Automatic segmentation of bladder cancer on MRI using a convolutional neural network and reproducibility of radiomics features.
Yusaku Moribata1, Yasuhisa Kurata1, Mizuho Nishio1, Aki Kido1, Satoshi Otani1, Yuki Himoto1, Naoko Nishio2, Akihiro Furuta2, Kimihiko Masui3, Takashi Kobayashi3, and Yuji Nakamoto1
1Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan, 2Department of Radiology, Japanese Red Cross Osaka Hospital, Osaka, Japan, 3Department of Urology, Kyoto University Graduate School of Medicine, Kyoto, Japan
This multi-center retrospective study performed automatic segmentation of bladder cancer (BC) on MRI with a convolutional neural network and evaluated the reproducibility of radiomics features. Of the total 170 patients, 140 were used to train our U-net model and 30 were used to evaluate the segmentation performance of the model. Our U-net model achieved a median Dice similarity coefficient of 0.811 in the test dataset and most of the automatically extracted radiomics features showed high reproducibility (median intraclass correlation coefficient: 0.83-0.86). Our model would lead to efficient medical image analysis of BC using the radiomics approach.
This abstract and the presentation materials are available to members only;
a login is required.