Endoscopic submucosal dissection for colorectal neoplasms: Risk factors for local recurrence and long-term surveillance

Objectives

Endoscopic submucosal dissection (ESD) is an effective procedure for the en bloc resection of colorectal neoplasms. However, risk factors for local recurrence after ESD have not been identified. This study aimed to evaluate such risk factors after ESD for colorectal neoplasms.

Methods

This retrospective study included 1344 patients with 1539 consecutive colorectal lesions who underwent ESD between September 2003 and December 2019. We investigated various factors associated with local recurrence in these patients. The main outcomes were the incidence of local recurrence and its relationship with clinicopathological factors during long-term surveillance.

Results

The en bloc resection rate was 98.6%, the R0 resection rate was 97.2%, and the histologically complete resection rate was 92.7%. Local recurrence was observed in 7/1344 (0.5%) patients and the median follow-up period was 72 months (range 4-195 months). The incidence of local recurrence was significantly higher in lesions ≥40 mm in diameter (hazard ratio [HR] 15.68 [1.88-130.5]; p = 0.011), piecemeal resection (HR 48.42 [10.7-218.7]; p < 0.001), non-R0 resection (HR 41.05 [9.025-186.7]; p < 0.001), histologically incomplete resection (HR 16.23 [3.627-72.63]; p<0.001), and severe fibrosis (F2; HR 9.523 [1.14-79.3]; p = 0.037).

Conclusions

Five risk factors for local recurrence after ESD were identified. Patients with such factors should undergo careful surveillance colonoscopy.

Diagnostic performance of endocytoscopy with normal pit-like structure sign for colorectal low-grade adenoma compared with conventional modalities

Objectives

A "resect-and-discard" strategy has been proposed for diminutive adenomas in the colorectum. However, this strategy is sometimes difficult to implement because of the lack of confidence in differentiating low-grade adenoma (LGA) from advanced lesions such as high-grade adenoma or carcinoma. To perform real-time precise diagnosis of LGA with high confidence, we assessed whether endocytoscopy (EC) diagnosis, considering normal pit-like structure (NP-sign), an excellent indicator of LGA, could have additional diagnostic potential compared with conventional modalities.

Methods

All the neoplastic lesions that were observed by non-magnifying narrow-band imaging (NBI), magnifying NBI (M-NBI), magnifying pit pattern, and EC prior to pathological examination between 2005 and 2018 were retrospectively investigated. The neoplastic lesions were classified into two categories: LGA and other neoplastic lesions. We assessed the differential diagnostic ability of EC with NP-sign between LGA and other neoplastic lesions compared with that of NBI, M-NBI, pit pattern, and conventional EC in terms of sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC).

Results

A total of 1376 lesions from 1097 patients were eligible. The specificity (94.9%), accuracy (91.5%), and area under the receiver operating characteristic curve (0.95) of EC with NP-sign were significantly higher than those of NBI, M-NBI, pit pattern, and conventional EC.

Conclusions

EC diagnosis with NP-sign has significantly higher diagnostic performance for predicting colorectal LGA compared with the conventional modalities and enables stratification of neoplastic lesions for "resect-and-discard" with higher confidence.

Performance evaluation of a computer-aided polyp detection system with artificial intelligence for colonoscopy

OBJECTIVES

A computer-aided detection (CAD) system was developed to support the detection of colorectal lesions by deep learning using video images of lesions and normal mucosa recorded during colonoscopy. The study's purpose was to evaluate the stand-alone performance of this device under blinded conditions.

METHODS

This multicenter prospective observational study was conducted at four Japanese institutions. We used 326 videos of colonoscopies recorded with patient consent at institutions in which the Ethics Committees approved the study. The sensitivity of successful detection of the CAD system was calculated using the target lesions, which were detected by adjudicators from two facilities for each lesion appearance frame; inconsistencies were settled by consensus. Successful detection was defined as display of the detection flag on the lesion for more than 0.5 s within 3 s of appearance.

RESULTS

Of the 556 target lesions from 185 cases, detection success sensitivity was 97.5% (95% confidence interval [CI] 95.8-98.5%). The "successful detection sensitivity per colonoscopy" was 93% (95% CI 88.3-95.8%). For the frame-based sensitivity, specificity, positive predictive value, and negative predictive value were 86.6% (95% CI 84.8-88.4%), 84.7% (95% CI 83.8-85.6%), 34.9% (95% CI 32.3-37.4%), and 98.2% (95% CI 97.8-98.5%), respectively.

TRIAL REGISTRATION

University Hospital Medical Information Network (UMIN000044622).

The "Watch and Wait" Method After Chemoradiotherapy for Rectal Cancer Requiring Abdominoperineal Resection

The present study examined the therapeutic effects of preoperative neoadjuvant chemoradiation therapy (NACRT) and predictive factors for complete clinical remission, compared the prognosis and costs of abdominoperineal resection (APR) and the "watch and wait" method (WW), and evaluated the usefulness of WW. In our department, patients with stage II-III lower rectal cancer requiring APR receive NACRT. NACRT was performed as a preoperative treatment (52 Gy + S-1: 80-120 mg/day × 25 days). Eight weeks after the completion of NACRT, rectal examination, endoscopic, computed tomography, and magnetic resonance imaging findings were evaluated to assess its therapeutic effects. APR was indicated for patients in whom endoscopic findings suggested a residual tumor in which a deep ulcer or marginal swelling remained or lymph node metastasis. However, WW was selected for patients who refused APR after informed consent was obtained. In the APR and WW groups, 5- and 20-year treatment costs after CRT were calculated using the Medical Fee Points of Japan in 2020. No significant differences were observed in 3-year disease-free survival rates for either parameter between the two groups. Regarding expenses, treatment costs were lower in the WW group than in the APR group. Organ preservation using active surveillance with CRT for rectal cancer requiring APR is feasible with the achievement of endoluminal complete remission.

Whole slide image-based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

OBJECTIVES

Lymph node metastasis (LNM) prediction for T1 colorectal cancer (CRC) is critical for determining the need for surgery after endoscopic resection because LNM occurs in 10%. We aimed to develop a novel artificial intelligence (AI) system using whole slide images (WSIs) to predict LNM.

METHODS

We conducted a retrospective single center study. To train and test the AI model, we included LNM status-confirmed T1 and T2 CRC between April 2001 and October 2021. These lesions were divided into two cohorts: training (T1 and T2) and testing (T1). WSIs were cropped into small patches and clustered by unsupervised K-means. The percentage of patches belonging to each cluster was calculated from each WSI. Each cluster's percentage, sex, and tumor location were extracted and learned using the random forest algorithm. We calculated the areas under the receiver operating characteristic curves (AUCs) to identify the LNM and the rate of over-surgery of the AI model and the guidelines.

RESULTS

The training cohort contained 217 T1 and 268 T2 CRCs, while 100 T1 cases (LNM-positivity 15%) were the test cohort. The AUC of the AI system for the test cohort was 0.74 (95% confidence interval [CI] 0.58-0.86), and 0.52 (95% CI 0.50-0.55) using the guidelines criteria (P = 0.0028). This AI model could reduce the 21% of over-surgery compared to the guidelines.

