Quantitative vessel tortuosity: A potential CT imaging biomarker for distinguishing lung granulomas from adenocarcinomas.
Ontology highlight
ABSTRACT:
SUBMITTER: Alilou M
PROVIDER: S-EPMC6191462 | biostudies-literature | 2018 Oct
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Purpose To evaluate ability of radiomic (computer-extracted imaging) features to distinguish non-small cell lung cancer adenocarcinomas from granulomas at noncontrast CT. Materials and Methods For this retrospective study, screening or standard diagnostic noncontrast CT images were collected for 290 patients (mean age, 68 years; range, 18-92 years; 125 men [mean age, 67 years; range, 18-90 years] and 165 women [mean age, 68 years; range, 33-92 years]) from two institutions between 2007 and 2013. Histopathologic analysis was available for one nodule per patient. Corresponding nodule of interest was identified on axial CT images by a radiologist with manual annotation. Nodule shape, wavelet (Gabor), and texture-based (Haralick and Laws energy) features were extracted from intra- and perinodular regions. Features were pruned to train machine learning classifiers with 145 patients. In a test set of 145 patients, classifier results were compared against a convolutional neural network (CNN) and diagnostic readings of two radiologists. Results Support vector machine classifier with intranodular radiomic features achieved an area under the receiver operating characteristic curve (AUC) of 0.75 on the test set. Combining radiomics of intranodular with perinodular regions improved the AUC to 0.80. On the same test set, CNN resulted in an AUC of 0.76. Radiologist readers achieved AUCs of 0.61 and 0.60, respectively. Conclusion Radiomic features from intranodular and perinodular regions of nodules can distinguish non-small cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Nishino in this issue.
| S-EPMC6394783 | biostudies-literature
Project description:ObjectiveThe most common histopathologic malignant and benign nodules are Adenocarcinoma and Granuloma, respectively, which have different standards of care. In this paper, we propose an automatic framework for the diagnosis of the Adenocarcinomas and the Granulomas in the CT scans of the chest from a private dataset. We use the radiomic features of the nodules and the attached vessel tortuosity for the diagnosis. The private dataset includes 22 CTs for each nodule type, i.e., adenocarcinoma and granuloma. The dataset contains the CTs of the non-smoker patients who are between 30 and 60 years old. To automatically segment the delineated nodule area and the attached vessels area, we apply a morphological-based approach. For distinguishing the malignancy of the segmented nodule, two texture features of the nodule, the curvature Mean and the number of the attached vessels are extracted.ResultsWe compare our framework with the state-of-the-art feature selection methods for differentiating Adenocarcinomas from Granulomas. These methods employ only the shape features of the nodule, the texture features of the nodule, or the torsion features of the attached vessels along with the radiomic features of the nodule. The accuracy of our framework is improved by considering the four selected features.
| S-EPMC7942003 | biostudies-literature
Project description:The diagnosis of primary lung adenocarcinomas with intestinal or mucinous differentiation (PAIM) remains challenging due to the overlapping histomorphological, immunohistochemical and genetic characteristics with lung metastatic colorectal cancer (lmCRC). This study aimed to explore the protein biomarkers that could distinguish between PAIM and lmCRC. To uncover differences between the two diseases, we used tandem mass tagging (TMT)-based shotgun proteomics to characterize proteomes of formalin-fixed paraffin-embedded (FFPE) tumor samples of PAIM (n = 22) and lmCRC (n = 17). Then three machine learning algorithms, namely support vector machine (SVM), random forest and the Least Absolute Shrinkage and Selection Operator (LASSO), were utilized to select protein features with diagnostic significance. These candidate proteins were further validated in an independent cohort (PAIM, n = 11; lmCRC, n = 19) by immunochemistry (IHC) to confirm their diagnostic performance. In total, 105 proteins out of 7871 proteins were significantly dysregulated between PAIM and lmCRC samples and well-separated two groups by Uniform Manifold Approximation and Projection (UMAP). The upregulated proteins in PAIM were involved in actin cytoskeleton organization, platelet degranulation, and regulation of leukocyte chemotaxis, while downregulated ones were involved in mitochondrial transmembrane transport, vasculature development, and stem cell proliferation. A set of 10 candidate proteins (high-level expression in lmCRC: CDH17, ATP1B3, GLB1, OXNAD1, LYST, FABP1; high-level expression in PAIM: NARR, MLPH, S100A14, CK7) was ultimately selected to distinguish PAIM from lmCRC by machine learning algorithms. We further confirmed using IHC that the five protein biomarkers including CDH17, CK7, MLPH, FABP1 and NARR were effective biomarkers for distinguishing PAIM from lmCRC. Our study depicts PAIM-specific proteomic characteristics and demonstrates the potential utility of new protein biomarkers for the differential diagnosis of PAIM and lmCRC. These findings may contribute to improving the diagnostic accuracy and guide appropriate treatments for these patients.
