Pridi Siregar

Spatio-temporal reasoning for multi-scale modeling in cardiology

In this paper, we present an overview of the CARDIOLAB environment where the hearts electrical activity is modeled at distinct space and time scales. CARDIOLAB uses three models, two of which are based on cellular automata, and the third on qualitative simulation. They are combined around a blackboard for multi-scale quantitative and qualitative modeling of cardiac electrical activity. A general account on how spatio-temporal representation and reasoning methods are applied to produce heuristic associations is also presented.

Model-based diagnosis of brain disorders: a prototype framework

This paper describes a prototype framework, named NEUROLAB, dedicated to research and diagnosis in the area of brain disorders. The diagnostic task uses a blending of factual knowledge, formal knowledge, and experiential knowledge. The prototypes first target clinical application is partial seizures in epilepsy. Diagnosis is carried out using qualitative electroencephalographic descriptions, clinical attack pattern descriptions, and pre- and post-ictal observations. From this information, the system builds explanations in the form of candidate epileptogenic foci and trajectories of the seizure spread. Hypothesis-testing and discrimination is based on minimal set coverage, and consistency-checking is performed using the general background knowledge. Upon completion, NEUROLAB will provide specific physiological knowledge for solving the so-called inverse problems in electroencephalography (EEG) and magnetoencephalography (MEG).

Introducing spatio-temporal reasoning into the inverse problem in electroencephalography.

Studying the Brains Electrical and Magnetic Signals (BEMS) requires the contribution of many area of research that include anatomy, neurophysiology and electromagnetic theory. NEUROLAB is a framework dedicated to the study of brain disorders. Upon completion, it should provide users with an intelligent computational environment that incorporates qualitative and quantitative models of the brain and head, and a model for representing and reasoning about time and space. Spatio-temporal knowledge of a given problem is represented as a constraint network where to each node of the network are attached temporal and spatial variables that must satisfy the constraints defined by the arch labels connecting the nodes. In this paper, we show how temporal reasoning can be combined with spatial descriptions to produce different scenarios of possible seizure spread. These scenarios can provide a priori information for the inverse problem the role of which is to localise the sources of the observed BEMS.

Computational morphogenesis – Embryogenesis, cancer research and digital pathology

Overall survival benefits of cancer therapies have, in general, fallen short of what was expected from them. By examining the many parallels that exist between embryogenesis and carcinogenesis, we discuss how clinical and fundamental cancer research can benefit from computational morphogenesis (CM) insofar as carcinogenesis is causally related to altered mechanisms underlying embryogenesis and post-embryonic tissue homeostasis. We also discuss about the critical role played by digital pathology (DP) since it constitutes the main source of data for the model-fitting and validation of CM-generated virtual tissues. Conversely, we outline how CM can provide support to DP by generating annotated synthetic 2D and 3D data that can be fed into machine-learning methods dedicated to the automated diagnosis of DP slides.