Publications by authors named "Y Furuki"
Fibrosarcoma in the mandible in children is a very rare condition. We present a rare case of central mandibular fibrosarcoma in a child, treated with radical tumor resection, reconstructive surgery, long-term prognostic evaluation, and morphofunctional reconstruction. The patient was an 8-year-old boy.
View Article and Find Full Text PDFElastofibromatous changes of the oral mucosa, such as an elastofibroma (EF) or an elastofibromatous lesion (EFL), are not well recognized, and the second such case in Japan is reported. A 72-year-old man wearing a complete maxillary denture presented with a small nodule on the hard palate. Histopathological examination showed abundant fibrous tissue with numerous elastic fibers on Elastica van Gieson (EvG) staining.
View Article and Find Full Text PDFThe purpose of this retrospective study was to identify risks of postoperative facial nerve injury (FNI) in mandibular condylar fractures. A total of 59 consecutive cases of condyle fracture or plate removal with a retromandibular transparotid approach (RMTA) were divided into FNI and non-FNI groups that were evaluated for associations with age, sex, laterality, fracture type, height, weight, body mass index (BMI), and maxillofacial bone height and width diameters on computed tomography (CT). FNI occurred in 11 of 59 patients (18.
View Article and Find Full Text PDFArticle Synopsis
- The study evaluated how accurately deep learning can determine the relationship between the inferior alveolar canal and mandibular third molars using a dataset of 1279 digital radiographs.
- The researchers specifically focused on two types of analysis: contact (presence or absence of contact between the molar and canal) and continuity (bone continuity as seen on CT scans).
- Results showed that the ResNet50v2 model using sharpness-aware minimization (SAM) performed well in contact analysis (accuracy 0.860, AUC 0.890), but the models struggled with continuity analysis, showing limited effectiveness.
Article Synopsis
- * The researchers compared the performance of CNN model VGG16 using both SAM and stochastic gradient descent (SGD) optimizers, with and without a learning rate scheduler over 300 epochs.
- * Results showed that SAM, particularly with the learning rate scheduler, achieved the highest accuracy (11.2), AUC (0.9328), and reduced overfitting, suggesting its potential for enhancing oral cytological diagnosis.