2024-06-23 | PXD050416 | Pride
Project description:Using unsupervised machine learning applied to computed tomography-based imaging characteristics we have found three distinct phenotypes of lung disease in two large cohorts of ever-smokers and have identified their molecular correlates.
2020-12-07 | GSE132829 | GEO
Project description:Iodine material images (aka iodine basis images) generated from dual energy computed tomography (DECT) have been used to assess potential perfusion defects in the pulmonary parenchyma. However, iodine material images do not provide the needed absolute quantification of the pulmonary blood pool, as materials with effective atomic numbers (Zeff ) different from those of basis materials may also contribute to iodine material images, thus confounding the quantification of perfusion defects. (i) To demonstrate the limitations of iodine material images in pulmonary perfusion defect quantification and (ii) to develop and validate a new quantitative biomarker using effective atomic numbers derived from DECT images. The quantitative relationship between the perfusion blood volume (PBV) in pulmonary parenchyma and the effective atomic number (Zeff ) spatial distribution was studied to show that the desired quantitative PBV maps are determined by the spatial maps of Zeff as PBVZeff(x)=aZeffβ(x)+b , where a, b, and β are three constants. Namely, quantitative PBVZeff is determined by Zeff images instead of the iodine basis images. Perfusion maps were generated for four human subjects to demonstrate the differences between conventional iodine material image-based PBV (PBViodine ) derived from two-material decompositions and the proposed PBVZeff method. Among patients with pulmonary emboli, the proposed PBVZeff maps clearly show the perfusion defects while the PBViodine maps do not. Additionally, when there are no perfusion defects present in the derived PBV maps, no pulmonary emboli were diagnosed by an experienced thoracic radiologist. Effective atomic number-based quantitative PBV maps provide the needed sensitive and specific biomarker to quantify pulmonary perfusion defects.
| S-EPMC8595877 | biostudies-literature
Project description:BACKGROUND:More than 80,000 people undergo resection of a pulmonary tumor each year, and the only method to determine if the tumor is malignant is histologic analysis. We propose that a targeted molecular contrast agent could bind lung adenocarcinomas, which could be identified using real-time optical imaging at the time of surgery. METHODS:Fifty patients with a biopsy-proven lung adenocarcinoma were enrolled. Before surgery, patients were systemically administered 0.1 mg/kg of a fluorescent folate receptor alpha (FR?)-targeted molecular contrast agent by intravenous infusion. During surgery, tumors were imaged in situ and ex vivo, after the lung parenchyma was dissected to directly expose the tumor to the imaging system. RESULTS:Tumors ranged from 0.3 to 7.5 cm (mean: 2.6 cm), and 46 of 50 (92%) lung adenocarcinomas were fluorescent. No false uptake occurred, and in 2 cases, intraoperative imaging revealed tumor metastases (3 mm and 6 mm) that were not recognized preoperatively. Four adenocarcinomas were not fluorescent, and immunohistochemistry showed that these adenocarcinomas did not express FR?. Tumor fluorescence was independent of nodule size, uptake of 2-deoxy-2-((18)F)fluoro-D-glucose, histology, and tumor differentiation. Molecular imaging could identify only 7 of the 50 adenocarcinomas in situ in the patient without bisection. The most important predictor of the success of molecular imaging in locating the tumor in situ was the distance of the nodule from the pleural surface. CONCLUSIONS:Intraoperative molecular imaging with a targeted contrast agent can identify lung adenocarcinomas, and this technology is currently useful in patients with subpleural tumors, irrespective of size. With further refinements, this tool may prove useful in locating adenocarcinomas that are deeper in the lung parenchyma, in lymph nodes, and at pleural and resection margins.
