Clinical outcomes of endoscopic submucosal dissection for esophageal squamous cell carcinoma with esophageal varices: Multicenter retrospective study.

OBJECTIVES: Clinical outcomes of endoscopic submucosal dissection (ESD) for esophageal squamous cell carcinoma (ESCC) with esophageal varices (EVs) are obscure. We aimed to elucidate the clinical outcomes of ESD for ESCC with EVs in a multicenter, retrospective study. METHODS: We established a retrospective cohort of 30 patients with ESCC complicating EVs, who underwent ESD at 11 Japanese institutions. Rates of en bloc resection and R0 resection, procedure time, and adverse events were evaluated as indicators of the feasibility and safety of ESD. Additional treatment, recurrence, and metastasis of the lesions were evaluated as indicators of the long-term efficacy of ESD. RESULTS: Portal hypertension was caused by cirrhosis, of which alcohol was the most common cause. En bloc resection was achieved in 93.3% and R0 resection in 80.0% of the patients. The median procedure time was 92 min. Adverse events included a case of uncontrolled intraoperative bleeding leading to discontinuation of ESD and a case of esophageal stricture due to extensive resection. During the follow-up period of a median for 42 months, a patient with local recurrence and another patient with liver metastasis were observed. One patient died of liver failure after receiving chemoradiotherapy as an additional treatment after ESD. No patient died of ESCC. CONCLUSION: This multicenter, retrospective cohort study demonstrated the safety and efficacy of ESD for ESCC with EVs. Further studies are needed to establish appropriate treatment methods for EVs before ESD and additional treatments for patients with insufficient ESD.

[Gastric varices treated by balloon-occluded retrograde transvenous obliteration following oxaliplatin-based chemotherapy for gastric cancer].

A 78-year-old female patient with stomach cancer (with hepatic metastasis and peritoneal dissemination) had received eight courses of an S-1 and oxaliplatin regimen as palliative chemotherapy. Computed tomography revealed liver deformities and incidental gastric varices. Esophagogastroduodenoscopy confirmed the findings of gastric varices in the cardia and fornix. It was suspected that oxaliplatin-based chemotherapy had induced non-variceal portal hypertension in the patient-similar to that which is seen in patients with colon cancer who are treated with oxaliplatin-based chemotherapy. We had chosen balloon-occluded retrograde transvenous obliteration (BRTO) for the preventive treatment of gastric varices because the patient had a gastro-renal shunt, which enabled access to the gastric varices via the vena cava. Our patient had undergone BRTO, which resulted in the endoscopic disappearance of gastric varices. Currently, the patient is continuing chemotherapy without bleeding from gastric varices. Our case suggests that patients with gastric cancer treated with oxaliplatin-based chemotherapy require careful follow-up for portal hypertension.

Automated evaluation of colon capsule endoscopic severity of ulcerative colitis using ResNet50.

Capsule endoscopy has been widely used as a non-invasive diagnostic tool for small or large intestinal lesions. In recent years, automated lesion detection systems using machine learning have been devised. This study aimed to develop an automated system for capsule endoscopic severity in patients with ulcerative colitis along the entire length of the colon using ResNet50. Capsule endoscopy videos from patients with ulcerative colitis were collected prospectively. Each single examination video file was partitioned into four segments: the cecum and ascending colon, transverse colon, descending and sigmoid colon, and rectum. Fifty still pictures (576 × 576 pixels) were extracted from each partitioned video. A patch (128 × 128 pixels) was trimmed from the still picture at every 32-pixel-strides. A total of 739,021 patch images were manually classified into six categories: 0) Mayo endoscopic subscore (MES) 0, 1) MES1, 2) MES2, 3) MES3, 4) inadequate quality for evaluation, and 5) ileal mucosa. ResNet50, a deep learning framework, was trained using 483,644 datasets and validated using 255,377 independent datasets. In total, 31 capsule endoscopy videos from 22 patients were collected. The accuracy rates of the training and validation datasets were 0.992 and 0.973, respectively. An automated evaluation system for the capsule endoscopic severity of ulcerative colitis was developed. This could be a useful tool for assessing topographic disease activity, thus decreasing the burden of image interpretation on endoscopists.

