Lung Cancer detection and Classification by using Machine Learning & Multinomial Bayesian

Abstract

Image Processing is a technique to enhance raw images received from cameras

Untitled

“…Mediastinoscopy is used for detailed chest X-ray images on the Bayi Hospital database [29]. [30][31][32][33]. Principal component analysis (PCA) by [30], Median filtering [6][7][8]21,27], Gabor filter [6][7][8]17,27,34], multi-scale selective filter [24], Gaussian filter, average filter, and disk filter [35], Auto-enhancement algorithm and Fast Fourier transform (FFT) [17], erosion, and dilation [21], isotropic re-sampling, tri-linear interpolation [10,36], linear interpolation algorithm [25,37], contrast enhancement [11,14], thresholding, blob analysis [11], template modeling [38], adaptive thresholding [39], background thresholding [40], and mass screening and edge preserving smoothness [41] are found to be suitable for medical images.…”

“…Similarly, area, perimeter, and eccentricity [7,33], structural features (area, convex area, equivalent diameter, and solidity) [18,34] and texture features (energy, mean, standard deviation) [18], and morphological and colorimeter features [6] are extracted features from the region of interest of lungs. Binarization is used to extract multiple features [16,17,20,27,30,31,39,47]. Several texture features proved to be useful a feature, including uniformity, entropy, maximum probability, inertia, inverse difference, correlation, homogeneity, dissimilarity, autocorrelation, cluster shade, cluster prominence, inverse difference normalized, sum entropy, sum average, sum of squares, sum variance, difference variance, difference entropy, information measures of correlation and maximal correlation coefficient extracted from gray level co-occurrence matrix (GLCM) [13,16,20,[30][31][32]39,47], sequential forward selection [28,31], spatial gray level dependence matrix (SGLDM) [40], genetic algorithm [32], masking approach [17,27], histogram [16,40], PCA [22,49], region growing technique [24,45], linear discriminant analysis (LDA) [15,45], filter bank method [28], box-counting method [40], contrast enhancement and calcification [34] and gray-we...…”

“…These multiple classifiers are used to enhance the prediction accuracy. Unsupervised learning algorithms include multivariate multinomial Bayesian [31], rule-based classifier [24,43], feature-selective classifier based on ANNs and genetic algorithms (FD-NEAT) [10], a combination of rule base classifier, and LDA [26], and these are used to classify lung nodule with its nodule type. Diagnostic rules are extracted features utilized to detect candidate nodule location for classification [37].…”

Fuzzy Based Contrast Enhancement Method for Lung Cancer CT Images

“…CAD system for early detection of lung cancer helps on an automatic diagnosis of the lung nodule included in chest CT .The problem for detecting lung nodules in radiographs include variation in nodule size, appearing anywhere in the lung area, nodule appearance may same as bone etc. [7][8]. Jiping (2016) evaluate the value of contrast enhancement in terms of mean density and enhancement extent of lesions for the 26 patients with respect to pretreatment value P significant reduced (p=0) after effective treatment of patients.…”

“…Sandeep et al (2014) proposed contrast limited Adaptive Histogram Equalization for preprocessing of images. But the time taken could be reduce for feature extraction of images [7]. Surya et al (2015) [11].…”