| S-EPMC4828933 | biostudies-literature
Project description:Background and objectiveThis study aimed to investigate whether quantitative lung vessel morphology determined by a new fully automated algorithm is associated with functional indices in idiopathic pulmonary fibrosis (IPF).MethodsA total of 152 IPF patients had vessel volume, density, tortuosity and heterogeneity quantified from computed tomography (CT) images by a fully automated algorithm. Separate quantitation of vessel metrics in pulmonary arteries and veins was performed in 106 patients. Results were evaluated against readouts from lung function tests.ResultsNormalized vessel volume expressed as a percentage of total lung volume was moderately correlated with functional indices on univariable linear regression analysis: forced vital capacity (R2 = 0.27, P < 1 × 10-6 ), diffusion capacity for carbon monoxide (DLCO ; R2 = 0.12, P = 3 × 10-5 ), total lung capacity (TLC; R2 = 0.45, P < 1 × 10-6 ) and composite physiologic index (CPI; R2 = 0.28, P < 1 × 10-6 ). Normalized vessel volume was correlated with vessel density but not with vessel heterogeneity. Quantitatively derived vessel metrics (and artery and vein subdivision scores) were not significantly linked with the transfer factor for carbon monoxide (KCO ), and only weakly with DLCO . On multivariable linear regression analysis, normalized vessel volume and vessel heterogeneity were independently linked with DLCO , TLC and CPI indicating that they capture different aspects of lung damage. Artery-vein separation provided no additional information beyond that captured in the whole vasculature.ConclusionOur study confirms previous observations of links between vessel volume and functional measures of disease severity in IPF using a new vessel quantitation tool. Additionally, the new tool shows independent linkages of normalized vessel volume and vessel heterogeneity with functional indices. Quantitative vessel metrics do not appear to reflect vasculopathic damage in IPF.
| S-EPMC6519024 | biostudies-literature
Project description:BackgroundWe aimed to assess if quantitative radiomic features can predict programmed death ligand 1 (PD-L1) expression in advanced stage lung adenocarcinoma.MethodsThis retrospective study included 153 patients who had advanced stage (>IIIA by TNM classification) lung adenocarcinoma with pretreatment thin section computed tomography (CT) images and PD-L1 expression test results in their pathology reports. Clinicopathological data were collected from electronic medical records. Visual analysis and radiomic feature extraction of the tumor from pretreatment CT were performed. We constructed two models for multivariate logistic regression analysis (one based on clinical variables, and the other based on a combination of clinical variables and radiomic features), and compared c-statistics of the receiver operating characteristic curves of each model to identify the model with the higher predictability.ResultsAmong 153 patients, 53 patients were classified as PD-L1 positive and 100 patients as PD-L1 negative. There was no significant difference in clinical characteristics or imaging findings on visual analysis between the two groups (P > 0.05 for all). Rad-score by radiomic analysis was higher in the PD-L1 positive group than in the PD-L1 negative group with a statistical significance (-0.378 ± 1.537 vs. -1.171 ± 0.822, P = 0.0008). A prediction model that uses clinical variables and CT radiomic features showed higher performance compared to a prediction model that uses clinical variables only (c-statistic = 0.646 vs. 0.550, P = 0.0299).ConclusionsQuantitative CT radiomic features can predict PD-L1 expression in advanced stage lung adenocarcinoma. A prediction model composed of clinical variables and CT radiomic features may facilitate noninvasive assessment of PD-L1 expression.Key pointsSignificant findings of the study Quantitative CT radiomic features can help predict PD-L1 expression, whereas none of the qualitative imaging findings is associated with PD-L1 positivity. What this study adds A prediction model composed of clinical variables and CT radiomic features may facilitate noninvasive assessment of PD-L1 expression.
