A 56-year-old woman was referred to our hospital because of an abnormal finding in the right pulmonary hilum on chest X-ray. Enhanced chest computed tomography showed hyperplastic bronchial arteries dilating and winding around the trachea and bronchi. A racemose hemangioma of the bronchial artery with multiple bronchial artery aneurysms (diameter <20mm) was seen displacing the trachea and both main bronchi. Bronchoscopy showed submucosal tumor-like lesions at the distal trachea and in both main bronchi, and a dusky-red elevated pulsatile lesion at the orifice of the left B3b＋c. We performed coil embolization of the bronchial artery aneurysm to prevent abrupt rupture of the bronchial aneurysm.

The median time of brain metastasis from the diagnosis of breast cancer is approximately 3 years. In this case report, a 69-year-old woman demonstrated cerebellar ataxia. Brain magnetic resonance imaging revealed enhanced lesions in bilateral cerebellar hemispheres. She had undergone surgery, radiation, and chemotherapy for uterine and breast cancer 24 years prior and 16 years prior, respectively. Although she had not received any anticancer treatment for 10 years, no recurrences were identified using whole body scans. A partial tumor resection was performed and the histological diagnosis was an adenocarcinoma from breast cancer. As no extracranial lesions were found, gamma-knife irradiation was performed, without additional systemic chemotherapy. One month posttreatment, the tumors dramatically reduced in size and the patient completely recovered from cerebellar ataxia. Systemic chemotherapy is not always required for brain metastasis from breast cancer with a long interval period, as long as no evidence of extracranial recurrence is detected.
Adenocarcinoma ; Aged ; Brain* ; Breast Neoplasms* ; Breast* ; Cerebellar Ataxia ; Diagnosis ; Drug Therapy ; Female ; Humans ; Magnetic Resonance Imaging ; Neoplasm Metastasis* ; Neoplasm Recurrence, Local ; Prognosis ; Recurrence* ; Whole Body Imaging

The purpose of this study was to clarify the number of types and frequencies of fundamental movement patterns (FMP) during Soccer Kids Program (SKP) recommended by the Japan Football Association for preschool children, and to clarify the relationship between FMP and Moderate to Vigorous Physical Activity (MVPA; ≥3 METs). The participants were 12 children (six boys and six girls). The SKP was conducted for 50 minutes with video recording, and researchers counted the number of FMP during SKP by replaying the video. The FMP during SKP was classified into three movement categories: stability (eight types), locomotion (eight types), and manipulation (18 types). The participants wore a triaxial accelerometer (Active Style Pro, OMRON) on their waist during SKP and measured their activity (intensity and step) every ten seconds. Partial correlation analysis was performed on the relationship between MVPA and FMP using age in months and gender as covariates. MVPA during SKP was 24.3±5.0 minutes (48.7%), which was considerably more than in previous studies. Total number of FMP during SKP was 637.8±183.5 (stability: 27.8±12.4, locomotion: 399.7±156.6, manipulation: 210.3±48.4) and the mean number of types of FMP was 14.6±2.0 types. The FMP was confirmed in all three categories. There were significant correlations between MVPA and the total FMP (r = 0.72), the number of stability (r = 0.83), and the types of FMP (r = 0.69). This study suggested that an association between MVPA and FMP (total FMP, total stability, and type of FMP) in SKP.

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.

The purpose of this study was to clarify the relationship between quality of motion and motor ability in early childhood, as well as the moderating effects of grade and gender. A total of 133 preschoolers (3- to 5-year-old class) were evaluated for quality of motion and motor ability using the “Athletic Aptitude Test II” developed by the Japan Sports Association to assess the fundamental movements of running, jumping, and throwing. Two observers evaluated quality of motion based on movies taken by tablet. The relationship between quality of motion and motor ability was determined using multiple regression analysis. In addition, we clarified the influence of grade and gender on the relationship between quality of motor and motor ability using moderation analysis. A significant relationship was found between quality of motion and motor ability for all movements. Grade moderated the relationship between the quality of running motion and the results of the 25-m run. Gender moderated the relationship between the quality of the throwing motion and the results of softball throwing. These results suggest an association between quality of motion and motor ability in early childhood, and show that improving quality of motion improves motor ability.