Impact of advanced endoscopy training on colonoscopy quality and efficiency.

Objectives: Few reports have detailed improvements in the quality of colonoscopies with continuous training post-fellowship completion. We examined the changes in colonoscopy performance among trainees during our advanced endoscopy training program. Methods: Screening or surveillance colonoscopies performed by 11 trainees who participated in our 3-year advanced endoscopy training program between April 2015 and March 2020 were retrospectively analyzed. Quality and efficiency metrics of colonoscopies were evaluated annually. Results: Altogether, 297, 385, and 438 colonoscopies were enrolled in the first, second, and third training years, respectively. The mean insertion times were 8.6, 7.6, and 6.9 min in the first, second, and third training years, respectively, with significant improvement from the first to second year (p = 0.03) and from the first to third year (p < 0.01). The adenoma detection rate, proximal adenoma detection rate, and mean number of adenomas per patient exhibited a tendency to improve annually; however, the difference was not significant. Polypectomy efficiency was 10.5%, 11.2%, and 13.0%, with significant improvements from the first to third year (p < 0.01) and from the second to third year (p = 0.02). Insertion time and polypectomy efficiency showed significant improvements, especially among trainees experienced with <500 colonoscopies. Conclusions: Through our advanced endoscopy training program, there has been an improvement in the quality and efficiency of colonoscopy for trainees who have completed their fellowships, particularly those with <500 colonoscopies.

Tumor thickness is associated with metastasis in patients with submucosal invasive adenocarcinoma of the esophagogastric junction.

In submucosal invasive adenocarcinoma of the esophagogastric junction (pT1b-SM AEG), the extent of tumor submucosal (SM) invasion is measured using the vertical depth of SM invasion with the muscularis mucosa. This study aimed to investigate whether tumor thickness and depth of invasion without accounting for muscularis mucosa were superior to the vertical depth of SM invasion as metastasis predictors. We enrolled patients with pT1b-SM AEG who underwent endoscopic resection or surgical resection (SR) at our institution between January 2011 and September 2019 and were followed up for ≥2 years. The relationship between metastasis and clinicopathological factors was examined. Metastasis was defined as pathologically confirmed lymph node metastasis in the surgical specimen or recurrence during follow-up. This study included 57 patients (44 men; median age, 72 years). Endoscopic resection and SR were performed in 16 and 41 patients, respectively. Nine patients were diagnosed with metastasis: five who underwent SR showed pathologically confirmed lymph node metastasis in the surgical specimens, and four experienced recurrences during a median follow-up of 48 months. Univariate analyses showed that tumor thickness was significantly associated with metastasis (P = 0.021), and the vertical depth of SM invasion (P = 0.48) and depth of invasion (P = 0.38) were not. Furthermore, in multivariate analysis, tumor thickness ≥2800 µm (odds ratio, 38.70; P = 0.013) was a significant predictor for metastasis. Tumor thickness may be a more convenient and useful predictor of metastasis in patients with pT1b-SM AEG than the vertical depth of SM invasion.

Possibility of determining high quantitative fecal occult blood on stool surface using hyperspectral imaging.

BACKGROUND: Fecal immunochemical tests are commonly performed for colorectal cancer screening. Instant fecal occult blood measurement in toilet bowel movements would improve convenience. Hyperspectral imaging (HSI) enables the nondestructive evaluation of materials that are difficult to assess visually. This study aimed to determine whether HSI could be used to identify fecal occult blood on stool surfaces. METHODS: The study included 100 patients who underwent colonoscopy, divided into groups A and B (50 patients, each) for creating a discriminant algorithm and validating the accuracy of the algorithm, respectively. In group A, 100 areas were randomly selected from the stool surface, and the fecal occult blood quantitative values were measured and photographed using a hyperspectral camera (cutoff: > 400 ng/mL). A discriminant algorithm image was created to extract spectral feature differences obtained from HSI via machine learning. In group B, 250 random areas were evaluated and compared to fecal occult blood quantitative values, measuring sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: Groups A and B comprised 28 and 26 patients with cancer, respectively. Cancer detection sensitivity at the 400 ng/mL cutoff was 67.9% and 42.3% in groups A and B, respectively. The discriminant algorithm image exhibited high accuracy in group A (sensitivity; 77.1%, specificity; 96.9%, accuracy; 90.0%, PPV; 93.1%, NPV; 88.7%). In group B, the sensitivity, specificity, accuracy, PPV, and NPV were 83.3, 92.9, 90.8, 76.3, and 95.3%, respectively. CONCLUSION: HSI can effectively discriminate high quantitative fecal occult blood, highlighting its potential for improved colorectal cancer screening.