| S-EPMC7113038 | biostudies-literature
Project description:BackgroundChronic tobacco smoke exposure results in a broad range of lung pathologies including emphysema, airway disease and parenchymal fibrosis as well as a multitude of extra-pulmonary comorbidities. Prior work using CT imaging has identified several clinically relevant subgroups of smoking related lung disease, but these investigations have generally lacked organ specific molecular correlates.Research questionCan CT imaging be used to identify clinical phenotypes of smoking related lung disease that have specific bronchial epithelial gene expression patterns to better understand disease pathogenesis?Study design and methodsUsing K-means clustering, we clustered participants from the COPDGene study (n = 5,273) based on CT imaging characteristics and then evaluated their clinical phenotypes. These clusters were replicated in the Detection of Early Lung Cancer Among Military Personnel (DECAMP) cohort (n = 360), and were further characterized using bronchial epithelial gene expression.ResultsThree clusters (preserved, interstitial predominant and emphysema predominant) were identified. Compared to the preserved cluster, the interstitial and emphysema clusters had worse lung function, exercise capacity and quality of life. In longitudinal follow-up, individuals from the emphysema group had greater declines in exercise capacity and lung function, more emphysema, more exacerbations, and higher mortality. Similarly, genes involved in inflammatory pathways (tumor necrosis factor-α, interferon-β) are more highly expressed in bronchial epithelial cells from individuals in the emphysema cluster, while genes associated with T-cell related biology are decreased in these samples. Samples from individuals in the interstitial cluster generally had intermediate levels of expression of these genes.InterpretationUsing quantitative CT imaging, we identified three groups of individuals in older ever-smokers that replicate in two cohorts. Airway gene expression differences between the three groups suggests increased levels of inflammation in the most severe clinical phenotype, possibly mediated by the tumor necrosis factor-α and interferon-β pathways.Clinical trial registrationCOPDGene (NCT00608764), DECAMP-1 (NCT01785342), DECAMP-2 (NCT02504697).
| S-EPMC8039011 | biostudies-literature
Project description:PURPOSE:To determine if clinical and CT characteristics of surgically resected lung adenocarcinomas can distinguish those harboring ALK rearrangements from EGFR mutations. MATERIALS AND METHODS:Patients who had surgical resection and histologically confirmed lung adenocarcinoma were enrolled, including 41 patients with ALK rearrangements and 66 patients with EGFR mutations. Eighteen categorical and six quantitative CT characteristics were used to evaluate the tumors. Differences in clinical and CT characteristics between the two groups were investigated. RESULTS:Age (P=0.003), histological subtypes (P<0.001), pathological stage (P=0.007), and five CT characteristics, including size (P<0.001), GGO (P=0.001), bubble-like lucency (P=0.048), lymphadenopathy (P=0.001), and tumor shadow disappearance rate (P=0.005) were significantly different between patients harboring ALK rearrangements compared to patients with EGFR mutations. When we compared histologic components, a solid pattern was more common (P=0.009) in tumors with ALK rearrangements, and lepidic and acinar patterns were more common (P<0.001 and P=0.040, respectively) in those with EGFR mutations. Backward elimination analyses revealed that age (OR=0.93; 95% CI 0.89-0.98), GGO (OR=0.14; 95% CI 0.03-0.67), and lymphadenopathy (OR=4.15; 95% CI 1.49-11.60) were significantly associated with ALK rearrangement status. CONCLUSION:Our analyses revealed that clinical and CT characteristics of lung adenocarcinomas harboring ALK rearrangements were significantly different, compared with those with EGFR mutations. These differences may be related to the molecular pathology of these diseases.
| S-EPMC5123695 | biostudies-literature