scholarly journals Feasibility of lung cancer prediction from low-dose CT scan and smoking factors using causal models

Thorax ◽  
2019 ◽  
Vol 74 (7) ◽  
pp. 643-649 ◽  
Author(s):  
Vineet K Raghu ◽  
Wei Zhao ◽  
Jiantao Pu ◽  
Joseph K Leader ◽  
Renwei Wang ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Graphical Models ◽  
Low Dose ◽  
Predictive Accuracy ◽  
Lung Cancer Screening ◽  
Study Cohort ◽  
Low Dose Ct ◽  
Lung Cancer Diagnosis ◽  
Early Lung Cancer ◽  
Benign Nodules

IntroductionLow-dose CT (LDCT) is currently used in lung cancer screening of high-risk populations for early lung cancer diagnosis. However, 96% of individuals with detected nodules are false positives.MethodsIn order to develop an efficient early lung cancer predictor from clinical, demographic and LDCT features, we studied a total of 218 subjects with lung cancer or benign nodules. Probabilistic graphical models (PGMs) were used to integrate demographics, clinical data and LDCT features from 92 subjects (training cohort) from the Pittsburgh Lung Screening Study cohort.ResultsLearnt PGMs identified three variables directly (causally) linked to malignant nodules and the largest benign nodule and used them to build the Lung Cancer Causal Model (LCCM), which was validated in a separate cohort of 126 subjects. Nodule and vessel numbers and years since the subject quit smoking were sufficient to discriminate malignant from benign nodules. Comparison with existing predictors in the training and validation cohorts showed that (1) incorporating LDCT scan features greatly enhances predictive accuracy; and (2) LCCM improves cancer detection over existing methods, including the Brock parsimonious model (p<0.001). Notably, the number of surrounding vessels, a feature not previously used in predictive models, significantly improves predictive efficiency. Based on the validation cohort results, LCCM is able to identify 30% of the benign nodules without risk of misclassifying cancer nodules.DiscussionLCCM shows promise as a lung cancer predictor as it is significantly improved over existing models. Validated in a larger, prospective study, it may help reduce unnecessary follow-up visits and procedures.

scholarly journals External validation of radiomics‐based predictive models in low‐dose CT screening for early lung cancer diagnosis

2020 ◽  
Vol 47 (9) ◽  
pp. 4125-4136
Author(s):  
Noemi Garau ◽  
Chiara Paganelli ◽  
Paul Summers ◽  
Wookjin Choi ◽  
Sadegh Alam ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Predictive Models ◽  
Low Dose ◽  
External Validation ◽  
Ct Screening ◽  
Low Dose Ct ◽  
Lung Cancer Diagnosis ◽  
Early Lung Cancer

Overwhelming Support Among Urban Irish COPD Patients for Lung Cancer Screening by Low-Dose CT Scan

Lung ◽  
2012 ◽  
Vol 190 (6) ◽  
pp. 621-628 ◽  
Author(s):  
M. Pallin ◽  
S. Walsh ◽  
M. F. O’Driscoll ◽  
C. Murray ◽  
A. Cahalane ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Ct Scan ◽  
Low Dose ◽  
Lung Cancer Screening ◽  
Low Dose Ct ◽  
Copd Patients

Radiomic Phenotyping of the Lung Parenchyma: Feasibility Study in a Screening Cohort

2021 ◽  
Author(s):  
Babak Haghighi ◽  
Hannah Horng ◽  
Peter B Noël ◽  
Eric Cohen ◽  
Lauren Pantalone ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Low Dose ◽  
Lung Cancer Screening ◽  
Lung Parenchyma ◽  
Ct Scans ◽  
Lung Field ◽  
Reconstruction Algorithms ◽  
Low Dose Ct ◽  
Significant Difference

