Oncol Case Rep J | Volume 6, Issue 1 | Review Article | Open Access
Vijay KG1* and Balaji S2
1Department of Computer Science & Engineering, Koneru Lakshmaiah Education Foundation, Deemed to be University, India
2Department of Computer Science & Engineering, Koneru Lakshmaiah Education Foundation, Deemed to be University, India
*Correspondance to: Vijay Kumar Gugulothu
Fulltext PDFThis paper presents a Computer-Aided Detection (CAD) system based on the acquisition of ThreeDimensional (3D) behavior to detect nodules in the lungs. The CAD provides useful second feedback and eliminates distinctions between visitors. In this paper, they present a computer system designed to detect lung nodes. It uses two different multi-level schemes to identify the lung field and separate candidate sets at high sensitivity speeds. The main task of this work is to classify the components into a highly balanced candidate set using Support Vector Machines (SVMs). The basic techniques used in lung nodes are pre-processing, division, characterization, and classification. Feed forward Neural Networks (NNs), SVMs, end trees (TDs), and Linear Discrimination Analysis (LDAs) were used to determine ROI. Synthetic neural networks and auxiliary Vector Machines (SVM) models are widely used in taxonomy for their ability to model complex systems. Imaging techniques can be useful for radiologists to im-prove the detection of lung nodes. The results show CNN (97.4%), SVM sensitivity (96.5%), and DNN (97.8%) specificity over other classifiers.
Lung nodule; Prediction; Classification; Preprocessing; Segmentation; Future extraction; Deep learning; Machine learning
Vijay KG, Balaji S. Early Prediction and Classification of Lung Nodule Diagnosis on CT Images with Machine Learning Techniques - A Brief Review. Oncol Case Report J. 2023; 6(1): 1055..