Efficacy and Safety of Self-Expandable Metallic Stent Placement for Malignant Esophageal Fistula.

Patients with malignant esophageal fistulas often experience dysphagia and infection, resulting in poor prognoses. Self-expandable metallic stent (SEMS) placement is a palliative treatment option; however, its efficacy and safety are unclear. We aimed to determine the efficacy and safety of SEMS placement for malignant esophageal fistulas. We retrospectively investigated patients who underwent SEMS placement for malignant esophageal fistulas between 2013 and 2022 at the Cancer Institute Hospital. Dysphagia scores (DSs) before and after SEMS placement, adverse events, and overall survival from SEMS placement until death were evaluated. A total of 17 patients underwent SEMS placement, including 12 and 5 patients with esophageal and lung cancers, respectively. Prior treatments included chemoradiotherapy (n = 11), radiotherapy (n = 4), and chemotherapy (n = 4); two patients underwent palliative radiotherapy after chemotherapy. All procedures were technically successful. After SEMS placement, 14 (82.4%) patients were able to consume semisolid or solid food (DS ≤ 2). Major adverse events were encountered in only one case. The median survival time after SEMS placement was 71 days (range 17-247 days). SEMS placement allowed most patients to resume oral intake with a low rate of major adverse events. SEMS placement is a reasonable palliative treatment option for patients with malignant fistulas who have poor prognoses.

Performance of an artificial intelligence-based diagnostic support tool for early gastric cancers: Retrospective study.

OBJECTIVES: Endoscopists' abilities to diagnose early gastric cancers (EGCs) vary, especially between specialists and nonspecialists. We developed an artificial intelligence (AI)-based diagnostic support tool "Tango" to differentiate EGCs and compared its performance with that of endoscopists. METHODS: The diagnostic performances of Tango and endoscopists (34 specialists, 42 nonspecialists) were compared using still images of 150 neoplastic and 165 non-neoplastic lesions. Neoplastic lesions included EGCs and adenomas. The primary outcome was to show the noninferiority of Tango (based on sensitivity) over specialists. The secondary outcomes were the noninferiority of Tango (based on accuracy) over specialists and the superiority of Tango (based on sensitivity and accuracy) over nonspecialists. The lower limit of the 95% confidence interval (CI) of the difference between Tango and the specialists for sensitivity was calculated, with >-10% defined as noninferiority and >0% defined as superiority in the primary outcome. The comparable differences between Tango and the endoscopists for each performance were calculated, with >10% defined as superiority and >0% defined as noninferiority in the secondary outcomes. RESULTS: Tango achieved superiority over the specialists based on sensitivity (84.7% vs. 65.8%, difference 18.9%, 95% CI 12.3-25.3%) and demonstrated noninferiority based on accuracy (70.8% vs. 67.4%). Tango achieved superiority over the nonspecialists based on sensitivity (84.7% vs. 51.0%) and accuracy (70.8% vs. 58.4%). CONCLUSIONS: The AI-based diagnostic support tool for EGCs demonstrated a robust performance and may be useful to reduce misdiagnosis.

A rare case of an enterochromaffin-like neuroendocrine tumor associated with parietal cell dysfunction treated using endoscopic submucosal dissection.

Most gastric neuroendocrine tumors (NETs) develop from enterochromaffin-like (ECL) cells. ECL-cell NETs are classically categorized into three types according to their etiology. A 50-year-old woman presented with submucosal tumor-like lesions in the stomach, which were identified via esophagogastroduodenoscopy. Although esophagogastroduodenoscopy and pathological findings of biopsy specimens showed an absence of mucosal atrophy in the body of the stomach, sticky, adherent, dense mucus was observed. All lesions were diagnosed as ECL-cell NETs based on histological examination findings; however, ECL-cell NETs did not apply to any of the classic types I-III categorization based on laboratory, computed tomography, and 24-h intragastric pH monitoring test findings. Endoscopic submucosal dissection of the tumor was performed. Pathological findings of the excised specimen indicated that parietal cell hyperplasia with a protrusion, dilated fundic glands, and endocrine cell hyperplasia in the background mucosa, and parietal cells were not immunostained for the α-subunits of H+/K+-ATPase. Genetic analysis identified mutation in the ATP4A gene. The patient opted for additional gastric resection due to the risk of lymph node metastasis with deeper submucosal invasion and vascular infiltration. This report describes the first case of ECL-cell NETs caused by parietal cell dysfunction, which was treated via endoscopic submucosal dissection.

