Active contours are a popular medical image segmentation strategy. However in practice, its accuracy is dependent on
the initialization of the process. The PCNN (Pulse Coupled Neural Network) algorithm developed by Eckhorn to model
the observed synchronization of neural assemblies in small mammals such as cats allows for segmenting regions of
similar intensity but it lacks a convergence criterion. In this paper we report a novel PCNN based strategy to initialize
the zero level contour for automatic brain cropping of T2 weighted MRI image volumes of Long-Evans rats. Individual
2D anatomy slices of the rat brain volume were processed by means of a PCNN and a surrogate image 'signature' was
constructed for each slice. By employing a previously trained artificial neural network (ANN) an approximate PCNN
iteration (binary mask) was selected. This mask was then used to initialize a region based active contour model to crop
the brain region. We tested this hybrid algorithm on 30 rat brain (256*256*12) volumes and compared the results against
manually cropped gold standard. The Dice and Jaccard similarity indices were used for numerical evaluation of the
proposed hybrid model. The highly successful system yielded an average of 0.97 and 0.94 respectively.
Medical research is dominated by animal models, especially rats and mice. Within a species most laboratory subjects
exhibit little variation in brain anatomy. This uniformity of features is used to crop regions of interest based upon a
known, cropped brain atlas. For any study involving N subjects, image registration or alignment to an atlas is required to
construct a composite result. A highly resolved stack of T2 weighted MRI anatomy images of a Sprague-Dawley rat was
registered and cropped to a known segmented atlas. This registered MRI volume was used as the reference atlas. A Pulse
Coupled Neural Network (PCNN) was used to separate brain tissue from surrounding structures, such as cranium and
muscle. Each iteration of the PCNN produces binary images of increasing area as the intensity spectrum is increased. A
rapid filtering algorithm is applied that breaks narrow passages connecting larger segmented areas. A Generalized
Invariant Hough Transform is applied subsequently to each PCNN segmented area to identify which segmented
reference slice it matches. This process is repeated for multiple slices within each subject. Since we have apriori
knowledge of the image ordering and fields of view this information provides initial estimates for subsequent
registration codes. This process of subject slice extraction to PCNN mask creations and GIHT matching with known
atlas locations is fully automatic.
An automatic 3D non-rigid body registration system based upon the genetic algorithm (GA) process is presented. The system has been successfully applied to 2D and 3D situations using both rigid-body and affine transformations. Conventional optimization techniques and gradient search strategies generally require a good initial start location. The GA approach avoids the local minima/maxima traps of conventional optimization techniques. Based on the principles of Darwinian natural selection (survival of the fittest), the genetic algorithm has two basic steps: 1. Randomly generate an initial population. 2. Repeated application of the natural selection operation until a termination measure is satisfied. The natural selection process selects individuals based on their fitness to participate in the genetic operations; and it creates new individuals by inheritance from both parents, genetic recombination (crossover) and mutation. Once the termination criteria are satisfied, the optimum is selected from the population. The algorithm was applied on 2D and 3D magnetic resonance images (MRI). It does not require any preprocessing such as threshold, smoothing, segmentation, or definition of base points or edges. To evaluate the performance of the GA registration, the results were compared with results of the Automatic Image Registration technique (AIR) and manual registration which was used as the gold standard. Results showed that our GA implementation was a robust algorithm and gives very close results to the gold standard. A pre-cropping strategy was also discussed as an efficient preprocessing step to enhance the registration accuracy.
In contrast to traditional 'video conferencing' the Access Grid (AG), developed by Argonne National Laboratory, is a collaboration of audio, video and shared application tools which provide the 'persistent presence' of each participant. Among the shared application tools are the ability to share viewing and control of presentations, browsers, images and movies. When used in conjunction with Virtual Network Computing (VNC) software, an investigator can interact with colleagues at a remote site, and control remote systems via local keyboard and mouse commands. This combination allows for effective viewing and discussion of information, i.e. data, images, and results. It is clear that such an approach when applied to the medical sciences will provide a means by which a team of experts can not only access, but interact and control medical devices for the purpose of experimentation, diagnosis, surgery and therapy. We present the development of an application node at our 4.7 Tesla MR magnet facility, and a demonstration of remote investigator control of the magnet. A local magnet operator performs manual tasks such as loading the test subject into the magnet and administering the stimulus associated with the functional MRI study. The remote investigator has complete control of the magnet console. S/he can adjust the gradient coil settings, the pulse sequence, image capture frequency, etc. A geographically distributed audience views and interacts with the remote investigator and local MR operator. This AG demonstration of MR magnet control illuminates the potential of untethered medical experiments, procedures and training.
An experimental implementation of an actuator switching scheme in a flexible structure that employs multiple piezoceramic actuators is reported in this manuscript and whose results support theoretical
predictions and agree with numerical findings. The proposed supervisory control scheme attempts to improve controller performance of a system subject to spatiotemporally varying disturbances. The intelligent controller achieves its tasks by switching to different
actuating devices at different time intervals. Specifically, the flexible structure under study is assumed to have multiple piezoceramic actuators available with only one being active over a time interval of fixed length while the remaining ones are kept dormant. By monitoring the state of the system, the supervisory controller engages the actuator that lies "spatially" closer to the
region (epicenter) of a spatially varying disturbances within the spatial domain. This actuator switching scheme mimics the case of a moving actuator capable of residing in predetermined positions within the spatial domain of the flexible structure. Numerical studies for
a flexible beam are presented in conjunction to the experimental ones to support the analytical findings of this work.