Related Experiment Video
Updated: Aug 16, 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
14.3K
Improving Lung Cancer Diagnosis with CT Radiomics and Serum Histoplasmosis Testing.
Hannah N Marmor1, Stephen A Deppen1,2, Valerie Welty3
1Department of Thoracic Surgery, Vanderbilt University Medical Center, Nashville, Tennessee.
Summary
A new biomarker approach improves diagnosis of indeterminate pulmonary nodules (IPN) in fungal disease regions. Combining fungal and imaging biomarkers enhances accuracy and speeds up diagnosis for lung cancer.
Area of Science:
- Pulmonology
- Radiology
- Infectious Disease
Background:
- Indeterminate pulmonary nodules (IPN) pose diagnostic challenges, particularly in areas with high rates of fungal disease and smoking.
- Accurate diagnosis is crucial for timely lung cancer detection and management.
Purpose of the Study:
- To evaluate a combined fungal and imaging biomarker approach for diagnosing IPNs.
- To compare this approach against the validated Mayo prediction model for ruling out benign disease and diagnosing lung cancer.
Main Methods:
- Adults aged 40-90 with 6-30 mm IPNs were enrolled across four sites.
- Serum samples were tested for histoplasmosis antibodies (IgG, IgM), and a CT-based radiomic risk score was calculated.
- Multivariable logistic regression models incorporated Mayo score, radiomics score, and histoplasmosis serology.
Main Results:
- The combined biomarker model showed improved diagnostic accuracy (AUC, 0.84) compared to the Mayo score (AUC, 0.73) when endemic histoplasmosis was considered.
- The model demonstrated significant reclassification of malignant nodules (cNRI of 0.18).
Conclusions:
- Fungal and imaging biomarkers can enhance diagnostic accuracy and reclassification of IPNs.
- Endemic histoplasmosis prevalence significantly impacts the performance of disease-specific biomarker models.
