Objective: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. Methods: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. Results: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. Conclusion Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.

Objective: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. Methods: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. Results: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. Conclusion Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.

Objective: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. Methods: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. Results: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. Conclusion Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.

Background/Aims: Poorly differentiated adenocarcinoma, signet-ring cell carcinoma, and mucinous adenocarcinoma (por/sig/muc), which are considered to be histologic subtypes with a poor prognosis, occur more frequently with colitis-associated cancer than with sporadic tumors. However, their invasiveness and manifestations are unclear. This study aimed to determine the prevalence of the por/sig/muc component in ulcerative colitis-associated neoplasms (UCANs) and its association with invasiveness and to clarify its clinicohistologic and endoscopic features. Methods: This retrospective observational study included patients diagnosed with ulcerative colitis-associated high-grade dysplasia or adenocarcinoma from 1997 to 2022 who were divided according to the presence or absence of a por/sig/muc component. Results: Thirty-five patients had UCAN with a por/sig/muc component and 66 had UCAN without this component. The 5-year survival rate was significantly lower in the por/sig/muc group than in the tub group (67% vs. 96%, P= 0.001), which was attributed to disease above stage III and depth to below the subserosa. Biopsy-based diagnosis before resection detected a por/sig/muc component in only 40% of lesions (14/35). Lesions with a por/sig/muc component were prevalent even in the early stages: stage 0 (4/36, 11%), I (8/20, 40%), II (7/12, 58%), III (10/14, 71%), and IV (6/8, 75%). Conclusions This is the first investigation that shows UCANs with a por/sig/muc component tended to be deeply invasive and were often not recognized preoperatively. Endoscopists should be aware that UCAN often has a por/sig/muc component that is not always recognized on biopsy, and the optimal treatment strategy needs to be carefully considered.

Background: The anti-programmed death 1 (PD-1) antibody has led to durable clinical responses in a wide variety of human tumors. We have previously developed the caninized anti-canine PD-1 antibody (ca-4F12-E6) and evaluated its therapeutic properties in dogs with advance-staged oral malignant melanoma (OMM), however, their therapeutic effects on other types of canine tumors remain unclear. Objective: The present clinical study was carried out to evaluate the safety profile and clinical efficacy of ca-4F12-E6 in dogs with advanced solid tumors except for OMM. Methods: Thirty-eight dogs with non-OMM solid tumors were enrolled prospectively and treated with ca-4F12-E6 at 3 mg/kg every 2 weeks of each 10-week treatment cycle. Adverse events (AEs) and treatment efficacy were graded based on the criteria established by the Veterinary Cooperative Oncology Group. Results: One dog was withdrawn, and thirty-seven dogs were evaluated for the safety and efficacy of ca-4F12-E6. Treatment-related AEs of any grade occurred in 13 out of 37 cases (35.1%).Two dogs with sterile nodular panniculitis and one with myasthenia gravis and hypothyroidism were suspected of immune-related AEs. In 30 out of 37 dogs that had target tumor lesions, the overall response and clinical benefit rates were 6.9% and 27.6%, respectively. The median progression-free survival and overall survival time were 70 days and 215 days, respectively. Conclusions The present study demonstrated that ca-4F12-E6 was well-tolerated in nonOMM dogs, with a small number of cases showing objective responses. This provides evidence supporting large-scale clinical trials of anti-PD-1 antibody therapy in dogs.

