Low-dose CT for lung cancer screening: position paper from the Italian college of thoracic radiology.

Smoking is the main risk factor for lung cancer (LC), which is the leading cause of cancer-related death worldwide. Independent randomized controlled trials, governmental and inter-governmental task forces, and meta-analyses established that LC screening (LCS) with chest low dose computed tomography (LDCT) decreases the mortality of LC in smokers and former smokers, compared to no-screening, especially in women. Accordingly, several Italian initiatives are offering LCS by LDCT and smoking cessation to about 10,000 high-risk subjects, supported by Private or Public Health Institutions, envisaging a possible population-based screening program. Because LDCT is the backbone of LCS, Italian radiologists with LCS expertise are presenting this position paper that encompasses recommendations for LDCT scan protocol and its reading. Moreover, fundamentals for classification of lung nodules and other findings at LDCT test are detailed along with international guidelines, from the European Society of Thoracic Imaging, the British Thoracic Society, and the American College of Radiology, for their reporting and management in LCS. The Italian College of Thoracic Radiologists produced this document to provide the basics for radiologists who plan to set up or to be involved in LCS, thus fostering homogenous evidence-based approach to the LDCT test over the Italian territory and warrant comparison and analyses throughout National and International practices.

Integrating Biological and Radiological Data in a Structured Repository: a Data Model Applied to the COSMOS Case Study.

Integrating the information coming from biological samples with digital data, such as medical images, has gained prominence with the advent of precision medicine. Research in this field faces an ever-increasing amount of data to manage and, as a consequence, the need to structure these data in a functional and standardized fashion to promote and facilitate cooperation among institutions. Inspired by the Minimum Information About BIobank data Sharing (MIABIS), we propose an extended data model which aims to standardize data collections where both biological and digital samples are involved. In the proposed model, strong emphasis is given to the cause-effect relationships among factors as these are frequently encountered in clinical workflows. To test the data model in a realistic context, we consider the Continuous Observation of SMOking Subjects (COSMOS) dataset as case study, consisting of 10 consecutive years of lung cancer screening and follow-up on more than 5000 subjects. The structure of the COSMOS database, implemented to facilitate the process of data retrieval, is therefore presented along with a description of data that we hope to share in a public repository for lung cancer screening research.

Impact of the COVID-19 pandemic on the selection of chest imaging modalities and reporting systems: a survey of Italian radiologists.

PURPOSE: Chest imaging modalities play a key role for the management of patient with coronavirus disease (COVID-19). Unfortunately, there is no consensus on the optimal chest imaging approach in the evaluation of patients with COVID-19 pneumonia, and radiology departments tend to use different approaches. Thus, the main objective of this survey was to assess how chest imaging modalities have been used during the different phases of the first COVID-19 wave in Italy, and which diagnostic technique and reporting system would have been preferred based on the experience gained during the pandemic. MATERIAL AND METHODS: The questionnaire of the survey consisted of 26 questions. The link to participate in the survey was sent to all members of the Italian Society of Medical and Interventional Radiology (SIRM). RESULTS: The survey gathered responses from 716 SIRM members. The most notable result was that the most used and preferred chest imaging modality to assess/exclude/monitor COVID-19 pneumonia during the different phases of the first COVID-19 wave was computed tomography (51.8% to 77.1% of participants). Additionally, while the narrative report was the most used reporting system (55.6% of respondents), one-third of participants would have preferred to utilize structured reporting systems. CONCLUSION: This survey shows that the participants' responses did not properly align with the imaging guidelines for managing COVID-19 that have been made by several scientific, including SIRM. Therefore, there is a need for continuing education to keep radiologists up to date and aware of the advantages and limitations of the chest imaging modalities and reporting systems.

Inter-observer agreement on the morphology of screening-detected lung cancer: beyond pulmonary nodules and masses.

