Casimir A. Kulikowski

A model-based method for computer-aided medical decision-making

A general method of computer-assisted medical decision-making has been developed based on causal-associational network (CASNET) models of disease. A CASNET model consists of three main components: observations of a patient, pathophysiological states, and disease classifications. As observations are recorded, they are associated with the appropriate states. States are causally related, forming a network that summarizes the mechanisms of disease. Patterns of states in the network are linked to individual disease classifications. Recommendations for broad classes of treatment are triggered by the appropriate diagnostic classes. Strategies of specific treatment selection are guided by the individual pattern of observations and diagnostic conclusions. This approach has been applied in a consultation program for the diagnosis and treatment of the glaucomas.

Robust and fast collaborative tracking with two stage sparse optimization

The sparse representation has been widely used in many areas and utilized for visual tracking. Tracking with sparse representation is formulated as searching for samples with minimal reconstruction errors from learned template subspace. However, the computational cost makes it unsuitable to utilize high dimensional advanced features which are often important for robust tracking under dynamic environment. Based on the observations that a target can be reconstructed from several templates, and only some of the features with discriminative power are significant to separate the target from the background, we propose a novel online tracking algorithm with two stage sparse optimization to jointly minimize the target reconstruction error and maximize the discriminative power. As the target template and discriminative features usually have temporal and spatial relationship, dynamic group sparsity (DGS) is utilized in our algorithm. The proposed method is compared with three state-of-art trackers using five public challenging sequences, which exhibit appearance changes, heavy occlusions, and pose variations. Our algorithm is shown to outperform these methods.

Glaucoma consultation by computer

Abstract This paper describes a computer-based system for consultation in the diagnosis and therapy of glaucoma. The reasoning procedures interpret the findings of a particular patient in terms of a causal-associational network (CASNET) model that characterizes the pathophysiological mechanisms and clinical course of treated and untreated diseases. The major new features of this program are: (a) generation of complex interpretations from a qualitative model of a disease process; (b) reasoning about detailed follow-up management of a patient; (c) incorporation of alternative expert opinions about subjects under debate; and (d) its testing and updating by a collaborative computer-based network of glaucoma researchers.

Artificial intelligence methods and systems for medical consultation

The major AI problems that arise in designing a consultation program involve choices of knowledge representations, diagnostic interpretation strategies, and treatment planning strategies. The need to justify decisions and update the knowledge base in the light of new research findings places a premium on the modularity of a representation and the ease with which its reasoning procedures can be explained. In both diagnosis and treatment decisions, the relative advantages and disadvantages of different schemes for quantifying the uncertainty of inferences raises difficult issues of a formal logical nature, as well as many specific practical problems of system design. An important insight that has resulted from the design of several artificial intelligence systems is that robustness of performance in the presence of many uncertainty relationships can be achieved by eliciting from the expert a segmentation of knowledge that will also provide a rich network of deterministic relationships to interweave the space of hypotheses.

Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection

Online learned tracking is widely used for its adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent literature demonstrates that appropriate combinations of trackers can help balance the stability and flexibility requirements. We have developed a robust tracking algorithm using a local sparse appearance model (SPT) and K-Selection. A static sparse dictionary and a dynamically updated online dictionary basis distribution are used to model the target appearance. A novel sparse representation-based voting map and a sparse constraint regularized mean shift are proposed to track the object robustly. Besides these contributions, we also introduce a new selection-based dictionary learning algorithm with a locally constrained sparse representation, called K-Selection. Based on a set of comprehensive experiments, our algorithm has demonstrated better performance than alternatives reported in the recent literature.

