The derivation of ventricular structures from a pediatric population is discussed. The original dataset is classified via a metric-based clustering algorithm which is tuned to the signature distribution from the magnetic resonance images (MRIs). The cluster set (or sets) interpreted as cerebrospinal fluid are aggregated throughout the dataset into a group of connected components whose topology is understood. This typically recursive procedure is replaced by a divide-and-conquer approach which substantially reduces the stack space needed for the aggregation. Other class sets can be equivalently aggregated. Visualization and geometry are then simply deduced from the aggregated cluster sets in the data. It is demonstrated how this hierarchical cluster/classification strategy can successfully demonstrate ventricular structure from multisignature MRIs.>

A distributed job shop scheduling algorithm has been implemented in the LAN (local area network) environment. The algorithm is a good candidate for distributed implementation since much of the computation time required for a solution is expended in distributable portions of the algorithm. A distributed processing support system (DPSS) was developed to ease the implementation of this and future distributed algorithms. Preliminary results indicate considerable potential for reducing the computation time. Additional portions of the algorithm may be distributed to improve the results, and streamlining of the underlying communication mechanism of DPSS is underway.>