Efficient and reliable lung nodule detection using a neural network based computer aided diagnosis system

Abstract

The manual examination of histological images like computed tomography (CT) images by physicians is prone to subjectivity and limited intra and inter-surgeon reproducibility, due to its heavy reliance on human interpretation. As result of which, diagnosis of cancer especially in lungs becomes less accurate and unreliable. So, a computer-aided diagnosis (CAD) system, based on artificial intelligence that efficiently detects nodules of any shape and size, is used for diagnosis without human intervention. In this work, we have developed a two stage CAD system in which the first stage involves pre-processing applied for a better quality image to enable higher success rate on detection following which the cancerous nodule region is segmented. The second stage involves artificial neural network (ANN) architecture which is trained using a modified BFGS algorithm.The proposed system was trained, tested, and evaluated specifically on the problem of detecting lung cancer nodules found on CT images to give a positive detection. A significant comparative analysis was done between the proposed method and several existing CAD systems used for lung nodule diagnosis and the proposed method using training-based neural networks prove to provide accuracy of 96.7% and also better specificity; thus, the overall performance of the CAD scheme was improved substantially.

Automatic 3D pulmonary nodule detection in CT images: A survey

“…Other techniques that can be considered for the preprocessing stage are: enhancement filter [70,71], contrast limited adaptive histogram equalization [72],auto-enhancement [73], wiener filter [73], fast Fourier transform [74], wavelet transform [74], anti-geometric diffusion [74], erosion filter [75], smoothing filters [76] and noise correction [76]. Figure 1 gives an illustration of preprocessing applied to a lung CT image, in which an improved distribution of level colors and, consequently, a better visualization of the lung and its structures, is accomplished.…”

“…Computational classifier Santos et al [4], Wang et al [25], Choi and Choi [24], Riccardi et al [30], Liu et al [31], Ozekes and Osman [37], Yang, Periaswamy and Wu [39] and Orozco et al [94] Support vector machines (SVM) El-Baz et al [22] Bayesian supervised Cascio et al [26], Ashwin et al [72], Lin et al [95] and Bellotti et al [96] Artificial neural networks (ANN)…”

Lung Cancer Detection using Curvelet Transform and Neural Network

“…The drawback of histogram equalization is that the image brightness is changed after apply this technique. To overcome the limitation of histogram equalization we used Contrast Limited Adaptive Histogram Equalization (CLAHE) technique to enhance CT scan images [9]. The CLAHE algorithm partitions the images into contextual regions and applies the histogram equalization to each one.…”

Fuzzy Based Contrast Enhancement Method for Lung Cancer CT Images

“…Ashwin et al (2012) suggested a CAD system for the lung nodule detection using neural network. The contrast limited adaptive histogram method was used to remove the noise presented in medical image and improve the contrast, However the brightness value could be further increase [22]. used Brightness Preserving Bi Histogram Equalization and Adaptive Histogram Equalization methods for contrast enhancement which divide image histogram in two parts mean and median and then process is performed [24].…”

“…Surya et al (2015) [11]. Ashwin et al (2012) suggested a CAD system for the lung nodule detection using neural network. The contrast limited adaptive histogram method was used to remove the noise presented in medical image and improve the contrast, However the brightness value could be further increase [22].…”