Efficacy of the pocket-creation method with a traction device in endoscopic submucosal dissection for residual or recurrent colorectal lesions.

BACKGROUND/AIMS: Endoscopic submucosal dissection (ESD) for residual or recurrent colorectal lesions after incomplete resection is challenging because of severe fibrosis. This study aimed to compare the efficacy of the pocket-creation method (PCM) with a traction device (TD) with that of conventional ESD for residual or recurrent colorectal lesions. METHODS: We retrospectively studied 72 patients with residual or recurrent colorectal lesions resected using ESD. Overall, 31 and 41 lesions were resected using PCM with TD and conventional ESD methods, respectively. We compared patient background and treatment outcomes between the PCM with TD and conventional ESD groups, respectively. The primary endpoints were en bloc resection and R0 resection rates. The secondary endpoints were the dissection speed and incidence of adverse events. RESULTS: En bloc resection was feasible in all cases with PCM with TD, but failed in 22% of cases of conventional ESD. The R0 resection rates for PCM with TD and conventional ESD were 97% and 66%, respectively. Dissection was significantly faster in the PCM with TD group (13.0 vs. 7.9 mm2/min). Perforation and postoperative bleeding were observed in one patient in each group. CONCLUSION: PCM with TD is an effective method for treating residual or recurrent colorectal lesions after incomplete resection.

Risk factors for vertical incomplete resection in endoscopic submucosal dissection of deep invasive submucosal colorectal cancer.

INTRODUCTION: It has been recently reported that deep invasive submucosal (T1b) colorectal cancer (CRC) without other pathological risk factors for lymph node metastasis has a low rate of lymph node metastasis, increasing the possibility of endoscopic submucosal dissection (ESD) in the future. However, ESD for T1b CRC is technically difficult, and some lesions cannot be resected en bloc. This study aimed to identify the risk factors associated with vertical incomplete ESD in T1b CRC. METHODS: We retrospectively studied 140 pathological T1b CRC lesions that underwent initial ESD at our institution between January 2011 and October 2020, and categorized them into positive vertical margin (PVM) and negative vertical margin (NVM) groups. The risk factors for PVM were examined using univariate and multivariate analyses, and a subgroup analysis for T1b CRC with an obvious depressed surface was performed. RESULTS: Multivariate analysis revealed obvious depression (hazard ratio [HR]: 7.4; 95% confidence interval [CI]: 2.47-22.5) and severe fibrosis (HR: 11.4; 95% CI: 3.95-33.0) as significant risk factors for PVM. Length of depressed surface ≥12 mm (HR: 6.19; 95% CI: 1.56 -24.6) was identified as an independent predictor of PVM for T1b CRC with an obvious depression. CONCLUSION: Pathological T1b CRC cases with an obvious depression and severe fibrosis are at a high risk of vertical incomplete ESD.

Additive effect of evaluating microsurface and microvascular patterns using magnifying endoscopy with narrow-band imaging in gastric cancer: a post-hoc analysis of a single-center observational study.

BACKGROUND: No studies have compared the performance of microvascular and microsurface patterns alone with their combination in patients undergoing magnifying endoscopy with narrow-band imaging for diagnosing gastric cancer. This study aimed to clarify the differences in diagnostic performance among these methods. METHODS: Thirty-three participating endoscopists who had received specialized training in magnifying endoscopy evaluated the microvascular and microsurface patterns of images of 106 cancerous and 106 non-cancerous lesions. If classified as "irregular," the lesion was diagnosed as gastric cancer. To evaluate diagnostic performance, we compared the diagnostic accuracy, sensitivity, and specificity of these methods. RESULTS: Performance-related items did not differ significantly between microvascular and microsurface patterns. However, the diagnostic accuracy and sensitivity were significantly higher when using a combination of these methods than when using microvascular (82.1% [76.4-86.7] vs. 76.4% [70.3-81.6] and 69.8% [60.5-77.8] vs. 63.2% [53.7-71.8]; P < 0.001 and P = 0.008, respectively) or microsurface (82.1% [76.4-86.7] vs. 73.6% [67.3-79.1] and 69.8% [60.5-77.8] vs. 52.8% [43.4‒62.1]; both, P < 0.001) patterns alone. The additive effect on diagnostic accuracy and sensitivity was 5.7‒8.6% and 6.6‒17.0%, respectively. CONCLUSIONS: We demonstrate the superiority of the combination of microvascular and microsurface patterns over microvascular or microsurface patterns alone for diagnosing gastric cancer. Our data support the use of the former method in clinical practice. Although a major limitation of this study was its retrospective, single-center design, our findings may help to improve the diagnosis of gastric cancer.

