A Non-invasive detection of lung cancer combined virtual gas sensors array with imaging recognition technique.

In this paper, we propose a non-invasive detection method of lung cancer combined with a sort of virtual SAW gas sensors array and imaging recognition method. A patient's breath goes through an electronic nose with solid phase micro extraction (SPME) and capillary column for pre-concentration and separation of volatile organic compounds (VOCs) respectively, a pair of SAW sensors one coated with a thin Poly-isobutylene (PIB) film is connected to the output of capillary column port for chemical compounds detection. A lung cancer tissues' culture medium study is also proposed for pathology validation. 11 VOCs which are considered as the biomarkers of lung cancer can be detected qualitatively and quantitatively. Finally these 11 VOCs are used to diagnose lung cancer patients in Run Run Shaw hospital by our e-nose with an improved artificial neural network (ANN) algorithm combined with imaging method for pattern recognition.