Pulmonary Nodule Characterization, Including Computer Analysis and Quantitative Features

Abstract

Pulmonary nodules are commonly detected in computed tomography (CT) chest screening of a high-risk population. The specific visual or quantitative features on CT or other modalities can be used to characterize the likelihood that a nodule is benign or malignant. Visual features on CT such as size, attenuation, location, morphology, edge characteristics, and other distinctive "signs" can be highly suggestive of a specific diagnosis and, in general, be used to determine the probability that a specific nodule is benign or malignant. Change in size, attenuation, and morphology on serial follow-up CT, or features on other modalities such as nuclear medicine studies or MRI, can also contribute to the characterization of lung nodules. Imaging analytics can objectively and reproducibly quantify nodule features on CT, nuclear medicine, and magnetic resonance imaging. Some quantitative techniques show great promise in helping to differentiate benign from malignant lesions or to stratify the risk of aggressive versus indolent neoplasm. In this article, we (1) summarize the visual characteristics, descriptors, and signs that may be helpful in management of nodules identified on screening CT, (2) discuss current quantitative and multimodality techniques that aid in the differentiation of nodules, and (3) highlight the power, pitfalls, and limitations of these various techniques.

Sensitivity of Thoracic Digital Tomosynthesis (DTS) for the Identification of Lung Nodules

“…They concluded that Bannual spiral CT scanning can detect lung cancer that is curable.^Results from more recent large screening trials such as the National Lung Screening Trial have contributed to our current knowledge on the risk of lung cancer and have proven that there can be a benefit to overall survival in some high-risk populations [4]. Furthermore, these trials have clarified our understanding of the importance of nodule size and other morphological characteristics [5]. The implication is clear: a validated test of high sensitivity, high specificity, low cost, and low radiation dose-a test that is currently lacking-would be potentially useful in clinical practice and management of disease.…”

Using Deep Learning for Classification of Early Lung Nodules on Computed Tomography Images

“…To perform the selection of the nodules according to their diameters, we initially estimated their sizes which were then attached to our database, as the LIDC-IDRC original database did not contain. The size of a nodule was calculated as a simple 2D measure of the greatest diameter, which can be realized in the axial plane along the axis of the longest diameter [Bartholmai et al 2015]. These approximations consisted of calculating the Euclidean distance between the minimum and maximum coordinates in the respective x and y axes of all slices of a nodule.…”

“…2000], a nodule can be as a small nodule when it has a diameter of less than 10mm. However, Bartholmai et al [Bartholmai et al 2015] affirm that tests have already shown that nodules with a diameter less than 5mm are probably benign, even in cases of high-risk patients, which makes it uninteresting to work with nodules predisposed to be benign. So, the threshold chosen for this work was nodules greater equal to 5mm and less than 11mm.…”

Comprehensive targeted super-deep next generation sequencing enhances differential diagnosis of solitary pulmonary nodules

“…Most SPN found in CT scans are benign, even among high-risk populations such as smokers. A few algorithms or prediction models based on nodule features in the CT scan have been developed; however, their accuracy remains unsatisfactory (7). On one hand, timely identification of malignant nodules is crucial because they represent a localized disease and are potentially curable.…”