Publications by authors named "Eiro Sakai"
Article Synopsis
- A retrospective study created and validated a deep learning model to classify chest X-ray images into three categories: COVID-19 pneumonia, non-COVID-19 pneumonia, and healthy.
- The model was developed using a large dataset of CXR images from public and private sources, totaling over 25,000 images, and was based on EfficientNet with a noisy student approach.
- The deep learning model outperformed a consensus of six radiologists in accurately identifying COVID-19 pneumonia, with a classification accuracy of 86.67% compared to the radiologists' accuracy which ranged from 56.67% to 77.33%.
[The effect of strontium-89 therapy in a patient with cholangiocellular carcinoma].
Gan To Kagaku Ryoho
November 2013
A 77-year-old man was diagnosed as having cholangiocellular carcinoma. The patient underwent partial right hepatectomy in June 2008, and multiple bone metastases occurred approximately 9 months after surgery. He refused salvage chemotherapy and radiation therapy.
View Article and Find Full Text PDF