Artificial intelligence using deep learning analysis of endoscopic ultrasonography images for the differential diagnosis of pancreatic masses.

BACKGROUND : There are several types of pancreatic mass, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognition of data patterns. This study aimed to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic mass (pancreatic ductal adenocarcinoma [PDAC], pancreatic adenosquamous carcinoma [PASC], acinar cell carcinoma [ACC], metastatic pancreatic tumor [MPT], neuroendocrine carcinoma [NEC], neuroendocrine tumor [NET], solid pseudopapillary neoplasm [SPN], chronic pancreatitis, and autoimmune pancreatitis [AIP]). METHODS : Patients who underwent EUS were included in this retrospective study. The included patients were divided into training, validation, and test cohorts. Using these cohorts, an AI model that can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions was developed using a deep-learning architecture and the diagnostic performance of the AI model was evaluated. RESULTS : 22 000 images were generated from 933 patients. The area under the curve, sensitivity, specificity, and accuracy (95 %CI) of the AI model for the diagnosis of pancreatic carcinomas in the test cohort were 0.90 (0.84-0.97), 0.94 (0.88-0.98), 0.82 (0.68-0.92), and 0.91 (0.85-0.95), respectively. The per-category sensitivities (95 %CI) of each disease were PDAC 0.96 (0.90-0.99), PASC 1.00 (0.05-1.00), ACC 1.00 (0.22-1.00), MPT 0.33 (0.01-0.91), NEC 1.00 (0.22-1.00), NET 0.93 (0.66-1.00), SPN 1.00 (0.22-1.00), chronic pancreatitis 0.78 (0.52-0.94), and AIP 0.73 (0.39-0.94). CONCLUSIONS : Our developed AI model can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions, but external validation is needed.

Risk factor analysis for adverse events and stent dysfunction of endoscopic ultrasound-guided choledochoduodenostomy.

BACKGROUND AND AIMS: Although the technique of endoscopic ultrasound-guided choledochoduodenostomy (EUS-CDS) is becoming standardized, its safety issues have not been sufficiently investigated. Therefore, we aimed to identify factors associated with adverse events and stent patency in EUS-CDS. METHODS: Consecutive patients who underwent EUS-CDS between September 2003 and July 2017 were included. Technical/clinical success, adverse events and stent dysfunctions were analyzed retrospectively. RESULTS: A total of 151 patients underwent EUS-CDS. In nine patients, procedures were discontinued before puncture. Technical and clinical success rates were 96.5% (137/142) and 98.5% (135/137), respectively. The adverse event rate was 20.4% (29/142). As a risk factor for peritonitis, plastic stents (PS) showed a significantly high odds ratio (OR) compared with covered self-expandable metal stents (CSEMS; OR, 4.31; P = 0.030). CSEMS cases showed a significantly longer patency period than PS cases (329 vs 89 days; HR, 0.35; P < 0.001). As a risk factor for early stent dysfunction (within 14 days), stent direction to the oral side showed a significantly high OR (OR, 43.47; P < 0.001). In cases with oblique-viewing EUS, double penetration of the duodenum occurred at significantly higher frequency than in cases with forward-viewing EUS (7.0 vs 0.0%; P = 0.024). CONCLUSIONS: Plastic stents and stent direction to the oral side were risk factors for peritonitis and early stent dysfunction, respectively. Using covered self-expandable metal stents and changing stent direction to the anal side seemed appropriate to prevent peritonitis and early stent dysfunction.

A Prospective Trial Evaluating the Safety of a Shortened Infusion of Ramucirumab in Patients with Gastrointestinal Cancer.

