Related Experiment Video
Updated: Jan 8, 2026
07:53
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
2.0K
Harnessing Native-Resolution 2D Embeddings for Lung Cancer Classification: A Feasibility Study with the RAD-DINO
Md Enamul Hoq1, Lawrence Tarbox2, Donald Johann2
1Department of Biomedical Informatics, University of Arkansas for Medical Sciences, AR, Little Rock, USA. mhoq@uams.edu.
Journal of Imaging Informatics in Medicine
|December 19, 2025
Summary
This study introduces a practical AI for lung cancer screening using low-dose CT scans. The AI effectively estimates patient risk, improving accuracy and reliability in identifying potential lung cancers.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Radiology and Medical Imaging
- Computational Pathology
Background:
- Low-dose CT (LDCT) screening significantly reduces lung cancer mortality but is hampered by high false-positive rates.
- There is a need for practical artificial intelligence (AI) tools that align with the slice-based review process common in clinical practice.
Purpose of the Study:
- To evaluate a label-efficient 2D AI pipeline for patient-level lung cancer risk estimation using frozen RAD-DINO embeddings.
- To assess the performance of the AI pipeline under realistic screening prevalence conditions and investigate its interpretability.
Main Methods:
- A 2D pipeline utilizing frozen RAD-DINO embeddings from axial CT slices and a multilayer perceptron (MLP) for risk estimation.
- Patient-level risk estimation was performed using mean aggregation and isotonic calibration on the NLST dataset with a fixed patient-level split.
- Performance was evaluated at screening prevalence (approx. 6%) using repeated imbalanced test draws, with secondary analyses on a near-balanced cohort and retrieval tasks.
Main Results:
- At screening prevalence, the RAD-DINO + MLP pipeline achieved a PR-AUC of 0.705 and ROC-AUC of 0.817 after calibration, demonstrating improved probability reliability.
- A secondary analysis on a balanced cohort yielded high performance metrics: accuracy 0.966, precision 0.974, recall 0.973, F1 0.973, and ROC-AUC 0.912.
- Retrieval tasks using fine-tuned embeddings achieved Precision@5 of 0.853, and interpretability analyses highlighted cancer cases with higher slice scores.
Conclusions:
- Frozen 2D foundation embeddings offer a computationally practical and transparent starting point for LDCT screening AI workflows.
- The evaluated AI pipeline demonstrates effectiveness in risk estimation and potential for image retrieval in lung cancer screening.
- Future work should focus on external validation and CT-native self-supervised learning to further enhance the AI's applicability.