Safety and Efficacy of Self-Expandable Metallic Stent Placement Using Low Radial Force Stent for Malignant Dysphagia after Radiotherapy.

INTRODUCTION: We aimed to investigate the safety and efficacy of self-expandable metallic stent (SEMS) placement in patients with prior radiotherapy (RT) using the Niti-S stent, which is characterized by low radial force, in comparison to patients without prior RT. METHODS: A consecutive series of 83 patients who were treated by SEMS placement using Niti-S stent for severe malignant esophageal obstruction or fistula were enrolled. The adverse event rates and efficacy were retrospectively compared between patients with/without prior RT before SEMS placement (RT group [n = 32] versus non-RT group [n = 51]). RESULTS: The incidence rate of major adverse events in the RT group was 6.3% and was not significantly different from that in the non-RT group (5.9%, p = 0.95). Among the RT group, 84.4% were able to resume oral intake within a median of 2 days. Among the patients with fistula, 78.6% could resume oral intake and survive for 73 days after SEMS placement. Cox proportional hazard regression analysis identified significant factors affecting overall survival to be prior RT (hazard ratio [HR]: 1.96), low performance status (HR: 3.87), and subsequent anticancer treatment after SEMS placement (HR: 0.41). However, compared to the non-RT group, the RT group had received longer duration of anticancer treatment before SEMS placement and a lower rate of subsequent anticancer treatment after SEMS placement. CONCLUSIONS: With the Niti-S stent, the incidence of major adverse events was sufficiently low even for patients after RT. SEMS with low radial force would be an effective palliative treatment option for patients, regardless of prior RT.

Evaluation of Microvascular Patterns Alone Using Endocytoscopy with Narrow-Band Imaging for Diagnosing Gastric Cancer.

INTRODUCTION: Although endocytoscopy (EC) with narrow-band imaging (NBI) is effective in diagnosing gastric cancer, no diagnostic system has been validated. We explored a specific diagnostic system for gastric cancer using EC with NBI. METHODS: Equal numbers of images from cancerous and noncancerous areas (114 images each) were assessed by endoscopists with (development group: 33) and without (validation group: 28) specific training in magnifying endoscopy with NBI. Microvascular and microsurface patterns (MS) in each image were evaluated. Lesions were diagnosed as cancerous when patterns were deemed "irregular." The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of a diagnosis according to patterns on EC with NBI (microvascular pattern [MV] alone, MS alone, and both) were evaluated and compared between groups to determine the diagnostic performance. RESULTS: In the development and validation groups, diagnoses based on the MV alone had significantly higher accuracy (91.7% vs. 76.3%, p < 0.0001 and 92.5% vs. 67.5%, p < 0.0001, respectively) and sensitivity (88.6% vs. 68.3%, p < 0.0001 and 89.5% vs. 38.6%, p < 0.0001, respectively) than those based on the MS alone. In both groups, there were no significant differences in diagnostic accuracy between using the MV alone and both patterns. DISCUSSION/CONCLUSION: Evaluation of the MV alone is a simple and accurate diagnostic method for gastric cancer. This system could find widespread applications in clinical practice.

Detecting early gastric cancer: Comparison between the diagnostic ability of convolutional neural networks and endoscopists.