LESSONS LEARNED: A shortened infusion of ramucirumab (from 60 to 20 minutes) was safe and feasible without infusion-related reactions.Twenty-minute infusions of ramucirumab can be an option for patients with no infusion-related reactions during the first 60-minute treatment. BACKGROUND: Ramucirumab is usually administered over 60 minutes, during which it is unlikely to cause infusion-related reactions (IRRs). This prospective study evaluated the safety of a shortened infusion of ramucirumab. METHODS: Patients who received their first dose of ramucirumab in a 60-minute infusion without developing IRRs were eligible and received their second ramucirumab dose for 20 minutes. The primary study endpoint was incidence of IRR during the first short-term infusion, and the secondary endpoints were incidence of IRR at any time and adverse events other than IRR. RESULTS: Of the 40 patients enrolled (median age, 68.5 years), 20 (55%) were male, 27 (67.5%) had stage IV gastric cancer, 25 (62.5%) received ramucirumab in combination with taxane-based chemotherapy, and 24 (60%) received only a single administration of ramucirumab prior to their enrollment. Notably, no IRR was observed during the first short-term infusion (IRR rate, 0%; 95% confidence interval [CI], 0%-0.72%). Among the 149 short-term infusions performed, there were no instances of IRRs or unexpected adverse events related to the treatment (Table 1). CONCLUSION: For patients without development of IRRs upon the first ramucirumab administration, shortening infusion time (from 60 to 20 minutes) is safe and feasible.

Usefulness of septal thickness measurement on endoscopic ultrasound as a predictor of malignancy of branched-duct and mixed-type intraductal papillary mucinous neoplasm of the pancreas.

BACKGROUND AND AIM: Septal thickness (ST) can predict a malignant branch-duct (BD) and mixed-type intraductal papillary mucinous neoplasm (IPMN) of the pancreas, but its cut-off value has not been established. The aim of the present study was to determine the optimal ST cut-off value to predict malignancy using endoscopic ultrasound (EUS). METHODS: We retrospectively identified 200 patients with IPMN, including 132 with BD- and mixed-IPMN, who underwent surgical resection between 1989 and 2017. ST was defined as the septum or lesion wall with the maximum diameter in BD- and mixed-IPMN. The possibility of ST as a malignant predictor was examined, as well as the diagnostic ability of ST combined with mural nodule (MN) height for malignant IPMN. RESULTS: Among the 132 IPMN patients, pathological diagnosis was benign in 81 (61.4%) and malignant in 51 (38.6%). Area under the curve for the diagnosis of malignancy using ST was 0.74 for pathological specimens, 0.70 for EUS and 0.56 for computed tomography. Multivariate analysis showed that the odds ratios for ST ≥2.5 mm and MN height ≥5 mm were 3.51 [95% confidence interval (CI), 1.55-7.97, P = 0.003] and 3.36 (95% CI, 1.52-7.45, P = 0.003), respectively. CONCLUSIONS: Septal thickness was an independent predictive factor similar to MN height for malignant IPMN in a multivariate analysis. The ST on EUS appeared to be the thickness of a fibrotic septum associated with the malignant transformation of IPMN. An ST cut-off value of 2.5 mm might provide an accurate prediction of malignant IPMN.

A rare case of schwannoma of the small intestine discovered during intussusception.

A woman in her 60s with anemia was diagnosed with a small intestinal intussusception on computed tomography. She underwent a double-balloon endoscopy, which revealed submucosal tumor in the ileum. Suspected to be the cause of anemia and intussusception, surgical intervention was carried out, revealing it to be a schwannoma. Schwannomas of the small intestine are very rare, and because exophytic growths are common, intussusception due to luminal side development is even rarer.

Prognostic impact of shift to low visceral fat mass after neoadjuvant chemotherapy in patients with esophageal cancer.

