Advances in Imaging and Automated Quantification of Malignant Pulmonary Diseases: A State-of-the-Art Review

Abstract

Quantitative imaging in lung cancer is a rapidly evolving modality in radiology that is changing clinical practice from a qualitative analysis of imaging features to a more dynamic, spatial, and phenotypical characterization of suspected lesions. Some quantitative parameters, such as the use of 18F-FDG PET/CT-derived standard uptake values (SUV), have already been incorporated into current practice as it provides important information for diagnosis, staging, and treatment response of patients with lung cancer. A growing body of evidence is emerging to support the use of quantitative parameters from other modalities. CT-derived volumetric assessment, CT and MRI lung perfusion scans, and diffusion-weighted MRI are some of the examples. Software-assisted technologies are the future of quantitative analyses in order to decrease intra-and inter-observer variability. In the era of "big data", widespread incorporation of radiomics (extracting quantitative information from medical images by converting them into minable high-dimensional data) will allow medical imaging to surpass its current status quo and provide more accurate histological correlations and prognostic value in lung cancer. This is a comprehensive review of some of the quantitative image methods and computer-aided systems to the diagnosis and followup of patients with lung cancer.

Using neighborhood gray tone difference matrix texture features on dual time point PET/CT images to differentiate malignant from benign FDG-avid solitary pulmonary nodules

“…18 F-FDG PET/CT has been widely used for SPN diagnosis. However, the specificity of FDG PET/CT is lower in granuloma-endemic regions than in nonendemic regions [5, 6]. Some benign lesions, such as tuberculosis and granuloma, also have increased 18 F-FDG uptake in PET, leading to false-positive results.…”

“…These infectious diseases also exhibit high uptake of FDG, especially tuberculosis [4]. This causes the specificity of PET/CT in granuloma-endemic regions to be much lower than that of nonendemic regions [5, 6]. To enhance the diagnostic accuracy of FDG PET/CT, some researchers suggest using dual time point imaging (DTPI) PET/CT [7].…”

Classification and Imaging Findings of Lung Neoplasms

“…81 The field is rapidly growing in evidences, particularly in lung cancer, because of the development of genotype-directed therapy for NSCLC. 82,83 The correlation of gene expression and imaging can be performed either using quantitative computer-derived imaging features (eg, edge sharpness) or semantic terms (eg, lobulated margins). Gevaert et al demonstrated that both computer-derived features and semantic terms are associated with the expression of specific gene clusters.…”

Expiratory CT scanning in COVID-19 patients: can we add useful data?

“…(13) A TC quantitativa tem sido utilizada para predizer desfechos clínicos de diversas doenças pulmonares, e a porcentagem de AA tem sido utilizada como uma das ferramentas quantitativas da TC na avaliação da asma, DPOC e doenças pulmonares intersticiais. (14)(15)(16)(17) Com relação à COVID-19, poucos artigos avaliaram os achados quantitativos da TC como marcadores de progressão e prognóstico da doença. Descobriu-se que porcentagens crescentes de consolidação e OVF na TC de tórax estimam o risco de deterioração clínica ou morte em pacientes com pneumonia por COVID-19.…”