The dangerous decade

Over the next 10 years, more information and communication technology (ICT) will be deployed in the health system than in its entire previous history. Systems will be larger in scope, more complex, and move from regional to national and supranational scale. Yet we are at roughly the same place the aviation industry was in the 1950s with respect to system safety. Even if ICT harm rates do not increase, increased ICT use will increase the absolute number of ICT related harms. Factors that could diminish ICT harm include adoption of common standards, technology maturity, better system development, testing, implementation and end user training. Factors that will increase harm rates include complexity and heterogeneity of systems and their interfaces, rapid implementation and poor training of users. Mitigating these harms will not be easy, as organizational inertia is likely to generate a hysteresis-like lag, where the paths to increase and decrease harm are not identical.

Composition of image analysis processes through object-centered hierarchical planning

This paper presents a new approach to the knowledge-based composition of processes for image interpretation and analysis. Its computer implementation in the VISIPLAN (Vision Planner) system provides a way of modeling the composition of image analysis processes within a unified, object-centered hierarchical planning framework. The approach has been tested and shown to be flexible in handling a reasonably broad class of multi-modality biomedical image analysis and interpretation problems. It provides a relatively general design or planning framework, within which problem specific image analysis and recognition processes can be generated more efficiently and effectively. In this way, generality is gained at the design and planning stages, even though the final implementation stage of interpretation processes is almost invariably problem- and domain-specific. >

Pattern Recognition Approach to Medical Diagnosis

A sequential method of pattern recognition was used to recognize hyperthyroidism in a sample of 2208 patients being treated at the Straub Clinic in Honolulu, Hawaii. For this, the method of class featuring information compression (CLAFIC) [1] was used, introducing some significant improvements in computer medical diagnosis, which by its very nature is a pattern recognition problem. A unique subspace characterizes each class at every decision stage, and the most prominent class features are selected. Thus the symptoms which best distinguish hyperthyroidism are extracted at every step and the number of tests required to reach a diagnosis is reduced.

Nanoinformatics and DNA-based computing: catalyzing nanomedicine.

Five decades of research and practical application of computers in biomedicine has given rise to the discipline of medical informatics, which has made many advances in genomic and translational medicine possible. Developments in nanotechnology are opening up the prospects for nanomedicine and regenerative medicine where informatics and DNA computing can become the catalysts enabling health care applications at sub-molecular or atomic scales. Although nanomedicine promises a new exciting frontier for clinical practice and biomedical research, issues involving cost-effectiveness studies, clinical trials and toxicity assays, drug delivery methods, and the implementation of new personalized therapies still remain challenging. Nanoinformatics can accelerate the introduction of nano-related research and applications into clinical practice, leading to an area that could be called “translational nanoinformatics.” At the same time, DNA and RNA computing presents an entirely novel paradigm for computation. Nanoinformatics and DNA-based computing are together likely to completely change the way we model and process information in biomedicine and impact the emerging field of nanomedicine most strongly. In this article, we review work in nanoinformatics and DNA (and RNA)-based computing, including applications in nanopediatrics. We analyze their scientific foundations, current research and projects, envisioned applications and potential problems that might arise from them.

Automated sequencing of amino acid spin systems in proteins using multidimensional HCC(CO)NH-TOCSY spectroscopy and constraint propagation methods from artificial intelligence

SummaryWe have developed an automated approach for determining the sequential order of amino acid spin systems in small proteins. A key step in this procedure is the analysis of multidimensional HCC(CO)NH-TOCSY spectra that provide connections from the aliphatic resonances of residue i to the amide resonances of residue i+1. These data, combined with information about the amino acid spin systems, provide sufficient constraints to assign most proton and nitrogen resonances of small proteins. Constraint propagation methods progressively narrow the set of possible assignments of amino acid spin systems to sequence-specific positions in the process of NMR data analysis. The constraint satisfaction paradigm provides a framework in which the necessary constraint-based reasoning can be expressed, while an object-oriented representation structures and facilitates the extensive list processing and indexing involved in matching. A prototype expert system, AUTOASSIGN, provides correct and nearly complete resonance assignments with one real and 31 simulated 3D NMR data sets for a 72-amino acid domain, derived from the Protein A of Staphylococcus aureus, and with 31 simulated NMR data sets for the 50-amino acid human type-α transforming growth factor.