Methods and systems for disease classification

• Main Authors: Savvides, Marios, Le, Thi Hoang Ngan
• Format: Patent
• Language: English
• Published: 11.09.2018
• Subjects: BEER; BIOCHEMISTRY; CALCULATING; CHEMISTRY; COMPOSITIONS OR TEST PAPERS THEREFOR; COMPUTING; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL ORENZYMOLOGICAL PROCESSES; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; ENZYMOLOGY; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEICACIDS OR MICROORGANISMS; METALLURGY; MICROBIOLOGY; MUTATION OR GENETIC ENGINEERING; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION; PRESENTATION OF DATA; PROCESSES OF PREPARING SUCH COMPOSITIONS; RECOGNITION OF DATA; RECORD CARRIERS; SPIRITS; VINEGAR; WINE

This invention describes methods and systems for use of computer vision systems for classification of biological cells as an aid in disease diagnostics. More particularly the present invention describes a process comprising employing a robust and discriminative color space which will help provide segmentation of the cells; employing a segmentation algorithm, such as a feature-based level set, that will be able to segment the cells using a different k-phase-segmentation process, which detect for example, if a while blood cell occurs for segmenting the internal components of the cell robustly; employing a combination of different type of features including shape, texture, and invariant information, and employing a classification step to associate abnormal cell characteristics with disease states.