Lung Cancer
Conditions
Keywords
lung cancer screening, nodule, multiparametric lung MRI, low-dose chest CT, artificial intelligence
Brief summary
Lung cancer screening trials using low-dose chest CT scans have shown a significant reduction of cancer related mortality in subjects at high risk of lung cancer. However, high rate of false positives and overdiagnosis have led to invasive methods, which are not without risks. Evaluation of lung nodules using lung MRI with ultra short echo time sequences (UTE) has been found comparable to chest CT scans. Moreover, MRI has the advantage of multiparametric characterization of lesions using different tissue contrasts. Following the recommendation of the French National Authority for Health (HAS) to evaluate new methods of lung cancer screening, this prospective single center pilot study is designed to evaluate the performance of multiparametric lung MRI combined to synthetic CT in the diagnosis of lung cancer in heavily smokers or ex-smokers professionally exposed to carcinogens
Detailed description
Lung cancer is the leading cause of cancer-related deaths worldwide. In France, its incidence was estimated at 46,300 in 2018. In most cases, the diagnosis is initially made by the detection of a nodule or mass on chest X-ray or CT scan. Thus, most often non-invasive follow-up by chest CT scans is recommended. More expensive and invasive methods may also be proposed. However, patients with benign nodules may undergo diagnostic methods that are not without risks (exposure to ionizing radiation, complications related to trans-thoracic or surgical biopsy, etc.). Lung Cancer Screening Trials (NLST, NELSON) have shown that lung cancer related mortality is reduced in subjects with high risk of lung cancer screened by using low-dose chest CT. Nevertheless, published systematic reviews and meta-analyses report a number of side effects of screening related to false positives and over diagnosis. In addition, the assessment of the risks related to the cumulative dose of exposure to ionising radiation during successive rounds of screening remains unknown. Consequently, the French National Authority for Health (HAS) recommends that pilot programs to be conducted to evaluate the different modalities for the organization of a national lung cancer screening program. The spatial resolution of magnetic resonance imaging (MRI) of the lung has been significantly improved in the last decade, thanks to the development of ultra-short echo time (UTE) sequences. The advantage of MRI, in addition of being a free-radiation imaging technique, lies in its multiparametric nature with T1-weighted, T2-weighted and diffusion-weighted imaging providing images of different contrasts allowing the characterization of lesions. However, the follow-up of lung nodules, especially with the calculation of the volume doubling time (VDT) on UTE MRI, has not been evaluated. In addition, the performance of multiparametric MRI combining T2 signal, apparent diffusion coefficient (ADC) and nodule volume in determining nodule malignancy remains to be assessed. Recently, the development of artificial intelligence (AI) techniques with generative adversarial networks (GANs) has made it possible to generate CT-like imaging from MRI images. A very recent work demonstrated that AI model is able to generate from UTE lung MRI images, a high resolution synthetic CT image with a very similar texture to the standard CT and better quality than UTE alone. Therefore, the present sudy hypothesis is that multiparametric MRI combined with synthetic CT could have a complementary role with low-dose CT in lung cancer screening to reduce the false positive rate and to perform a free-radiation follow-up of lung nodules
Interventions
DEVICEmultiparametric MRI
An MRI scan will be performed within 2 weeks of the discovery of a solid lung nodule ≥ 5mm on the screening scan. When a follow-up scan is indicated, an MRI will be repeated on the same day as the follow-up scan. The MRI sequences that will be performed are: SpiraleVibe UTE, T1map, T2 map and Diffusion. A synthetic scanner image will be generated from the UTE morphological MRI image using a generative artificial intelligence (GAN) model.
Sponsors
University Hospital, Bordeaux
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DIAGNOSTIC
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
55 Years to 74 Years
Healthy volunteers
No
Inclusion criteria
* Subject aged between 55 and 74 years * High risk of developing lung cancer: by a combination of exposure to lung carcinogens and smoking (exposure to tobacco at the rate of 30 packs/year or cessation \< 15 years) * Presence of at least one lung solid nodule ≥ 5mm on the initial scan. * Subject able and willing to complete all scheduled visits and assessments. * Subject with health insurance. * Signed informed consent.
Exclusion criteria
* Subject with signs of lung cancer * Subject with history of lung cancer * Presence of severe life-threatening comorbidities at 6 months (recent CVA, recent discovery of advanced stage cancer) * Subject who had already undergone a chest scan less than a year previously * No exposure to occupational lung carcinogens according to the predefined criteria. * No exposure to tobacco or insufficient exposure to tobacco or cessation \> 15 years. * Contra-indication to MRI (Pace maker, implants, claustrophobia…) * Pregnant or breastfeeding woman * Poor understanding of French * Subject under legal protection
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Positivity threshold | Baseline, Month 3, Month 12 | Positivity threshold of the combined score to obtain a specificity of at least 90%, and diagnostic performance parameters associated with this threshold (sensitivity, positive and negative predictive values). |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Area under the ROC curve | Baseline, Month 3, Month 12 | Area under the ROC curve (AUROC) of each of the radiological parameters (nodule volume in mm3 measured on UTE images, nodule mean T1/T2 signal in msec and mean of nodule ADC in mm2/s) and of the combined multiparametric MRI score (i.e., volume and signal) in predicting nodule progression (benign vs. malignant) Area under the ROC curve (AUROC) of each of the radiological parameters (nodule volume in mm3 measured on UTE images, nodule mean T1/T2 signal in msec and mean of nodule ADC in mm2/s) and of the combined multiparametric MRI score (i.e., volume and signal) in predicting nodule progression (benign vs. malignant) |
| Intraclass correlation coefficient between CT and synthetic CT | Baseline, Month 3, Month 12 | Intraclass correlation coefficient between measurements performed using standard CT and synthetic CT generated from UTE MRI. |
| multiparametric MRI characteristics | Baseline, Month 3, Month 12 | Description of the multiparametric MRI characteristics of the different histological types of the malignant nodule. |
Countries
France
Contacts
Primary ContactIlyes Benlala, MD
Outcome results
None listed