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.

Current Status of Artificial Intelligence-Based Computer-Assisted Diagnosis Systems for Gastric Cancer in Endoscopy.

Artificial intelligence (AI) is gradually being utilized in various fields as its performance has been improving with the development of deep learning methods, availability of big data, and the progression of computer processing units. In the field of medicine, AI is mainly implemented in image recognition, such as in radiographic and pathologic diagnoses. In the realm of gastrointestinal endoscopy, although AI-based computer-assisted detection/diagnosis (CAD) systems have been applied in some areas, such as colorectal polyp detection and diagnosis, so far, their implementation in real-world clinical settings is limited. The accurate detection or diagnosis of gastric cancer (GC) is one of the challenges in which performance varies greatly depending on the endoscopist's skill. The diagnosis of early GC is especially challenging, partly because early GC mimics atrophic gastritis in the background mucosa. Therefore, several CAD systems for GC are being actively developed. The development of a CAD system for GC is considered challenging because it requires a large number of GC images. In particular, early stage GC images are rarely available, partly because it is difficult to diagnose gastric cancer during the early stages. Additionally, the training image data should be of a sufficiently high quality to conduct proper CAD training. Recently, several AI systems for GC that exhibit a robust performance, owing to being trained on a large number of high-quality images, have been reported. This review outlines the current status and prospects of AI use in esophagogastroduodenoscopy (EGDS), focusing on the diagnosis of GC.

Implementation of artificial intelligence in upper gastrointestinal endoscopy.

The application of artificial intelligence (AI) using deep learning has significantly expanded in the field of esophagogastric endoscopy. Recent studies have shown promising results in detecting and differentiating early gastric cancer using AI tools built using white light, magnified, or image-enhanced endoscopic images. Some studies have reported the use of AI tools to predict the depth of early gastric cancer based on endoscopic images. Similarly, studies based on using AI for detecting early esophageal cancer have also been reported, with an accuracy comparable to that of endoscopy specialists. Moreover, an AI system, developed to diagnose pharyngeal cancer, has shown promising performance with high sensitivity. These reports suggest that, if introduced for regular use in clinical settings, AI systems can significantly reduce the burden on physicians. This review summarizes the current status of AI applications in the upper gastrointestinal tract and presents directions for clinical practice implementation and future research.

Asynchronous bilateral anastomosis site sigmoid colon cancer after ureterosigmoidostomy: a case report.

BACKGROUND: We present a case of asynchronously occurring adenocarcinomas 29 and 36 years after ureterosigmoidostomy for bladder cancer, respectively, at both anastomosis sites. CASE PRESENTATION: A colonoscopy that was performed on a 69-year-old man because of bloody stool and an elevated carcinoembryonic antigen (CEA) level revealed a polypoid lesion at the right ureterosigmoid anastomosis site 29 years after the patient's ureterosigmoidostomy. Endoscopic resection was performed, and the lesion was diagnosed as adenocarcinoma. Seven years later (36 years after ureterosigmoidostomy), an elevated lesion was detected at the left ureterosigmoid anastomosis site by colonoscopy performed after detection of high CEA levels. Biopsy revealed an adenocarcinoma that was immunohistologically positive for CDX2; sigmoidectomy and ureterectomy were subsequently performed. The pathological diagnosis of the second tumor was adenocarcinoma arising in the ureterosigmoid anastomosis site and invading the left ureter. CONCLUSIONS: Diligent long-term follow-up of patients who underwent ureterosigmoidostomy is essential.

Continuous Hemodiafiltration with an AN69ST Hemofilter (AN69ST-CHDF) as FGF-23-Lowering Therapy.

BACKGROUND: Recent studies have shown that fibroblast growth factor-23 (FGF-23) is elevated not only in chronic kidney disease (CKD), but also in acute illnesses such as acute kidney injury, septic shock, and acute heart failure. FGF-23 would be not only a simple biomarker but also a direct toxic factor in acute illness. Therefore, lowering circulating FGF-23 levels in clinical practice would be an exciting and valuable interventional strategy. Continuous hemodiafiltration (CHDF) is often performed for the treatment of the aforementioned acute illnesses. We have previously reported that an acrylonitrile-co-methallyl sulfonate surface-treated (AN69ST) membrane has a greater capacity for in vitro FGF-23 adsorption than polysulfone and polymethyl methacrylate membranes. However, reports related to the influence of AN69ST-CHDF on serum FGF-23 levels in acute illness are lacking. In this study, we investigated the effect of AN69ST-CHDF on circulating FGF-23 concentrations in clinical practice. METHODS: Subjects comprised six inpatients who underwent AN69ST-CHDF for an acute illness. Blood samples for the measurement of serum FGF-23 were collected at 0, 3, and 12 hours post-treatment. Blood samples were also drawn from the extracorporeal circuit at the inlet and outlet of the hemofilter 3 hours after CHDF initiation, in order to calculate the clearance of serum FGF-23. RESULTS: Three and 12 hours after the start of AN69ST-CHDF, circulating FGF-23 levels decreased from baseline values with a marginal statistical significance (p = 0.0625 and 0.0938, respectively). An FGF-23 clearance of 27.5 [interquartile range: 19.4 - 29.2] mL/minute 3 hours after the initiation of AN69ST-CHDF was achieved. CONCLUSIONS: Our results suggest that AN69ST-CHDF can be a novel FGF-23 lowering therapy for acute illnesses requiring acute blood purification.

Prognostic Impact of Histologic Type in Curatively Resected Stage IV Colorectal Cancer: A Japanese Multicenter Retrospective Study.

BACKGROUND: This study aimed to clarify differences in prognostic factors, metastatic features, and recurrence rates between histologic types in patients with stage 4 colorectal cancer (CRC) who had undergone curative resection. METHODS: The data from 1131 patients with stage 4 colorectal cancer from the databases of referral institutions were analyzed. The patients were divided into two groups according to histologic types as follows: patients with poorly differentiated adenocarcinoma, mucinous adenocarcinoma, or signet-ring cell carcinoma (Por/Muc/Sig) and patients with well-differentiated or moderately differentiated adenocarcinoma (Wel/Mod). Differences in clinicopathologic features, relapse-free survival (RFS) rates, and cancer-specific survival (CSS) rates between the groups were evaluated. RESULTS: Although RFS did not differ between the Por/Muc/Sig and Wel/Mod groups, CSS was significantly shorter in the Por/Muc/Sig group's than in the Wel/Mod group, and survival after recurrence was significantly worse in the Por/Muc/Sig group than in theWel/Mod group. The incidence of peritoneal or local recurrence was significantly higher for the Por/Muc/Sig patients, whereas the resection recurrence rate was 16.4 %. Multivariate analysis suggested that histologic type was an independent prognostic factor for survival after recurrence. CONCLUSIONS: The patients with Por/Muc/Sig CRC synchronous metastasis had significantly shorter survival times than the patients with other CRC histologies, even if the metastases were curatively resected.