BACKGROUND: Based on the JCOG1109 trial, it is suggested that the combination of docetaxel, cisplatin, and 5-fluorouracil (DCF) could potentially become a standard neoadjuvant chemotherapy regimen, alongside the conventional 5-fluorouracil and cisplatin (CF) therapy, for esophageal cancer. However, there are few reports on the impact of body composition changes associated with neoadjuvant chemotherapy on prognosis. AIM: Our study aimed to explore the effect of different neoadjuvant chemotherapy regimens on body composition during treatment and the impacts of body composition changes on their prognosis. METHODS AND RESULTS: This is a retrospective study of 215 patients with advanced thoracic esophageal cancer who had surgery after neoadjuvant chemotherapy from 2013 to 2019. Computed tomography scans were performed before and after neoadjuvant chemotherapy to assess body composition. Skeletal muscle mass index (SMI) was calculated by dividing total skeletal muscle mass at the 3rd lumbar level by the square of height, while visceral and subcutaneous fat masses were measured at the level of umbilicus. Patients in the lowest 25% of both sexes were classified into the low visceral fat and low subcutaneous fat groups, respectively. Of the patients enrolled, 178 were male and 37 were female. Among them, 91 had clinical Stage II disease, and 124 had clinical Stage III disease. Additionally, 146 patients received neoadjuvant chemotherapy CF, and 69 received neoadjuvant chemotherapy DCF. Comparing the DCF and CF groups, the DCF group consisted of significantly younger patients (p < .01), a higher proportion of males (p = .03), and a greater number of clinical Stage III cases (p < .01). However, although percent change in SMI and visceral fat mass was not significantly different between two regimens, percent change in subcutaneous fat mass was significant in the DCF group. The major prognostic factors for patients undergoing surgery after neoadjuvant chemotherapy for thoracic esophageal cancer were clinical Stage III, transition to low visceral fat, and response rating (SD/PD), while the specific neoadjuvant chemotherapy regimen did not significantly influence the outcomes. CONCLUSION: This study suggests that prevention of the shift to low visceral fat throughout the neoadjuvant chemotherapy process should improve patient outcomes.

A rare case of a superficial squamous cell carcinoma (so-called cloacogenic carcinoma) of the rectum.

A rare case of a squamous cell carcinoma (so-called cloacogenic carcinoma) showing extensive superficial spread to the rectum is presented. A 69-year-old woman had undergone colonoscopy for annual check-up, and a whitish, flat lesion with a central depressed area, 20 mm in size, was identified in the lower rectum. Narrow-band imaging with magnifying observation showed abnormal microvessels without the intrapapillary capillary loop patterns. Endoscopically, the margin of the lesion was unclear. Biopsy was performed, and a histological diagnosis of transitional cell carcinoma was made. Computed tomography showed no evidence of involvement of adjacent organs, lymph nodes or distant sites. Cystoscopy found no abnormality in the bladder mucosa. Owing to difficulty diagnosing this tumor accurately, local excision with transanal endoscopic microsurgery was performed. Cloacogenic carcinoma with submucosal invasion was diagnosed. A human papilloma virus (HPV) polymerase chain reaction test was positive. Judging from the histological findings and the positive HPV test, we hypothesis that the tumor was likely arising from the anal transitional zone with marked superficial spread to the rectum. Clinicians should keep in mind that this variant of squamous cell carcinoma may occur in the rectum, even if no endoscopic findings are seen in the anal transitional zone.

Skeletal Muscle Quality and Quantity Affect Prognosis after Neoadjuvant Chemotherapy with a Triple Regimen of Docetaxel/Cisplatin/5-FU in Patients with Esophageal Cancer.

The purpose of this study was to identify factors associated with the prognosis after docetaxel, cisplatin, and 5-fluorouracil (DCF) neoadjuvant chemotherapy (NAC) in patients with advanced esophageal squamous cell carcinoma (ESCC) undergoing surgical resection. We retrospectively examined a total of 100 patients who received neoadjuvant DCF therapy for ESCC at our institution between 2011 and 2020. The psoas muscle index (PMI) was calculated from the psoas muscle area at the L3 vertebral level, and the intramuscular adipose tissue content (IMAC) was calculated from the mean CT value of the multifidus muscle and from four points of subcutaneous fat. The median PMI value was 6.11 cm2/m2 (range, 3.12-11.07 cm2/m2) in men and 3.65 cm2/m2 (range, 2.70-6.82 cm2/m2) in women. The median IMAC was -0.426 (range, -0.079--0.968) in men and -0.359 (range, -0.079--0.671) in women. Based on the PMI, IMAC, and other patient factors, factors associated with NAC-DCF postoperative survival were identified using multivariate Cox regression analysis. A high IMAC was significantly related to overall survival after surgery (p = 0.005, hazard ratio 2.699). A comparison of Kaplan-Meier curves showed that the 5-year survival rate was 76.5% in the low IMAC group and 42.7% in the high IMAC group (log-rank test; p = 0.001). A low IMAC was associated with good survival outcomes and was an independent prognostic factor in patients with cStage II/III ESCC who were treated with the NAC-DCF regimen and underwent surgical resection.

