An Effective Method for Lung Cancer Diagnosis from CT Scan Using Deep Learning-Based Support Vector Network

Abstract

The diagnosis of early-stage lung cancer is challenging due to its asymptomatic nature, especially given the repeated radiation exposure and high cost of computed tomography(CT). Examining the lung CT images to detect pulmonary nodules, especially the cell lung cancer lesions, is also tedious and prone to errors even by a specialist. This study proposes a cancer diagnostic model based on a deep learning-enabled support vector machine (SVM). The proposed computer-aided design (CAD) model identifies the physiological and pathological changes in the soft tissues of the cross-section in lung cancer lesions. The model is first trained to recognize lung cancer by measuring and comparing the selected profile values in CT images obtained from patients and control patients at their diagnosis. Then, the model is tested and validated using the CT scans of both patients and control patients that are not shown in the training phase. The study investigates 888 annotated CT scans from the publicly available LIDC/IDRI database. The proposed deep learning-assisted SVM-based model yields 94% accuracy for pulmonary nodule detection representing early-stage lung cancer. It is found superior to other existing methods including complex deep learning, simple machine learning, and the hybrid techniques used on lung CT images for nodule detection. Experimental results demonstrate that the proposed approach can greatly assist radiologists in detecting early lung cancer and facilitating the timely management of patients.

Quantum-enhanced hybrid feature engineering in thoracic CT image analysis for state-of-the-art nodule classification: an advanced lung cancer assessment

“…A better methodology for deep learning techniques may render satisfactory outcomes for lung nodule classification. It has also been studied in the literature that a combination of deep learning and machine learning techniques is also gaining greater attention in terms of the classification of lung nodules, as it is also proposed by one of the authors mentioned in [20] table 4. They have used different configurations of the max-pooling layer in the deep learning network to extract the feature.…”

“…Another study on multiscale CNN demonstrates that weight initialization with a transfer learning mechanism improved the model performance to classify the nodules and obtained an accuracy of 93.88%. In the study published in 2022, it has been presented that deep learning and Support Vector Machine (SVM) classifiers collaboratively perform nodule classification with an improved accuracy of 94% [20].…”

Can lung airway geometry be used to predict autism? A preliminary machine learning‐based study

“…Support vector machines (SVMs) are a popular supervised learning method that in the healthcare domain alone have been used in predicting ailments such as diabetes, cancer, neurodegenerative diseases such as Alzheimer's and orthopedic conditions such as osteoarthritis (Battineni et al, 2019; Charon et al, 2021; Razzaghi et al, 2016; Yu et al, 2010). They have recently been used specifically for diagnosis of lung diseases such as Chronic Obstructive Pulmonnary Disease (COPD), lung nodules and lung cancer (Shafi et al, 2022; Sui et al, 2015; Xia et al, 2020). While more powerful methods exist, SVMs benefit from being simple linear models with high interpretability.…”

Lung Cancer Detection Using Wavelet Scattering Transform and Artificial Intelligence Technique

“…In sense of classi er/detector, there are many methods that appeared in the literature for lung cancer detection. These methods are mainly based on machine learning (ML) or deep learning networks (DLN) [8][9][10][11]. In [8], ML is used for cancer detection from histopathological images.…”

“…In [9], a cancer diagnostic model based on a deep learning-enabled support vector machine (SVM) is proposed. This method used a convolutional neural network (CNN) with an SVM classi er.…”