CONCLUSION

We developed a pathologist-independent predictive model for LNM in T1 CRC using WSI for determination of the need for surgery after endoscopic resection.

TRIAL REGISTRATION

UMIN Clinical Trials Registry (UMIN000046992, https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000053590).

Use of advanced endoscopic technology for optical characterization of neoplasia in patients with ulcerative colitis: Systematic review

OBJECTIVES

Advances in endoscopic technology, including magnifying and image-enhanced techniques, have been attracting increasing attention for the optical characterization of colorectal lesions. These techniques are being implemented into clinical practice as cost-effective and real-time approaches. Additionally, with the recent progress in endoscopic interventions, endoscopic resection is gaining acceptance as a treatment option in patients with ulcerative colitis (UC). Therefore, accurate preoperative characterization of lesions is now required. However, lesion characterization in patients with UC may be difficult because UC is often affected by inflammation, and it may be characterized by a distinct "bottom-up" growth pattern, and even expert endoscopists have relatively little experience with such cases. In this systematic review, we assessed the current status and limitations of the use of optical characterization of lesions in patients with UC.

METHODS

A literature search of online databases (MEDLINE via PubMed and CENTRAL via the Cochrane Library) was performed from 1 January 2000 to 30 November 2021.

RESULTS

The database search initially identified 748 unique articles. Finally, 25 studies were included in the systematic review: 23 focused on differentiation of neoplasia from non-neoplasia, one focused on differentiation of UC-associated neoplasia from sporadic neoplasia, and one focused on differentiation of low-grade dysplasia from high-grade dysplasia and cancer.

CONCLUSIONS

Optical characterization of neoplasia in patients with UC, even using advanced endoscopic technology, is still challenging and several issues remain to be addressed. We believe that the information revealed in this review will encourage researchers to commit to the improvement of optical diagnostics for UC-associated lesions.

Current problems and perspectives of pathological risk factors for lymph node metastasis in T1 colorectal cancer: Systematic review

With the prevalence of endoscopic submucosal dissection and endoscopic full thickness resection, which enable complete resection of T1 colorectal cancer with a negative margin, the treatment strategy following endoscopic resection has become more important. The necessity of secondary surgical resection is determined on the basis of the risk of lymph node metastasis according to the histopathological findings of resected specimens because ~10% of T1 colorectal cancer cases have lymph node metastasis. The current Japanese treatment guidelines state four risk factors for lymph node metastasis: lymphovascular invasion, histological differentiation, depth of submucosal invasion, and tumor budding. These guidelines have succeeded in stratifying the low-risk group for lymph node metastasis, in which endoscopic resection alone is acceptable for cure. On the other hand, there are some problems: there is variation in diagnosis methods and low interobserver agreement for each pathological factor and 90% of surgical resections are unnecessary, with lymph node metastasis negativity. To ensure patients with T1 colorectal cancer receive more appropriate treatment, these problems should be addressed. In this systematic review, we gave some suggestions to these practical issues of four pathological factors as predictors.

Beyond complete endoscopic healing: Goblet appearance using an endocytoscope to predict future sustained clinical remission in ulcerative colitis

OBJECTIVES

Complete endoscopic healing, defined as Mayo endoscopic score (MES) = 0, is an optimal target in the treatment of ulcerative colitis (UC). However, some patients with MES = 0 show clinical relapse within 12 months. Histologic goblet mucin depletion has emerged as a predictor of clinical relapse in patients with MES = 0. We observed goblet depletion in vivo using an endocytoscope, and analyzed the association between goblet appearance and future prognosis in UC patients.

METHODS

In this retrospective cohort study, all enrolled UC patients had MES = 0 and confirmed clinical remission between October 2016 and March 2020. We classified the patients into two groups according to the goblet appearance status: preserved-goblet and depleted-goblet groups. We followed the patients until March 2021 and evaluated the difference in cumulative clinical relapse rates between the two groups.

RESULTS

We identified 125 patients with MES = 0 as the study subjects. Five patients were subsequently excluded. Thus, we analyzed the data for 120 patients, of whom 39 were classified as the preserved-goblet group and 81 as the depleted-goblet group. The patients were followed-up for a median of 549 days. During follow-up, the depleted-goblet group had a significantly higher cumulative clinical relapse rate than the preserved-goblet group (19% [15/81] vs. 5% [2/39], respectively; P = 0.02).

CONCLUSIONS

Observing goblet appearance in vivo allowed us to better predict the future prognosis of UC patients with MES = 0. This approach may assist clinicians with onsite decision-making regarding treatment interventions without a biopsy.

Combined endocytoscopy with pit pattern diagnosis in ulcerative colitis-associated neoplasia: Pilot study

OBJECTIVES

Ulcerative colitis-associated neoplasias (UCAN) are often flat with an indistinct boundary from surrounding tissues, which makes differentiating UCAN from non-neoplasias difficult. Pit pattern (PIT) has been reported as one of the most effective indicators to identify UCAN. However, regenerated mucosa is also often diagnosed as a neoplastic PIT. Endocytoscopy (EC) allows visualization of cell nuclei. The aim of this retrospective study was to demonstrate the diagnostic ability of combined EC irregularly-formed nuclei with PIT (EC-IN-PIT) diagnosis to identify UCAN.

METHODS

This study involved patients with ulcerative colitis whose lesions were observed by EC. Each lesion was diagnosed by two independent expert endoscopists, using two types of diagnostic strategies: PIT alone and EC-IN-PIT. We evaluated and compared the diagnostic abilities of PIT alone and EC-IN-PIT. We also examined the difference in the diagnostic abilities of an EC-IN-PIT diagnosis according to endoscopic inflammation severity.

RESULTS

We analyzed 103 lesions from 62 patients; 23 lesions were UCAN and 80 were non-neoplastic. EC-IN-PIT diagnosis had a significantly higher specificity and accuracy compared with PIT alone: 84% versus 58% (P < 0.001), and 88% versus 67% (P < 0.01), respectively. The specificity and accuracy were significantly higher for Mayo endoscopic score (MES) 0-1 than MES 2-3: 93% versus 68% (P < 0.001) and 95% versus 74% (P < 0.001), respectively.

CONCLUSIONS

Our novel EC-IN-PIT strategy had a better diagnostic ability than PIT alone to predict UCAN from suspected and initially detected lesions using conventional colonoscopy. UMIN clinical trial (UMIN000040698).

Impact of the clinical use of artificial intelligence-assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score-matched study (with video)

BACKGROUND AND AIMS

Recently, the use of computer-aided detection (CADe) for colonoscopy has been investigated to improve the adenoma detection rate (ADR). We aimed to assess the efficacy of a regulatory-approved CADe in a large-scale study with high numbers of patients and endoscopists.