Juvenile Hepatocellular Carcinoma in a Healthy Liver.

Primary hepatocellular carcinoma (HCC) in patients <30 years old is extremely rare. In younger patients, HCC develops against a background of persistent hepatitis B virus infection. We herein report a 23-year-old woman with HCC with all-negative hepatitis virus markers developing in an apparently healthy liver. Imaging studies showed a 50-mm hypervascular mass in segment 4 of the left liver lobe, compatible with HCC. The patient underwent surgical resection. A histological examination showed the presence of poorly differentiated HCC. The patient was diagnosed with HCC developing in a healthy liver. This is an extremely rare case of non-B non-C HCC.

Effect of Body Composition Change during Neoadjuvant Chemotherapy for Esophageal Squamous Cell Carcinoma.

Effects of changes in body composition during neoadjuvant chemotherapy (NAC) on perioperative complications and prognosis are unknown in patients with esophageal squamous cell carcinoma (ESCC). A total of 175 patients who underwent surgery for ESCC in our hospital between 2016 and 2019 were examined. The psoas muscle index (PMI) was calculated from the total psoas muscle area, and the visceral fat mass (VFM) at the umbilical level was measured. We defined body composition change (BCC) group as those with increased VFM of ≥ 3% and decreased PMI of ≥ 3% during NAC. Sarcopenia (S) was defined as PMI < 5.89 (male) and <4.06 (female). Nutritional assessment using the Subjective Global Assessment tool was performed upon admission. The percentages of BCC group, pre-NAC S, and post-NAC S was 32.5%, 79.4%, and 80.0%, respectively. BCC group had significantly more postoperative complications (p < 0.01) and longer hospital stays (p = 0.03) than groups pre-NAC S and post-NAC S. Overall survival (OS) analysis using the Cox hazard model showed that stage III (p < 0.01) and post-NAC S (p = 0.03) were poor prognostic factors. Changes in body composition during NAC affected perioperative complications and prognosis of patients with ESCC.

B2 puncture with forward-viewing EUS simplifies EUS-guided hepaticogastrostomy (with video).

Background and Objectives: EUS-guided hepaticogastrostomy (EUS-HGS) is in widespread use; however, there are few dedicated devices. The B2 route is technically easier than the B3 route for guidewire insertion, dilation, and stenting but if performed with conventional oblique-viewing (OV) EUS, B2 puncture can cause transesophageal puncture and severe adverse events. The aim of this study was to assess the efficacy of forward-viewing (FV) EUS, which we have developed to improve safety for B2 puncture in EUS-HGS (B2-EUS-HGS). Patients and Methods: This single-center retrospective study included 61 consecutive patients who underwent B2-EUS-HGS with FV between February 2020 and March 2021 at Aichi Cancer Center, Japan. The patients were prospectively enrolled, and clinical data were retrospectively collected for these 61 cases. Results: The overall technical success rate of EUS-HGS was 98.3% (60/61). The rate of EUS-HGS with FV was 95.0% (58/61) after three cases converted to OV, and that of B2-EUS-HGS with FV was 88.5% (54/61). The early adverse event rate was 6.5% (4/61). There were no instances of transesophageal puncture. Median procedure time was 24 min (range, 8-70), and no patient required cautery dilation. Conclusions: B2-EUS-HGS can be performed safely using FV, without transesophageal puncture, and supportability of the device is improved as FV is coaxial with the guidewire. FV was efficacious in B2-EUS-HGS, which shows promise for clinical application in the future.

Split-dose low-volume polyethylene glycol is non-inferior but less preferred compared with same-day bowel preparation for afternoon colonoscopy.

