A novel CAD system to automatically detect cancerous lung nodules using wavelet transform and SVM

Abstract

A novel cancerous nodules detection algorithm for computed tomography images (CT-images) is presented in this paper. CT-images are large size images with high resolution. In some cases, number of cancerous lung nodule lesions may missed by the radiologist due to fatigue. A CAD system that is proposed in this paper can help the radiologist in detecting cancerous nodules in CT- images. The proposed algorithm is divided to four stages. In the first stage, an enhancement algorithm is implement to highlight the suspicious regions. Then in the second stage, the region of interest will be detected. The adaptive SVM and wavelet transform techniques are used to reduce the detected false positive regions. This algorithm is evaluated using 60 cases (normal and cancerous cases), and it shows a high sensitivity in detecting the cancerous lung nodules with TP ration 94.5% and with FP ratio 7 cluster/image.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

“…Other traditional vision algorithms found successful results in juxtapleural nodules detection [ 89 ]. In the context of this problem, missing a true nodule should be more penalized than predicting too many false suspicions; however, there is an obvious effort in the literature to decrease false positive mistakes, mostly approached by combining different classification networks [ 78 , 90 ], using multi-scaled patches for capturing features at different expression levels [ 80 , 81 , 91 , 92 ], employing other classification algorithms, such as SVM [ 82 , 86 , 87 , 93 , 94 , 95 ], Bayesian networks, and neuro-fuzzy classifiers [ 95 ], or proposing a graph-based image representation with deep point cloud models [ 96 ].…”

Energy, economic and environmental analysis of fuzzy logic controllers used in smart buildings

“…As reported by the Jordanian office of climate, the CO2 factor is about 88.2g/kWh. The overall annual emission is recognized to be one of the most significant indicators of the environmental measures and assessment [26]. Figure 6 shows that using proposed control system, the yearly eliminated greenhouse gas emission is nearly 25.5 tons of CO2 by applying the most of fuzzy role sets.…”

Automated 3D convolutional neural network architecture design using genetic algorithm for pulmonary nodule classification

“…However, the manual nodule detection process is laborious and time-consuming for radiologists since it requires a long time owing to the fact that they review sheer volume of scans in a day, which may affect their capacity to accurately identifying and classifying tumors [2], [8]. Even expert radiologists sometimes faces difficulty detecting and diagnosing lung nodules in CT scans [9]. Also, the accuracy of a radiologist's diagnosis are heavily influenced by the individual clinician's experience [10].…”

“…Also, the accuracy of a radiologist's diagnosis are heavily influenced by the individual clinician's experience [10]. Recently, computer-aided diagnosis (CAD) systems have emerged as a valuable tool for easing the burden on radiologists by providing objective prediction with non-invasive solution to aid radiologists to diagnose pulmonary nodules [3], [7], [9]. Typically, CAD systems for lung nodule detection involve five stages: i) image acquisition, ii) preprocessing, iii) lung segmentation, iv) nodule detection, and v) classification [6].…”