Content-based tissue image mining

Biological data management and mining are critical areas of modern-day biology research. High throughput and high information content are two important aspects of any Tissue Microarray Analysis (TMA) system. Tissue image mining is efficient and faster if the tissue images are indexed, stored and mined on content. A four-level system to harness the knowledge of a pathologist with image analysis, pattern recognition, and artificial intelligence is proposed in this article. At Image Processing and Information Level, information such as contrast or color is used. At Object Level, pathological objects, including cell components, are identified. At Semantic Level, layout and formation of individual cells into sheets in a tissue image are analyzed. At the highest level. Knowledge Level, inference of the expert is indicated. A pilot system that uses two levels of harnessing involving the first two levels´ features of tissue images with immunohistochemical markers is implemented.