Automated lung nodule detection and classification based on multiple classifiers voting

Abstract

Lung cancer is the most common cause of cancer‐related death globally. Currently, lung nodule detection and classification are performed by radiologist‐assisted computer‐aided diagnosis systems. However, emerged artificially intelligent techniques such as neural network, support vector machine, and HMM have improved the detection and classification process of cancer in any part of the human body. Such automated methods and their possible combinations could be used to assist radiologists at early detection of lung nodules that could reduce treatment cost, death rate. Literature reveals that classification based on voting of classifiers exhibited better performance in the detection and classification process. Accordingly, this article presents an automated approach for lung nodule detection and classification that consists of multiple steps including lesion enhancement, segmentation, and features extraction from each candidate's lesion. Moreover, multiple classifiers logistic regression, multilayer perceptron, and voted perceptron are tested for the lung nodule classification using k‐fold cross‐validation process. The proposed approach is evaluated on the publically available Lung Image Database Consortium benchmark data set. Based on the performance evaluation, it is observed that the proposed method performed better in the stateof the art and achieved an overall accuracy rate of 100%.

Radiomic Feature Analysis for Distinguishing Solitary Pulmonary Capillary Hemangioma From Lepidic-Predominant Lung Adenocarcinoma in Ground Glass Lung Nodules

“…Radiomic texture features have been widely used in tissue characterization for discriminating different types of lesions in thoracic CT images, such as automatic lung nodule detection [28][29][30][31][32][33][34][35][36], differential diagnosis of benign and malignant lung nodules [15,16], and differentiation of lung cancer subtypes [17]. Several texture features have been suggested for automated detection of pulmonary nodules in CT images, including the mean, skewness, and kurtosis values of intensity histograms [28][29][30][31][32][33], local binary patterns [9,14,34,35], and gray-level co-occurrence matrix (GLCM)-based features [28][29][30]36]. While radiomic texture features were shown to be effective in distinguishing various types of lung nodules, discrimination between SPCH and LPA was intrinsically di cult due to their common GGN-like appearance.…”

Quantitative Assessment of Parenchymal Involvement Using 3D Lung Model in Adolescent With Covid-19 Interstitial Pneumonia

“…Moreover, since CT represents an important imaging biomarker and is pivotal to guide pharmacological management and improve ventilation strategies, further implementation of semi-automatic and/or fully automatic (AI-based) algorithms for image processing ( 12 , 13 ) might be beneficial in order to rapidly and systematically provide accurate data about the extent of lung disease in these patients.…”

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

“…There are two main categories of features: handcrafted and non‐handcrafted features. The first category employed with traditional machine learning techniques while the second works for deep learning (Rehman, Khan, Mehmood, et al, 2020; Rehman, Khan, Saba, et al, 2020; Saba, 2019; Saba, Mohamed, El‐Affendi, Amin, & Sharif, 2020).…”