Towards a histological depiction in 3D imaging PET

• This article probes a useful diagnostic tool of cancer, via PET imaging, based on the detection and progress of abnormal cells.
• This article highlights two current activities from the area of chemical biology and mathematical modeling.
• One activity offers data from the cycle of metabolism of cells and expression of cancer factors.
• Another activity connects the biological data with the field of mathematical equations using a well-fitted artificial neural network.

In this study we examine the possibility of constructing metadata from Positron Emission Tomography images based on a Radial Basis Function neural network, which uses histological data extracted via the enzyme-linked immunosorbent assay abbreviation. The aim of constructing such metadata is to achieve a bringing between the binding potential receptor in vitro and in vivo Positron Emission Tomography procedures, which it is possible to calculate using a classic simplified reference tissue model. This knowledge representation procedure may then be transmitted in the Positron Emission Tomography using the testing neural network procedure. The latest satisfies the primary aim of this study, which was to avoid painful and risky biopsies of patients.

Figure optionsDownload as PowerPoint slide