Pradeep G. Mutalik

Voice-activated retrieval of mammography reference images

We undertook this project to integrate context sensitive computer-based educational and decision making aids into the film interpretation and reporting process, and to determine the clinical utility of this method as a guide for further system development. An image database of 347 digital mammography images was assembled and image features were coded. An interface was developed to a computerized speech recognition radiology reporting system which was modified to translate reported findings into database search terms. These observations were used to formulate database search strategies which not only retrieved similar cases from the image database, but also other cases that were related to the index case in different ways. The search results were organized into image sets intended to address common questions that arise during image interpretation. An evaluation of the clinical utility of this method was performed as a guide for further system development. We found that voice dictation of prototypical mammographic cases resulted in automatic retrieval of reference images. The retrieved images were organized into sets matching findings, diagnostic hypotheses, diagnosis, spectrum of findings or diagnoses, closest match to dictated case, or user specified parameters. Two mammographers graded the clinical utility of each form of system output. We concluded that case specific and problem specific image sets may be automatically generated from spoken case dictation. A potentially large number of retrieved images may be divided into subsets which anticipate common clinical problems. This automatic method of context sensitive image retrieval may provide a “continuous’; form of education integrated into routine case interpretation.

Abnormal excitability of oblique dendrites implicated in early Alzheimer's: a computational study

The integrative properties of cortical pyramidal dendrites are essential to the neural basis of cognitive function, but the impact of amyloid beta protein (aβ) on these properties in early Alzheimers is poorly understood. In animal models, electrophysiological studies of proximal dendrites have shown that aβ induces hyperexcitability by blocking A-type K+ currents (IA), disrupting signal integration. The present study uses a computational approach to analyze the hyperexcitability induced in distal dendrites beyond the experimental recording sites. The results show that back-propagating action potentials in the dendrites induce hyperexcitability and excessive calcium concentrations not only in the main apical trunk of pyramidal cell dendrites, but also in their oblique dendrites. Evidence is provided that these thin branches are particularly sensitive to local reductions in IA. The results suggest the hypothesis that the oblique branches may be most vulnerable to disruptions of IA by early exposure to aβ, and point the way to further experimental analysis of these actions as factors in the neural basis of the early decline of cognitive function in Alzheimers.

Approaches to neuroscience data integration

As the number of neuroscience databases increases, the need for neuroscience data integration grows. This paper reviews and compares several approaches, including the Neuroscience Database Gateway (NDG), Neuroscience Information Framework (NIF) and Entrez Neuron, which enable neuroscience database annotation and integration. These approaches cover a range of activities spanning from registry, discovery and integration of a wide variety of neuroscience data sources. They also provide different user interfaces for browsing, querying and displaying query results. In Entrez Neuron, for example, four different facets or tree views (neuron, neuronal property, gene and drug) are used to hierarchically organize concepts that can be used for querying a collection of ontologies. The facets are also used to define the structure of the query results.

The Prospect of Expert System-Based Cognitive Support as a By-Product of Image Acquisition and Reporting

In order for computer-based decision-support tools to find routine use in the everyday practice of clinical radiology, further development of user interface and knowledge content are required. In an ideal interface, the interaction between the radiologist and the computer would be minimized and painlessly integrated into existing work patterns. In this article, we explore some of the ways that pre-existing computer interactions in the processes of image acquisition and reporting can be used to feed case information into an expert system and thereby allow users to acquire advice from it in an automatic fashion. We describe interface models that we have developed in the domains of mammography and obstetric ultrasound, and discuss interface and content-related questions that have arisen from informal evaluations of these systems. In particular, the need for clinical outcome-relevant decision support and training level-appropriate decision support are discussed in detail.

P1-141: Modeling the “dendritic hypothesis” of Alzheimer pathogenesis: A neuroinformatics approach for elucidating part of the amyloid beta cascade

inclusions positive for both anti-phosphorylated TDP-43 and anti-ubiquitin antibodies were observed. The expression of delta187-192 caused the formation of intranuclear inclusions after proteasome inhibition. Furthermore, when the double-deletion mutant (delta78-84 and 187-192) was expressed, cytoplasmic inclusions positive for both anti-phosphorylated TDP-43 and anti-ubiquitin were observed without proteasome inhibition. These all mutants had no exon skipping activity of CFTR exon 9, suggesting that loss of function in TDP-43 may lead to its accumulation in cells. Conclusions: We successfully established the cellular models recapitulating the pathological lesions found in FTLD-U and ALS.

Expert System Advice as a By-Product of Image Acquisition and Reporting: Obstacles to be Overcome

Computer systems are commonplace in radiology today, perhaps more so than in any other branch of medicine. Computers are routinely used to acquire radiological images (e.g. CT, MR, ultrasound, etc.), in radiology information systems, and more recently, in image archiving (PACS) and in film-reporting (computerized voice recognition). The long-term goal of our research has been to extend this use of computers to enhance the actual cognitive processes used in the practice of diagnostic radiology by pairing the strengths of computers (superior memory) with those of humans (superior visual pattern recognition). Specifically, we seek to build computer-based expert systems that can give a radiologist intelligent decision support without intruding on his or her normal film-reading activity and without requiring specific and lengthy computer interaction. To this end we have developed prototype systems that use the computer interactions already being carried out for image acquisition and reporting to acquire case-knowledge about the films being interpreted. This knowledge can then be used by an expert system working in the background to generate intelligent diagnostic advice [1]. The radiologist thus gets the benefit of automatic expert system consultation without having to do anything different from what he or she normally does during the film-reading process.