An Early Prediction and Classification of Lung Nodule Diagnosis on CT Images Based on Hybrid Deep Learning Techniques

Abstract

Detection of malignant lung nodules at an early stage may allow for clinical interventions that increase the survival rate of lung cancer patients. The use of hybrid deep learning techniques to detect nodules will improve the sensitivity of lung cancer screening and the interpretation speed of lung scans.Accurate detection of lung nodes is an important step in computed tomography (CT) imaging to detect lung cancer. However, it is very difficult to identify strong nodes due to the diversity of lung nodes and the complexity of the surrounding environment.Here, we proposed alung nodule detection and classification with CT images based on hybrid deep learning (LNDC-HDL) techniques. First, we introduce achaotic bird swarm optimization (CBSO) algorithm for lung nodule segmentation using statistical information. Second, we illustrate anImproved Fish Bee (IFB) algorithm for feature extraction and selection process. Third, we develop hybrid classifier i.e. hybrid differential evolution based neural network (HDE-NN) for tumor prediction and classification.Experimental results have shown that the use of computed tomography, which demonstrates the efficiency and importance of the HDE-NN specific structure for detecting lung nodes on CT scans, increases sensitivity and reduces the number of false positives. The proposed method shows that the benefits of HDE-NN node detection can be reaped by combining clinical practice.

Residual Partial Derivative Multilayer Perceptron Deep Learning Based Classifier for Lung Cancer Detection

“…The diagnostic performance of the proposed RN-PDMP method and existing methods 3D-CNN [1] and LNDC-HDL [2] are tested under the complexity, accuracy, precision and recall factors. The corresponding formulaeof these measures are as given below.…”

“…Experimental assessment of proposed, RN-PDMP method and two existing methods 3D-CNN [1] and LNDC-HDL [2] Simulations were performed in Parametric metrics considered for the evaluation of lung cancer detection consists of complexity, disease detection accuracy, precision and recall. Each method has been tested individually over 1000 images of testing set involved that 400 cases diagnosed as malignant, 100 cases diagnosed with benign and 500 cases classified as normal cases to evaluate all performance metrics.…”

“…It is measured in percentage (%). Table 1 given below lists the disease detection accuracy using the proposed RN-PDMP method and two existing methods, 3D-CNN [1] and LNDC-HDL [2] by substituting the values in equation ( 15) with respect to sample images ranging between 100 and 1000. As shown in the observed results, the disease detection accuracy of three methods namely the RN-PDMP method provides better accuracy results when compared to existing methods.…”

“…As shown in the observed results, the disease detection accuracy of three methods namely the RN-PDMP method provides better accuracy results when compared to existing methods. For example, with the number of samples being 100, the accuracy observed by 93.15% of RN-PDMP method and accuracy of existing 3D-CNN [1] and LNDC-HDL [2] was found to be 89% and 97% respectively. The disease detection accuracy observed results of the proposed RN-PDMP method are compared to existing methods.…”

A hybrid machine learning technique for early prediction of lung nodules from medical images using a learning‐based neural network classifier

“…Gugulothu et al 31 recommended the diagnostic process based on CNN deep transmission and extreme learning machine (ELM), which combines the synergistic effect of both methods to manage the classification of naked dead nodes. DTCNN was the first to adopt high beard characteristics in an already trained image‐net database.…”