METHODS

This was a propensity score-matched prospective study that took place at a university hospital between July 2020 and December 2020. We recruited patients aged ≥20 years who were scheduled for colonoscopy. Patients with polyposis, inflammatory bowel disease, or incomplete colonoscopy were excluded. We used a regulatory-approved CADe system and conducted a propensity score matching-based comparison of the ADR between patients examined with and without CADe as the primary outcome.

RESULTS

During the study period, 2261 patients underwent colonoscopy with the CADe system or routine colonoscopy, and 172 patients were excluded in accordance with the exclusion criteria. Thirty endoscopists (9 nonexperts and 21 experts) were involved in this study. Propensity score matching was conducted using 5 factors, resulting in 1836 patients included in the analysis (918 patients in each group). The ADR was significantly higher in the CADe group than in the control group (26.4% vs 19.9%, respectively; relative risk, 1.32; 95% confidence interval, 1.12-1.57); however, there was no significant increase in the advanced neoplasia detection rate (3.7% vs 2.9%, respectively).

CONCLUSIONS

The use of the CADe system for colonoscopy significantly increased the ADR in a large-scale prospective study including 30 endoscopists (Clinical trial registration number: UMIN000040677.).

Clinicopathological features of small T1 colorectal cancers

BACKGROUND

Although small colorectal neoplasms (< 10 mm) are often easily resected endoscopically and are considered to have less malignant potential compared with large neoplasms (≥ 10 mm), some are invasive to the submucosa.

AIM

To clarify the clinicopathological features of small T1 colorectal cancers.

METHODS

Of 32025 colorectal lesions between April 2001 and March 2018, a total of 1152 T1 colorectal cancers resected endoscopically or surgically were included in this study and were divided into two groups by tumor size: a small group (< 10 mm) and a large group (≥ 10 mm). We compared clinicopathological factors including lymph node metastasis (LNM) between the two groups.

RESULTS

The incidence of small T1 cancers was 10.1% (116/1152). The percentage of initial endoscopic treatment in small group was significantly higher than in large group (< 10 mm 74.1% vs ≥ 10 mm 60.2%, P < 0.01). In the surgical resection cohort (n = 798), the rate of LNM did not significantly differ between the two groups (small 12.3% vs large 10.9%, P = 0.70). In addition, there were also no significant differences between the two groups in pathological factors such as histological grade, vascular invasion, or lymphatic invasion.

CONCLUSION

Because there was no significant difference in the rate of LNM between small and large T1 colorectal cancers, the requirement for additional surgical resection should be determined according to pathological findings, regardless of tumor size.

Efficacy and safety of oral sulfate solution for bowel preparation in Japanese patients undergoing colonoscopy: Noninferiority-based, randomized, controlled study

OBJECTIVES

To compare the efficacy and safety of oral sulfate solution administered using the same-day dose and the split-dose regimens with those of polyethylene glycol plus ascorbate solution, used for bowel preparation in Japanese patients undergoing colonoscopy.

METHODS

This multicenter (n = 13), randomized, active-controlled, colonoscopist- and image evaluator-blinded, noninferiority study with parallel-group comparison recruited 632 patients from December 2018 to June 2019. Of these, 602 patients were divided into the oral sulfate solution same-day dose group (n = 200); oral sulfate solution split-dose group (n = 202); and polyethylene glycol plus ascorbate same-day dose group (n = 200). Differences in the efficacy rates between the polyethylene glycol plus ascorbate group and each oral sulfate solution group were calculated using the asymptotic method. The safety of the oral sulfate solution was evaluated, based on the occurrence of adverse events and reactions.

RESULTS

Both oral sulfate solution protocols were confirmed as noninferior to the polyethylene glycol plus ascorbate protocol for bowel-cleansing. The occurrence of adverse reactions was significantly lower in the oral sulfate solution same-day dose group than in the polyethylene glycol plus ascorbate group (P = 0.010). The occurrence of adverse reactions was not significantly different between the oral sulfate solution split-dose and the polyethylene glycol plus ascorbate group.

CONCLUSIONS

Oral sulfate solution is not only safe and efficacious but also not inferior to polyethylene glycol plus ascorbate solution (active control). It could be used for bowel preparation in Japanese patients scheduled for colonoscopy (Clinical trial registration number: NCT03794310).

Clinical and endoscopic characteristics of post-colonoscopy colorectal cancers detected within 10 years after a previous negative examination

Background and study aims We sometimes encounter colorectal cancer (CRC) that is discovered during the time interval between initial colonoscopy and the recommended follow-up examination. Although several studies reported such cases of CRC, most were based on registry data, which implied that the endoscopic quality was not consistent or guaranteed. We aimed to clarify these clinical and endoscopic characteristics at our high-volume center where a retrospective survey could be precisely performed.

Patients and methods We retrospectively analyzed patients with CRC who underwent endoscopic resection or surgery from April 2002 to December 2010, categorizing them into two groups: a “study group” of patients with a negative colonoscopy during the previous 10 years, and a “control group” of patients without a previous colonoscopy or with a previous colonoscopy more than 10 years prior.

Results A total of 2042 patients had CRC, among which 55 patients were classified into the study group and the remaining 1989 into the control group. The CRC cases in the study group showed a significant association with smaller (< 30 mm) tumor size (odds ratio [OR] 2.3; 95 % confidence interval [CI] 1.3–4.0) and proximal tumor site (OR 1.7; 95 %CI 0.9–2.9). In addition, right-sided and depressed-type T1 CRCs were significantly more common in the study group.

Conclusions Tumor size and location were associated with CRCs detected within 10 years after the negative examination. In addition, depressed-type T1 CRCs were more common. Therefore, we should pay more attention to small, right-sided, or depressed-type tumors in daily colonoscopy.

Clinical Efficacy of Endocytoscopy for Gastrointestinal Endoscopy

Endocytoscopy (EC) is a contact-type optical endoscope that allows in vivo cellular observation during gastrointestinal endoscopy and is now commercially available not only in Japan but also in Asian, European Union, and Middle Eastern countries. EC helps conduct a highly accurate pathological prediction without biopsy. Initially, EC was reported to be effective for esophageal diseases. Subsequently, its efficacy for stomach and colorectal diseases has been reported. In this narrative review, we searched for clinical studies that investigated the efficacy of EC. EC seems to accurately diagnose gastrointestinal diseases without biopsy. Most of the studies aimed to clarify the relationship between endocytoscopic findings of gastrointestinal neoplasia and pathological diagnosis. Some studies have investigated non-epithelial lesions or diseases, such as inflammatory bowel disease or infectious diseases. However, there are few high-level pieces of evidence, such as randomized trials; thus, further studies are needed.

