Search

An artificial neural network can be trained to detect a structure of interest within medica1 images. The method entails the training of the neural net with hand-drawn masks using the backpropagation algorithm. Multiple neural nets, each a detector for a different structure, can be created in this fashion. In order to enhance the detection of a single target structure, a final neural net can be trained to incorporate the output of a primary target detector as well as related structure detectors. This paper describes a method for aorta detection using neural nets trained to detect the aorta, spinal cord, and inferior vena cava.

This paper describes the development of a Physician's Workstation (PWS) for the evaluation of soft tissue types utilizing MR, which includes the analysis, quantification and 3-D visualization of the pertinent tissues. A major theme underlying our work is that it is possible to develop robust image processinglpattem recognition algorithms for the evaluation of diseased tissue by focusing on specific diseases involving localized regions of the body obtained with consistent and well developed imaging protocols. We have implemented two specific image processinglpattem recognition and display systems for (1) the evaluation of atherosclerosis; and (2) the differentiation of breast lesions.

In this paper, algorithms for the segmentation of head structures within three-dimensional magnetic resonance images are described. The process can be described as passing the raw images through a series of image processing programs to form afinal image with voxel values corresponding to tissue type. This resulting image can be loaded into a commercial graphics package in order to produce near photorealistic pictures and spinning animations of head structures.

Three experience-based learning techniques are explored using the game Go-Moku (Connect-5). The first method, an exception tree, is used to prevent poor lines of play by recording critical moves in a move tree. The second method simply records all games in a large experience tree, backtracking the eventual outcomes in traditional minimax fashion. Both techniques allow a computer player to modify its behavior based on past experience, and, therefore, typically defeat static game programs. The last method explored is the use of a multilayer feedforward artificial neural network for strategy calculation. The network was trained on selected interior nodes of the experience tree using the backpropagation algorithm. The neural network strategy algorithm compares favorably with a fine-tuned hand-crafted strategy algorithm. >

An automated procedure for segmentation of the brain from 3-D MR images of the head is described. This process combines some heuristics with a number of three-dimensional image processing and computer vision techniques including seed-based volume growing, DOG convolution and zero-crossing detection, convolution with the Zucker-Hummel operator, and watershed anaylsis. There are two broad steps: (1) rough estimation of brain voxels, and (2) refinement of the first step through a reverse-gravity watershed analysis. All operations are performed in three-dimensions in order to fully utilize the information present in the voxels generated by the 3-D MP-RAGE sequence.

This paper describes the rationale and importance of utilizing a priori, model based information to guide segmentation and classification in complex medical images represented by Magnetic Resonance Imaging (MRI). The incorporation of such a priori, model based information requires the development of a "top down" model driven system, rather than the more traditional "bottom up" data driven system. Two different examples which incorporate such model based a priori information are discussed: (1) The segmentation and classification of tissues involved in atherosclerosis; and (2) The segmentation and classification of brain tissue for neurosurgical applications.