The Classification Power of Classical and Intra-voxel Incoherent Motion (IVIM) Fitting Models of Diffusion-weighted Magnetic Resonance Images: An Experimental Study.

This study aims at investigating the classification power of different b-values of the diffusion-weighted magnetic resonance images (DWI) as indicator of prostate cancer. This paper investigates several techniques for analyzing data from DWI acquired at a range of b-values for the purpose of detecting prostate cancer. In the first phase of experiments, we analyze the available data by producing two main parametric maps using two common models, namely: the intra-voxel incoherent motion (IVIM) model and the mono-exponential ADC model. Accordingly, we evaluated the benign/malignant tissue classification potential of several parametric maps produced using different combinations of b-values and fitting models. In the second phase, we utilized the maps that performed best in the first phase of experiments to design a machine learning-based computer-assisted diagnosis system for the detection of early stage prostate cancer. The system performance was cross-validated using data from 20 patients. On a fivefold cross-validation scheme, a maximum accuracy and an area under the receiver operating characteristic (AUC) of 90% and 0.978, respectively, was achieved by a system that uses ADC maps fitted using the mono-exponential model at 11 different b-values. The results suggest that the proposed machine learning-based diagnosis system is potentially powerful in differentiating between malignant and benign prostate tissues when combined with carefully generated ADC maps.

A Deep Learning-Based Approach for the Detection and Localization of Prostate Cancer in T2 Magnetic Resonance Images.

We address the problem of prostate lesion detection, localization, and segmentation in T2W magnetic resonance (MR) images. We train a deep convolutional encoder-decoder architecture to simultaneously segment the prostate, its anatomical structure, and the malignant lesions. To incorporate the 3D contextual spatial information provided by the MRI series, we propose a novel 3D sliding window approach, which preserves the 2D domain complexity while exploiting 3D information. Experiments on data from 19 patients provided for the public by the Initiative for Collaborative Computer Vision Benchmarking (I2CVB) show that our approach outperforms traditional pattern recognition and machine learning approaches by a significant margin. Particularly, for the task of cancer detection and localization, the system achieves an average AUC of 0.995, an accuracy of 0.894, and a recall of 0.928. The proposed mono-modal deep learning-based system performs comparably to other multi-modal MR-based systems. It could improve the performance of a radiologist in prostate cancer diagnosis and treatment planning.