Value of Shape and Texture Features from 18F-FDG PET/CT to Discriminate between Benign and Malignant Solitary Pulmonary Nodules: An Experimental Evaluation.

Barbara Palumbo,Maria Lina Stazza,Angela Spanu,Francesco Bianconi,Mario Luca Fravolini,Matteo Minestrini,Susanna Nuvoli,Isabella Palumbo,Maria Rondini

doi:10.3390/diagnostics10090696

Barbara Palumbo, Maria Lina Stazza + Show 7 more

Open Access

https://doi.org/10.3390/diagnostics10090696

Copy DOI

Journal: Diagnostics	Publication Date: Sep 15, 2020
Citations: 31	License type: CC BY 4.0

Affiliation: University of Perugia, University of Sassari

Abstract

In this paper, we investigate the role of shape and texture features from F-FDG PET/CT to discriminate between benign and malignant solitary pulmonary nodules. To this end, we retrospectively evaluated cross-sectional data from 111 patients (64 males, 47 females, age = 67.5 ± 11.0) all with histologically confirmed benign () or malignant () solitary pulmonary nodules. Eighteen three-dimensional imaging features, including conventional, texture, and shape features from PET and CT were tested for significant differences (Wilcoxon-Mann-Withney) between the benign and malignant groups. Prediction models based on different feature sets and three classification strategies (Classification Tree, k-Nearest Neighbours, and Naïve Bayes) were also evaluated to assess the potential benefit of shape and texture features compared with conventional imaging features alone. Eight features from CT and 15 from PET were significantly different between the benign and malignant groups. Adding shape and texture features increased the performance of both the CT-based and PET-based prediction models with overall accuracy gain being 3.4–11.2 pp and 2.2–10.2 pp, respectively. In conclusion, we found that shape and texture features from F-FDG PET/CT can lead to a better discrimination between benign and malignant lung nodules by increasing the accuracy of the prediction models by an appreciable margin.

Highlights

A solitary pulmonary nodule (SPN) is usually defined as an “approximately round lesion that is less than 3 cm in diameter and that is completely surrounded by pulmonary parenchyma, without other abnormalities” [1]
We investigated whether shape and texture features from PET/CT could lead to a better discrimination between benign and malignant SPN compared with standard imaging features alone—that is, lesion size, density, and radiotracer uptake
The second-order statistics show that GLCM energy and entropy were, respectively, significantly lower and higher in the malignant group—both results indicating higher heterogeneity of the malignant lesions compared with the benign ones. This is consistent with NGTDM coarseness, which was significantly higher in the benign nodules than in the malignant ones

Summary

Introduction

A solitary pulmonary nodule (SPN) is usually defined as an “approximately round lesion that is less than 3 cm in diameter and that is completely surrounded by pulmonary parenchyma, without other abnormalities” [1]. In the United States, the estimated detection rate (defined as at least one positive CT scan) increased from. Other works have reported estimates about the prevalence and malignancy rate of SPN between 2% and 69% [2,5,6] and between 7% and. Differential diagnosis of SPN includes benign aetiologies, such as pneumonia, fungi infection, tuberculosis, and hamartoma, as well as malignant ones—most commonly primary lung cancer, distant (metastatic) lesions, or lymphoma [7,9]. Assessment of the malignancy risk involves the evaluation of clinical and radiographic variables. Clinical management of patients with SPN is determined on the basis of the risk assessed, and may involve routine CT follow-ups, functional imaging, and/or tissue sampling [7,9,12]

Methods

Results

Discussion

Conclusion