No abstract

In this modern era the clinical laboratory has greater attention to produce an accurate result for every test particularly in the area of lung tumour. The lung tumour is very essential to detect as well as to follow the treatment of many diseases like benign, malignant etc. This paper is focusing on the segmentation part to find the juxta vascular region. For finding the juxta vascular region in lung three stages are used. First stage is the image acquisition here input lung image is read and then resized. Second stage is the image pre-processing here improved linear iterative clustering technique is used .Third stage is the segmentation here the adjustable surface normal overlap is used. While using the above stages the output for juxta vascular region in the segmentation part is segmented clearly. The juxta vascular region is not clearly found in the previous paper. The research gap for this paper is to find the juxta vascular region in the lung. This juxta vascular region is present in the right side of the lung. Using the Adjustable Surface Normal Overlap (ASNO) segmentation the juxta vascular region is segmented clearly.

No abstract

Medical images are an important part of a patient’s health record, and they need data manipulation, processing, and handling by computers. As a result, medical data is a type of bigdata, and its analysis has become complex. Because manual disease diagnosis takes longer and produces less accurate results, it may result in incorrect treatment. Three DCNN architectures have been exploited and evaluated for tumor detection and classification. The sample image for the experimentation is chosen from Lung Image Database Consortium (LIDC) with Image Database Resource Initiative (IDRI) and Kaggle dataset which consists of normal and abnormal image. The experimental results of proposed DCNN classifier achieved best accuracy than the GoogleNet, AlexNet, Artificial neural network and support vector machine.