OBJECTIVES: Pulmonary nodules and masses are the typical presentations of lung cancer. However, a spectrum of focal opacities cannot be defined as either "pulmonary nodule" or "mass," despite representing cancer. We aimed to assess the morphology of screening-detected lung cancers at low-dose computed tomography LDTC and to evaluate inter-observer agreement in their classification. METHODS: Four radiologists with different experiences in thoracic imaging retrospectively reviewed 273 screening-detected lung cancers. Readers were asked to assess if morphology at the time of diagnosis was consistent with the Fleischner Society definition of pulmonary "nodule" or "mass." Cancers not consistent were defined as "non-nodular/non-mass" (NN/NM) and sub-classified as follows: associated with cystic airspaces, stripe-like, scar-like, endobronchial, or not otherwise defined (NOD). Inter-observer agreement was evaluated using Cohen's K statistic among pairs of readers and modified Fleiss' kappa statistic for overall agreement. RESULTS: Two hundred forty-one of the 273 (88%) lesions were defined as pulmonary nodule or mass by complete agreement, while 20/273 (7.3%) were defined as NN/NM. Six (2.2%) of 273 were sub-classified as lesions associated with cystic airspace, six (2.2%) as scar-like, five (1.8%) as endobronchial, and one (0.7%) as NOD by complete agreement. The concordance in defining morphology was excellent (261/273; 96%, 95%CI 92-98%; k 0.85, 95%CI 0.75-0.92) and also in the sub-classification (18/20; 90%, 95%CI 68-99%, k 0.93, 95%CI 0.86-1.00). There was incomplete agreement regarding lesion morphology in 4.4% (12/273) of cases. CONCLUSIONS: A non-negligible percentage of screening-detected lung cancers has a NN/NM appearance at LDCT. The concordance in defining lesion morphology was excellent. The awareness of various presentations can avoid missed or delayed diagnosis. KEY POINTS: • A non-negligible percentage of screening-detected lung cancers have neither nodular nor mass appearance at low-dose CT. • The awareness of various LDCT presentations of lung cancer can avoid missed or delayed diagnosis. • Optimal protocol management in CT screening should take into consideration lung nodules as well as various other focal abnormalities.

Management of incidental pulmonary nodule in CT: a survey by the Italian College of Chest Radiology.

OBJECTIVES: The aim of this study is to present the results of the Italian survey on the management of pulmonary nodules incidentally identified at computed tomography (CT). MATERIALS AND METHODS: An online electronic survey, consisting of 23 multiple-choice questions, was created using the SurveyMonkey web-based tool. The questionnaire was developed by the Board of the Italian College of Chest Radiology of the Italian Society of Medical and Interventional Radiology (SIRM) and by an experienced group of Italian Academic Chest Radiologists. The link to the online electronic survey was submitted by email to all the SIRM members. RESULTS: A total of 767 radiologists, corresponding to 7.5% of all the SIRM members, participated in the online survey. The majority of participants (92%) routinely describe the attenuation of pulmonary nodules in the report, and 84.1% recommend the further follow-up, with 92.7% of respondents taking CT nodule morphological features into consideration. The 57.7% of participants adhere to the Fleischner Society guidelines for the management of incidental pulmonary nodules. However, 56.6% and 75.6% of respondents have a more cautious approach than that recommended by the guidelines and tend to use a shorter follow-up for both solid and ground-glass nodules, respectively. Finally, 94.5% of participants favor congresses and refresher courses dedicated to insights on lung nodule diagnosis and management. CONCLUSIONS: This survey demonstrates that the management of pulmonary nodules incidentally detected on CT is still complex and controversial. The majority of SIRM members express a need for an update on this topic.

Optimization and Standardization of Circulating MicroRNA Detection for Clinical Application: The miR-Test Case.

