Related Experiment Video
Updated: May 30, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
An intelligent lung cancer detection from computed tomography images using robust optimal deep transfer learning with
B Prabha1, M Poonkodi2, M Premalatha2
1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India. prabha.b@vit.ac.in.
BMC Medical Informatics and Decision Making
|May 19, 2026
Summary
This study introduces a novel AI framework for early lung cancer detection using CT scans. The system achieves high accuracy and interpretability, aiding clinical decisions and improving patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Lung cancer is a leading cause of mortality worldwide, necessitating advanced diagnostic tools.
- Current diagnostic methods require improvement in precision and early detection capabilities.
Purpose of the Study:
- To develop an explainable AI framework for accurate and early lung cancer detection using CT images.
- To enhance the reliability and interpretability of automated lung cancer diagnosis.
Main Methods:
- A hybrid approach combining DeepLabV3+ segmentation, an Enriched Deep Neural Network (DNN), Modified Shark Smell Optimization (MSSO), and Inception ResNetV2 transfer learning.
- Explainable AI (XAI) using GradCAM++ for visualizing critical lung regions.
Main Results:
- The proposed MSSO-InceptionResNetV2 framework demonstrated superior accuracy, sensitivity, specificity, ROC, and precision compared to traditional models.
- The system achieved reduced False Positive Rate (FPR) and computational time.
- Explainable AI provided critical insights into decision-making processes.
Conclusions:
- The developed framework offers a reliable and interpretable solution for automated lung cancer diagnosis.
- The system shows significant potential for clinical integration, enabling early intervention and improved patient prognosis.
