What is it about?
This study explores how CT scans alone can predict the severity of non-small cell lung cancer (NSCLC) using fractal analysis, a mathematical technique that examines tumor texture patterns. Since PET scans, which assess tumor glucose consumption, are often used but can be costly and less accessible, this research shows that CT-based fractal analysis may offer similar insights into cancer stage and progression. By identifying tumor complexity as a potential marker for prognosis, this approach could help doctors make faster, more cost-effective decisions about treatment, even in settings where advanced imaging like PET scans is unavailable.
Featured Image
Photo by CDC on Unsplash
Why is it important?
This work is unique because it applies fractal analysis, an emerging radiomics technique, to predict lung cancer severity from CT scans—an area that remains largely unexplored. Unlike traditional methods, which rely on visual assessment or variable computational techniques, fractal analysis provides an objective and quantitative way to evaluate tumor complexity and heterogeneity. This is particularly important because changes in tumor texture between stages are often subtle and difficult to detect manually. The study is timely as there is growing interest in AI and computational methods to enhance cancer detection and characterization. While fractal analysis has shown promise in distinguishing benign from malignant lung nodules, its potential for prognosis in NSCLC has not been fully realized. By demonstrating how CT-based fractal features correlate with tumor aggressiveness, this work bridges a gap in lung cancer research and could lead to more accurate, accessible, and cost-effective diagnostic tools—especially in settings where advanced imaging like PET scans is not available. It is particularly relevant to chest radiologists and researchers focused on tumor characterization, radiomics, and computational image analysis.
Perspectives
This research presents a novel approach to lung cancer prognosis by using fractal analysis on standard CT scans to predict disease severity—potentially reducing reliance on costly and less accessible PET scans. The findings indicate that higher fractal dimension (FD) values in CT images are linked to more advanced cancer stages and greater glucose uptake on PET scans, key indicators of tumor aggressiveness. This is important because current methods for evaluating lung cancer progression rely on subjective visual assessments or expensive imaging like PET, which is not always available in all medical settings. By demonstrating that fractal analysis of CT scans alone can serve as a prognostic marker, this research opens the door to more accessible, faster, and cost-effective cancer diagnostics. It could help doctors identify high-risk patients earlier and determine who would benefit most from further PET imaging or aggressive treatment, ultimately improving patient outcomes.
Dr Omar S Al-Kadi
University of Jordan
Read the Original
This page is a summary of: Prediction of FDG-PET stage and uptake for non-small cell lung cancer on non-contrast enhanced CT scans via fractal analysis, Clinical Imaging, September 2020, Elsevier,
DOI: 10.1016/j.clinimag.2020.03.005.
You can read the full text:
Resources
Graphical abstract
Graphical abstract
Preprint
Purpose: To investigate whether the FD of non-small cell lung cancer (NSCLC) on CT predicts tumor stage and uptake on 18F-fluorodeoxyglucose positron emission tomography. Material and Methods: The FD within a tumor region was determined using a box counting algorithm and compared to the lymph node involvement (NI) and metastatic involvement (MI) and overall stage as determined from PET. A Mann-Whitney U test was applied to the extracted FD features for the NI and the MI. Results: The two tests showed good significance with p< 0.05 (pNI= 0.0139, pMI= 0.0194). Also after performing fractal analysis to all cases, it was found that for those who had a CT of stage I or II had a higher likelihood of the NI and/or MI stage being upstaged by PET, Odds Ratio 5.38 (95% CI 0.99 -29.3). For those who are CT stage III or IV had an increased likelihood of the NI and/or MI stage being down staged by PET, Odds Ratio: 7.33 (95% CI 0.48 -111.2). Conclusion: Initial results of this study indicate higher FD in CT images of NSCLC is associated with advanced stage and greater FDG uptake on PET. Measurements of tumor fractal analysis on conventional non-contrast CT examinations could potentially be used as a prognostic marker and/or to select patients for PET.
Article source
Highlights • Fractal analysis can quantify complexity within image texture. • Conventional non-contrast enhanced CT scans are employed. • Fractal dimension (FD) estimated within a tumor region using box counting algorithm • FD values correlate with PET lymph node, metastasis and overall tumor stage. • Fractal analysis could potentially be used as a prognostic marker and/or to select patients for PET.
Contributors
The following have contributed to this page
