The Usefulness of Imaging Quantification in Discriminating Non-Calcified Pulmonary Hamartoma From Adenocarcinoma

Abstract

Background: Patients with non-calcified hamartoma were more susceptible to surgery or needle biopsy for the tough discrimination from lung adenocarcinoma. Radiomics have the ability to quantify the lesion features and potentially improve disease diagnosis. Thus, this study aimed to discriminate non-calcified hamartoma from adenocarcinoma by employing imaging quantification and machine learning. Methods: Forty-two patients with non-calcified hamartoma and 49 patients with adenocarcinoma were retrospentation; Manual lesion segmentation, feature quantification (e.g., texture features), and artificial neural network were performed consecutively. Independent t-test was used to conduct the inter-group comparisons of those imaging features. Receiver operating characteristic curve was performed to investigate the discriminating efficacy. Results: Significantly higher contrast, cluster prominence, cluster shade, dissimilarity, energy, and entropy in non-calcified hamartoma were observed compared with lung adenocarcinoma. Texture-grey-level co-occurrence matrix showed a well discrimination between non-calcified hamartoma and adenocarcinoma as the detection sensitivity, specificity, accuracy, and the area under the curve were 87.22% ± 9.07%, 82.64% ± 8.07%, 85.11% ± 5.40%, and 0.942, respectively. Conclusion: Quantifying imaging features is a potentially useful tool for clinical diagnosis. This study demonstrated that non-calcified hamartoma has a heterogeneous distribution of attenuations probably resulting from its complex organizations. Based on this property, imaging quantification could improve discrimination of non-calcified hamartoma from adenocarcinoma.

A CT-Based Radiomic Signature for the Differentiation of Pulmonary Hamartomas from Carcinoid Tumors

“…Radiomics involves using high-dimensional quantitative features extracted from imaging data to non-invasively quantify pathology. Recent studies have shown the potential for the application of radiomics in the oncological field [ 8 , 12 ]. This technique could complement the conventional approaches for analyzing the images and facilitate the process of delivering treatment tailored to individual patients [ 13 ].…”

“…It is possible to extract multiple quantitative features from medical images, including CT and MRI, through the application of high-throughput computing [ 15 ]. These features include the use of intensity, shape, texture, wavelet, and LOG features to build predictive or prognostic non-invasive biomarkers for imaging modalities [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ].…”

“…Differentiating NFT-PHs from PCTs with non-invasive methods remains problematic, and the patients with an NFT-PH may undergo unnecessary surgery or needle biopsy for diagnostic and therapeutic purposes. Although it is quite easy to diagnose these tumors on tissue sections, PHs can be mistaken for adenocarcinoma in fine-needle aspiration biopsy specimens if invaginated epithelium is prominent and/or showing reactive atypia [ 8 , 17 , 18 , 19 , 20 ]. On the other hand, PCTs are usually enhanced on a CT scan after contrast administration, but this radiological finding is not diagnostic.…”

“…Several researchers have previously utilized radiomics models to pathologically differentiate PHs from other pulmonary pathologies. Guan et al differentiated PH from adenocarcinoma and found that the average contrast, cluster prominence, cluster shade, energy, and entropy were considerably higher in PHs in comparison to adenocarcinomas [ 8 ]. Another research group found that the internal structure of malignant lung tumors has greater complexity and inhomogeneity in comparison to lesions that are benign as a result of quantification via radiomics analysis [ 21 ].…”

“…However, PHs can be mistaken for adenocarcinomas on fine-needle aspiration biopsies if the invaginated epithelium is prominent and reactive. As a result, particularly in the cases with no adipose component, or those lacking the characteristic calcification pattern, the diagnosis of PH can be problematic and surgery becomes mandatory to rule out an underlying malignancy [ 8 , 9 ].…”