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study

Background and study aims  Large adenomas are sometimes misidentified as cancers during colonoscopy and are surgically removed. To address this overtreatment, we developed an artificial intelligence (AI) tool that identified cancerous pathology in vivo with high specificity. We evaluated our AI tool under the supervision of a government agency to obtain regulatory approval. Patients and methods  The AI tool outputted three pathological class predictions (cancer, adenoma, or non-neoplastic) for endocytoscopic images obtained at 520-fold magnification and previously trained on 68,082 images from six academic centers. A validation test was developed, employing 500 endocytoscopic images taken from various parts of randomly selected 50 large (≥ 20 mm) colorectal lesions (10 images per lesion). An expert board labelled each of the 500 images with a histopathological diagnosis, which was made using endoscopic and histopathological images. The validation test was performed using the AI tool under a controlled environment. The primary outcome measure was the specificity in identifying cancer. Results  The validation test consisted of 30 cancers, 15 adenomas, and five non-neoplastic lesions. The AI tool could analyze 83.6 % of the images (418/500): 231 cancers, 152 adenomas, and 35 non-neoplastic lesions. Among the analyzable images, the AI tool identified the three pathological classes with an overall accuracy of 91.9 % (384/418, 95 % confidence interval [CI]: 88.8 %-94.3 %). Its sensitivity and specificity for differentiating cancer was 91.8 % (212/231, 95 % CI: 87.5 %-95.0 %) and 97.3 % (182/187, 95 % CI: 93.9 %-99.1 %), respectively. Conclusions  The newly developed AI system designed for endocytoscopy showed excellent specificity in identifying colorectal cancer.

Artificial Intelligence System to Determine Risk of T1 Colorectal Cancer Metastasis to Lymph Node

BACKGROUND & AIMS

In accordance with guidelines, most patients with T1 colorectal cancers (CRC) undergo surgical resection with lymph node dissection, despite the low incidence (∼10%) of metastasis to lymph nodes. To reduce unnecessary surgical resections, we used artificial intelligence to build a model to identify T1 colorectal tumors at risk for metastasis to lymph node and validated the model in a separate set of patients.

METHODS

We collected data from 3134 patients with T1 CRC treated at 6 hospitals in Japan from April 1997 through September 2017 (training cohort). We developed a machine-learning artificial neural network (ANN) using data on patients' age and sex, as well as tumor size, location, morphology, lymphatic and vascular invasion, and histologic grade. We then conducted the external validation on the ANN model using independent 939 patients at another hospital during the same period (validation cohort). We calculated areas under the receiver operator characteristics curves (AUCs) for the ability of the model and US guidelines to identify patients with lymph node metastases.

RESULTS

Lymph node metastases were found in 319 (10.2%) of 3134 patients in the training cohort and 79 (8.4%) of /939 patients in the validation cohort. In the validation cohort, the ANN model identified patients with lymph node metastases with an AUC of 0.83, whereas the guidelines identified patients with lymph node metastases with an AUC of 0.73 (P < .001). When the analysis was limited to patients with initial endoscopic resection (n = 517), the ANN model identified patients with lymph node metastases with an AUC of 0.84 and the guidelines identified these patients with an AUC of 0.77 (P = .005).

CONCLUSIONS

The ANN model outperformed guidelines in identifying patients with T1 CRCs who had lymph node metastases. This model might be used to determine which patients require additional surgery after endoscopic resection of T1 CRCs. UMIN Clinical Trials Registry no: UMIN000038609.

Short- and long-term outcomes of self-expanding metallic stent placement vs. emergency surgery for malignant colorectal obstruction

The European Society of Gastrointestinal Endoscopy does not recommend self-expanding metal stent (SEMS) placement as a bridge to surgery (BTS) for malignant colorectal obstruction (MCRO). However, no universally accepted consensus has been determined. The present study aimed to evaluate the short- and long-term outcomes of SEMS placement vs. emergency surgery (ES) for MCRO. Surgical resection of colorectal cancer was performed in 3,840 patients between April 2001 and June 2016. Of these, 93 patients had MCRO requiring emergency decompression. Only patients in whom the colorectal lesion was ultimately resected were included; thus, the present study included 62 patients treated with MCRO via SEMS placement as a BTS (n=25) or via ES (n=37). The rates of laparoscopic surgery, primary anastomosis, stoma formation, lymph node dissection, adverse events, 30-day mortality and disease-free survival were evaluated. The clinical success rate of SEMS placement was 92.0% (23/25). Compared with the ES group, the SEMS group had higher rates of laparoscopic surgery (68.0 vs. 2.7%; P<0.001) and primary anastomosis (88.0 vs. 51.4%; P=0.003), a greater number of dissected lymph nodes (30 vs. 18; P=0.001), and lower incidences of stoma formation (24.0 vs. 67.6%; P=0.002) and overall adverse events (24.0 vs. 62.2%; P=0.004). The 30-day mortality and disease-free survival of the SEMS group were not significantly different to that of the ES group (0 vs. 2.7%; P=1.000; log-rank test; P=0.10). In conclusion, as long as adverse events such as perforation are minimized, SEMS placement as a BTS could be a first treatment option for MCRO. The present study is registered in the University Hospital Medical Network Clinical Trials Registry (UMIN R000034868).

Current status and future perspective on artificial intelligence for lower endoscopy

The global incidence and mortality rate of colorectal cancer remains high. Colonoscopy is regarded as the gold standard examination for detecting and eradicating neoplastic lesions. However, there are some uncertainties in colonoscopy practice that are related to limitations in human performance. First, approximately one-fourth of colorectal neoplasms are missed on a single colonoscopy. Second, it is still difficult for non-experts to perform adequately regarding optical biopsy. Third, recording of some quality indicators (e.g. cecal intubation, bowel preparation, and withdrawal speed) which are related to adenoma detection rate, is sometimes incomplete. With recent improvements in machine learning techniques and advances in computer performance, artificial intelligence-assisted computer-aided diagnosis is being increasingly utilized by endoscopists. In particular, the emergence of deep-learning, data-driven machine learning techniques have made the development of computer-aided systems easier than that of conventional machine learning techniques, the former currently being considered the standard artificial intelligence engine of computer-aided diagnosis by colonoscopy. To date, computer-aided detection systems seem to have improved the rate of detection of neoplasms. Additionally, computer-aided characterization systems may have the potential to improve diagnostic accuracy in real-time clinical practice. Furthermore, some artificial intelligence-assisted systems that aim to improve the quality of colonoscopy have been reported. The implementation of computer-aided system clinical practice may provide additional benefits such as helping in educational poorly performing endoscopists and supporting real-time clinical decision-making. In this review, we have focused on computer-aided diagnosis during colonoscopy reported by gastroenterologists and discussed its status, limitations, and future prospects.

A novel Lugol's iodine staining technique to visualize the upper margin of the surgical anal canal intraoperatively for Hirschsprung disease: a case series

Background

In cases of Hirschsprung disease, complete and reproducible resection of the aganglionic bowel is ideal to achieve good postoperative bowel function. Reliable identification of the upper margin of the surgical anal canal, which is the squamous-columnar junction, is necessary during transanal pull-through. Here, we describe a novel staining technique using Lugol’s iodine stain to visualize the upper margin of the surgical anal canal.