BACKGROUND: The identification of circulating microRNAs (miRNAs) in the blood has been recently exploited for the development of minimally invasive tests for the early detection of cancer. Nevertheless, the clinical transferability of such tests is uncertain due to still-insufficient standardization and optimization of methods to detect circulating miRNAs in the clinical setting. METHODS: We performed a series of tests to optimize the quantification of serum miRNAs that compose the miR-Test, a signature for lung cancer early detection, and systematically analyzed variables that could affect the performance of the test. We took advantage of a large-scale (>1000 samples) validation study of the miR-Test that we recently published, to evaluate, in clinical samples, the effects of analytical and preanalytical variables on the quantification of circulating miRNAs and the clinical output of the signature (risk score). RESULTS: We developed a streamlined and standardized pipeline for the processing of clinical serum samples that allows the isolation and analysis of circulating miRNAs by quantitative reverse-transcription PCR, with a throughput compatible with screening trials. The major source of analytical variation came from RNA isolation from serum, which could be corrected by use of external (spike-in) or endogenous miRNAs as a reference for normalization. We also introduced standard operating procedures and QC steps to check for unspecific fluctuations that arise from the lack of standardized criteria in the collection or handling of the samples (preanalytical factors). CONCLUSIONS: We propose our methodology as a reference for the development of clinical-grade blood tests on the basis of miRNA detection.

CT Radiogenomic Characterization of EGFR, K-RAS, and ALK Mutations in Non-Small Cell Lung Cancer.

OBJECTIVES: To assess the association between CT features and EGFR, ALK, KRAS mutations in non-small cell lung cancer. METHODS: Patients undergoing chest CT and testing for the above gene mutations were included. Qualitative evaluation of CTs included: lobe; lesion diameter; shape; margins; ground-glass opacity; density; cavitation; air bronchogram; pleural thickening; intratumoral necrosis; nodules in tumour lobe; nodules in non-tumour lobes; pleural retraction; location; calcifications; emphysema; fibrosis; pleural contact; pleural effusion. Statistical analysis was performed to assess association of features with each gene mutation. ROC curves for gene mutations were drawn; the corresponding area under the curve was calculated. P-values <0.05 were considered significant. RESULTS: Of 285 patients, 60/280 (21.43 %) were positive for EGFR mutation; 31/270 (11.48 %) for ALK rearrangement; 64/240 (26.67 %) for KRAS mutation. EGFR mutation was associated with air bronchogram, pleural retraction, females, non-smokers, small lesion size, and absence of fibrosis. ALK rearrangements were associated with age and pleural effusion. KRAS mutation was associated with round shape, nodules in non-tumour lobes, and smoking. CONCLUSIONS: This study disclosed associations between CT features and alterations of EGFR (air bronchogram, pleural retraction, small lesion size, absence of fibrosis), ALK (pleural effusion) and KRAS (round lesion shape, nodules in non-tumour lobes). KEY POINTS: Air bronchogram, pleural retraction, small size relate to EGFR mutation in NSCLC. Pleural effusion and younger age relate to ALK mutation. Round lesion shape, nodules in non-tumour lobes relate to KRAS mutation.

Dietary inflammatory index and risk of lung cancer and other respiratory conditions among heavy smokers in the COSMOS screening study.

PURPOSE: To test whether the inflammatory potential of diet, as measured using the dietary inflammatory index (DII), is associated with risk of lung cancer or other respiratory conditions and to compare results obtained with those based on the aMED score, an established dietary index that measures adherence to the traditional Mediterranean diet. METHODS: In 4336 heavy smokers enrolled in a prospective, non-randomized lung cancer screening program, we measured participants' diets at baseline using a self-administered food frequency questionnaire from which dietary scores were calculated. Cox proportional hazards and logistic regression models were used to assess association between the dietary indices and lung cancer diagnosed during annual screening, and other respiratory outcomes that were recorded at baseline, respectively. RESULTS: In multivariable analysis, adjusted for baseline lung cancer risk (estimated from age, sex, smoking history, and asbestos exposure) and total energy, both DII and aMED scores were associated with dyspnoea (p trend = 0.046 and 0.02, respectively) and radiological evidence of emphysema (p trend = 0.0002 and 0.02). After mutual adjustment of the two dietary scores, only the association between DII and radiological evidence of emphysema (Q4 vs. Q1, OR 1.30, 95 % CI 1.01-1.67, p trend = 0.012) remained statistically significant. At univariate analysis, both DII and aMED were associated with lung cancer risk, but in fully adjusted multivariate analysis, only the association with aMED remained statistically significant (p trend = 0.04). CONCLUSIONS: Among heavy smokers, a pro-inflammatory diet, as indicated by increasing DII score, is associated with dyspnoea and radiological evidence of emphysema. A traditional Mediterranean diet, which is associated with a lower DII, may lower lung cancer risk.

