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.

Objective: Most women with early stage endometrial cancer have a favorable prognosis. However, there is a subset of patients who develop recurrence. In addition to the pathological stage, clinical and therapeutic factors affect the probability of recurrence. Machine learning is a subtype of artificial intelligence that is considered effective for predictive tasks. We tried to predict recurrence in early stage endometrial cancer using machine learning methods based on clinical data. Methods: We enrolled 75 patients with early stage endometrial cancer (International Federation of Gynecology and Obstetrics stage I or II) who had received surgical treatment at our institute. A total of 5 machine learning classifiers were used, including support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and boosted tree, to predict the recurrence based on 16 parameters (age, body mass index, gravity/parity, hypertension/diabetic, stage, histological type, grade, surgical content and adjuvant chemotherapy). We analyzed the classification accuracy and the area under the curve (AUC). Results: The highest accuracy was 0.82 for SVM, followed by 0.77 for RF, 0.74 for LR, 0.66 for DT, and 0.66 for boosted trees. The highest AUC was 0.53 for LR, followed by 0.52 for boosted trees, 0.48 for DT, and 0.47 for RF. Therefore, the best predictive model for this analysis was LR. Conclusion The performance of the machine learning classifiers was not optimal owing to the small size of the dataset. The use of a machine learning model made it possible to predict recurrence in early stage endometrial cancer.

The Japanese Society of Hepato-Biliary-Pancreatic Surgery launched the clinical practice guidelines for the management of biliary tract cancers (cholangiocarcinoma, gallbladder cancer, and ampullary cancer) in 2007, then published the 2nd version in 2014. In this 3rd version, clinical questions (CQs) were proposed on six topics. The recommendation, grade for recommendation, and statement for each CQ were discussed and finalized by an evidence-based approach. Recommendations were graded as grade 1 (strong) or grade 2 (weak) according to the concepts of the grading of recommendations assessment, development, and evaluation system. The 31 CQs covered the six topics: (1) prophylactic treatment, (2) diagnosis, (3) biliary drainage, (4) surgical treatment, (5) chemotherapy, and (6) radiation therapy. In the 31 CQs, 14 recommendations were rated strong and 14 recommendations weak. The remaining three CQs had no recommendation. Each CQ includes a statement of how the recommendations were graded. This latest guideline provides recommendations for important clinical aspects based on evidence. Future collaboration with the cancer registry will be key for assessing the guidelines and establishing new evidence.

Objective: Most women with early stage endometrial cancer have a favorable prognosis. However, there is a subset of patients who develop recurrence. In addition to the pathological stage, clinical and therapeutic factors affect the probability of recurrence. Machine learning is a subtype of artificial intelligence that is considered effective for predictive tasks. We tried to predict recurrence in early stage endometrial cancer using machine learning methods based on clinical data. Methods: We enrolled 75 patients with early stage endometrial cancer (International Federation of Gynecology and Obstetrics stage I or II) who had received surgical treatment at our institute. A total of 5 machine learning classifiers were used, including support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and boosted tree, to predict the recurrence based on 16 parameters (age, body mass index, gravity/parity, hypertension/diabetic, stage, histological type, grade, surgical content and adjuvant chemotherapy). We analyzed the classification accuracy and the area under the curve (AUC). Results: The highest accuracy was 0.82 for SVM, followed by 0.77 for RF, 0.74 for LR, 0.66 for DT, and 0.66 for boosted trees. The highest AUC was 0.53 for LR, followed by 0.52 for boosted trees, 0.48 for DT, and 0.47 for RF. Therefore, the best predictive model for this analysis was LR. Conclusion The performance of the machine learning classifiers was not optimal owing to the small size of the dataset. The use of a machine learning model made it possible to predict recurrence in early stage endometrial cancer.