Currently, the same-day polyethylene glycol-electrolyte lavage solution (PEG-ELS) regimen is particularly recommended for afternoon colonoscopy as an alternative to the split-dose regimen in western countries. However, in Japan, the split-dose regimen has never been used as a standard colonoscopy preparation regimen. The aim of this study was to compare the efficacy and tolerability of split-dose PEG containing ascorbic acid (ASC) with same-day single dose PEG-ASC in Japan.This was a single-blinded, non-inferiority, two-center, randomized, controlled study. In-hospital patients were randomized to the same-day regimen or the split regimen using a web-based registry system. The same-day group was instructed to take 5 mL of sodium picosulfate in the evening, and on the day of the colonoscopy, they took 1.5 L of PEG-ASC. The split group was instructed to take 1 L of PEG-ASC before the day of colonoscopy, followed by another 1 L of PEG-ASC on the day of colonoscopy. Bowel cleansing was evaluated by the Boston Bowel Preparation Scale.A total of 153 patients were randomized to either the same-day group (n=78, males 60.0%, mean age 62.7 years) or the split group (n=75, 61.3%, 61.9 years). The rates of successful bowel cleansing were 83.3% in the same-day group vs. 92.0% (83.4%-97.0%) in the split group, P=0.10). No serious adverse events occurred in the study population. However, more patients in the same-day group were willing to repeat the same preparation regimen (P<0.001). The split-dose regimen was not inferior to the same-day regimen with respect to the efficacy of bowel preparation, but the patients preferred the same-day regimen.

Outcomes of Endoscopic Ultrasound-Guided Biliary Drainage in Patients Undergoing Antithrombotic Therapy.

BACKGROUND/AIMS: The Japan Gastroenterological Endoscopy Society (JGES) has published guidelines for gastroenterological endoscopy in patients undergoing antithrombotic treatment. These guidelines classify endoscopic ultrasound-guided biliary drainage (EUS-BD) as a high-risk procedure. Nevertheless, the bleeding risk of EUS-BD in patients undergoing antithrombotic therapy is uncertain. Therefore, this study aimed to assess the bleeding risk in patients undergoing antithrombotic therapy. METHODS: This single-center retrospective study included 220 consecutive patients who underwent EUS-BD between January 2013 and December 2018. We managed the withdrawal and continuation of antithrombotic agents according to the JGES guidelines. We compared the bleeding event rates among patients who received and those who did not receive antithrombotic agents. RESULTS: A total of 18 patients (8.1%) received antithrombotic agents and 202 patients (91.8%) did not. Three patients experienced bleeding events, with an overall bleeding event rate of 1.3% (3/220): one patient was in the antithrombotic group (5.5%) and two patients were in the non-antithrombotic group (0.9%) (p=0.10). All cases were moderate. The sole thromboembolic event (0.4%) was a cerebral infarction in a patient in the non-antithrombotic group. CONCLUSION: The rate of EUS-BD-related bleeding events was low. Even in patients receiving antithrombotic therapy, the bleeding event rates were not significantly different from those in patients not receiving antithrombotic therapy.

Ursodeoxycholic acid and bezafibrate were useful for steroid-refractory, immune-related hepatitis: a case report.

BACKGROUND: Immune checkpoint inhibitors have shown clinically significant antitumor efficacy and have been approved for the treatment of various kinds of advanced malignancies. On the other hand, these immunotherapies show unique adverse events, termed "immune-related adverse events," which are distinctly associated with conventional cytotoxic chemotherapy. Hepatotoxicity is recognized as an immune-related adverse event; prompt treatment with corticosteroids is recommended. However, some cases are refractory to steroids. Here, we report the first case (to our knowledge) of steroid-refractory immune-related hepatitis that was successfully treated with ursodeoxycholic acid and bezafibrate. CASE PRESENTATION: A 68-year-old Asian man, came to our hospital for the treatment of malignant melanoma involving the gingiva and presenting with multiple lymph node and bone metastases was administered nivolumab as a first-line treatment. Two months into treatment, the patient developed diarrhea as a result of immune-related colitis; the colitis was treated successfully with prednisolone 60 mg/ day, resulting in improvement in the patient's symptoms. However, when steroids were being tapered, acute elevation of liver enzymes was observed. Autoimmune hepatitis was suspected as an immune-related adverse event, and treatment with intravenous prednisolone 60 mg/ day was reinitiated. However, restoration of the steroid treatment failed to improve the patient's liver enzymes. On the basis of histological findings from liver biopsy and exclusion of other etiologies such as viral infection and other drug-induced hepatitis, steroid-refractory hepatic immune-related adverse event was deemed the most likely cause of the patient's acute hepatitis. In general, mycophenolate mofetil or tacrolimus is known to provide benefits in cases of steroid-refractory hepatitis. We therefore decided to add oral ursodeoxycholic acid and bezafibrate in consideration of the patient's background of repeated aspiration pneumonia. Administration of this regimen resulted in an improvement in liver function, which remained normal even after tapering of prednisolone. CONCLUSIONS: Ursodeoxycholic acid and bezafibrate may be useful for treatment of steroid-refractory immune-related adverse event hepatitis.

