Poster Poster Program Diagnostic and Interventional Radiology Physics

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.

People

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
B-Trac – Breast Tissue Rotation and Compression Apparatus for Calibration

Mammography (compressed 2D) and MRI (uncompressed 3D) capture breast tissue under different conditions, complicating tumor localization across modalities. To bridge this gap, we developed a customizable physical platform to simul...

Dayadna Hernandez Perez
Diagnostic and Interventional Radiology Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
Comprehensive Medical Physics Assessment of Digital Mammography Equipment: A Three-Year Multi-Site Evaluation of Technical Performance and Radiation Safety at 24 Saudi Arabian Healthcare Institutions (2022–2024)

To conduct a comprehensive multi-center audit evaluating the technical performance, image quality, and radiation safety of digital mammography systems across 24 unique healthcare facilities in Saudi Arabia. This study aims to est...

Sami Alshaikh, PhD
Diagnostic and Interventional Radiology Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
Starting Small: Implementing a CT Protocol Optimization Program

This talk describes our organization’s CT optimization program, and how we implemented it to make efficient use of limited physicist time.

Robert J. Cropp, PhD
Diagnostic and Interventional Radiology Physics 0 people interested