Abstract Rationale: High-throughput extraction of radiomic features from low-dose CT scans can characterize the heterogeneity of the lung parenchyma and potentially aid in identifying subpopulations that may have higher risk of lung diseases, such as COPD, and lung cancer due to inflammation or obstruction of the airways. We aim to determine the feasibility a lung radiomics phenotyping approach in a lung cancer screening cohort, while quantifying the effect of different CT reconstruction algorithms on phenotype robustness. Methods: We identified low-dose CT scans (n = 308) acquired with Siemens Healthineers scanners from patients who completed low-dose CT within our lung cancer screening program between 2015-2018 and had two different sets of image reconstructions kernel available (i.e., medium (I30f), sharp (I50f)) for the same acquisition. Following segmentation of the lung field, a total of 26 radiomic features were extracted from the entire 3D lung-field using a previously validated fully-automated lattice-based software pipeline, adapted for low-dose CT scans. The features extracted included gray-level histogram, co-occurrence, and run-length descriptors. Each feature was averaged for each scan within a range of lattice window sizes (W) ranging from 4-20mm. The extracted imaging features from both datasets were harmonized to correct for differences in image acquisition parameters. Subsequently, unsupervised hierarchal clustering was applied on the extracted features to identify distinct phenotypic patterns of the lung parenchyma, where consensus clustering was used to identify the optimal number of clusters (K = 2). Differences between? phenotypes for demographic and clinical covariates including sex, age, BMI, pack-years of smoking, Lung-RADS and cancer diagnosis were assessed for each phenotype cluster, and then compared across clusters for the two different CT reconstruction algorithms using the cluster entanglement metric, where a lower entanglement coefficient corresponds to good cluster alignment. Furthermore, an independent set of low-dose CT scans (n = 88) from patients with available pulmonary function data on lung obstruction were analyzed using the identified optimal clusters to assess associations to lung obstruction and validate the lung phenotyping paradigm. Results: Heatmaps generated by radiomic features identified two distinct lung parenchymal phenotype patterns across different feature extraction window sizes, for both reconstruction algorithms (P < 0.05 with K = 2). Associations of radiomic-based clusters with clinical covariates showed significant difference for BMI and pack-years of smoking (P < 0.05) for both reconstruction kernels. Radiomic phenotype patterns where similar across the two reconstructed kernels, specifically when smaller window sizes (W=4 and 8mm) were used for radiomic feature extraction, as deemed by their entanglement coefficient. Validation of clustering approaches using cluster mapping for the independent sample with lung obstruction also showed two statistically significant phenotypes (P < 0.05) with significant difference for BMI and smoking pack-years.ConclusionsRadiomic analysis can be used to characterize lung parenchymal phenotypes from low-dose CT scans, which appear reproducible for different reconstruction kernels. Further work should seek to evaluate the effect of additional CT acquisition parameters and validate these phenotypes in characterizing lung cancer screening populations, to potentially better stratify disease patterns and cancer risk.

scholarly journals Kezdeti tapasztalatok a HUNCHEST – alacsony dózisú CT-tüdőrákszűrési pilotprogrammal

2018 ◽  
Vol 159 (43) ◽  
pp. 1741-1746 ◽  
Author(s):  
Anna Kerpel-Fronius ◽  
Zsuzsanna Monostori ◽  
Diana Solymosi ◽  
Zsolt Markóczy ◽  
Lívia Rojkó ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Low Dose ◽  
Screening Programme ◽  
Lung Cancer Screening ◽  
Lung Cancer Mortality ◽  
Chronic Obstructive ◽  
International Studies ◽  
Obstructive Pulmonary Disease ◽  
Low Dose Ct ◽  
First Results

Abstract: Introduction: Lung cancer is the cause of death of around 8000 Hungarians each year. Aim: International studies have proved that low-dose CT (LDCT) screening lowers the lung cancer mortality of high risk patients. The HUNCHEST pilot study launched in 2014 studies the possibilities of a lung cancer screening programme in Hungary. The study is also aimed at showing whether there is an increased number of detected lung cancer in the subgroup with chronic obstructive pulmonary disease (COPD). Method: COPD and nonCOPD subjects, smokers and non-smokers are screened with low-dose CT in the 50–79 age group. Results and conclusion: The study is still undergoing recruitement, but in the light of the first results, the principles of the screening programme at the National Korányi Institute of Pulmonology are also presented. Orv Hetil. 2018; 159(43): 1741–1746.

Results of second round lung cancer screening by low-dose CT scan - French cohort study (DEP-KP80)

2021 ◽  
Author(s):  
Olivier Leleu ◽  
Damien Basille ◽  
Marianne Auquier ◽  
Caroline Clarot ◽  
Estelle Hoguet ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cohort Study ◽  
Cancer Screening ◽  
Ct Scan ◽  
Low Dose ◽  
Lung Cancer Screening ◽  
Low Dose Ct ◽  
French Cohort

Early detection system using low-dose CT lung cancer screening and related SNP information

2021 ◽  
Author(s):  
Yuta Azuma ◽  
Yoshiki Kawata ◽  
Noboru Niki ◽  
Issei Imoto ◽  
Masahiko Kusumoto ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Early Detection ◽  
Low Dose ◽  
Detection System ◽  
Lung Cancer Screening ◽  
Low Dose Ct
Sign in / Sign up

Export Citation Format

Share Document