Submucosal Tunnel Formation as a Complication Caused by Long Intestinal Tube Insertion: A Case Report.

We present a case of a 76-year-old man with submucosal tunnel formation caused by long intestinal tube (LIT) insertion. The patient had undergone an LIT insertion to treat bowel obstruction caused by ascending colon cancer. Although intestinal decompression was achieved successfully, a procedural pre-scheduled endoscopy incidentally revealed that the LIT had penetrated the abdominal esophageal mucosa and re-entered the gastric lumen, passing through the submucosal layer at the gastroesophageal junction. Therefore, the LIT was removed under endoscopic observation during ileocecal resection surgery and the patient was treated conservatively. The current case suggests that this unfamiliar complication can occur without any signs or symptoms.

Prognostic Impact of Sarcopenic Obesity after Neoadjuvant Chemotherapy Followed by Surgery in Elderly Patients with Esophageal Squamous Cell Carcinoma.

We evaluated the impact of body composition on clinical outcomes after neoadjuvant chemotherapy (NAC) followed by surgery for elderly cStage II/III esophageal squamous cell carcinoma (ESCC). Ninety-one patients ≥70 years old and 116 patients <70 years old with ECSS who underwent NAC between January 2013 and June 2018 at the Aichi Cancer Center were included. Body composition as assessed from computed tomography (CT), American Society of Anesthesiologists physical status (ASA-PS), and subjective global assessment (SGA) was assessed before initiation of NAC. Although elderly patients showed significantly poorer ASA-PS (p < 0.01) and SGA (p < 0.01), and significantly more frequent history of malignancy (p < 0.05), no significant differences were identified in the frequencies of adverse events, postoperative complications, or in cancer-specific survival (p = 0.65, hazard ratio 1.15), or overall survival (p = 0.42, hazard ratio 1.26). However, multivariate analysis identified sarcopenic obesity as the only independent predictor of prognosis in elderly patients. Sarcopenic obesity was associated with higher body mass index (p = 0.04), better SGA (p < 0.01), and lower pre-treatment weight loss (p = 0.03). NAC was as effective and safe for elderly patients without sarcopenic obesity as for young patients. However, diagnosing sarcopenic obesity based on clinical findings is difficult, so the preoperative CT assessment of sarcopenic obesity is important.

Prognostic Significance of Sarcopenia in Patients with Unresectable Advanced Esophageal Cancer.

The prognostic significance of sarcopenia in unresectable advanced esophageal cancer remains unclear. Our study retrospectively evaluated 176 consecutive Japanese patients with esophageal squamous cell carcinoma who had been diagnosed with unresectable advanced cancer in Aichi Cancer Center Hospital between January 2007 and December 2014. Skeletal muscle mass was calculated from abdominal computed tomography (CT) scans before treatment, and patients were divided into sarcopenic and non-sarcopenic groups. Sarcopenia was present in 101 patients (57.4%). Eighty-two patients in the sarcopenic group and 63 patients in the non-sarcopenic group died during follow-up (mean: 20.3 months). The overall survival (OS) rate was significantly lower in the sarcopenic group compared to the non-sarcopenic group (2-year OS: 9.8% vs. 23.7%, p < 0.01). Cox regression analysis revealed only pretreatment sarcopenia as an independent prognostic factor (hazard ratio (HR): 1.48, 95% confidence interval (CI): 1.04-2.10, p = 0.03). In the sarcopenic group, withdrawn cases, for whom the planned treatment was discontinued for some reason, showed a significantly lower OS rate compared to complete cases (1-year OS: 11.0% vs. 59.9%, p < 0.01). The most common reason for discontinuation was aspiration pneumonia (64.5%). Presence of sarcopenia was an independent prognostic factor for unresectable advanced esophageal cancer. Identifying the presence of sarcopenia prior to treatment may improve the prognosis.