OBJECTIVES: Detecting early gastric cancer is difficult, and it may even be overlooked by experienced endoscopists. Recently, artificial intelligence based on deep learning through convolutional neural networks (CNNs) has enabled significant advancements in the field of gastroenterology. However, it remains unclear whether a CNN can outperform endoscopists. In this study, we evaluated whether the performance of a CNN in detecting early gastric cancer is better than that of endoscopists. METHODS: The CNN was constructed using 13,584 endoscopic images from 2639 lesions of gastric cancer. Subsequently, its diagnostic ability was compared to that of 67 endoscopists using an independent test dataset (2940 images from 140 cases). RESULTS: The average diagnostic time for analyzing 2940 test endoscopic images by the CNN and endoscopists were 45.5 ± 1.8 s and 173.0 ± 66.0 min, respectively. The sensitivity, specificity, and positive and negative predictive values for the CNN were 58.4%, 87.3%, 26.0%, and 96.5%, respectively. These values for the 67 endoscopists were 31.9%, 97.2%, 46.2%, and 94.9%, respectively. The CNN had a significantly higher sensitivity than the endoscopists (by 26.5%; 95% confidence interval, 14.9-32.5%). CONCLUSION: The CNN detected more early gastric cancer cases in a shorter time than the endoscopists. The CNN needs further training to achieve higher diagnostic accuracy. However, a diagnostic support tool for gastric cancer using a CNN will be realized in the near future.

Clinical utility of the pocket-creation method with a traction device for colorectal endoscopic submucosal dissection.

BACKGROUND: Colorectal endoscopic submucosal dissection (ESD) is technically demanding while ensuring safety, especially in cases with fibrosis and/or poor maneuverability. To overcome such difficulties, we developed a novel method called the pocket-creation method with a traction device (PCM with TD). We then evaluated the effectiveness and safety of PCM with TD in colorectal ESD compared to other conventional methods. METHODS: In total, 324 colorectal lesions treated with ESD from July 2018 to June 2019 were included. The following three treatment strategies were used: conventional ESD (CE), CE with TD, and PCM with TD. Patient backgrounds and treatment outcomes were retrospectively compared and analyzed. RESULTS: As ESD methods, CE, CE with TD, and PCM with TD account for 58% (187/324), 24% (78/324), and 18% (59/324), respectively. No significant difference was observed among the three groups in en bloc and R0 resection rates or adverse events. The rate of lesions with fibrosis and poor maneuverability was significantly higher in the PCM with TD group (CE group vs CE with TD group vs PCM with TD group: fibrosis, 24% vs 47% vs 64%, p < 0.001; poor maneuverability, 5.3% vs 13% vs 20%, p = 0.002). Dissection speed was significantly higher in the PCM with TD than in the CE with TD group (p = 0.003). CONCLUSIONS: PCM with TD can achieve a stable en bloc resection rate and R0 dissection rate without adverse events even in the hands of trainees, irrespective of the size and location of the lesion, presence of fibrosis, and under poor maneuverability conditions.

Current status and future perspective of artificial intelligence applications in endoscopic diagnosis and management of gastric cancer.

Image recognition using artificial intelligence (AI) has progressed significantly due to innovative technologies such as machine learning and deep learning. In the field of gastric cancer (GC) management, research on AI-based diagnosis such as anatomical classification of endoscopic images, diagnosis of Helicobacter pylori infection, and detection and qualitative diagnosis of GC is being conducted, and an accuracy equivalent to that of physicians has been reported. It is expected that AI will soon be introduced in the field of endoscopic diagnosis and management of gastric cancer as a supportive tool for physicians, thus improving the quality of medical care.

Diagnostic performance in gastric cancer is higher using endocytoscopy with narrow-band imaging than using magnifying endoscopy with narrow-band imaging.

