A Computer-Aided Early Detection System of Pulmonary Nodules in CT Scan Images

Utilizing Support Vector Machine Algorithm and Feature Reduction for Accurate Breast Cancer Detection An Exploration of Normalization and Hyperparameter Tuning Techniques

“…Agudelo Gaviria and Sarria-Paja [2] described a breast cancer detection strategy applying deep learning models based on digital diagnostic pictures. Amer et al [3] developed a technique for identifying lung lesions in CT images using feature integration and a genetic algorithm.…”

Lung Cancer Detection System Using Image Processing and Machine Learning Techniques

“…Hanan M. et al (2018) [14], In this proposed system with the support of comp. assisted diagnosis CAD) system researchers are targeting to discover the Cancer Nodules from Computed-Tomography(CT) images, this system is working in four stages: in the first stage preprocessing on Computed Tomography (CT) images is conducted which will help to improve the contrast of image and noise removal from input image dataset in Second step the system performs the segmentation of pulmonary nodules and blood vessels by applying double level of thresholding in addition to the help of morphological operation, in third step feature fusion technique is to apply for extracting the features from segmented image, the feature fusion is made up of four feature extraction methods which are valued histogram (VH) feature, histograms of oriented gradients (HOG) feature, the statistical feature of first and second order and texture Feature of the gray scale co occurrence matrix(GLCM), at last in the fourth step to get the superior accuracy there are three classifier are bring into play which are Multilayer's FF forward NN (MffNN), the second classifier is a neural network function with radial basis (RBFNN), the third classifier is used as SVM Support_Vector_Machine.…”

“…The diverse techniques are used by the researchers for producing high-quality result in detection of lung cancer, correspondingly as SVM Support_Vector_Machine [34], K-NN K-nearest neighbors [34], Decision tree and Artificial Neural Networks (ANN), RBF-ANN [35]. The result of these classification techniques was adequately statistically compared and presented by Hanan et al (2018) [14]. In table 1 it is represented that the how result is modified prior and subsequent use of Genetic Algorithm, from this it has been understand that the SVM and ANN has similar values of Accuracy and Specificity Hanan et al (2018).…”

“…Shows the number of features extracted prior and later using GA Algorithm, achieved Accuracy, Sensitivity and Specificity[14].…”

Utilizing Support Vector Machine Algorithm and Feature Reduction for Accurate Breast Cancer Detection An Exploration of Normalization and Hyperparameter Tuning Techniques

“…However, present diagnostic procedures largely rely on the competency of physicians and physical tests, leaving them prone to errors [2]. As people may cope with ambiguous assessments, automated breast cancer screening applying machine learning has developed as a practical technique to enhance diagnostic accuracy [3][4][5]. A study comparing machine learning with human analysis found that machine learning obtained an accuracy of 91.1%, topping even the highly trained physicians at 79.97% [6].…”