Association between pathological T1 colorectal cancer with lymphoid follicular replacement and risk of lymph node metastasis.

BACKGROUND AND AIM: Endoscopic resection (ER) is widely performed to treat early colorectal cancer. However, additional surgery for pathological T1 colorectal cancer (pT1CRC) after ER is controversial because of the imprecise prediction of lymph node metastasis (LNM). Recently, several patients of pT1CRC with lymphoid follicular replacement (LFR) without LNM have been reported. This study aimed to investigate the clinicopathological features and risk of LNM in patients with pT1CRC with LFR. METHODS: We retrospectively analyzed patients who underwent ER or surgical resection and were diagnosed with pT1CRC between January 2010 and December 2020. We defined pT1CRC with LFR as the replacement of a part of the lymphoid follicular component within the submucosal area by adenocarcinoma, with no invasion into other submucosal areas. RESULTS: Among the 600 eligible patients, the incidence rate of pT1CRC with LFR was 6.7% (40/600). Patients with pT1CRC with LFR represented 14.3% (37/258) of the endoscopically treated patients and 0.9% (3/342) of the surgically treated patients. For patients with pT1CRC with LFR, 80.0% (32/40) had flat and depressed lesions, and 35.0% (14/40) had submucosal invasion depth ≥1000 µm. Patients with pT1CRC with LFR had negative lymphovascular invasion, differentiated type, and budding grade 1. In the median follow-up of 61 months, patients with pT1CRC with LFR had no LNM. CONCLUSIONS: The presence of LFR in pT1CRC may be associated with a low risk of LNM. In patients with pT1CRC with LFR, follow-up without additional surgery is possible even if the submucosal invasion depth is ≥1000 µm.

Smartphone application for artificial intelligence-based evaluation of stool state during bowel preparation before colonoscopy.

OBJECTIVES: Colonoscopy (CS) is an important screening method for the early detection and removal of precancerous lesions. The stool state during bowel preparation (BP) should be properly evaluated to perform CS with sufficient quality. This study aimed to develop a smartphone application (app) with an artificial intelligence (AI) model for stool state evaluation during BP and to investigate whether the use of the app could maintain an adequate quality of CS. METHODS: First, stool images were collected in our hospital to develop the AI model and were categorized into grade 1 (solid or muddy stools), grade 2 (cloudy watery stools), and grade 3 (clear watery stools). The AI model for stool state evaluation (grades 1-3) was constructed and internally verified using the cross-validation method. Second, a prospective study was conducted on the quality of CS using the app in our hospital. The primary end-point was the proportion of patients who achieved Boston Bowel Preparation Scale (BBPS) ≥6 among those who successfully used the app. RESULTS: The AI model showed mean accuracy rates of 90.2%, 65.0%, and 89.3 for grades 1, 2, and 3, respectively. The prospective study enrolled 106 patients and revealed that 99.0% (95% confidence interval 95.3-99.9%) of patients achieved a BBPS ≥6. CONCLUSION: The proportion of patients with BBPS ≥6 during CS using the developed app exceeded the set expected value. This app could contribute to the performance of high-quality CS in clinical practice.

An elderly case of paraneoplastic anti-NMDA receptor encephalitis associated with large cell neuroendocrine carcinoma of the lung.

BACKGROUND: Recent studies have suggested that N-methyl-D-aspartate (NMDA) receptors are involved in the cell proliferation in several tumors. However, there have been no reports demonstrating the expression of NR1 subunit of the NMDA receptor in large cell neuroendocrine carcinoma (LCNEC). CASE PRESENTATION: Here, we report the first elderly case of paraneoplastic anti-NMDA receptor encephalitis associated with LCNEC of the lung with NR1 expression. Of note, NR1 subunit expression in the tumor cells of the present case was confirmed by immunohistochemistry (IHC). Radiation therapy and immunotherapies, such as corticosteroids and intravenous immunoglobulin (IVIG), shrank the tumors and improved neurological symptoms in the present case. Additionally, we also confirmed the expression of NR1 in the tumor cells obtained from three other cases with LCNEC of the lung at our hospital by IHC. CONCLUSION: Our IHC results indicate that LCNEC generally expresses NR1 subunit and NMDA receptor may be involved in the tumor development and growth.

