Jinwoo Han1, Suk-Joo Hong1, Zepa Yang1, Woo Young Kang1, Yoonmi Choi1, Chang Ho Kang2, Kyung-sik Ahn2, Baek Hyun Kim3, and Euddeum Shim3
1Radiology, Korea University Guro Hospital, KUGH-MIDC, Seoul, Korea, Republic of, 2Korea University Anam Hospital, Seoul, Korea, Republic of, 3Korea University Ansan Hospital, Ansan, Korea, Republic of
1Radiology, Korea University Guro Hospital, KUGH-MIDC, Seoul, Korea, Republic of, 2Korea University Anam Hospital, Seoul, Korea, Republic of, 3Korea University Ansan Hospital, Ansan, Korea, Republic of
To
develop and evaluate automated knee joint cartilage segmentation method using modified
U-net architecture based deep-learning technique in three dimensional magnetic resonance (MR) images. To evaluate the performance, Dice similarity coefficient, and visual inspection were used.
Illustration
of the deep
learning model. The process was split into two way to solve the weight-imbalance
problem and improve
efficiency of
the model.
Modified inception model and UNET was used to detect presence of knee
cartilage. In segmentation stage, ‘Modified UNET’, which means custom weight
function and additional fully-connected layer applied UNET, was used.