Positron emission tomography in the diagnostic work-up of screening-detected lung nodules.

Low-dose computed tomography (CT) screening for lung cancer can reduce lung cancer mortality, but overdiagnosis, false positives and invasive procedures for benign nodules are worrying. We evaluated the utility of positron emission tomography (PET)-CT in characterising indeterminate screening-detected lung nodules. 383 nodules, examined by PET-CT over the first 6 years of the COSMOS (Continuous Observation of Smoking Subjects) study to diagnose primary lung cancer, were reviewed and compared with pathological findings (surgically-treated patients) or follow-up (negative CT for ⩾2 years, considered negative); 196 nodules were malignant. The sensitivity, specificity and accuracy of PET-CT for differentially diagnosing malignant nodules were, respectively, 64%, 89% and 76% overall, and 82%, 92% and 88% for baseline-detected nodules. Performance was lower for nodules found at repeat annual scans, with sensitivity ranging from 22% for nonsolid to 79% for solid nodules (p=0.0001). Sensitivity (87%) and specificity (73%) were high for nodules ⩾15 mm, better (sensitivity 98%) for solid nodules ⩾15 mm. PET-CT was highly sensitive for the differential diagnosis of indeterminate nodules detected at baseline, nodules ⩾15 mm and solid nodules. Sensitivity was low for sub-solid nodules and nodules discovered after baseline for which other methods, e.g. volume doubling time, should be used.

Ultra-low-dose CT with model-based iterative reconstruction (MBIR): detection of ground-glass nodules in an anthropomorphic phantom study.

PURPOSE: The authors sought to evaluate the effect of model-based iterative reconstruction (MBIR) on the sensitivity of ground-glass nodule (GGN) detection at different dose levels. MATERIALS AND METHODS: Fifty-four artificial GGN were randomly divided into three sets, each positioned in an anthropomorphic phantom. The three sets were evaluated on standard-dose (SD, 350 mA), low-dose (LD, 35 mA) and ultra-low-dose (ULD, 10 mA) CT scans (100 kV, 64 × 0.625 mm, 0.5 s), and each scan was reconstructed twice with filtered back projection (FBP) and MBIR. Three radiologists independently evaluated the scans for GGN presence and size. SD + FBP was considered the reference standard. A region of interest (ROI) was used to calculate signal-to-noise ratio (SNR) and contrast-to-noise ratio normalised to dose (CNRD). McNemar's test, Bland-Altman analysis and t test were used for statistical assessment (p < 0.05). RESULTS: The mean diameter of the 54 GGNs was 9.2 mm (range 3.7-17.3 mm). For the three readers, no statistically significant differences were observed in the sensitivity of GGN detection between LD + MBIR, ULD + MBIR and SD + FBP (p > 0.05). Bland-Altman analysis showed a good reader agreement (±1.5 mm) for GGN size between SD + FBP and ULD + MBIR. For low dose and ultra-low dose, the SNR and CNRD were significantly higher with MBIR (p < 0.0001). The effective dose was 97.1 % lower with ultra-low dose (0.15 mSv) than standard dose (5.15 mSv). CONCLUSIONS: The detection of GGN with MBIR at low-dose and ultra-low-dose CT does not differ significantly from standard-dose CT with FBP in an anthropomorphic phantom.

Phase ib of sorafenib in combination with everolimus in patients with advanced solid tumors, selected on the basis of molecular targets.