BACKGROUND: For diagnosing gastric cancer, differences in the diagnostic performance between endocytoscopy with narrow-band imaging and magnifying endoscopy with narrow-band imaging have not been reported. We aimed to clarify these differences by analyzing diagnoses made by endoscopists in Japan. METHODS: This single-center retrospective cohort study used 106 cancerous and 106 non-cancerous images obtained via both modalities (total, 424 images) for diagnosis. Sixty-one endoscopists with varying experience levels from 45 institutions were included. Diagnostic accuracy, sensitivity, specificity, and positive and negative predictive values were evaluated to determine the diagnostic performance of each modality and compared using the Mann-Whitney U test. RESULTS: Among all endoscopists, diagnostic accuracy, sensitivity, positive predictive value, and negative predictive value were higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging (percentage [95% confidence interval]: 78.8% [76.4-83.0%] versus 72.2% [69.3-73.6%], p < 0.0001; 82.1% [78.3-85.9%] versus 64.2% [60.4-69.8%], p < 0.0001; 88.7% [82.6-90.7%] versus 78.5% [75.4-85.1%], p = 0.0023; 79.0% [75.3-80.5%] versus 68.5% [66.4-71.6%], p < 0.0001, respectively). In the magnifying endoscopy with narrow-band imaging-trained group, these values were also higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging (p < 0.0001, p = 0.0001, p = 0.0143, and p < 0.0001, respectively). Diagnostic accuracy, sensitivity, and negative predictive value were higher with endocytoscopy with narrow-band imaging than with magnifying endoscopy with narrow-band imaging in the magnifying endoscopy with narrow-band imaging-untrained group (p = 0.0041, p = 0.0049, and p = 0.0098, respectively). CONCLUSIONS: Diagnostic performance was higher using endocytoscopy with narrow-band imaging than using magnifying endoscopy with narrow-band imaging. Our results may help change the technique used to diagnose gastric cancer.

Adding Narrow-Band Imaging to Chromoendoscopy for the Evaluation of Tumor Response to Neoadjuvant Therapy in Rectal Cancer.

BACKGROUND: Endoscopic assessment is crucial in diagnosing clinical complete response after neoadjuvant therapy in rectal cancer. OBJECTIVE: The purpose of this research was to evaluate the benefits of adding narrow-band imaging endoscopy to conventional chromoendoscopy in predicting pathologic complete response in the surgical specimen. DESIGN: This was a prospective nonrandomized study. SETTINGS: This was an ad hoc study of a prospective phase II trial at a single comprehensive cancer center that evaluated oncologic outcomes of a neoadjuvant therapy for rectal cancer. PATIENTS: Patients with high-risk stage II to III low rectal cancer who received neoadjuvant modified folinic acid, fluorouracil, and oxaliplatin plus bevacizumab followed by chemoradiotherapy and surgery were included. INTERVENTION: Tumor response after neoadjuvant therapy was evaluated using conventional white light endoscopy plus chromoendoscopy then followed by using narrow-band imaging based on a predefined diagnostic protocol. MAIN OUTCOME MEASURES: Diagnostic accuracy for predicting pathologic complete response and inter-rater agreement between an expert and trainee endoscopists were compared between the assessments using conventional white light endoscopy plus chromoendoscopy and the assessment adding narrow-band imaging. RESULTS: In total, 61 patients were eligible for the study, and 19 had pathologic complete response (31.1%). Although the addition of narrow-band imaging correctly converted the diagnosis in 3 patients, overall diagnostic improvement in predicting pathologic complete response was limited (conventional chromoendoscopy vs adding narrow-band imaging: accuracy, 70.5% vs 75.4%; sensitivity, 63.2% vs 73.7%; specificity, 73.8% vs 76.2%; positive predictive value, 52.2% vs 58.3%; and negative predictive value, 81.6% vs 86.5%). A κ value for the inter-rater agreement improved from 0.599 to 0.756 by adding narrow-band imaging. LIMITATIONS: This was a single-center study with a relatively small sample size. CONCLUSIONS: Despite the limited improvement in diagnostic accuracy, adding narrow-band imaging to chromoendoscopy improved inter-rater agreement between the expert and nonexpert endoscopists. Narrow-band imaging is a reliable and promising modality for universal standardization of the diagnosis of clinical complete response. See Video Abstract at http://links.lww.com/DCR/B275. ADICIÓN DE IMÁGENES DE BANDA ESTRECHA A LA CROMOENDOSCOPÍA PARA LA EVALUACIÓN DE LA RESPUESTA TUMORAL A LA TERAPIA NEOADYUVANTE EN EL CÁNCER DE RECTO: La evaluación endoscópica es fundamental para valorar la respuesta clínica completa después de la terapia neoadyuvante en el cáncer de recto.Evaluar los beneficios de agregar endoscopia de imagen de banda estrecha a la cromoendoscopía convencional para predecir la respuesta patológica completa en la muestra quirúrgica.Estudio prospectivo no aleatorizado.Un estudio ad hoc de un ensayo prospectivo de fase II en un solo centro integral de cáncer que evaluó los resultados oncológicos de una terapia neoadyuvante para el cáncer rectal.Pacientes con cáncer rectal bajo de alto riesgo en estadio II-III que recibieron ácido folínico neoadyuvante modificado, fluorouracilo y oxaliplatino más bevacizumab seguido de quimiorradioterapia y cirugía.La respuesta tumoral después de la terapia neoadyuvante se evaluó mediante endoscopia de luz blanca convencional más cromoendoscopía, seguido de imágenes de banda estrecha basadas en un protocolo de diagnóstico predefinido.La precisión diagnóstica para predecir la respuesta patológica completa y el acuerdo entre evaluadores entre un experto y un endoscopista en entrenamiento se compararon entre las evaluaciones utilizando endoscopia de luz blanca convencional más cromoendoscopía y la evaluación agregando imágenes de banda estrecha.En total, 61 pacientes fueron elegibles para el estudio, y 19 tuvieron una respuesta patológica completa (31.1%). Aunque la adición de imágenes de banda estrecha convirtió correctamente el diagnóstico en 3 pacientes, la mejora diagnóstica general en la predicción de la respuesta patológica completa fue limitada (cromoendoscopía convencional versus adición de imágenes de banda estrecha: precisión, 70.5% versus 75.4%; sensibilidad, 63.2% versus 73.7%; especificidad, 73.8% versus 76.2%; valor predictivo positivo, 52.2% versus 58.3%; y valor predictivo negativo, 81.6% versus 86.5%). Un valor de kappa para el acuerdo entre evaluadores mejoró de 0.599 a 0.756 al agregar imágenes de banda estrecha.Un estudio de centro único con un tamaño de muestra relativamente pequeño.A pesar de la mejora limitada en la precisión diagnóstica, agregar imágenes de banda estrecha a la cromoendoscopía mejoró el acuerdo entre evaluadores entre los endoscopistas expertos y no expertos. La imagenología de banda estrecha es una modalidad confiable y prometedora para la estandarización universal del diagnóstico de respuesta clínica completa. Consulte Video Resumen en http://links.lww.com/DCR/B275.

