Three convolutional neural network architectures were applied to differentiate prostate cancer from benign prostate hyperplasia based on DCE-MRI: (1) VGG serial convolutional neural network; (2) one-directional Convolutional Long Short Term Memory (CLSTM) network; (3) bi-directional CLSTM network. A total of 104 patients were analyzed, including 67 prostate cancer and 37 benign prostatic hyperplasia. Upon 10-fold cross-validation, the differentiation accuracy was 0.64-0.77 (mean 0.68) using VGG, 0.75-0.87 (mean 0.81) using the CLSTM, and 0.73-0.89 (mean 0.84) using bi-directional CLSTM. The radiomics model built by SVM using histogram and texture features extracted from the manually-drawn tumor ROI yielded accuracy of 0.81.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords