White matter hyperintensities (WMHs) are found on magnetic resonance (MR) images of older individuals and are associated with many neurodegenerative disorders, although the exactrole of WMHs in Alzheimer’s disease and other dementias remains an open area of research. Fluid-attenuated inversion recovery (FLAIR) MR imaging sequences show WMHs with good image contrast. Manual segmentation of WMHs on FLAIR images is the widely accepted “gold standard”, however, this step is often time-consuming and has a high inter-rater variability. The absence of an automated, robust and accurate approach to segment WMHs remains a processing bottleneck. We explored convolutional neural networks (CNNs) for performing semantic segmentation of WMHs in FLAIR images. Two sets of experiments were conducted: (1) Variations of U-shaped CNNs (U-Nets) were evaluated in 186 individuals, specifically, four architectures (VGG16, VGG19, ResNet152 and EfficientNetB0) having three dimensionalities (2D, 2.5D and 3D). (2) New data from 60 individuals were added to test the generalizability of U-Net, LinkNet and Feature-Pyramid Network (FPN) variants. The first experiment showed that the 2.5D implementation with VGG16 or VGG19 was the most suitable configuration when segmenting WMH (F-measure > 95% and intersection-over-union > 90%). The second experiment confirmed generalizability of these variants when using unprocessed FLAIR images.

Prostate cancer biopsy is a routine medical procedure, yet conventional techniques suffer from low sensitivity attributed to suboptimal image guidance and needle placement. Targeting small lesions and foci (5 mm in diameter) is particularly prone to errors. We developed an integrated system to perform robot-assisted transperineal needle insertions into the prostate, under Magnetic Resonance Imaging (MRI) guidance. The system provides arbitrary needle trajectories and allows for simultaneous surveillance and correction of the needle path, based on intra-operative MRI. System functionality and data transfer and processing tests were conducted. Five lesions embedded in the gel phantom were targeted successfully, while communication delays (due to higher image frame rates) had no adverse affect on robot-software communication. The system was sufficiently resistant to high network loads and performed with an acceptable transfer rate.

A major limitation of the use of endoscopes in minimally invasive surgery is the lack of relative context between the endoscope and its surroundings. The purpose of this work was to fuse images obtained from a tracked endoscope to surfaces derived from three-dimensional (3-D) preoperative magnetic resonance or computed tomography (CT) data, for assistance in surgical planning, training and guidance. We extracted polygonal surfaces from preoperative CT images of a standard brain phantom and digitized endoscopic video images from a tracked neuro-endoscope. The optical properties of the endoscope were characterized using a simple calibration procedure. Registration of the phantom (physical space) and CT images (preoperative image space) was accomplished using fiducial markers that could be identified both on the phantom and within the images. The endoscopic images were corrected for radial lens distortion and then mapped onto the extracted surfaces via a two-dimensional 2-D to 3-D mapping algorithm. The optical tracker has an accuracy of about 0.3 mm at its centroid, which allows the endoscope tip to be localized to within 1.0 mm. The mapping operation allows multiple endoscopic images to be "painted" onto the 3-D brain surfaces, as they are acquired, in the correct anatomical position. This allows panoramic and stereoscopic visualization, as well as navigation of the 3-D surface, painted with multiple endoscopic views, from arbitrary perspectives.