Peer-Reviewed Publication
April 2026
Deep Convolutional Neural Network-Based Multiclass Classification of Pulmonary Lesions Using Computed Tomography Imaging from the IQ-OTH/NCCD Dataset
Medical Research Archives · European Society of Medicine · Volume 14, Issue 4 · 2026
Citation:
Patel, D., et al., 2026. Deep Convolutional Neural Network-Based
Multiclass Classification of Pulmonary Lesions Using Computed
Tomography Imaging from the IQ-OTH/NCCD Dataset.
Medical Research Archives, [online] 14(4).
Developed a VGG16-based deep transfer learning framework for multiclass pulmonary lesion classification from CT images, distinguishing Normal, Benign, and Malignant cases. The research incorporated medical image preprocessing, data augmentation, class-balanced training, model evaluation, and cross-validation to improve classification reliability.
97.73%
Accuracy
99.34%
AUC
1,190
CT Images
3
Classes
Research Highlights
- Developed a VGG16 transfer learning architecture for multiclass pulmonary lesion classification.
- Applied preprocessing, image augmentation, and class-balanced training for medical CT images.
- Evaluated performance using accuracy, precision, recall, F1-score, ROC-AUC, confusion matrices, and 5-fold cross-validation.
- Investigated model confidence and prediction reliability for AI-assisted medical image classification.