Breast cancer has become one of the main causes of death among women in the many countries. The chances of patient survival can be considerably enhanced if breast tumors are identified at the earliest stage. In this study, we propose a cost effective and non-invasive detection technique, which is based on precision breast geometry, infrared breast temperature and inverse thermal modeling in order to prove that the inverse FEM is applicable for detection of the location and size of the tumor inside the breast. As a first step in this comprehensive study, we develop a novel and cost-effective experiment to obtain repeatable data for FEM validation, in which an artificial breast was 3D printed based on realistic breast geometry, tumors were simulated with heaters and thermograms of the breast were taken. Then forward thermal modeling was performed and validated with the experimental data. Furthermore, the effect of tumors on the thermal profile of the breast was examined by using both experimental and numerical approaches.

Coronary heart disease (CHD) is one of the leading killers worldwide. Lipoprotein and apolipoprotein play an important role in developing CHDs. To tackle the challenging task of CHD lipoprotein and atherosclerotic research, collaborative work is crucial. With an interdiscipline in nature, such research involves bio-chemistry, cardiovascular biology, lipoprotein structure, fluorescent imaging, 3D modelling, data mining, etc. This project aims to create a Web based and integrated solution to support a multi-disciplinary knowledge discovery process for the study of cardiovascular and atherosclerotic biology. The emphasis of the project is to address (1) the sharing of cardiovascular clinical data; and (2) the system integration for CHD cardiovascular research. The system currently under development is mainly implemented on a PC Window platform with an intranet-centric design. An Apache HTTP server, a MySQL SQL server, Perl, and R Language, are employed for the system development independent to hardware platforms. The system offers easy information management and data sharing by multiple parties across Internet. Major datasets include lipoprotein phenotype/genotype and laser confocal images. A user-friendly interface is designed allowing users to deposit, retrieve, visualize and analyze the CHD information from different sites.

This paper identifies and describes how knowledge based systems (KBSs), fuzzy logic and artificial neural networks (ANNs) can be integrated, and provides a novel (fuzzy) expert Petri net (EPN (FEPN)) based approach for the integration of KBSs and ANNs. A generic expert Petri net model of single neuron is presented, and a two-layer generic Petri net model for (fuzzy) neural networks and neural (fuzzy) expert Petri nets (NEPN, NFEPN)) that use this neuron model as a building block is described. The NEPN and NFEPN models can be used for representing a (fuzzy) knowledge base and (fuzzy) reasoning. Also, they can be utilized to develop ANN-like multilayered Petri net architectures of distributed hybrid intelligence having learning ability. Some application examples are illustrated for validation of the proposed models.