Methods

Lugol’s iodine staining was performed in five patients with Hirschsprung disease treated using a single-stage laparoscopic transanal pull-through modified Swenson procedure. In two of these patients, endocytoscopic observation with ultra-high magnification was performed using methylene blue and crystal violet to mark the border of the squamous epithelium at 1 week before surgery. The alignment between the incisional line, which was revealed using Lugol’s iodine staining and endocytoscopic marking, was evaluated. Complications, including postoperative bowel dysfunction, were evaluated.

Results

In all cases, Lugol’s iodine staining produced a well-demarcated line. The endocytoscopic marking of the upper margin of the surgical anal canal was aligned with the line revealed by Lugol’s iodine staining. There were no complications associated with the transanal pull-through procedure, including postoperative bowel dysfunction.

Conclusions

Lugol’s iodine staining could be a safe and practical method to visualize the upper margin of the surgical anal canal intraoperatively. This finding may be useful for surgeons to make a consistent removal of the aganglionic bowel during surgery for Hirschsprung disease.

Endocytoscopic intramucosal capillary network changes and crypt architecture abnormalities can predict relapse in patients with an ulcerative colitis Mayo endoscopic score of 1

OBJECTIVES

Recent studies have suggested the necessity of therapeutic intervention for patients with ulcerative colitis at high risk of clinical relapse with a Mayo endoscopic score (MES) of 1. The aim of this retrospective cohort study was to demonstrate the impact of intramucosal capillary network changes and crypt architecture abnormalities to stratify the risk of relapse in patients with an MES of 1.

METHODS

All included patients had an MES of ≤1 and confirmed sustained clinical remission between October 2016 and April 2019. We classified patients with an MES of 1 as "intramucosal capillary/crypt (ICC)-active" or "ICC-inactive" using endocytoscopic evaluation. We followed patients until October 2019 or until relapse; the main outcome measure was the difference in clinical relapse-free rates between ICC-active and ICC-inactive patients with an MES of 1.

RESULTS

We included 224 patients and analyzed data for 218 (82 ICC-active and 54 ICC-active with an MES of 1 and 82 with an MES of 0). During follow-up, among the patients with an MES of 1, 30.5% (95% confidence interval 20.8-41.6; 25/82) of the patients relapsed in the ICC-active group and 5.6% (95% confidence interval 1.2-15.4; 3/54) of the patients relapsed in the ICC-inactive group. The ICC-inactive group had a significantly higher clinical relapse-free rate compared with the ICC-active group (P < 0.01).

CONCLUSIONS

In vivo intramucosal capillary network and crypt architecture patterns stratified the risk of clinical relapse in patients with an MES of 1 (UMIN 000032580; UMIN 000036359).

Treatment policy for colonic laterally spreading tumors based on each clinicopathologic feature of 4 subtypes: actual status of pseudo-depressed type

BACKGROUND AND AIMS

Laterally spreading tumors (LSTs) are originally classified into 4 subtypes. Pseudo-depressed nongranular types (LSTs-NG-PD) are gaining attention because of their high malignancy potential. Previous studies discussed the classification of nongranular (LST-NG) and granular types (LST-G); however, the actual condition or indication for endoscopic treatment of LSTs-NG-PD remains unclear. We aimed to compare the submucosal invasion pattern of LSTs-NG-PD with the other 3 subtypes.

METHODS

A total of 22,987 colonic neoplasms including 2822 LSTs were resected endoscopically or surgically at Showa University Northern Yokohama Hospital. In these LSTs, 322 (11.4%) were submucosal invasive carcinomas. We retrospectively evaluated the clinicopathologic features of LSTs divided into 4 subtypes. In 267 LSTs resected en bloc, their submucosal invasion site was further evaluated.

RESULTS

The frequency of LSTs in all colonic neoplasms was significantly higher in women (14.9%) than in men (11.0%). Rates of submucosal invasive carcinoma were .8% in the granular homogenous type (LSTs-G-H), 15.2% in the granular nodular mixed type (LSTs-G-M), 8.0% in the nongranular flat elevated type (LSTs-NG-F), and 42.5% in LSTs-NG-PD. Tumor size was associated with submucosal invasion rate in LSTs-NG-F and LSTs-NG-PD (P < .001). The multifocal invasion rate of LSTs-NG-PD (46.9%) was significantly higher than that of LSTs-G-M (7.9%) or LSTs-NG-F (11.8%). In LSTs-NG-PD, the invasion was significantly deeper (≥1000 μm) if observed in 1 site.

CONCLUSIONS

For LSTs-G-M and LSTs-NG-F that may have invaded the submucosa, en bloc resection could be considered. Considering that LSTs-NG-PD had a higher submucosal invasion rate, more multifocal invasive nature, and deeper invasion tendency, regardless if invasion was only observed in 1 site, than LSTs-NG-F, we should endoscopically distinguish LSTs-NG-PD from LSTs-NG-F and strictly adopt en bloc resection by endoscopic submucosal dissection or surgery for LSTs-NG-PD. (Clinical trial registration number: UMIN 000020261.).

Cost savings in colonoscopy with artificial intelligence-aided polyp diagnosis: an add-on analysis of a clinical trial (with video)

BACKGROUND AND AIMS

Artificial intelligence (AI) is being implemented in colonoscopy practice, but no study has investigated whether AI is cost saving. We aimed to quantify the cost reduction using AI as an aid in the optical diagnosis of colorectal polyps.

METHODS

This study is an add-on analysis of a clinical trial that investigated the performance of AI for differentiating colorectal polyps (ie, neoplastic versus non-neoplastic). We included all patients with diminutive (≤5 mm) rectosigmoid polyps in the analyses. The average colonoscopy cost was compared for 2 scenarios: (1) a diagnose-and-leave strategy supported by the AI prediction (ie, diminutive rectosigmoid polyps were not removed when predicted as non-neoplastic), and (2) a resect-all-polyps strategy. Gross annual costs for colonoscopies were also calculated based on the number and reimbursement of colonoscopies conducted under public health insurances in 4 countries.

RESULTS

Overall, 207 patients with 250 diminutive rectosigmoid polyps (104 neoplastic, 144 non-neoplastic, and 2 indeterminate) were included. AI correctly differentiated neoplastic polyps with 93.3% sensitivity, 95.2% specificity, and 95.2% negative predictive value. Thus, 105 polyps were removed and 145 were left under the diagnose-and-leave strategy, which was estimated to reduce the average colonoscopy cost and the gross annual reimbursement for colonoscopies by 18.9% and US$149.2 million in Japan, 6.9% and US$12.3 million in England, 7.6% and US$1.1 million in Norway, and 10.9% and US$85.2 million in the United States, respectively, compared with the resect-all-polyps strategy.

CONCLUSIONS

The use of AI to enable the diagnose-and-leave strategy results in substantial cost reductions for colonoscopy.

Small invasive colon cancer with adenoma observed by endocytoscopy: A case report

BACKGROUND

Endocytoscopy is a next-generation endoscopic system that facilitates real-time histopathologic endoscopic diagnosis of colorectal lesions by virtue of its 520 × maximum magnification.