BACKGROUND: Molecular alterations of the PI3K and Ras pathways often occur in human cancer. In this trial, the pharmacokinetics, toxicity, and activity of two drugs inhibiting these pathways-everolimus and sorafenib-were investigated. METHODS: Thirteen patients with progressing solid tumors were treated with everolimus and sorafenib, according to a 3+3 scheme. Patients were selected on the basis of immunohistochemical expression of tumor molecular targets, including phospho-AKT, -p70S6K, and -ERK1/2. RESULTS: The daily recommended dose identified was 2.5 mg of everolimus and 600 mg of sorafenib. Dose-limiting toxicities included grade 3 asthenia and hand-foot skin reaction. No grade 4 adverse events were observed. The most frequent grade 3 toxicities were hypophosphatemia (30.8%), alanine aminotransferase level increase, asthenia, and anorexia (14%). No pharmacokinetic interactions were identified between everolimus and sorafenib. Of 12 evaluable patients, we observed 2 partial responses, with greater than 10% shrinkage in an additional 5 patients. Objective responses were observed in one patient with a thymoma and in one patient with a lung adenocarcinoma. Tumor shrinkage that did not qualify as a partial response was seen in an abdominal leiomyosarcoma and in adenoid cystic carcinomas. CONCLUSION: The combination of everolimus and sorafenib is safe. The tumor activity observed in different tumor types could be the result of the combined action of these drugs as well as the molecular selection of the treated population. Further research is warranted to better investigate drugs simultaneously blocking the PI3K and the Ras pathways and to refine patient selection.

Assessment of pulmonary vascular anatomy: comparing augmented reality by holograms versus standard CT images/reconstructions using surgical findings as reference standard.

BACKGROUND: We compared computed tomography (CT) images and holograms (HG) to assess the number of arteries of the lung lobes undergoing lobectomy and assessed easiness in interpretation by radiologists and thoracic surgeons with both techniques. METHODS: Patients scheduled for lobectomy for lung cancer were prospectively included and underwent CT for staging. A patient-specific three-dimensional model was generated and visualized in an augmented reality setting. One radiologist and one thoracic surgeon evaluated CT images and holograms to count lobar arteries, having as reference standard the number of arteries recorded at surgery. The easiness of vessel identification was graded according to a Likert scale. Wilcoxon signed-rank test and κ statistics were used. RESULTS: Fifty-two patients were prospectively included. The two doctors detected the same number of arteries in 44/52 images (85%) and in 51/52 holograms (98%). The mean difference between the number of artery branches detected by surgery and CT images was 0.31 ± 0.98, whereas it was 0.09 ± 0.37 between surgery and HGs (p = 0.433). In particular, the mean difference in the number of arteries detected in the upper lobes was 0.67 ± 1.08 between surgery and CT images and 0.17 ± 0.46 between surgery and holograms (p = 0.029). Both radiologist and surgeon showed a higher agreement for holograms (κ = 0.99) than for CT (κ = 0.81) and found holograms easier to evaluate than CTs (p < 0.001). CONCLUSIONS: Augmented reality by holograms is an effective tool for preoperative vascular anatomy assessment of lungs, especially when evaluating the upper lobes, more prone to anatomical variations. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04227444 RELEVANCE STATEMENT: Preoperative evaluation of the lung lobe arteries through augmented reality may help the thoracic surgeons to carefully plan a lobectomy, thus contributing to optimize patients' outcomes. KEY POINTS: • Preoperative assessment of the lung arteries may help surgical planning. • Lung artery detection by augmented reality was more accurate than that by CT images, particularly for the upper lobes. • The assessment of the lung arterial vessels was easier by using holograms than CT images.

Low-dose CT for quantitative analysis in acute respiratory distress syndrome.