Proportions and characteristics of interval cancer in annual fecal immunochemical test screening and postcolonoscopy colorectal cancer: Results from a Japanese multicenter prospective study using questionnaires, the C-DETECT study.

OBJECTIVES: There are several types of colorectal cancer (CRC) according to the detection methods and intervals, including interval CRC (iCRC) and postcolonoscopy CRC (PCCRC). We aimed to examine their proportions and characteristics. METHODS: We conducted a multicenter prospective study using questionnaires in Japan ("C-DETECT study"), in which differences in CRC characteristics according to detection methods and intervals were examined from consecutive adult patients. Because the annual fecal immunochemical test (FIT) was used in population-based screening, the annual FIT-iCRC was assessed. RESULTS: In total, 1241 CRC patients (1064 with invasive CRC) were included. Annual FIT-iCRC (a), 3-year PCCRC (b), and CRC detected within 1 year after a positive FIT with noncompliance to colonoscopy (c) accounted for 4.5%, 7.0%, and 3.9% of all CRCs, respectively, and for 3.9%, 5.4%, and 4.3% of invasive CRCs, respectively. The comparison among these (a, b, c) and other CRCs (d) demonstrated differences in the proportions of ≥T2 invasion ([a] 58.9%, [b] 44.8%, [c] 87.5%, [d] 73.0%), metastasis ([a] 33.9%, [b] 21.8%, [c] 54.2%, [d] 43.9%), right-sided CRC ([a] 42.9%, [b] 40.2%, [c] 18.8%, [d] 28.6%), and female sex ([a] 53.6%, [b] 49.4%, [c] 27.1%, [d] 41.6%). In metastatic CRC, (a) and (b) showed a higher proportions of BRAF mutations ([a] [b] 12.0%, [c] [d] 3.1%). CONCLUSIONS: Annual FIT-iCRC and 3-year PCCRC existed in nonnegligible proportions. They were characterized by higher proportions of right-sided tumors, female sex, and BRAF mutations. These findings suggest that annual FIT-iCRC and 3-year PCCRC may have biological features different from those of other CRCs.

Investigation of vertical margin involvement in endoscopic resection for T1 colorectal cancer.

OBJECTIVES: The resection of vertical margin-negative submucosally invasive colorectal cancer (CRC) relies on the pathological risk assessment of lymph node metastasis. However, no large-scale study has clarified the endoscopic resection (ER) outcome for submucosally invasive CRC, focusing on the vertical margin status. This retrospective study aimed to examine vertical margin involvement in ER for submucosally invasive CRC and explore the treatment consequences associated with vertical margin status. METHODS: We analyzed 395 submucosally invasive CRC cases in 389 patients who underwent ER at our hospital between 2008 and 2020. The presence of residual tumors and simultaneous lymph node metastasis in patients who underwent additional surgery was assessed and compared between the vertical incomplete ER and the vertical margin-negative groups. RESULTS: Among the patients, 270 were men, with a median age of 69 years. The vertical incomplete ER rate was 21.5%, with positive vertical margins and unclear vertical margins identified in 12.2% and 9.3% of the cases, respectively. Among 154 patients who underwent additional surgery after ER, the vertical incomplete ER group had a significantly higher residual tumor rate than the vertical margin-negative group (P = 0.001). The vertical incomplete ER group had a significantly higher lymph node metastasis rate than the vertical margin-negative group (P = 0.029). CONCLUSION: This study clarified the substantial risk of vertical incomplete ER in submucosally invasive CRC and revealed the high risk of residual tumor and lymph node metastasis in vertical incomplete ER for submucosal CRC.

Hot snare polypectomy vs endoscopic mucosal resection using bipolar snare for intermediate size colorectal lesions: Propensity score matching.

