expert Team (JNET) classification is the first universal narrow-band imaging magnifying endoscopic classification of colorectal tumors. Considering each type in ...this classification, the diagnostic ability of Type 2B is the weakest. Generally, clinical behavior is believed to be different in each gross type of colorectal tumor. We evaluated the differences in the diagnostic performance of JNET classification for each gross type (polypoid and superficial) and examined whether the diagnostic performance of Type 2B could be improved by subtyping. Methods We analyzed 2933 consecutive cases of colorectal lesions, including 136 hyperplastic polyps/sessile serrated polyps, 1926 low-grade dysplasias (LGDs), 571 high-grade dysplasias (HGDs), and 300 submucosal (SM) carcinomas. We classified lesions as polypoid and superficial type and compared the diagnostic performance of the classification system in each type. Additionally, we subtyped Type 2B into 2B-low and 2B-high based on the level of irregularity in surface and vessel patterns, and we evaluated the relationship between the subtypes and histology, as analyzed separately for polypoid and superficial types. We also estimated interobserver and intraobserver variability. Results The diagnostic performance of JNET classification did not differ significantly between polypoid and superficial lesions. Ninety-nine percent of Type 2B-low lesions were LGDs, HGDs, or superficial submucosal invasive (SM-s) carcinomas. In contrast, 60% of Type 2B-high lesions were deep submucosal invasive (SM-d) carcinomas. The results were not different between each gross type. Interobserver and intraobserver agreements for Type 2B subtyping were good, with kappa values of .743 and .786, respectively. Conclusions Type 2B subtyping may be useful for identifying lesions that are appropriate for endoscopic resection. JNET classification and Type 2B sub classification are useful criteria, regardless of gross type.
PDF
