Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI
This work addresses prostate cancer diagnosis for medical imaging, showing incremental improvement over existing methods in a specific challenge.
The researchers tackled prostate cancer diagnosis by developing a deep learning architecture (XmasNet) for classifying lesions using 3D multiparametric MRI data, achieving an AUC of 0.84 and outperforming 69 methods in the PROSTATEx challenge.
A novel deep learning architecture (XmasNet) based on convolutional neural networks was developed for the classification of prostate cancer lesions, using the 3D multiparametric MRI data provided by the PROSTATEx challenge. End-to-end training was performed for XmasNet, with data augmentation done through 3D rotation and slicing, in order to incorporate the 3D information of the lesion. XmasNet outperformed traditional machine learning models based on engineered features, for both train and test data. For the test data, XmasNet outperformed 69 methods from 33 participating groups and achieved the second highest AUC (0.84) in the PROSTATEx challenge. This study shows the great potential of deep learning for cancer imaging.