BACKGROUND: Endoscopic resection (ER) with bipolar snare, in which the electric current only passes through the tissue between the device's two electrodes, is a prominent method used to prevent perforation due to electricity potentially. ER using bipolar snare with or without submucosal injection enabled safe resection of colorectal lesions measuring 10-15 mm in an ex vivo porcine model. ER with bipolar snare is expected to have good treatment outcomes in 10-15 mm colorectal lesions, with high safety even without submucosal injection. However, no clinical reports have compared treatment outcomes with and without submucosal injection. AIM: To compare the treatment outcomes of bipolar polypectomy with hot snare polypectomy (HSP) to those with endoscopic mucosal resection (EMR). METHODS: In this single-centre retrospective study, we enrolled 10-15 mm nonpedunculated colorectal lesions (565 Lesions in 463 patients) diagnosed as type 2A based on the Japan Narrow-band Imaging Expert Team classification, resected by either HSP or EMR between January 2018 and June 2021 at the National Cancer Center Hospital East. Lesions were divided into HSP and EMR groups, and propensity score matching was performed. In the matched cohort, en bloc and R0 resection rates and adverse events were compared between the two groups. RESULTS: Of the 565 lesions in 463 patients, 117 lesions each in the HSP and EMR groups were selected after propensity score matching. In the original cohort, there was a significant difference in antithrombotic drug use (P < 0.05), lesion size (P < 0.01), location (P < 0.01), and macroscopic type (P < 0.05) between the HSP and EMR groups. In the matched cohort, the en bloc resection rates were comparable between both groups [93.2% (109/117) vs 92.3% (108/117), P = 0.81], and there was no significant difference in the R0 resection rate [77.8% (91/117) vs 80.3% (94/117), P = 0.64]. The incidence of delayed bleeding was similar in both groups [1.7% (2/117)]. Perforation occurred in the EMR group [0.9% (1/117)] but not in the HSP group. CONCLUSION: Using bipolar snare, ER of nonpedunculated 10-15 mm colorectal lesions may be performed safely and effectively, even without submucosal injection.

Computer-aided demarcation of early gastric cancer: a pilot comparative study with endoscopists.

BACKGROUND: Precise area diagnosis of early gastric cancer (EGC) is critical for reliable endoscopic resection. Computer-aided diagnosis (CAD) shows strong potential for detecting EGC and reducing cancer-care disparities caused by differences in endoscopists' skills. To be used in clinical practice, CAD should enable both the detection and the demarcation of lesions. This study proposes a scheme for the detection and delineation of EGC under white-light endoscopy and validates its performance using 1-year consecutive cases. METHODS: Only 300 endoscopic images randomly selected from 68 consecutive cases were used for training a convolutional neural network. All cases were treated with endoscopic submucosal dissection, enabling the accumulation of a training dataset in which the extent of lesions was precisely determined. For validation, 462 cancer images and 396 normal images from 137 consecutive cases were used. From the validation results, 38 randomly selected images were compared with those delineated by six endoscopists. RESULTS: Successful detections of EGC in 387 cancer images (83.8%) and the absence of lesions in 307 normal images (77.5%) were achieved. Positive and negative predictive values were 81.3% and 80.4%, respectively. Successful detection was achieved in 130 cases (94.9%). We achieved precise demarcation of EGC with a mean intersection over union of 66.5%, showing the extent of lesions with a smooth boundary; the results were comparable to those achieved by specialists. CONCLUSIONS: Our scheme, validated using 1-year consecutive cases, shows potential for demarcating EGC. Its performance matched that of specialists; it might therefore be suitable for clinical use in the future.

Anatomical classification of pharyngeal and laryngeal endoscopic images using artificial intelligence.

BACKGROUND: The entire pharynx should be observed endoscopically to avoid missing pharyngeal lesions. An artificial intelligence (AI) model recognizing anatomical locations can help identify blind spots. We developed and evaluated an AI model classifying pharyngeal and laryngeal endoscopic locations. METHODS: The AI model was trained using 5382 endoscopic images, categorized into 15 anatomical locations, and evaluated using an independent dataset of 1110 images. The main outcomes were model accuracy, precision, recall, and F1-score. Moreover, we investigated focused regions in the input images contributing to the model predictions using gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM. RESULTS: Our AI model correctly classified pharyngeal and laryngeal images into 15 anatomical locations, with an accuracy of 93.3%. The weighted averages of precision, recall, and F1-score were 0.934, 0.933, and 0.933, respectively. CONCLUSION: Our AI model has an excellent performance determining pharyngeal and laryngeal anatomical locations, helping endoscopists notify of blind spots.

