Lung CT Image Processing Based On Fuzzy Mathematics

Lung cancer is the leading cause of cancer death among people nowadays.Computer-Aided Detection (CAD) for pulmonary nodules on CT images can helpradiologist find pulmonary nodules efficiently and decrease the rate of missed diagnosis,which provides a significant way for lung cancer diagnosis in early stage.CT image is an important basis in lung cancer diagnosis and treatment. It makesthe doctor to observe the lung tissues more direct and clear, then to improve accuracyrate in diagnosis. So CT images have very important value in clinical application.Generally, images suffer information loss when the three dimensions target is projectedon the two dimensions image plane. There is some confusion in defining boundary,region and texture of image, bringing fuzzy character when explaining the result of thelow level image processing. All in all images are fuzzy by nature, so does the lung CTimage. Fuzzy mathematics is a branch of mathematics subjects which studies the fuzzyphenomena and their concepts, now is used in wide areas. Therefore the applications offuzzy mathematics methods in medical image processing and analysis are rational andnecessary.Based on consulting much previous research studies, this paper has finished somework as following:(1) A detailed review about the fuzzy mathematics methods in medical imageprocessing and analysis during the past few years is done in this paper. The applicationsof fuzzy sets, fuzzy clustering, fuzzy inference, fuzzy connectedness and fuzzycomputing intelligence method in medical image processing and analysis are introduced,with discussions of these different methods on their principles, merit and demerit,characteristics and existing problems. Researches show that fuzzy mathematics hasalready made a large amount of fruitful applications results in the area of medical imageprocessing. As a young subject, it still has shown a huge potential in the application ofmedical image processing and analysis. With the further development of computertechnology and the continuous emergence of advanced technology, medical imageprocessing and analysis based on fuzzy mathematics will become mature and perfect.(2) An experimental investigation of fuzzy enhancement algorithms for nonsolidpulmonary nodules is performed in this paper. For the detection of the nonsolid pulmonary nodules with irregular shape, blurry edge and low contrast to lungparenchyma is more difficult, the image enhancement for nonsolid pulmonary isnecessary in CAD systems. Based on consulting a lot of related references, we attemptthe classic Pal-King fuzzy enhancement algorithm and several kinds of improvedalgorithms. Finally an applicative method for the enhancement of nonsolid pulmonarynodules is proposed. Practices prove that our proposed method can efficiently enhancethe nonsolid pulmonary nodules’ contrast to lung parenchyma and decrease thedisturbance of blood vessels at the same time.(3) Segmentation is a key step in CAD systems, for its accuracy directly affects thefollowing steps of CAD system. According to the characteristics of subsolid pulmonarynodules in lung CT images, through attempting fuzzy c-means (FCM), kernel fuzzyc-means (KFCM) and its improved algorithms (WKFCM), a novel improved weighedkernel fuzzy c-means (IWKFCM) method considering information about vesselsstructure and classes’ distribution as weights is proposed in this paper. The method istested on both clinical data and standard LIDC datasets including18clinical nodulesand36LIDC nodules. Overlaps of two datasets are71.65%and76.18%respectively,both with low FPR and FNR less than17%. Experimental results show that theproposed method can get more accurate result than FCM, KFCM and WKFCM, andalso is superior to other methods published in recent reports and literature.Our research work in this paper can provide a consultative reference to the furtherstep of feature extraction and classification for pulmonary nodules in CAD systems.