INTRODUCTION: The clinical use of serial quantitative computed tomography (CT) to characterize lung disease and guide the optimization of mechanical ventilation in patients with acute respiratory distress syndrome (ARDS) is limited by the risk of cumulative radiation exposure and by the difficulties and risks related to transferring patients to the CT room. We evaluated the effects of tube current-time product (mAs) variations on quantitative results in healthy lungs and in experimental ARDS in order to support the use of low-dose CT for quantitative analysis. METHODS: In 14 sheep chest CT was performed at baseline and after the induction of ARDS via intravenous oleic acid injection. For each CT session, two consecutive scans were obtained applying two different mAs: 60 mAs was paired with 140, 15 or 7.5 mAs. All other CT parameters were kept unaltered (tube voltage 120 kVp, collimation 32 × 0.5 mm, pitch 0.85, matrix 512 × 512, pixel size 0.625 × 0.625 mm). Quantitative results obtained at different mAs were compared via Bland-Altman analysis. RESULTS: Good agreement was observed between 60 mAs and 140 mAs and between 60 mAs and 15 mAs (all biases less than 1%). A further reduction of mAs to 7.5 mAs caused an increase in the bias of poorly aerated and nonaerated tissue (-2.9% and 2.4%, respectively) and determined a significant widening of the limits of agreement for the same compartments (-10.5% to 4.8% for poorly aerated tissue and -5.9% to 10.8% for nonaerated tissue). Estimated mean effective dose at 140, 60, 15 and 7.5 mAs corresponded to 17.8, 7.4, 2.0 and 0.9 mSv, respectively. Image noise of scans performed at 140, 60, 15 and 7.5 mAs corresponded to 10, 16, 38 and 74 Hounsfield units, respectively. CONCLUSIONS: A reduction of effective dose up to 70% has been achieved with minimal effects on lung quantitative results. Low-dose computed tomography provides accurate quantitative results and could be used to characterize lung compartment distribution and possibly monitor time-course of ARDS with a lower risk of exposure to ionizing radiation. A further radiation dose reduction is associated with lower accuracy in quantitative results.

Nutrient intake and nutrient patterns and risk of lung cancer among heavy smokers: results from the COSMOS screening study with annual low-dose CT.

The role of nutrients in lung cancer aetiology remains controversial and has never been evaluated in the context of screening. Our aim was to investigate the role of single nutrients and nutrient patterns in the aetiology of lung cancer in heavy smokers. Asymptomatic heavy smokers (≥20 pack-years) were invited to undergo annual low-dose computed tomography. We assessed diet using a self-administered food frequency questionnaire and collected information on multivitamin supplement use. We performed principal component analysis identifying four nutrient patterns and used Cox proportional Hazards regression to assess the association between nutrients and nutrients patterns and lung cancer risk. During a mean follow-up of 5.7 years, 178 of 4,336 participants were diagnosed with lung cancer by screening. We found a significant risk reduction of lung cancer with increasing vegetable fat consumption (HR for highest vs. lowest quartile = 0.50, 95% CI = 0.31-0.80; P-trend = 0.02). Participants classified in the high "vitamins and fiber" pattern score had a significant risk reduction of lung cancer (HR = 0.57; 95% CI = 0.36-0.90, P-trend = 0.01). Among heavy smokers enrolled in a screening trial, high vegetable fat intake and adherence to the "vitamin and fiber" nutrient pattern were associated with reduced lung cancer incidence.

Estimating overdiagnosis in low-dose computed tomography screening for lung cancer: a cohort study.

BACKGROUND: Lung cancer screening may detect cancer that will never become symptomatic (overdiagnosis), leading to overtreatment. Changes in size on sequential low-dose computed tomography (LDCT) screening, expressed as volume-doubling time (VDT), may help to distinguish aggressive cancer from cases that are unlikely to become symptomatic. OBJECTIVE: To assess VDT for screening-detected lung cancer as an indicator of overdiagnosis. DESIGN: Retrospective estimation of the VDT of cancer detected in a prospective LDCT screening cohort. SETTING: Nonrandomized, single-center screening study involving persons at high risk for lung cancer enrolled between 2004 and 2005 who received LDCT annually for 5 years. PATIENTS: 175 study patients diagnosed with primary lung cancer. MEASUREMENTS: VDT was measured on LDCT and classified as fast-growing (<400 days), slow-growing (between 400 and 599 days), or indolent (≥600 days). RESULTS: Fifty-five cases of cancer were diagnosed at baseline, and 120 were diagnosed subsequently. Of the latter group, 19 cases (15.8%) were new (not visible on previous scans) and fast-growing (median VDT, 52 days); 101 (84.2%) were progressive, including 70 (58.3%) fast-growing and 31 (25.8%) slow-growing (15.0%) or indolent (10.8%) cases. Lung cancer-specific mortality was significantly higher (9.2% per year) in patients with new compared with slow-growing or indolent (0.9% per year) cancer. Sixty percent of fast-growing progressive cancer and 45% of new cancer were stage I, for which survival was good. LIMITATIONS: This is a retrospective study. Volume-doubling time can only indicate overdiagnosis and was estimated for new cancer from 1 measurement (a diameter of 2 mm assumed the previous year). CONCLUSION: Slow-growing or indolent cancer comprised approximately 25% of incident cases, many of which may have been overdiagnosed. To limit overtreatment in these cases, minimally invasive limited resection and nonsurgical treatments should be investigated. PRIMARY FUNDING SOURCE: Italian Association for Cancer Research.

