Detection of Abdominal and Mediastinal LYMPH Nodes Using CT Images

Lymph nodes are small structures that contain immune cells which help to carry the unwanted substances to be removed and also fight against infections. The condition of lymph nodes in cancer staging is very important, which decides the treatment to be used, and also determines the prognosis. Computed Tomography (CT) imaging modality is most commonly used in clinical routine for lymph node assessment. Due to the low contrast of surrounding structures in CT, it is difficult to segment the lymph nodes manually. Thus Lymph node segmentation is an important yet challenging problem in medical image analysis due to its varying size, shapes, and similar surrounding structures. In this paper, our aim is to automatically segment Lymph nodes in abdominal and mediastinal CT images. To get clear visibility, firstly the CT image was pre-processed using TopHat Filter to enhance the contrast of the image and then the lymph nodes was segmented automatically using Histogram Thresholding, K means Clustering and Region growing The presented method helps physicians for proper detection of lymph nodes for diagnosis of cancer.