Tagged: Neural Networks

Training neural networks for computer-aided diagnosis: experience in the intelligence community

Neural networks are often used in computer-aided diagnosis (CAD) systems for detecting clinically significant objects. They have also been applied in the AI community to cue image analysts (IAs) for assisted target recognition and wide-area searching. Given the similarity between the applications in the two communities, there are a number of common issues that must be considered when training these neural networks. Two such issues are: (1) exploiting information at multiple scales (e.g. context and detail structure), and (2) dealing with uncertainty (e.g. errors in truth data). We address these two issues, transferring architectures and training algorithms originally developed for assisting IAs in search applications, to improve CAD for mammography. These include hierarchical pyramid neural net (HPNN) architectures that automatically learn and integrate multi-resolution features for improving microcalcification and mass detection in CAD systems. These networks are trained using an uncertain object position (UOP) error function for the supervised learning of image searching/detection tasks when the position of the objects to be found is uncertain or ill-defined. The results show that the HPNN architecture trained using the UOP error function reduces the false-positive rate of a mammographic CAD system by 30%-50% without any significant loss in sensitivity. We conclude that the transfer of assisted target recognition technology from the AI community to the medical community can significantly impact the clinical utility of CAD systems.

Perceptual Decision Making Investigated via Sparse Decoding of a Spiking Neuron Model of V1

Recent empirical evidence supports the hypothesis that invariant visual object recognition might result from non-linear encoding of the visual input followed by linear decoding [1]. This hypothesis has received theoretical support through the development of neural network architectures which are based on a non-linear encoding of the input via recurrent network dynamics followed by a linear decoder [2], [3]. In this paper we consider such an architecture in which the visual input is non-linearly encoded by a biologically realistic spiking model of V1, and mapped to a perceptual decision via a sparse linear decoder. Novel is that we 1) utilize a large-scale conductance based spiking neuron model of V1 which has been well-characterized in terms of classical and extra-classical response properties, and 2) use the model to investigate decoding over a large population of neurons. We compare decoding performance of the model system to human performance by comparing neurometric and psychometric curves.

Hierarchical multi-resolution models for object recognition: Applications to mammographic computer-aided diagnosis

A fundamental problem in image analysis is the integration of information across scale to detect and classify objects. We have developed, within a machine learning framework, two classes of multiresolution models for integrating scale information for object detection and classification-a discriminative model called the hierarchical pyramid neural network and a generative model called a hierarchical image probability model. Using receiver operating characteristic analysis, we show that these models can significantly reduce the false positive rates for a well-established computer-aided diagnosis system.

Multi-resolution neural networks for mammographic mass detection

We have previously presented a hierarchical pyramid/neural network (HPNN) architecture which combines multi-scale image processing techniques with neural networks. This coarse-to- fine HPNN was designed to learn large-scale context information for detecting small objects. We have developed a similar architecture to detect mammographic masses (malignant tumors). Since masses are large, extended objects, the coarse-to-fine HPNN architecture is not suitable for the problem. Instead we constructed a fine-to- coarse HPNN architecture which is designed to learn small- scale detail structure associated with the extended objects. Our initial result applying the fine-to-coarse HPNN to mass detection are encouraging, with detection performance improvements of about 30%. We conclude that the ability of the HPNN architecture to integrate information across scales, from fine to coarse in the case of masses, makes it well suited for detecting objects which may have detail structure occurring at scales other than the natural scale of the object.

A neural network model of object segmentation and feature binding in visual cortex

The authors present neural network simulations of how the visual cortex may segment objects and bind attributes based on depth-from-occlusion. They briefly discuss one particular subprocess in the occlusion-based model most relevant to segmentation and binding: determination of the direction of figure. They propose that the model allows addressing a central issue in object recognition: how the visual system defines an object. In addition, the model was tested on illusory stimuli, with the network’s response indicating the existence of robust psychophysical properties in the system.

Coarse-grain parallel computing for very large scale neural simulations in the NEXUS simulation environment

We describe a neural simulator designed for simulating very large scale models of cortical architectures. This simulator, NEXUS, uses coarse-grain parallel computing by distributing computation and data onto multiple conventional workstations connected via a local area network. Coarse-grain parallel computing offers natural advantages in simulating functionally segregated neural processes. We partition a complete model into modules with locally dense connections–a module may represent a cortical area, column, layer, or functional entity. Asynchronous data communications among workstations are established through the Network File System, which, together with the implicit modularity, decreases communications overhead, and increases overall performance. Coarse-grain parallelism also benefits from the standardization of conventional workstations and LAN, including portability between generations and vendors.