Mammography is an effective method for breast cancer detection and breast tumor analysis. In mammography, low dose x-ray is used for imaging, due to which the images are poor in contrast and are contaminated by noise. Hence it is difficult for the radiologist to screen the mammograms for diagnostic signs such as micro calcifications and masses. This ensures the need for image enhancement to aid radiologist. In this paper we present a different algorithm for enhancement of digital mammographic images. The proposed methodology uses mathematical morphology for contrast enhancement and wavelet for denoising. The main contribution of this paper is in differentiating the edge pixels from noise. A quantitative measure of Contrast Improvement Index (CII) and Edge Preservation Index (EPI) are used to evaluate the performance of the algorithm. The algorithm has been tested on a large number of images from standard dataset, comparing the results with the state-of-the-art. By both the analytical indices and ROC analysis, the proposed algorithm shows promising results in early detection of breast cancer and diagnosis.

Segmentation of lung regions with lung nodules at mediastinum is the first step in computer-aided detection (CAD) which provides a better diagnosis of lung cancer. The existing methods fail in segmentation of lung regions with the cancer tumors at the mediastinum of the lungs. In this paper, a new approach is proposed that extracts lung regions with cancer tumors at the mediastinum of the lungs based on curve analysis. The proposed algorithm is tested on 05 patient's dataset which consists of 60 images of the Lung Image Database Consortium (LIDC) and the results are found to be satisfactory with 99 % average overlap measure (AΩ). The proposed algorithm extracts lung nodules at the mediastinum of the lungs which helps in detection of lung cancer.

No abstract

Ultrasound imaging is a widely used diagnostic technique for the early detection of breast diseases. However, the usefulness of ultrasound imaging is degraded by the multiplicative speckle noise. This reduces the efficiency of diagnosis by radiologists. In order to improve the efficiency of diagnosis, we propose an algorithm for speckle denoising and edge enhancement for the segmentation of ROI. The algorithm is performed in three steps. In the first step, speckle denoising is achieved through shrinkage based on local variance matrix. The second step enhances the edges based on formation of homogenous blocks. The third steps segments the object boundaries based on K-means clustering algorithm. The results of the proposed method have been compared with the well known filters. The experimental results show that the proposed algorithm has considerably improved the image quality without providing any noticeable artifact.

No abstract