CASE SUMMARY

We present the case of a 63-year-old man with sigmoid colon cancer who was regularly referred for follow-up colonoscopy after endoscopic resection of T1 rectal cancer. Colonoscopy revealed a 12 mm reddish polyp, including a depression and a flat area in the sigmoid colon. Endocytoscopic observation showed unclear gland formation and agglomeration of distorted nuclei (depression), suggesting a submucosal invasive (T1) cancer. In the flat area, slit-like smooth lumens and regular pattern of fusiform nuclei were found, suggesting an adenoma. On the basis of these endocytoscopic findings, we predicted this lesion as T1 cancer (depression) with adenoma (flat area) and performed endoscopic resection corresponding to the final histopathological diagnosis.

CONCLUSION

We could perform an optical diagnosis of T1 sigmoid cancer with adenoma by using endocytoscopy before treatment.

How Far Will Clinical Application of AI Applications Advance for Colorectal Cancer Diagnosis?

Integrating artificial intelligence (AI) applications into colonoscopy practice is being accelerated as deep learning technologies emerge. In this field, most of the preceding research has focused on polyp detection and characterization, which can mitigate inherent human errors accompanying colonoscopy procedures. On the other hand, more challenging research areas are currently capturing attention: the automated prediction of invasive cancers. Colorectal cancers (CRCs) harbor potential lymph node metastasis when they invade deeply into submucosal layers, which should be resected surgically rather than endoscopically. However, pretreatment discrimination of deeply invasive submucosal CRCs is considered difficult, according to previous prospective studies (e.g., <70% sensitivity), leading to an increased number of unnecessary surgeries for large adenomas or slightly invasive submucosal CRCs. AI is now expected to overcome this challenging hurdle because it is considered to provide better performance in predicting invasive cancer than non-expert endoscopists. In this review, we introduce five relevant publications in this area. Unfortunately, progress in this research area is in a very preliminary phase, compared to that of automated polyp detection and characterization, because of the lack of number of invasive CRCs used for machine learning. However, this issue will be overcome with more target images and cases. The research field of AI for invasive CRCs is just starting but could be a game changer of patient care in the near future, given rapidly growing technologies, and research will gradually increase.

Endocytoscopy for the differential diagnosis of colorectal low-grade adenoma: a novel possibility for the "resect and discard" strategy

BACKGROUND AND AIMS

Endocytoscopy, a next-generation endoscopic system, facilitates observation at a maximum magnification of ×520. To our knowledge, no study has reported high-precision diagnosis of colorectal low-grade adenoma, endoscopically. We aimed to reveal which endocytoscopic findings may be used as indicators of low-grade adenoma and to assess whether a "resect and discard" strategy using endocytoscopy is feasible.

METHODS

Lesions diagnosable with endocytoscopy were examined retrospectively between May 2005 and July 2017. A normal pit-like structure in endocytoscopic images was considered a normal pit (NP) sign and used as an indicator of low-grade adenoma. The primary outcome was the diagnostic accuracy of the NP sign for low-grade adenoma. We evaluated agreement rates between endocytoscopic and pathologic diagnosis for surveillance colonoscopy interval recommendation (SCIR) and performed a validation study to verify the agreement rates.

RESULTS

For 748 lesions in 573 cases diagnosed as colorectal adenoma using endocytoscopy, the results were as follows: sensitivity of the NP sign for low-grade adenoma, 85.0%; specificity, 90.7%; positive predictive value, 96.6%; negative predictive value, 66.1%; accuracy, 86.4%; and positive likelihood ratio, 9.2 (P < .001). The agreement rate between endocytoscopic and pathologic diagnosis for SCIR was 94.4% (95% confidence interval [CI], 92.2%-96.1%; P < .001) under United States guidelines and 96.3% (95% CI, 94.5%-97.7%; P < .001) under European Union guidelines. All inter- and intraobserver agreement rates for expert and nonexpert endoscopists had κ values ≥0.8 except one nonexpert pair.

CONCLUSIONS

Endocytoscopy is an effective modality in determining the differential diagnosis of colorectal low-grade adenoma. (University Hospital Medical Information Network Clinical Trials database registration number: UMIN000018623.).

Endocytoscopy with NBI has the potential to correctly diagnose diminutive colorectal polyps that are difficult to diagnose using conventional NBI

Background and study aims  Real-time diagnosis of colorectal polyps is needed to prevent unnecessary resection of benign polyps. The vessels in hyperplastic polyps sometimes mimic the characteristic meshed capillary network of neoplastic lesions on non-magnified narrow-band imaging (NBI). Endocytoscopy in conjunction with NBI (EC-NBI) enables more detailed vessel observation. The current study evaluated whether EC-NBI can accurately diagnose small colorectal lesions with visible vessels on non-magnified NBI. Patients and methods  This retrospective study was conducted from January to December 2016. During colonoscopy, lesion images were obtained using NBI and EC-NBI. On EC-NBI, lesions were classified as having "clear," "unclear," or "invisible" blood vessel margins. All specimens were resected and pathologically examined, and the association between vessel margin findings and pathological diagnosis was assessed. The lesion surface to vessel depth was measured in clear, unclear, and invisible lesions. Results  Among 114 adenomas, 108 were clear, while six were unclear. Among 36 hyperplastic polyps, eight were clear, while 28 were unclear. A micro-network (MN) pattern was seen in 106 of 114 adenomas, and four of 36 hyperplastic polyps. The sensitivity, specificity, correct diagnostic rate, and positive and negative predictive values of clear blood vessel margins or a MN pattern as an adenoma index were 98.2 %, 69.4 %, 91.3 %, 91.1 %, and 92.6 %, respectively. EC-NBI correctly diagnosed 69.4 % (25/36) of hyperplastic polyps. The lesion surface-blood vessel distance was greater in unclear versus clear lesions ( P  < 0.001), and invisible versus unclear lesions ( P  < 0.001). Conclusions  EC-NBI may effectively differentiate hyperplastic polyps with visible vessels from adenomas. Blood vessel depth affects visibility.

Artificial intelligence and colonoscopy: Current status and future perspectives

BACKGROUND AND AIM

Application of artificial intelligence in medicine is now attracting substantial attention. In the field of gastrointestinal endoscopy, computer-aided diagnosis (CAD) for colonoscopy is the most investigated area, although it is still in the preclinical phase. Because colonoscopy is carried out by humans, it is inherently an imperfect procedure. CAD assistance is expected to improve its quality regarding automated polyp detection and characterization (i.e. predicting the polyp's pathology). It could help prevent endoscopists from missing polyps as well as provide a precise optical diagnosis for those detected. Ultimately, these functions that CAD provides could produce a higher adenoma detection rate and reduce the cost of polypectomy for hyperplastic polyps.

