Dataset Information

Quantification of Cystic Fibrosis Lung Disease with Radiomics-based CT Scores.

ABSTRACT:

Purpose

To develop radiomics-based CT scores for assessing lung disease severity and exacerbation risk in adult patients with cystic fibrosis (CF).

Materials and methods

This two-center retrospective observational study was approved by an institutional ethics committee, and the need for patient consent was waived. A total of 215 outpatients with CF referred for unenhanced follow-up chest CT were evaluated in two different centers between January 2013 and December 2016. After lung segmentation, chest CT scans from center 1 (training cohort, 162 patients [median age, 29 years; interquartile range {IQR}, 24-36 years; 84 men]) were used to build CT scores from 38 extracted CT features, using five different machine learning techniques trained to predict a clinical prognostic score, the Nkam score. The correlations between the developed CT scores, two different clinical prognostic scores (Liou and CF-ABLE), forced expiratory volume in 1 second (FEV₁), and risk of respiratory exacerbations were evaluated in the test cohort (center 2, 53 patients [median age, 27 years; IQR, 22-35 years; 34 men]) using the Spearman rank coefficient.

Results

In the test cohort, all radiomics-based CT scores showed moderate to strong correlation with the Nkam score (R = 0.57 to 0.63, P < .001) and Liou scores (R = -0.55 to -0.65, P < .001), whereas the correlation with CF-ABLE score was weaker (R = 0.28 to 0.38, P = .005 to .048). The developed CT scores showed strong correlation with predicted FEV₁ (R = -0.62 to -0.66, P < .001) and weak to moderate correlation with the number of pulmonary exacerbations to occur in the 12 months after the CT examination (R = 0.38 to 0.55, P < .001 to P = .006).

Conclusion

Radiomics can be used to build automated CT scores that correlate to clinical severity and exacerbation risk in adult patients with CF.Supplemental material is available for this article.See also the commentary by Elicker and Sohn in this issue.© RSNA, 2020.

SUBMITTER: Chassagnon G

PROVIDER: S-EPMC7977785 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Computed tomography (CT) of the lungs is the gold standard for assessing the extent of structural changes in the lungs. Spirometry-controlled chest CT (SCCCT) has improved the usefulness of CT by standardising inspiratory and expiratory lung volumes during imaging. This was a single-centre cross-sectional study in children with cystic fibrosis (CF). Using SCCCT we wished to investigate the association between the quantity and extent of structural lung changes and pulmonary function outcomes, and prevalence of known CF lung pathogens. Methods: CT images were analysed by CF-CT scoring (expressed as % of maximum score) to quantify different aspects of structural lung changes including bronchiectasis, airway wall thickening, mucus plugging, opacities, cysts, bullae and gas trapping. Clinical markers consisted of outcomes from pulmonary function tests, microbiological cultures from sputum and serological samples reflecting anti-bacterial and anti-fungal antibodies. Results: Sixty-four children with CF, median age (range) of 12.7 (6.4-18.1) years, participated in the study. The median (range) CF-CT total score in all children was 9.3% (0.4-46.8) with gas trapping of 40.7% (3.7-100) as the most abundant finding. Significantly higher median CF-CT total scores (21.9%) were found in patients with chronic infections (N = 12) including Gram-negative infection and allergic bronchopulmonary aspergillosis (ABPA) exhibiting CF-CT total scores of 14.2% (ns) and 24.0% (p < 0.01), respectively, compared to 8.0% in patients with no chronic lung infection. Lung clearance index (LCI) derived from multiple breath washout exhibited closest association with total CF-CT scores, compared to other pulmonary function outcomes. Conclusions: The most prominent structural lung change was gas trapping, while CF-CT total scores were generally low, both showing close association with LCI. Chronic lung infections, specifically in the form of ABPA, were associated with increased scores in lung changes. Further investigation of impact of infections with different microorganisms on extent and progression of structural CF lung disease is needed.

