Expert-driven label fusion in multi-atlas-based segmentation of the prostate using weighted atlases.

PURPOSE: Automated segmentation is required for radiotherapy treatment planning, and multi-atlas methods are frequently used for this purpose. The combination of multiple intermediate results from multi-atlas segmentation into a single segmentation map can be achieved by label fusion. A method that includes expert knowledge in the label fusion phase of multi-atlas-based segmentation was developed. The method was tested by application to prostate segmentation, and the accuracy was compared to standard techniques. METHODS: The selective and iterative method for performance level estimation (SIMPLE) algorithm for label fusion was modified with a weight map given by an expert that indicates the importance of each region in the evaluation of segmentation results. Voxel-based weights specified by an expert when performing the label fusion step in atlas-based segmentation were introduced into the modified SIMPLE algorithm. These weights incorporate expert knowledge on accuracy requirements in different regions of a segmentation. Using this knowledge, segmentation accuracy in regions known to be important can be improved by sacrificing segmentation accuracy in less important regions. Contextual information such as the presence of vulnerable tissue is then used in the segmentation process. This method using weight maps to fine-tune the result of multi-atlas-based segmentation was tested using a set of 146 atlas images consisting of an MR image of the lower abdomen and a prostate segmentation. Each image served as a target in a set of leave-one-out experiments. These experiments were repeated for a weight map derived from the clinical practice in our hospital. RESULTS: The segmentation accuracy increased 6 % in regions that border vulnerable tissue using expert-specified voxel-based weight maps. This was achieved at the cost of a 4 % decrease in accuracy in less clinically relevant regions. CONCLUSION: The inclusion of expert knowledge in a multi-atlas-based segmentation procedure was shown to be feasible for prostate segmentation. This method allows an expert to ensure that automatic segmentation is most accurate in critical regions. This improved local accuracy can increase the practical value of automatic segmentation.

A stereotactic method for image-guided transcranial magnetic stimulation validated with fMRI and motor-evoked potentials.

Transcranial Magnetic Stimulation (TMS) delivers short magnetic pulses that penetrate the skull unattenuated, disrupting neural processing in a noninvasive, reversible way. To disrupt specific neural processes, coil placement over the proper site is critical. Therefore, a neural navigator (NeNa) was developed. NeNa is a frameless stereotactic device using structural and functional magnetic resonance imaging (fMRI) data to guide TMS coil placement. To coregister the participant's head to his MRI, 3D cursors are moved to anatomical landmarks on a skin rendering of the participants MRI on a screen, and measured at the head with a position measurement device. A method is proposed to calculate a rigid body transformation that can coregister both sets of coordinates under realistic noise conditions. After coregistration, NeNa visualizes in real time where the device is located with respect to the head, brain structures, and activated areas, enabling precise placement of the TMS coil over a predefined target region. NeNa was validated by stimulating 5 x 5 positions around the 'motor hotspot' (thumb movement area), which was marked on the scalp guided by individual fMRI data, while recording motor-evoked potentials (MEPs) from the abductor pollicis brevis (APB). The distance between the center of gravity (CoG) of MEP responses and the location marked on the scalp overlying maximum fMRI activation was on average less then 5 mm. The present results demonstrate that NeNa is a reliable method for image-guided TMS coil placement.