computerized classification of CT lung images using CNN with watershed segmentation

Abstract : Cancer is a major threat to the lives of human beings. Around 74% of the people who get affected by cancer lost their lives. But early detection of cancer cells can prevent death rates. CT(Computerized Tomography) is one of the major used for cancer cell identifications by the oncologist. Computer-aided cancer detection plays a major role in the detection of cancer in an early stage. Classification of CT scan images comes as the first stage for computer-aided detection of cancer cells. CNN(Convolution Neural Network) based classification method along with Gaussian Filtering and Watershed Segmentation is proposed for effective classification of CT Scan Images.500 CT Scan images of Bone, Brain, Lung, Kidney, Neck are collected from the Oncology Department, Manipal Hospitals, Vijayawada. The accuracy rate of 94.5% is achieved with the proposed CNN based classification CT Scan images.
 EXISTING SYSTEM :
 Lung cancer is the most common cause of cancer-related deaths worldwide. Hence, the survival rate of patients can be increased by early diagnosis. Recently, machine learning methods on Computed Tomography (CT) images have been used in the diagnosis of lung cancer to accelerate the diagnosis process and assist physicians. However, in conventional machine learning techniques, using handcrafted feature extraction methods on CT images are complicated processes. Hence, deep learning as an effective area of machine learning methods by using automatic feature extraction methods could minimize the process of feature extraction.
 DISADVANTAGE :
 Detection of lung cancer was very challenging and radiologist used to take enormous amount of time, if they manually detect the nodules by using CT scans. Therefore, an automatic system is required which help the radiologist to take the decision fast while reducing their work load.
 PROPOSED SYSTEM :
 In this study, two Convolutional Neural Network (CNN)-based models were proposed as deep learning methods to diagnose lung cancer on lung CT images. To investigate the performance of the two proposed models (Straight 3D-CNN with conventional softmax and hybrid 3D-CNN with Radial Basis Function (RBF)-based SVM), the altered models of two-well known CNN architectures (3D-AlexNet and 3D-GoogleNet) were considered. Experimental results showed that the performance of the two proposed models surpassed 3D-AlexNet and 3D-GoogleNet. Furthermore, the proposed hybrid 3D-CNN with SVM achieved more satisfying results (91.81%, 88.53% and 91.91% for accuracy rate, sensitivity and precision respectively) compared to straight 3D-CNN with softmax in the diagnosis of lung cancer.
 ADVANTAGE :
 ? Accurately identifying lung cancer in the early stages is preferred; otherwise it may lead to a disaster. CT scan is done by radiologists to identify lung cancer using CAD (Computer Aided Diagnosis). ? CT scan images are high resolution and very clear with low noise distortion.Second stage is preprocessing which helps in enhancing the image quality.

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com