Longitudinal assessment of lung lesion burden in CT

2025-04-09

Medical Imaging 2025: Computer-Aided Diagnosis

AI Summary

Early detection of pulmonary nodules and personalized treatment assessment require longitudinal, quantitative measurement of total lung lesion burden from CT imaging. Method: We propose a fully automated 3D nnUNet-based lesion segmentation framework—the first to systematically perform dynamic, multi-phase CT tracking of total lung lesion burden. Notably, incorporating anatomical priors degraded segmentation performance, highlighting the superiority of data-driven modeling in pulmonary quantitative imaging. Results: The model achieves an F1-score of 69.8% for lesions >1 cm and a Dice coefficient of 77.1±20.3% for segmentation; volumetric measurement bias has a median of only 0.02 mL. Bland–Altman analysis and linear regression confirm strong longitudinal consistency and clinical reliability. This work delivers a generalizable, high-accuracy quantitative imaging biomarker for assessing pulmonary disease progression.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In the U.S., lung cancer is the second major cause of death. Early detection of suspicious lung nodules is crucial for patient treatment planning, management, and improving outcomes. Many approaches for lung nodule segmentation and volumetric analysis have been proposed, but few have looked at longitudinal changes in total lung tumor burden. In this work, we trained two 3D models (nnUNet) with and without anatomical priors to automatically segment lung lesions and quantified total lesion burden for each patient. The 3D model without priors significantly outperformed ($p<.001$) the model trained with anatomy priors. For detecting clinically significant lesions $>$ 1cm, a precision of 71.3%, sensitivity of 68.4%, and F1-score of 69.8% was achieved. For segmentation, a Dice score of 77.1 $pm$ 20.3 and Hausdorff distance error of 11.7 $pm$ 24.1 mm was obtained. The median lesion burden was 6.4 cc (IQR: 2.1, 18.1) and the median volume difference between manual and automated measurements was 0.02 cc (IQR: -2.8, 1.2). Agreements were also evaluated with linear regression and Bland-Altman plots. The proposed approach can produce a personalized evaluation of the total tumor burden for a patient and facilitate interval change tracking over time.

Problem

• Automatically segment lung lesions for tumor burden assessment
• Track longitudinal changes in total lung tumor burden
• Compare 3D models with and without anatomical priors

Innovation

• 3D models for lung lesion segmentation
• Quantified total lesion burden automatically
• Evaluated performance with clinical metrics