Related Experiment Video
Updated: Jun 30, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.2K
Uncertainty-aware image classification on 3D CT lung
Rahimi Zahari1, Julie Cox2, Boguslaw Obara3
1School of Computing, Newcastle University, Newcastle upon Tyne, UK.
Computers in Biology and Medicine
|March 20, 2024
Summary
This study introduces an uncertainty-aware framework for lung nodule classification using 3D CT scans. It enhances model reliability by quantifying uncertainty, improving diagnostic accuracy and patient survival rates.
Area of Science:
- Medical Imaging Analysis
- Artificial Intelligence in Healthcare
- Oncology
Background:
- Early lung cancer detection is vital for patient survival, with deep learning models showing promise.
- Current models often lack reliability and robustness, exhibiting overconfidence on unseen data.
- Model uncertainty can guide referral to medical experts for critical second opinions.
Purpose of the Study:
- To develop and evaluate an uncertainty-aware framework for classifying benign and malignant lung nodules from 3D CT images.
- To quantify prediction uncertainty using Monte Carlo Dropout (MCD), Deep Ensemble (DE), and Ensemble Monte Carlo Dropout (EMCD).
- To assess the impact of uncertainty quantification and data referral on diagnostic performance.
Main Methods:
- Proposed a three-phase framework: data preprocessing/model selection, uncertainty quantification (UQ), and uncertainty measurement/data referral.
- Evaluated eight deep learning models (ResNet, DenseNet, Inception family), employing MCD, DE, and EMCD for UQ.
- Utilized 3D CT images for nodule classification, comparing UQ approaches and implementing a data referral threshold.
Main Results:
- All evaluated deep learning models achieved average F1 scores above 0.832, with InceptionResNetV2 reaching 0.845.
- Incorporating UQ significantly improved overall model performance.
- MCD excelled in uncertainty estimation, while DE and EMCD demonstrated superior URecall, identifying incorrect predictions effectively.
- A data referral threshold further enhanced accuracy to 0.959.
Conclusions:
- The proposed uncertainty-aware framework enhances the reliability and robustness of lung nodule classification from 3D CT scans.
- Uncertainty quantification methods, particularly DE and EMCD for URecall, are crucial for identifying unreliable predictions in medical diagnostics.
- Implementing a data referral strategy based on uncertainty thresholds significantly boosts diagnostic accuracy, aiding clinical decision-making.
