Form Factors as Potential Imaging Biomarkers to Differentiate Benign vs. Malignant Lung Lesions on CT Scans

Abstract

Indeterminate lung nodules detected on CT scans are common findings in clinical practice. Their correct assessment is critical, as early diagnosis of malignancy is crucial to maximise the treatment outcome. In this work, we evaluated the role of form factors as imaging biomarkers to differentiate benign vs. malignant lung lesions on CT scans. We tested a total of three conventional imaging features, six form factors, and two shape features for significant differences between benign and malignant lung lesions on CT scans. The study population consisted of 192 lung nodules from two independent datasets, containing 109 (38 benign, 71 malignant) and 83 (42 benign, 41 malignant) lung lesions, respectively. The standard of reference was either histological evaluation or stability on radiological followup. The statistical significance was determined via the Mann-Whitney U nonparametric test, and the ability of the form factors to discriminate a benign vs. a malignant lesion was assessed through multivariate prediction models based on Support Vector Machines. The univariate analysis returned four form factors (Angelidakis compactness and flatness, Kong flatness, and maximum projection sphericity) that were significantly different between the benign and malignant group in both datasets. In particular, we found that the benign lesions were on average flatter than the malignant ones; conversely, the malignant ones were on average more compact (isotropic) than the benign ones. The multivariate prediction models showed that adding form factors to conventional imaging features improved the prediction accuracy by up to 14.5 pp. We conclude that form factors evaluated on lung nodules on CT scans can improve the differential diagnosis between benign and malignant lesions.

Keywords: computed tomography; form factors; lung cancer; radiomics.

Figure 1

Illustration of the lesion delineation process. The top row shows the cropped areas from contiguous axial slices containing the suspicious lesion; the fuchsia overlays in the bottom row indicate the manually-delineated regions of interest. The lesion in the picture was diagnosed as adenocarcinoma in a 76-year-old man.

Figure 2

Adenocarcinoma in a 76-year-old man: lesion on the CT scan (left) and the reconstructed three-dimensional volume within the axis-aligned bounding box (right).

Figure 3

Fibrosis in a 46-year-old man: lesion on the CT scan (left) and the reconstructed three-dimensional volume within the axis-aligned bounding box (right).

Figure 4

Boxplots/stripplots of the features that were significantly different between the benign and malignant tumours in the SSR-1 dataset.

Figure 4

Boxplots/stripplots of the features that were significantly different between the benign and malignant tumours in the SSR-1 dataset.

Figure 5

Boxplots/stripplots of the features that were significantly different between the benign and malignant tumours in the LUNGx dataset.

Figure 5

Boxplots/stripplots of the features that were significantly different between the benign and malignant tumours in the LUNGx dataset.