Esophageal achalasia with mucosal damage due to enteric-coated aspirin.

A 76-year-old man was referred to our hospital for examination and treatment of dysphagia. He has been taking enteric-coated aspirin for myocardial infarction. Esophagogastroduodenoscopy (EGD) revealed the presence of esophageal ulcers in the distal esophagus and five to six tablets of enteric-coated aspirin. The esophageal ulcers were believed to have been caused by the retention of aspirin within the esophagus due to achalasia. We substituted enteric-coated aspirin with powdered aspirin. A follow-up EGD performed 1 month later showed improvement of esophageal mucosa. The patient was diagnosed with type I achalasia. Per-oral endoscopic myotomy was performed, and his symptoms improved after the procedure. Although a few studies have investigated the direct effect of aspirin, none of them has reported on the direct effect of aspirin on the esophagus. It might be effective to administer powdered aspirin for patients with achalasia to prevent esophageal ulcers caused by the direct effect of aspirin.

Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet.

BACKGROUND: Machine learning has led to several endoscopic studies about the automated localization of digestive lesions and prediction of cancer invasion depth. Training and validation dataset collection are required for a disease in each digestive organ under a similar image capture condition; this is the first step in system development. This data cleansing task in data collection causes a great burden among experienced endoscopists. Thus, this study classified upper gastrointestinal (GI) organ images obtained via routine esophagogastroduodenoscopy (EGD) into precise anatomical categories using AlexNet. METHOD: In total, 85,246 raw upper GI endoscopic images from 441 patients with gastric cancer were collected retrospectively. The images were manually classified into 14 categories: 0) white-light (WL) stomach with indigo carmine (IC); 1) WL esophagus with iodine; 2) narrow-band (NB) esophagus; 3) NB stomach with IC; 4) NB stomach; 5) WL duodenum; 6) WL esophagus; 7) WL stomach; 8) NB oral-pharynx-larynx; 9) WL oral-pharynx-larynx; 10) WL scaling paper; 11) specimens; 12) WL muscle fibers during endoscopic submucosal dissection (ESD); and 13) others. AlexNet is a deep learning framework and was trained using 49,174 datasets and validated using 36,072 independent datasets. RESULTS: The accuracy rates of the training and validation dataset were 0.993 and 0.965, respectively. CONCLUSIONS: A simple anatomical organ classifier using AlexNet was developed and found to be effective in data cleansing task for collection of EGD images. Moreover, it could be useful to both expert and non-expert endoscopists as well as engineers in retrospectively assessing upper GI images.

Case report of lanthanum deposition in the esophagus.

A 69-year-old woman had received hemodialysis for chronic renal failure and was taking lanthanum carbonate since 63 years of age. She presented with appetite loss and nausea. We performed esophagogastroduodenoscopy, which revealed multiple longitudinal white plaques in the esophagus. Lesion biopsies showed lanthanum deposition, and lanthanum carbonate was found histologically by energy-dispersive X-ray spectroscopy. The plaques of this patient appeared like those of dabigatran-induced esophagitis, and may have occurred due to long-term contact of the esophageal epithelium with lanthanum carbonate because patient spent time in lying state. Although a few studies regarding lanthanum deposition in the stomach have been conducted, there are no reports on lanthanum deposition in the esophagus. This case suggests that the presence of longitudinal white plaques in the esophagus may indicate lanthanum deposition.

Aquaporin-4 antibody positive neuromyelitis optica spectrum disorder associated with esophageal cancer.

Autoimmune diseases are sometimes associated with neoplasms. A 70-year-old Japanese woman with myelitis, seropositive for aquaporin-4 (AQP4) antibody, was diagnosed with neuromyelitis optica spectrum disorder (NMOSD); thereafter an esophageal squamous cell carcinoma was identified. Immunohistochemically, her cancer was anti-AQP4 antibody negative. Her symptoms, imaging findings and AQP4 titer markedly improved with corticosteroid and anti-cancer therapies. Although AQP4 may be a paraneoplastic antigen, paraneoplastic syndrome could not be definitively diagnosed in this case. Nevertheless, this is the first report of an association between AQP4 antibody-seropositive NMOSD and esophageal cancer. The possibility of underlying malignancy should be considered in patients diagnosed with NMOSD.