Feature extraction is one of the most important step in CAD (Computer Assisted Diagnosis) system. It helps CAD system to take correct decision and increase its accuracy by providing distinguish feature of malignant and benign tumor. Computer based system is proposed in this paper for feature extraction of lung nodule from the X-ray image. In recent years, the image processing mechanisms are widely used in several medical areas for early detection and in deciding treatment stages, where the time and cost factor is very important to discover the disease in the patient. Among the cancer, lung cancer is one of the most common causes of death worldwide. Therefore, early detection using diagnostic tests promises to reduce mortality from lung cancer. Present paper deals with the problem of developing a computer based system for the extraction of maximum features from the segmented suspicious area from the lung X-ray image. Further, these properties can be used to classify lung tumor as benign or malignant from the X-ray image directly. Calculated features will help the CAD system to take correct decision.

CAD (Computer Aided Diagnosis) is a concept established by taking into account equally the roles of physician and computer to comment on disease. With CAD system, the performance given by computer does not have to be comparable to or better than that by physician, but need to be complementary to that by physician. To reduce the false positive and false negative diagnosis in determining whether the tumor is malignant or benign, doctors are taking help of CAD system. CAD using image processing technique has become one of the major research subjects in medical imaging and diagnostic radiology. Radiologist uses the CAD system output as a ‘second opinion’ and make the final decision to conform the disease. In present paper, suspicious area is segmented from the chest X-ray image after doing pre-processing of the image. Characterization of lung nodule means describing distinctive essential features. By doing segmentation, the features are extracted from the segmented region. All features are calculated from their respective mathematical formulas. Calculated features values vary according to arrangement of pixels in the image. Further this information can be used as an input to the CAD system for determining whether the segmented suspicious tumor area is malignant or benign. The proposed system will not replace the doctor’s role in detection of cancer but it will help doctor to take correct decision in short time with accuracy. It will act as second opinion before conformation of cancer.

Abstract-According to WHO (World Health Organization) report, because of chest diseases more than 12 million death cases are reported during the year 2008. If chest disease is detected in its early stage then the possibility of surviving the patient is more. One of the most preferred scan for the early detection of chest disease is X-ray scan. X-ray is inexpensive, painless and required less time to generate image. X-ray image contain a lot of irrelevant information and has intensity problems, which makes the task of locating and analyzing suspicious area difficult by the doctor. By using pre-processing and segmentation technique, suspicious area is easily separate out from the rest of the structure. In the present paper, segmentation techniques and the segmentation results after applying on the X-ray images are discussed. In segmentation, image is partition into a meaningful region. The result of image segmentation is a set of segments that collectively cover the entire image and all pixel in the segmented region which are similar with respect to some characteristic or computed property such as color, intensity, texture etc. In present paper, some of the segmentation techniques such as edge detection, thresholding, skeletonization, contour and watershed transform are applied on the chest X-ray image and the effectiveness of each techniques are shown with the help of images and properties extracted.