Efficacy and safety of repeated endoscopic radial incision and cutting procedure for benign esophageal stricture.

Background and study aims: Radial incision and cutting (RIC) is indicated for refractory benign esophageal strictures after curative treatment for esophageal cancer and has shown favorable short-term outcomes. However, re-stricture after RIC may occur in the long term, and RIC is performed repeatedly in such cases, but the efficacy and safety of repeated RIC are unclear. Therefore, we aimed to demonstrate the efficacy and safety of the repeated RIC for refractory benign esophageal strictures after surgical and non-surgical treatment. Patients and methods: Between April 2008 and September 2019, we enrolled patients who were treated with the first RIC for benign esophageal strictures. The RIC was indicated for the refractory stricture and repeatedly performed for re-refractory esophageal stricture after RIC. We retrospectively evaluated the 6-month refractory stricture-free rate, and adverse events (AEs) in the first RIC and repeated RICs. Results: Forty-six patients (39 men, 7 women; median age, 71 years, range 49-85) were included. RIC was performed once in 24 patients (non-repeated RIC group) and two or more times in 22 patients (repeated RIC group). In all patients, the 6-month refractory stricture-free rate after the first RIC were 42.3 %. In the repeated RIC group, the 6-month refractory stricture-free rate after the first and repeated RICs were 18.2 % vs 18.2 %, respectively. No AEs were noted. Conclusions: Repeated RIC could be effective in the short-term and safe even for patients with refractory benign esophageal stricture after the first RIC. However, it cannot be considered curative treatment for refractory stricture because of poor long-term results.

Prospective study on the risk of transmission due to droplets and aerosols during an endoscopic procedure and the usefulness of extraoral suction devices.

OBJECTIVES: Endoscopy poses a high risk of severe acute respiratory syndrome coronavirus 2 infection for medical personnel due to the dispersal of aerosols from the patient. We investigated the location and size of droplets generated during esophagogastroduodenoscopy (EGD) and endoscopic submucosal dissection (ESD), the contamination of the surrounding area before and after the procedures, and the effectiveness of using an extraoral suction device (Free arm arteo; TOKYO GIKEN, Inc., Tokyo, Japan). METHODS: Patients who consented to the study and underwent EGD or ESD between December 8, 2020, and April 15, 2021, at the National Cancer Center East Hospital were included. Adenosine triphosphate (ATP) hygiene monitoring tests and a particle counter were used for measurements. RESULTS: Assessments were performed on 22 EGD and 15 ESD cases. ATP hygiene monitoring tests showed significant elevations at three sites near the patient, and two sites 1.5 m away, for EGD, and at four sites near the patient and 1.5 m away for ESD. In both ESD and EGD, extraoral suction devices reduced the extent of the contamination. Particles <5 µm in size were generated during endoscopic procedures and dispersed from both the forceps hole and the patient's mouth. The extraoral suction device did not reduce the number of particles generated. CONCLUSIONS: During endoscopic procedures, cleaning the surrounding environment is important in addition to standard precautions the endoscopist and caregivers take. The use of extraoral suction devices can also potentially reduce contamination of the surrounding environment.

Development of new gastric endoscopic submucosal dissection training model: A reproducibility evaluation study.

Background and study aims Gastric endoscopic submucosal dissection (ESD) is a highly technical procedure mainly due to the distinctive shape of the stomach and diverse locations of lesions. We developed a new gastric ESD training model (G-Master) that could accurately recreate the location of the stomach and assessed the reproducibility of located lesions in the model. Methods The model comprises a simulated mucous membrane sheet made of konjac flour and a setting frame, which can simulate 11 locations of the stomach. We assessed the reproducibility of each location in the model by assessing the procedure speed and using a questionnaire that was distributed among experts. In the questionnaire, each location was scored on a six-point scale for similarity of locations. Results The mean score for all locations was high with > 4 points. Regarding locations, lower anterior and posterior walls had medium scores with 3 to 4 points. The procedure speed was slower in the greater curvature of the upper and middle gastric portions, where ESD is considered more difficult than the overall procedure speed. Conclusions The new gastric ESD training model appears to be highly reproducible for each gastric location and its application for training in assuming actual gastric ESD locations.

