Objects detection and recognition in biomedical microscopic images for the purpose of non-invasive and more precise diagnostic

Abstract

In the last years, it has become very popular as well as significant to diagnose patients as less invasively as only it is possible. This becomes extremely important mainly when diagnosing adolescent patients or even babies. This paper describes the possibilities of medical diagnostics from a different point of view which is the evaluation of microscopic biomedical images of patient's body instead of examining him directly, i.e., invasively. The subject of research is human respiratory system and its diseases which are often caused or closely connected with proper function of small microscopic structures which should serve to clean one's airways. Such structures are called cilia of respiratory epithelium and can be found within nose, trachea or bronchi. The old way of diagnostic of a patient who is suspected to suffer from a disease called Primary ciliary dyskinesia (PCD), as he often undergoes serious inflammations and other breathing complications, comprises several repeated bronchoscopies which cut a small pieces of epithelium from selected parts of respiratory apparatus that are consequently observed using microscope. This is very uncomfortable and many times very hard to perform as the most affected group of patients are children under the age of three. Moreover, evaluation of microscopic samples is often imprecise because doctors assess it subjectively and the proper frequency of ciliary movement is only estimated and classified “slow” or “quick enough”, without accurate value. This paper proposes automated, much faster and much more exact ways of frequency measurements of ciliary movement based on processing and segmentation of biomedical microscopic images, which means more precise evaluation of patient's ciliary health status without such invasiveness as it is used during older methods of examination.