Histology is the study and analysis of the microscopic structure of cells and tissues of organisms, essential for the evaluation of grading and prognosis of disease. Nowadays this analysis is still performed manually, involving numerous drawbacks, in particular the results accuracy heavily depends on operator skills. In addition, this process is really slow and time-consuming. Thus a computer-assisted disease system could be very useful to speed up the process and to reduce subjectivity. In particular, developing general applications not dependent on specific histology data sets is still a challenging open problem. In this chapter a general color texture-based histology image classification framework is proposed. The features are based on a generalization of some existent gray-scale approaches to color images and used to train a support vector machine model. Also, we investigate different color spaces to individuate a general representation able to solve the classification problem efficiently without any dependence on specific data sets or specific clinical fields. The system has been tested on very different public biological image data sets, representative of different medical problems and so different classification problems, obtaining an average accuracy always higher than 96%.
|Titolo:||A Feature Learning Framework for Histology Images Classification|
|Data di pubblicazione:||2016|
|Tipologia:||2.1 Contributo in volume (Capitolo o Saggio)|