METHODS AND RESULTS

Currently, research on automated polyp detection has been limited to experimental assessments using an algorithm based on ex vivo videos or static images. Performance for clinical use was reported to have >90% sensitivity with acceptable specificity. In contrast, research on automated polyp characterization seems to surpass that for polyp detection. Prospective studies of in vivo use of artificial intelligence technologies have been reported by several groups, some of which showed a >90% negative predictive value for differentiating diminutive (≤5 mm) rectosigmoid adenomas, which exceeded the threshold for optical biopsy.

CONCLUSION

We introduce the potential of using CAD for colonoscopy and describe the most recent conditions for regulatory approval for artificial intelligence-assisted medical devices.

Clinicopathological features of T1 colorectal carcinomas with skip lymphovascular invasion

With recent advances in endoscopic treatment, many T1 colorectal carcinomas (CRCs) are resected endoscopically with a negative margin. However, some lesions exhibit skip lymphovascular invasion (SLVI), which is defined as the discontinuous foci of the tumor cells within the colon wall. The aim of the present study was to reveal the clinicopathological features of T1 CRCs with SLVI and validate the Japanese guidelines regarding SLVI. A total of 741 patients with T1 CRCs that were resected surgically between April 2001 and October 2016 in our hospital were divided into two groups: With SLVI and without SLVI. Clinicopathological features compared between the two groups were patient's gender, age, tumor size, location, morphology, lymphovascular invasion, tumor differentiation, tumor budding and lymph node metastasis. The incidence of T1 CRCs with SLVI was 0.9% (7/741). All cases with SLVI were found in the sigmoid colon or rectum. T1 CRCs with SLVI showed significantly higher rates of lymphovascular invasion than those without SLVI (P<0.01). In conclusion, lymphovascular invasion was a significant risk factor for SLVI in T1 CRCs, and for which surgical colectomy was necessary. The Japanese guidelines are appropriate regarding SLVI. Registered in the University Hospital Medical Network Clinical Trials Registry (UMIN000027097).

New-generation full-spectrum endoscopy versus standard forward-viewing colonoscopy: a multicenter, randomized, tandem colonoscopy trial (J-FUSE Study)

BACKGROUND AND AIMS

Although colonoscopy is the criterion standard for detection of colorectal adenomas, some adenomas are missed. Full-spectrum endoscopy (FUSE) allows for observation with a 330-degree angle of view, which is expected to decrease the miss rate. However, no consensus has been reached regarding the superiority of FUSE over standard forward-viewing colonoscopy (SFVC) for detection of adenomas; we therefore compared new-generation FUSE and SFVC regarding colorectal adenoma miss rate (AMR) in this, the first reported randomized control trial using new-generation FUSE.

METHODS

We enrolled individuals aged 40 to 75 years who had been referred for screening, surveillance, fecal occult blood test positivity, or symptoms in a prospective randomized trial of tandem colonoscopy in 8 institutions. Patients were randomly assigned (1:1) via computer-generated stratified randomization. Neither the endoscopists nor patients were blinded to the allocation. The primary endpoint was AMR per patient (AMR-PP).

RESULTS

We enrolled 345 patients and included 319 in the per-protocol analyses. AMR-PP was significantly lower with FUSE (11.7%; 95% confidence interval [CI], 8.0%-15.4%) than with SFVC (22.9%; 95% CI, 17.5%-28.3%; P < .001). AMR-PP for lesions ≤5 mm in size was significantly lower with FUSE (10.4%; 95% CI, 6.5%-14.3%) than with SFVC (20.0%; 95% CI, 14.4%-25.6%; P = .0057). Furthermore, AMR-PP in the ascending colon was significantly lower with FUSE (4.3%; 95% CI, 1.4%-7.2%) than with SFVC (10.6%; 95% CI, 6.1%-15.1%; P = .0212).

CONCLUSIONS

FUSE is superior to SFVC regarding both AMR-PP and AMR; additionally, AMR-PP is both significantly lower with FUSE than SFVC for lesions ≤5 mm in size and in the ascending colon. (Clinical trial registration number: UMIN000020448.).

Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study

BACKGROUND

Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost.

OBJECTIVE

To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization of colorectal polyps after application of the narrow-band imaging [NBI] and methylene blue staining modes, respectively).

DESIGN

Single-group, open-label, prospective study. (UMIN [University hospital Medical Information Network] Clinical Trial Registry: UMIN000027360).

SETTING

University hospital.

PARTICIPANTS

791 consecutive patients undergoing colonoscopy and 23 endoscopists.

INTERVENTION

Real-time use of CAD during colonoscopy.

MEASUREMENTS

CAD-predicted pathology (neoplastic or nonneoplastic) of detected diminutive polyps (≤5 mm) on the basis of real-time outputs compared with pathologic diagnosis of the resected specimen (gold standard). The primary end point was whether CAD with the stained mode produced a negative predictive value (NPV) of 90% or greater for identifying diminutive rectosigmoid adenomas, the threshold required to "diagnose-and-leave" nonneoplastic polyps. Best- and worst-case scenarios assumed that polyps lacking either CAD diagnosis or pathology were true- or false-positive or true- or false-negative, respectively.

RESULTS

Overall, 466 diminutive (including 250 rectosigmoid) polyps from 325 patients were assessed by CAD, with a pathologic prediction rate of 98.1% (457 of 466). The NPVs of CAD for diminutive rectosigmoid adenomas were 96.4% (95% CI, 91.8% to 98.8%) (best-case scenario) and 93.7% (CI, 88.3% to 97.1%) (worst-case scenario) with stained mode and 96.5% (CI, 92.1% to 98.9%) (best-case scenario) and 95.2% (CI, 90.3% to 98.0%) (worst-case scenario) with NBI.

LIMITATION

Two thirds of the colonoscopies were conducted by experts who had each experienced more than 200 endocytoscopies; 186 polyps not assessed by CAD were excluded.

CONCLUSION

Real-time CAD can achieve the performance level required for a diagnose-and-leave strategy for diminutive, nonneoplastic rectosigmoid polyps.

PRIMARY FUNDING SOURCE

Japan Society for the Promotion of Science.

Clinical features and outcomes of Merkel cell carcinoma in 20 cats

The biological behaviour and prognostic factors of Merkel cell carcinoma (MCC) in 20 cats were studied. The tumours were surgically removed and histopathologically examined. The animals were 8 to 20 years old (median age: 14 years), and the tumours were predominantly located in the neck and head. Follow-up data were available in 17 cases, and 12 cats died within a year of surgery. The overall median survival time after resection was 243 days (range 16-360 days). Recurrence occurred in 11 cases, although 6 of them (55%) were found to be margin-negative. Possible metastasis occurred after the surgery in 10 cases, although 6 of them (60%) were found to be margin-negative. The histopathological features of MCC included tumour necrosis in 16 cases (80%), vascular invasion in 6 cases (38%) and high mitotic counts (median: 28.5 per high-power field). Irregular acanthosis was noted adjacent to the tumours in 9 cases (60%). Immunohistochemically, the tumour cells were positive for cytokeratin (CK) 20 and p63 in all cases, synaptophysin in 19 (95%) cases, and CK18 in 16 cases (80%). The study shows that feline MCC is associated with a poor prognosis and exhibited a strong tendency towards local recurrence, regional lymph node metastasis and distant spread.