Incidence of metachronous cancer after endoscopic submucosal dissection: a comparison between undifferentiated-type and differentiated-type early gastric cancer.

BACKGROUND AND AIMS: Endoscopic submucosal dissection (ESD) has become an important and minimally invasive treatment for early gastric cancer (EGC) with a negligible risk of metastasis not only for differentiated-type (D-type) cancer but also for undifferentiated-type (UD-type) cancer. We aimed to investigate the incidence and characteristics of metachronous cancer after ESD for UD-type cancer, which has not yet been elucidated. METHODS: In total, 175 patients who underwent ESD for UD-type EGC were enrolled. For comparison, 350 patients who underwent ESD for D-type EGC during the same period were randomly selected. These patients underwent a follow-up EGD annually. The median observation period was 6.0 years and 5.4 years, respectively. RESULTS: The annual incidence of metachronous cancer after ESD for UD-type and D-type cancer was .9% and 5.3%, respectively. Among the patients who underwent ESD for UD-type cancer, 30.9% of patients were uninfected with Helicobacter pylori, whereas all patients who underwent ESD for D-type cancer were infected with H pylori. All patients who developed metachronous cancer were infected with H pylori. UD-type metachronous cancer developed more frequently in patients after ESD for UD-type cancer than after ESD for D-type cancer, and the curative resection rate of ESD was significantly lower in these cases. CONCLUSIONS: Metachronous cancers developed only in H pylori-infected patients in this cohort. Although metachronous cancer incidence was significantly less frequent in patients after ESD for UD-type cancer, the curative resection rate of ESD was significantly lower. Routine surveillance should be conducted more carefully after ESD for UD-type cancer, especially in H pylori-infected patients.

