High-quality expert annotations enhance artificial intelligence model accuracy for osteosarcoma X-ray diagnosis.

Primary malignant bone tumors, such as osteosarcoma, significantly affect the pediatric and young adult populations, necessitating early diagnosis for effective treatment. This study developed a high-performance artificial intelligence (AI) model to detect osteosarcoma from X-ray images using highly accurate annotated data to improve diagnostic accuracy at initial consultations. Traditional models trained on unannotated data have shown limited success, with sensitivities of approximately 60%-70%. In contrast, our model used a data-centric approach with annotations from an experienced oncologist, achieving a sensitivity of 95.52%, specificity of 96.21%, and an area under the curve of 0.989. The model was trained using 468 X-ray images from 31 osteosarcoma cases and 378 normal knee images with a strategy to maximize diversity in the training and validation sets. It was evaluated using an independent dataset of 268 osteosarcoma and 554 normal knee images to ensure generalizability. By applying the U-net architecture and advanced image processing techniques such as renormalization and affine transformations, our AI model outperforms existing models, reducing missed diagnoses and enhancing patient outcomes by facilitating earlier treatment. This study highlights the importance of high-quality training data and advocates a shift towards data-centric AI development in medical imaging. These insights can be extended to other rare cancers and diseases, underscoring the potential of AI in transforming diagnostic processes in oncology. The integration of this AI model into clinical workflows could support physicians in early osteosarcoma detection, thereby improving diagnostic accuracy and patient care.

Rehabilitation Treatment Involving Language Evaluation and Training Considering Poor Japanese Proficiency of Hongkongese Patient with Brain Tumor：A Case Report / The Japanese Journal of Rehabilitation Medicine

Since foreign patients may have inadequate Japanese language proficiency, rehabilitation techniques and evaluations of the higher brain and language function are often challenging. Here, we report a Hongkongese patient who suffered from higher brain dysfunction and dysgraphia after brain surgery. The patient was a 29-year-old left-handed man admitted to the Osaka International Cancer Institute for surgical resection of a choroid plexus tumor located on the trigone in the right lateral ventricle. Since the patient's mastery of the Japanese language was poor on preoperative evaluation, we partially evaluated his higher brain functions in Cantonese and English. However, he experienced left hemispatial neglect and spatial dysgraphia on postoperative day (POD) 2. On POD 48, his spatial dysgraphia (mainly in Cantonese) and higher brain functions improved with rehabilitation treatment, which involved verbal and non-verbal techniques such as task presentation and pointing. Although rehabilitation tasks and techniques are difficult due to language barriers, non-verbal techniques can be effective in providing treatment. Furthermore, it is important to evaluate the patient's language proficiency on preoperative assessment, especially in non-native Japanese speakers.