Off-pump coronary artery bypass (OPCAB) has recently increased in popularity, but the longterm results are still unknown. We evaluated the mid-term results of OPCAB surgery using multi-slice computed tomography (MSCT), which is a non-invasive postoperative evaluation method. Thirty-one consecutive patients who underwent OPCAB surgery at least 2 years prior to the study were selected. The age was 50 to 79 years (66.9±6.5) and the ratio of men to women was 26: 5. Coronary angiography was performed in all patients at 2 weeks postoperatively. The follow-up was complete, and mean follow-up was 30.9 months. There were no hospital deaths and 1 non-cardiac late death. The graft patency rate in coronary angiography was left internal thoracic artery (LITA) 30/30 (100%), right internal thoracic artery (RITA) 2/2 (100%), radial artery (RA) 14/15 (93%), saphenous vein graft (SVG) 15/17 (88%). No graft became occluded on MSCT study and all patients have been angina-free during the follow-up period. We suggest that OPCAB is feasible in most patients with good patency and low mortality. MSCT is an effective follow up method for the morphological findings and noninvasive quantitative evaluation of the bypass grafts.

Inflammatory aneurysms of the thoracic aorta are extremely uncommon. We present a 58 year-old man with an inflammatory aneurysm of the aortic arch. He was admitted because of chest pain. Coronary angiographies showed severe stenosis of the left anterior descending artery and computed tomography revealed an aneurysm of the distal aortic arch. We conducted combined graft replacement of the aortic arch and coronary artery bypass grafting. During the operation, the patient was noted to have extensive peri-aneurysmal fibrosis and inflammation with a thick aneurysmal wall. To avoid excessive hemorrhage, distal anastomosis was performed using the graft inclusion technique. He was discharged 35 days after operation without any major complication. Pathological evaluation of the aneurysmal wall revealed destruction of the mural structure and inflammatory cell infiltration in the adventitia.

Quercetin, a flavonoid, widely distributed in many fruits and vegetables, is well known to have an antitumor effect despite its mutagenicity. In this study, we examined the effect of dietary quercetin on duodenum-tumorigenicity of mice induced by a chemical carcinogen, N-ethyl-N'-nitro-N-nitrosoguanidine (ENNG). Eight-week-old male C57BL/6 mice were divided into 4 groups; ENNG without quercetin (group A), ENNG with 0.2% quercetin (group B), ENNG with 2% quercetin (group C), and 2% quercetin without ENNG (group D). ENNG was given in drinking water for the first 4 weeks, and thereafter quercetin was given in a mixed diet. At week 20, the average number of duodenal tumors per mouse was significantly higher in group C (mean±SE, 7.26±1.75, p<0.05) than in group A (2.32±0.31). The size of the duodenal tumors increased significantly in group B (1.79±0.09 mm, p<0.001) compared with group A (1.43±0.09 mm). In contrast, no duodenal tumor was induced in group D. The present findings suggest that excessive intake of quercetin occasionally is a risk factor for carcinogenesis of some specific organs such as the upper intestine.

Objectives: The aim of this study was to identify characteristic lifestyles in children with obese parents. Methods: 8,030 children (4,072 males and 3,958 females) aged 6 to 7 years were investigated. A questionnaire relating to the lifestyles of children was distributed through elementary schools for completion by parents. The heights and weights of parents were self-reported. A parent with a body mass index (weight in kilograms divided by the square of height in meters) greater than the 90th percentile for gender (26.7 kg/m2 for fathers and 24.3 kg/m2 for mothers) was defined as an obese parent. A chi-square test for each trend was applied to evaluate an increasing trend in the frequency or level of each lifestyle in children with obese parents. Results: Children with obese parents were significantly associated with increasing trends in the proportions categorized by irregular intake of breakfast, faster eating, longer TV watching, and shorter sleeping hours. Conclusions: These lifestyles are considered to be possible risk factors for the development of obesity. These characteristic lifestyles observed in children with obese parents could strengthen the relationship between child and parental body compositions, in addition to the genetic predisposition to obesity in children with obese parents. These findings indicate that education with lifestyle modification for obese parents will be required to prevent further weight gain in children with obese parents.
Child ; Parents ; Life Style ; seconds ; trends