Several new image-guidance tools and devices are being prototyped, investigated, and compared. These tools are introduced and include prototype software for image registration and fusion, thermal modeling, electromagnetic tracking, semiautomated robotic needle guidance, and multimodality imaging. The integration of treatment planning with computed tomography robot systems or electromagnetic needle-tip tracking allows for seamless, iterative, "see-and-treat," patient-specific tumor ablation. Such automation, navigation, and visualization tools could eventually optimize radiofrequency ablation and other needle-based ablation procedures and decrease variability among operators, thus facilitating the translation of novel image-guided therapies. Much of this new technology is in use or will be available to the interventional radiologist in the near future, and this brief introduction will hopefully encourage research in this emerging area.

No abstract

Accurate automatic segmentation of the prostate in magnetic resonance images (MRI) is a challenging task due to the high variability of prostate anatomic structure. Artifacts such as noise and similar signal intensity of tissues around the prostate boundary inhibit traditional segmentation methods from achieving high accuracy. We investigate both patch-based and holistic (image-to-image) deep-learning methods for segmentation of the prostate. First, we introduce a patch-based convolutional network that aims to refine the prostate contour which provides an initialization. Second, we propose a method for end-to-end prostate segmentation by integrating holistically nested edge detection with fully convolutional networks. Holistically nested networks (HNN) automatically learn a hierarchical representation that can improve prostate boundary detection. Quantitative evaluation is performed on the MRI scans of 250 patients in fivefold cross-validation. The proposed enhanced HNN model achieves a mean ± standard deviation. A Dice similarity coefficient (DSC) of [Formula: see text] and a mean Jaccard similarity coefficient (IoU) of [Formula: see text] are used to calculate without trimming any end slices. The proposed holistic model significantly ([Formula: see text]) outperforms a patch-based AlexNet model by 9% in DSC and 13% in IoU. Overall, the method achieves state-of-the-art performance as compared with other MRI prostate segmentation methods in the literature.