|
| Serial no. | Ref | Title | Methods | Accuracy (%) | Specificity (%) | Sensitivity (%) |
|
| 1 | [22] | Using deep learning for classification of lung nodules on computed tomography images | CNN with deep neural network and stack auto encoder | 84.1 | 83.9 | 84.3 |
| 2 | [45] | Lung’s nodule classification using combination of CNN, second, and higher order features | CNN withharalick, grey level run length matrix and spatial features | 93.5 | 86.6 | 96.5 |
| 3 | [46] | A computer-aided pipeline for automatic lung cancer classification on computed tomography scans | LUVEM with energy shape and texture features | 96 | 97.4 | 94.2 |
| 4 | [47] | Lung nodule detection in CT images using statistical features | Histogram based threshold technique with statistical and shape features | 92 | 91 | 93.9 |
| 5 | [48] | Artificial neural network-based classification of lung nodules in CT images using intensity, shape, and texture features | ANN with texture, shape and intensity features | 93.2 | 91.3 | 93.1 |
| 6 | [19] | Multimodel ensemble learning architecture based on CNN for lung nodule malignancy suspiciousness classification | CNN-based multimodal framework (VGGNet, InsepNet, ResNet) | 94 | 93.9 | 83.7 |
| 7 | [49] | A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework | DL-based convolutional neural network | 96.33% | NA | 96.37 |
| 8 | Proposed | Identification and classification of lungs focal opacity using CNN segmentation and optimal feature selection | CCN with geometric, HOG, LBP features and SVM classifier | 97.8 | 93.3 | 100 |
|