Objective: Ovarian clear cell carcinoma (OCCC) is a subtype of epithelial ovarian carcinoma with poor prognosis. However, no effective biomarkers have been established for predicting unfavorable events, including recurrence and poor prognoses. Serum microRNAs (miRNAs) have been increasingly reported to be useful in predicting a patient’s condition and have been recognized as a potentially less-invasive source for liquid biopsy in cancer. Therefore, this study aimed to evaluate serum miRNA profiles from patients with OCCC and to establish biomarker for predicting the prognoses. Methods: The GSE106817, which included preoperative serum miRNA profiles of patients with ovarian tumors, was used, and clinical information was investigated. In all, 66 patients with OCCC were included, excluding those with other histological subtypes or insufficient prognostic information. Moreover, miRNA profiles of OCCC tissues were also examined. Results: The median follow-up period was 64.3 (8.0–153.3) months. Based on multivariable Cox regression analyses and the expression of miRNAs in OCCC tissues, miR-150-3p, miR-3195, and miR-7704 were selected as miRNA candidates associated with both progression-free survival (PFS) and overall survival (OS). Then, the prognostic index was calculated based on expression values of 3 serum miRNAs. Kaplan-Meier survival analysis indicated that the prognostic index was significantly predictive of PFS and OS (p=0.004 and p=0.012, respectively). Conclusion Preoperative serum miRNA profiles of miR-150-3p, miR-3195, and miR-7704 can be used to potentially predict the prognosis of patients with OCCC.

A 77-year-old woman underwent endovascular abdominal aortic repair (EVAR) for an abdominal aortic aneurysm (AAA)．Five years after surgery, she visited the hospital with the chief complaint of a fever. Enhanced computed tomography (CT) showed enlargement of the AAA around the stent-graft and a mass, which was suspected to be an abscess, outside the aneurysm. A blood test revealed a high level of inflammatory response. The patient was diagnosed with infectious AAA. She received antibiotics; however, the inflammatory response did not completely improve. A second CT scan revealed that the suspected abscess had a spreading tendency. The patient was referred to our hospital for a highly suspected stent-graft infection. We performed Y-graft replacement using a rifampicin-immersed graft, and as much as possible of the wall around the aortic aneurysm was removed. The inflammatory response improved rapidly after the operation, and the patient was discharged 15 days later. According to the results of a pathological examination, a diagnosis of xanthogranulomatous inflammation and fibrosis was made. Here, we report a rare case of xanthogranulomatous inflammation of the aortic aneurysm wall after EVAR.

The case is that of a 90-years-old man. A previous doctor performed abdominal graft replacement for an abdominal aortic aneurysm 5 years earlier and continued outpatient CT follow-up. Follow-up CT showed the right aortic arch and dilation of the thoracic aortic aneurysm, and the patient was referred to our hospital. Contrast-enhanced CT showed an aortic arch aneurysm ; the aneurysm diameter was 62 mm in major axis and 60 mm in minor axis, which was judged to be suitable for surgery. It was a rare right-sided aortic arch with no congenital heart malformation and no situs inversus. Endovascular treatment was considered because he was 90 years old and very elderly, but there were concerns about the risk of embolism, irregular manipulation and central landing. For the surgical method, we selected total arch replacement using a frozen elephant trunk technique. We succeeded in avoiding serious complications by selecting an appropriate treatment method through careful evaluation.

A 65-year-old man who had been taking warfarin for a mitral mechanical valve, was transported to our hospital for acute heart failure 3 months after switching to edoxaban. The fluoroscopy revealed restriction of the mechanical valve opening, and the catheterization showed an increased pressure gradient of the mechanical valve. The patient was diagnosed with valve thrombosis, and emergency redo mitral valve replacement was performed. The patient recovered well without complication. In cases with mechanical heart valves, sufficient explanation and education about warfarin administration is mandatory for patients' home doctors as well as patients and their families.

We started a prophylactic rehabilitation class from fiscal year 2016 and 1 year later we identified 4 problems, namely, a small number of participants (mean, 4.6), a small male population (ratio of 1 male to 9 females), no follow up because only 1 session was given per area, and a low home exercise rate (42.5%). For the class in fiscal year 2017, discussions were held with the comprehensive regional support center. Accordingly, relevant information was disseminated via public relations magazines, neighborhood circulars, and the local government to address the problems with the number of participants and sex ratio, and a series of 4 sessions were held per area to address the problems with the lack of follow-up and continuation of home exercise. Objective assessments (grip strength, one-leg standing, and knee extension strength) were included in the physical assessment. Through these measures, based on questionnaire results, we found that there was an increase in the number of participants and that more participants continued the exercise at home after the class was increased.