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: and Purpose Carotid artery stenosis or occlusion (CASO) is a causative disease of vascular cognitive impairment (VCI) attributed to cerebral hypoperfusion, even without the development of symptomatic ischemic stroke. Preclinically, resveratrol has been demonstrated to play an important role in improving cognitive function in rodent CASO models. This study investigated the association between long-term resveratrol intake and improvements in cognitive and cerebral hemodynamic impairments in patients with CASO. Methods: A retrospective cohort study was conducted on patients with asymptomatic carotid artery stenosis of ≥50% or occlusion who underwent 15O-gas positron emission tomography (15O-gas PET) and neuropsychological tests such as Montreal Cognitive Assessment (MoCA) and Alzheimer’s Disease Assessment Scale-Cognitive Subscale 13 (ADAS-Cog) twice between July 2020 and March 2022 allowing >125-day interval. Patients were administered 30 mg/day resveratrol after the first 15O-gas PET and neuropsychological tests were compared with those who were not. Results: A total of 79 patients were enrolled in this study; 36 received resveratrol and 43 did not. Over a mean follow-up of 221.2 and 244.8 days, long-term resveratrol treatment significantly improved visuospatial/executive function (P=0.020) in MoCA, and memory domain (P=0.007) and total score (P=0.019) in ADAS-Cog. Cerebral blood flow demonstrated improvement in the right frontal lobe (P=0.027), left lenticular nucleus (P=0.009), right thalamus (P=0.035), and left thalamus (P=0.010) on 15O-gas PET. No adverse events were reported. Conclusion Long-term daily intake of oral resveratrol may prevent or treat VCI by improving the cerebral blood flow in asymptomatic patients with CASO.

Oral infection with Porphyromonas (P.) gingivalis causes periodontitis that is manifested by the destruction of gingival connective tissues. Although a few types of antibiotics are effective against the infection, its use induces the appearance of drug-resistant bacteria. The present study shows that the fermented product of Aspergillus (A.) oryzae S-03, cultivated on the fat-removed soybean, inhibits the cell growth of the P. gingivalis. Likewise, the fermented product of the S-03 strain cultured for 26~42 h displays an inhibitory activity to gingipain as a virulence factor of P. gingivalis. The activity is not lost even with heat treatment at 100degrees C for 15 min. We also demonstrate that the S-03 strain exhibits high protease activity. In addition, the strain does not produce aflatoxin because of the loss of a regulatory gene, aflR, necessary for the toxin biosynthesis.
Aflatoxins ; Anti-Bacterial Agents ; Aspergillus ; Aspergillus oryzae* ; Bacteria ; Connective Tissue ; Genes, Regulator ; Hot Temperature ; Oryza ; Periodontitis ; Porphyromonas ; Porphyromonas gingivalis* ; Soybeans ; Virulence*