The characteristics of missed pharyngeal and laryngeal cancers at gastrointestinal endoscopy.

OBJECTIVES: Understanding the miss rate and characteristics of missed pharyngeal and laryngeal cancers during upper gastrointestinal endoscopy may aid in reducing the endoscopic miss rate of this cancer type. However, little is known regarding the miss rate and characteristics of such cancers. Therefore, the aim of this study was to investigate the upper gastrointestinal endoscopic miss rate of oro-hypopharyngeal and laryngeal cancers, the characteristics of the missed cancers, and risk factors associated with the missed cancers. METHODS: Patients who underwent upper gastrointestinal endoscopy and were pathologically diagnosed with oro-hypopharyngeal and laryngeal squamous cell carcinoma from January 2019 to November 2020 at our institution were retrospectively evaluated. Missed cancers were defined as those diagnosed within 15 months after a negative upper gastrointestinal endoscopy. RESULTS: A total of 240 lesions were finally included. Eighty-five lesions were classified as missed cancers, and 155 lesions as non-missed cancers. The upper gastrointestinal endoscopic miss rate for oro-hypopharyngeal and laryngeal cancers was 35.4%. Multivariate analysis revealed that a tumor size of <13 mm (odds ratio: 1.96, P=0.026), tumors located on the anterior surface of the epiglottis/valleculae (odds ratio: 2.98, P=0.045) and inside of the pyriform sinus (odds ratio: 2.28, P=0.046) were associated with missed cancers. CONCLUSIONS: This study revealed a high miss rate of oro-hypopharyngeal and laryngeal cancers during endoscopic observations. High-quality upper gastrointestinal endoscopic observation and awareness of missed cancer may help reduce this rate.

The safety and feasibility of endoscopic submucosal dissection using a flexible three-dimensional endoscope for early gastric cancer and superficial esophageal cancer: A prospective observational study.

BACKGROUND AND AIM: Endoscopic submucosal dissection (ESD) is performed as one of standard treatments for patients with early gastric cancer (EGC) and superficial esophageal squamous cancer (SESCC). A prototype of a flexible endoscope with a 3-D system has been recently developed. This study aimed to investigate the safety and feasibility of ESD using a 3-D flexible endoscope (3-D ESD) for EGC and SESCC. METHODS: This single-center, prospective, observational study enrolled patients who underwent planned 3-D ESD. The clinical outcomes, including the incidence of adverse events and treatment results, were analyzed. Visibility and manipulation during 3-D ESD were evaluated using a visual analog scale (VAS). We also evaluated the effect of the 3-D system on the endoscopist using VAS and the critical flicker fusion frequency (CFFF). RESULTS: We analyzed 47 EGC and 20 SESCC cases. There are no bleeding cases that required transfusion and perforation during 3-D ESD in both EGC and SESCC patients. However, the incidence of delayed bleeding and delayed perforation was 1.5% (one case) each. The mean VAS scores for recognizing the submucosal layer during the submucosal dissection, visual perception of blood vessel, and depth perception were 72.7 ± 22.2, 74.7 ± 21.8, and 78.2 ± 19.9, respectively. In contrast, the mean VAS score for manipulation was 25.4 ± 19.7. Among endoscopists, there was no significant difference in the VAS of eyestrain and headache before and after ESD, and there was no significant difference in the CFFF. CONCLUSION: The safety and feasibility of 3-D ESD for EGC and SESCC are acceptable in both patients and endoscopists.

Long-term clinical outcome after endoscopic resection of esophageal squamous cell carcinoma invading the muscularis mucosae without lymphovascular invasion.

