| 研究実績の概要 |
The purpose of this research is to develop an interpretable deep learning (DL)-based computer-aided diagnosis (CAD) system for breast cancer diagnosis in mammogram. As the final financial year, we mainly achieved the following results.
(1) A new digital mammogram dataset with clinical annotation was collected in cooperation with medical doctors in Tohoku university hospital. (2) The new deep learning training method, which was proposed last FY, was further improved and tested on the new mammogram dataset. The experimental results demonstrate the effectiveness of our proposed method. (3) The methods developed in the project were also extended to other medical application, such as forensic medicine.(4) Four papers have been published in the related international journals.
|
