Deep Learning-Based Lung Nodule Classification Using Ct Scans
Abstract
Purpose
Lung cancer remains one of the leading causes of cancer-related deaths worldwide and often begins with small lung nodules visible on CT scans. Early and accurate classification of these nodules is essential for timely diagnosis and effective treatment. However, differentiating benign from malignant nodules remains challenging due to similar imaging appearances and variability in radiologist interpretation. This study introduces a deep learning–based CNN model for automated lung nodule classification in CT images to support early detection and reduce radiologist workload.
Methods
A total of 130 patient cases with corresponding XML annotations were obtained from the LIDC-IDRI dataset. Patient-wise splitting was performed to avoid data overlap, dividing cases into 70% training, 15% validation, and 15% testing sets. Using the first radiologist’s reading, only nodules with malignancy scores of 1–2 (benign) and 4–5 (malignant) were included, while ambiguous nodules (score 3) were excluded. Around each valid nodule, 128 x128 pixel image patches were extracted, converted to RGB, and resized to 224 x 224 pixels. Manual augmentation (flips and +10° rotation) was applied to benign patches in the training and validation sets to address class imbalance, yielding 948 total patches. The proposed network was based on EfficientNetB0 (pretrained on ImageNet), followed by a GlobalAveragePooling2D layer, dropout (0.2), and a sigmoid-activated dense layer for binary classification.
Results
At the patch-level, the model achieved 81% accuracy, 87% precision, 60% specificity, 88% recall, and 87% F1-score. At the patient-level, it achieved 73% accuracy, 67% precision, 86% recall, 75% F1-score, and 63% specificity. Grad-CAM was applied to highlight regions influencing model predictions.
Conclusion
Overall, the proposed model demonstrates strong potential for binary lung nodule classification from CT patches. Given the dataset size and encouraging performance outcomes, this approach shows promise for future development of reliable AI-based tools for lung cancer diagnosis.