BACKGROUND AND AIMS: Lymph node recurrence (LNR) after endoscopic resection (ER) in patients with esophageal squamous cell carcinoma (ESCC) pathologically invading the muscularis mucosae (pMM) without lymphovascular invasion (LVI) has been reported as non-negligible in the ER guidelines for esophageal cancer by the Japan Gastroenterological Endoscopy Society. However, these data were not regarded as high-level evidence because several retrospective case series were tabulated without sufficient long-term follow-up. Hence, this guideline stated that the administration of additional treatment after ER could not be determined for this population. This study aimed to clarify the long-term clinical outcomes after ER of pMM ESCC without LVI. METHODS: Between January 2009 and November 2017, we enrolled followed patients who underwent ER and were diagnosed with pMM ESCC without LVI with no additional treatments. We retrospectively investigated the cumulative recurrence rate and recurrence-free, overall, and disease-specific survival at 5 years after ER. RESULTS: Eighty-seven patients were enrolled. During the median follow-up period of 64 months (range, 12-117), 3 patients developed lymph node and/or distant recurrence, and 2 of these cases occurred more than 3 years after ER; all 3 patients died of the primary disease. The 5-year cumulative recurrence rate was 4.3%, and the 5-year recurrence-free, disease-specific, and overall survival rates were 88.8%, 98.2%, and 91.7%, respectively. CONCLUSIONS: The long-term outcome for patients with pMM ESCC without LVI was favorable after ER; however, this population had a risk of recurrence directly leading to death. Long-term follow-up is necessary, with attention to the timing of recurrence.

Long-term clinical outcomes of patients diagnosed with pT1a-muscularis mucosae with lymphovascular invasion or pT1b after endoscopic resection for cT1N0M0 esophageal squamous cell carcinoma.

BACKGROUND: Endoscopic resection (ER) is performed for early esophageal squamous cell carcinoma (ESCC) cases. Additional esophagectomy or chemoradiotherapy is recommended for non-curative resection (NCR) even with pathologically negative vertical margins (pVM0); however, their clinical outcomes remain unknown. We examined the long-term clinical outcomes of NCR for ESCCs according to additional treatments. METHODS: We retrospectively analyzed the data of patients who underwent ER for cT1N0M0 ESCC between 2009 and 2017 judged to have NCR, which defined when pathologically diagnosed as invading the submucosa (SM) or muscularis mucosae (MM) involving lymphovascular invasion (LVI), pVM0, and endoscopically judged as negative horizontal margin. Additional esophagectomy (involving three-field lymphadenectomy), chemoradiotherapy [mainly cisplatin and 5-fluorouracil with concurrent radiotherapy (41.4 Gy)], or observation was undertaken. Thereafter, computed tomography was performed every 6-12 months. The cumulative recurrence (CRR) and recurrence-free survival (RFS) rates were evaluated. RESULTS: Eighty-nine patients were included. Among them, 14 had pathologically diagnosed pMM with LVI; 9 and 6, and 32 and 28 patients had pSM1 and pSM2 without and with LVI. Twenty-one patients underwent observation, whereas 18 and 50 underwent esophagectomy and chemoradiotherapy. During the 60.6-month median follow-up period, nine patients had recurrence; among them, six patients had occurrence at > 4 years after ER. The 5-year CRR/RFS rates were 35.7%/48.1%, 13.4%/80.4%, and 0.0%/98.0% in the observation, esophagectomy, and chemoradiotherapy groups, respectively (observation vs. chemoradiotherapy; P < 0.001). CONCLUSIONS: Additional treatments showed better long-term outcomes than observation for patients with NCR. As recurrence may occur at > 4 years after ER, careful long-term follow-up examinations are needed.

Artificial intelligence system for detecting superficial laryngopharyngeal cancer with high efficiency of deep learning.

BACKGROUND: There are no published reports evaluating the ability of artificial intelligence (AI) in the endoscopic diagnosis of superficial laryngopharyngeal cancer (SLPC). We presented our newly developed diagnostic AI model for SLPC detection. METHODS: We used RetinaNet for object detection. SLPC and normal laryngopharyngeal mucosal images obtained from narrow-band imaging were used for the learning and validation data sets. Each independent data set comprised 400 SLPC and 800 normal mucosal images. The diagnostic AI model was constructed stage-wise and evaluated at each learning stage using validation data sets. RESULTS: In the validation data sets (100 SLPC cases), the median tumor size was 13.2 mm; flat/elevated/depressed types were found in 77/21/2 cases. Sensitivity, specificity, and accuracy improved each time a learning image was added and were 95.5%, 98.4%, and 97.3%, respectively, after learning all SLPC and normal mucosal images. CONCLUSIONS: The novel AI model is helpful for detection of laryngopharyngeal cancer at an early stage.