Artificial intelligence-based diagnostic system classifying gastric cancers and ulcers: comparison between the original and newly developed systems.

BACKGROUND: We previously reported for the first time the usefulness of artificial intelligence (AI) systems in detecting gastric cancers. However, the "original convolutional neural network (O-CNN)" employed in the previous study had a relatively low positive predictive value (PPV). Therefore, we aimed to develop an advanced AI-based diagnostic system and evaluate its applicability for the classification of gastric cancers and gastric ulcers. METHODS: We constructed an "advanced CNN" (A-CNN) by adding a new training dataset (4453 gastric ulcer images from 1172 lesions) to the O-CNN, which had been trained using 13 584 gastric cancer and 373 gastric ulcer images. The diagnostic performance of the A-CNN in terms of classifying gastric cancers and ulcers was retrospectively evaluated using an independent validation dataset (739 images from 100 early gastric cancers and 720 images from 120 gastric ulcers) and compared with that of the O-CNN by estimating the overall classification accuracy. RESULTS: The sensitivity, specificity, and PPV of the A-CNN in classifying gastric cancer at the lesion level were 99.0 % (95 % confidence interval [CI] 94.6 %-100 %), 93.3 % (95 %CI 87.3 %-97.1 %), and 92.5 % (95 %CI 85.8 %-96.7 %), respectively, and for classifying gastric ulcers were 93.3 % (95 %CI 87.3 %-97.1 %), 99.0 % (95 %CI 94.6 %-100 %), and 99.1 % (95 %CI 95.2 %-100 %), respectively. At the lesion level, the overall accuracies of the O- and A-CNN for classifying gastric cancers and gastric ulcers were 45.9 % (gastric cancers 100 %, gastric ulcers 0.8 %) and 95.9 % (gastric cancers 99.0 %, gastric ulcers 93.3 %), respectively. CONCLUSION: The newly developed AI-based diagnostic system can effectively classify gastric cancers and gastric ulcers.

[Endoscopic Diagnosis Using Artificial Intelligence].

Image recognition using artificial intelligence(AI)has developed dramatically with innovative technologies such as machine learning and deep learning. Currently, it is considered that AI has exceeded human ability in image recognition. In the field of endoscopic diagnosis, development of computer-aided diagnosis(CAD)systems using AI is progressing. The CAD is expected to help endoscopists improve detection and characterization of polyp, cancer, and inflamation in all digestive area. Some CAD systemes showing ability better than endoscopists have been reported. It may be well applicable to daily clinical practice as real time endoscopic diagnosis in the near future.

Risk Factors Linking Esophageal Squamous Cell Carcinoma With Head and Neck Cancer or Gastric Cancer.

GOALS: To investigate retrospectively the risk factors for synchronous and metachronous cancers in the upper gastrointestinal tract in patients with superficial esophageal squamous cell carcinoma (ESCC). BACKGROUND: In patients who have received endoscopic resection (ER) for ESCC, synchronous and metachronous cancers are frequently detected not only in the esophagus but also in the head and neck area and the stomach. STUDY: A total of 285 patients who received ER for superficial ESCC were enrolled in this analysis. These patients were periodically followed-up endoscopically. Cumulative occurrence rates of the metachronous second primary cancers were determined by Kaplan-Meier method. Risk factors for synchronous and metachronous cancers in the head and neck area and the stomach were determined by logistic regression analyses. RESULTS: During a mean follow-up period of 76 months, the 5-year cumulative occurrence of metachronous esophageal, head and neck, and stomach cancer was 14.0%, 2.8%, and 4.1%, respectively. Although the presence of multiple lugol-voiding lesions in the esophagus was a significant risk factor for synchronous and metachronous head and neck cancers (odds ratio, 3.8; 95% confidence interval, 1.7-9.0), older age (>65 y) was a significant risk factor for synchronous and metachronous gastric cancer (odds ratio, 3.1; 95% confidence interval, 1.2-9.3). CONCLUSIONS: The risk factors for the cooccurrence of head and neck cancer and that of gastric cancer in patients with ESCC differ. This information will likely be useful for managing patients who have been treated with ER for ESCC and who possess carcinogenic potential throughout the upper gastrointestinal tract.