Publications by authors named "Saki Tsuchihashi"
This study performed three-dimensional (3D) magnetic resonance imaging (MRI)-based statistical shape analysis (SSA) by comparing patellofemoral instability (PFI) and normal femur models, and developed a machine learning (ML)-based prediction model. Twenty (19 patients) and 31 MRI scans (30 patients) of femurs with PFI and normal femurs, respectively, were used. Bone and cartilage segmentation of the distal femurs was performed and subsequently converted into 3D reconstructed models.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to assess the effectiveness of MRI findings and texture features (TFs) in distinguishing between uterine endometrial carcinoma and uterine carcinosarcoma.
- It included 102 patients and utilized various MRI assessments, including conventional MRI findings and specific imaging techniques, to identify key features for diagnosis.
- The results indicated that a combined model of conventional MRI findings and TFs outperforming individual models, demonstrating a high diagnostic performance with an AUC of 0.915.
Background: The second demonstration experiment of supporting elderly people going out with the Choisoko system was conducted. The first study showed that for women, friends, shopping, convenience, and events are factors that have the potential to be effective motivational factors for encouraging these women to go out. On the other hand, these factors did not lead to any behavioral change in men.
View Article and Find Full Text PDFMaintaining a social environment that enables going out freely is important for older people and aids the prevention of frailty syndrome. However, losing a driver's license can increase the long-term care needs of older people. Therefore, outing support systems are important.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to assess how effective conventional MRI features and texture analysis are in distinguishing between ovarian thecoma-fibroma groups (OTFGs) and ovarian granulosa cell tumors (OGCTs).
- A total of 52 patients were surveyed, and various MRI-based and texture features were analyzed to create a model capable of differentiating between the two types of ovarian tumors.
- The findings showed that the MRI-based model and a combination model performed nearly equally well in terms of diagnostic accuracy, while texture analysis alone did not significantly improve diagnosis, suggesting MRI analysis is a reliable method for distinguishing these tumors.
Article Synopsis
- The study evaluated the Discovery NM/CT 670 CZT scanner’s ability to measure heart-to-mediastinum ratios (HMR) in patients with suspected Lewy body diseases (LBD) using I-MIBG planar imaging.
- It found significant differences in HMRs between patients with and without clinically diagnosed LBD, indicating that those with LBD had lower HMR values.
- The results also showed that shorter collection times (down to 50 seconds) provided consistent HMR measurements compared to the standard 300-second collection, highlighting the scanner's clinical utility and potential for time efficiency.