Project description:Variability in pulmonary disease severity is found in patients with cystic fibrosis (CF) who have identical mutations in the CF transmembrane conductance regulator (CFTR) gene. We hypothesized that one factor accounting for heterogeneity in pulmonary disease severity is variation in the family of genes affecting the biology of interleukin-1 (IL-1), which impacts acquisition and maintenance of Pseudomonas aeruginosa infection in animal models of chronic infection.We genotyped 58 single nucleotide polymorphisms (SNPs) in the IL-1 gene cluster in 808 CF subjects from the University of North Carolina and Case Western Reserve University (UNC/CWRU) joint cohort. All were homozygous for DeltaF508, and categories of "severe" (cases) or "mild" (control subjects) lung disease were defined by the lowest or highest quartile of forced expired volume (FEV(1)) for age in the CF population. After adjustment for age and gender, genotypic data were tested for association with lung disease severity. Odds ratios (ORs) comparing severe versus mild CF were also calculated for each genotype (with the homozygote major allele as the reference group) for all 58 SNPs. From these analyses, nine SNPs with a moderate effect size, OR < or =0.5 or >1.5, were selected for further testing. To replicate the case-control study results, we genotyped the same nine SNPs in a second population of CF parent-offspring trios (recruited from Children's Hospital Boston), in which the offspring had similar pulmonary phenotypes. For the trio analysis, both family-based and population-based associations were performed.SNPs rs1143634 and rs1143639 in the IL1B gene demonstrated a consistent association with lung disease severity categories (P < 0.10) and longitudinal analysis of lung disease severity (P < 0.10) in CF in both the case-control and family-based studies. In females, there was a consistent association (false discovery rate adjusted joint P-value <0.06 for both SNPs) in both the analysis of lung disease severity in the UNC/CWRU cohort and the family-based analysis of affection status.Our findings suggest that IL1beta is a clinically relevant modulator of CF lung disease.

Project description:PurposeThis study aimed to develop and verify a multi-phase (MP) computed tomography (CT)-based radiomics nomogram to differentiate pancreatic serous cystic neoplasms (SCNs) from mucinous cystic neoplasms (MCNs), and to compare the diagnostic efficacy of radiomics models for different phases of CT scans.Materials and methodsA total of 170 patients who underwent surgical resection between January 2011 and December 2018, with pathologically confirmed pancreatic cystic neoplasms (SCN=115, MCN=55) were included in this single-center retrospective study. Radiomics features were extracted from plain scan (PS), arterial phase (AP), and venous phase (VP) CT scans. Algorithms were performed to identify the optimal features to build a radiomics signature (Radscore) for each phase. All features from these three phases were analyzed to develop the MP-Radscore. A combined model comprised the MP-Radscore and imaging features from which a nomogram was developed. The accuracy of the nomogram was evaluated using receiver operating characteristic (ROC) curves, calibration tests, and decision curve analysis.ResultsFor each scan phase, 1218 features were extracted, and the optimal ones were selected to construct the PS-Radscore (11 features), AP-Radscore (11 features), and VP-Radscore (12 features). The MP-Radscore (14 features) achieved better performance based on ROC curve analysis than any single phase did [area under the curve (AUC), training cohort: MP-Radscore 0.89, PS-Radscore 0.78, AP-Radscore 0.83, VP-Radscore 0.85; validation cohort: MP-Radscore 0.88, PS-Radscore 0.77, AP-Radscore 0.83, VP-Radscore 0.84]. The combination nomogram performance was excellent, surpassing those of all other nomograms in both the training cohort (AUC, 0.91) and validation cohort (AUC, 0.90). The nomogram also performed well in the calibration and decision curve analyses.ConclusionsRadiomics for arterial and venous single-phase models outperformed the plain scan model. The combination nomogram that incorporated the MP-Radscore, tumor location, and cystic number had the best discriminatory performance and showed excellent accuracy for differentiating SCN from MCN.