Narrow band imaging efficiency in evaluation of mucosal healing/relapse of ulcerative colitis

BACKGROUND AND STUDY AIMS

 Mucosal healing is a current treatment target in ulcerative colitis (UC), while histological remission is another target. The aim of this study was to evaluate the efficiency of magnified narrow band imaging (NBI) findings of mucosal healing and their relationship with histological activity and prognosis.

PATIENTS AND METHODS

 Patients with UC who underwent total colonoscopy between January 2010 and December 2012 with left-sided or total-colitis type UC and achieved clinical remission with an endoscopic Mayo score of 0 or 1 were included. Each colon section was observed with white light and magnified NBI, with the colonoscopy being repeated at 1-year follow-up. We assessed the relationships of magnified NBI with histological disease activity and prognosis. Magnified NBI findings were divided into three categories; honeycomb-like blood vessels (BV-H), blood vessels shaped like bare branches (BV-BB), and blood vessels shaped like vines (BV-V).

RESULTS

 Fifty-two patients were included. The percentage of remitted mucosa with BV-BB was 37 %, while that of mucosa with scars with BV-H was 35 %. BV-H and BV-BB did not show pathological activity (12/292 and 8/299, respectively), while BV-V showed high pathological activity (27/33, 81 %). There was a correlation between magnified NBI findings and pathological findings ( P  < 0.01). The odds ratio for inflammation activity at 1-year follow-up was 14.2 for BV-BB (95 % CI, 3.3 - 60.9).

CONCLUSION

 Magnified NBI findings showed a good relationship with histological activity. This suggests that we could estimate histological activity without biopsy, and also the possibility of predicting relapse over the following year.

White light-emitting contrast image capsule endoscopy for visualization of small intestine lesions: a pilot study

BACKGROUND AND STUDY AIMS

 Capsule endoscopy (CE) has become a routine means of diagnosing obscure gastrointestinal bleeding (OGIB) in the small intestine. Capsules using novel blue-enhanced white light-emitting diodes are expected to acquire clearer contrast images (CIs) of the small bowel vasculature. We conducted a pilot study to examine whether CIs facilitate visualization of small bowel erosions, ulcers, and areas of angioectasia compared with standard white light images (WLIs).

PATIENTS AND METHODS

 A total of 24 patients with OGIB were recruited in this study. The main outcome measure was visibility of lesions on CIs compared with WLIs. We also examined the color difference between lesions and normal mucosa (ΔE) with each imaging modality.

RESULTS

 Three experienced physicians retrospectively evaluated 138 images of small bowel lesions (107 erosions, or ulcers, and 31 areas of angioectasia) obtained from 24 CE examinations. The endoscopists judged that compared with WLIs, CIs afforded easier identification of erosions or ulcers in 29 of 107 cases (27.1 %), were non-inferior in 68 of 107 cases (63.6 %), and were inferior in 10 of 107 cases (9.3 %). Identification of angioectasia was judged to be easier with CIs in 15 of 31 cases (48.4 %), non-inferior in 13 of 31 cases (41.9 %), and inferior in 3 of 31 cases (9.7 %). ΔE was significantly higher for CIs than WLIs, especially for angioectasia, potentially explaining why lesions were easier to visualize.

CONCLUSIONS

 CIs obtained by CE appear to facilitate identification of small bowel erosions, ulcers, and areas of angioectasia compared with WLIs.

Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer

BACKGROUND AND STUDY AIMS

Decisions concerning additional surgery after endoscopic resection of T1 colorectal cancer (CRC) are difficult because preoperative prediction of lymph node metastasis (LNM) is problematic. We investigated whether artificial intelligence can predict LNM presence, thus minimizing the need for additional surgery.

PATIENTS AND METHODS

Data on 690 consecutive patients with T1 CRCs that were surgically resected in 2001 - 2016 were retrospectively analyzed. We divided patients into two groups according to date: data from 590 patients were used for machine learning for the artificial intelligence model, and the remaining 100 patients were included for model validation. The artificial intelligence model analyzed 45 clinicopathological factors and then predicted positivity or negativity for LNM. Operative specimens were used as the gold standard for the presence of LNM. The artificial intelligence model was validated by calculating the sensitivity, specificity, and accuracy for predicting LNM, and comparing these data with those of the American, European, and Japanese guidelines.

RESULTS

Sensitivity was 100 % (95 % confidence interval [CI] 72 % to 100 %) in all models. Specificity of the artificial intelligence model and the American, European, and Japanese guidelines was 66 % (95 %CI 56 % to 76 %), 44 % (95 %CI 34 % to 55 %), 0 % (95 %CI 0 % to 3 %), and 0 % (95 %CI 0 % to 3 %), respectively; and accuracy was 69 % (95 %CI 59 % to 78 %), 49 % (95 %CI 39 % to 59 %), 9 % (95 %CI 4 % to 16 %), and 9 % (95 %CI 4 % - 16 %), respectively. The rates of unnecessary additional surgery attributable to misdiagnosing LNM-negative patients as having LNM were: 77 % (95 %CI 62 % to 89 %) for the artificial intelligence model, and 85 % (95 %CI 73 % to 93 %; P < 0.001), 91 % (95 %CI 84 % to 96 %; P < 0.001), and 91 % (95 %CI 84 % to 96 %; P < 0.001) for the American, European, and Japanese guidelines, respectively.

CONCLUSIONS

Compared with current guidelines, artificial intelligence significantly reduced unnecessary additional surgery after endoscopic resection of T1 CRC without missing LNM positivity.

A novel ability of endocytoscopy to diagnose histological grade of differentiation in T1 colorectal carcinomas

BACKGROUND AND STUDY AIMS

Endocytoscopic images closely resemble histopathology. We assessed whether endocytoscopy could be used to determine T1 colorectal cancer histological grade.

PATIENTS AND METHODS

Endocytoscopic images of 161 lesions were divided into three types: tubular gland lumens, unclear gland lumens, and fused gland formations on endocytoscopy (FGFE). We retrospectively compared endocytoscopic findings with histological grade in the resected specimen superficial layer, and examined the incidence of risk factors for lymph node metastasis.

RESULTS

Of the 118 eligible lesions, the sensitivity, specificity, accuracy, negative predictive value, and positive likelihood ratio of tubular or unclear gland lumens to identify well-differentiated adenocarcinomas were 91.0 %, 93.1 %, 91.5 %, 77.1 %, and 13.20, respectively. To identify moderately differentiated adenocarcinomas for FGFE, these values were 93.1 %, 91.0 %, 91.5 %, 97.6 %, and 10.36, respectively. In the 35 lesions with FGFE, the rates of massive invasion, lymphovascular infiltration, and tumor budding were 97.1 %, 60.0 %, and 37.1 %, respectively.

CONCLUSIONS

Endocytoscopy could be used to diagnose T1 colorectal cancer histological grade, and FGFE was a marker for recommending surgery.