Association between Contrast-Enhanced Computed Tomography Radiomic Features, Genomic Alterations and Prognosis in Advanced Lung Adenocarcinoma Patients.

Non-invasive methods to assess mutational status, as well as novel prognostic biomarkers, are warranted to foster therapy personalization of patients with advanced non-small cell lung cancer (NSCLC). This study investigated the association of contrast-enhanced Computed Tomography (CT) radiomic features of lung adenocarcinoma lesions, alone or integrated with clinical parameters, with tumor mutational status (EGFR, KRAS, ALK alterations) and Overall Survival (OS). In total, 261 retrospective and 48 prospective patients were enrolled. A Radiomic Score (RS) was created with LASSO-Logistic regression models to predict mutational status. Radiomic, clinical and clinical-radiomic models were trained on retrospective data and tested (Area Under the Curve, AUC) on prospective data. OS prediction models were trained and tested on retrospective data with internal cross-validation (C-index). RS significantly predicted each alteration at training (radiomic and clinical-radiomic AUC 0.95-0.98); validation performance was good for EGFR (AUC 0.86), moderate for KRAS and ALK (AUC 0.61-0.65). RS was also associated with OS at univariate and multivariable analysis, in the latter with stage and type of treatment. The validation C-index was 0.63, 0.79, and 0.80 for clinical, radiomic, and clinical-radiomic models. The study supports the potential role of CT radiomics for non-invasive identification of gene alterations and prognosis prediction in patients with advanced lung adenocarcinoma, to be confirmed with independent studies.

A methodological quality evaluation of the published guidelines and recommendations about the lung cancer screening.

BACKGROUND: A project to assess the existing literature and to benchmark the quality of past guidelines and recommendations on lung cancer screening projects was developed with a particular focus on the assessment of the methodology used in producing them. METHODS: Each guideline was assessed in the different items and domains with the Appraisal of Guidelines for Research and Evaluation (AGREE) II instrument and scored on a seven-point scale. RESULTS: Eight guidelines matched the inclusion criteria and were assessed. A multinational collaboration produced three out of five guidelines. The multivariable analysis shows that improved scores of stakeholders' involvement were related to internationally developed guidelines. Improved methodological quality was related to the involvement of scientific societies due to the better rigor of development and editorial independence. Countries with higher expenditure on healthcare produced significantly better guidelines. CONCLUSIONS: Assessed by the AGREE II criteria, the methodological quality of previous guidelines was relatively low. Nevertheless, the National Comprehensive Cancer Network Guidelines should be recommended as a model for the development of best methodological quality guidelines.

Reproducibility of radiomic features in CT images of NSCLC patients: an integrative analysis on the impact of acquisition and reconstruction parameters.

BACKGROUND: We investigated to what extent tube voltage, scanner model, and reconstruction algorithm affect radiomic feature reproducibility in a single-institution retrospective database of computed tomography images of non-small-cell lung cancer patients. METHODS: This study was approved by the Institutional Review Board (UID 2412). Images of 103 patients were considered, being acquired on either among two scanners, at 100 or 120 kVp. For each patient, images were reconstructed with six iterative blending levels, and 1414 features were extracted from each reconstruction. At univariate analysis, Wilcoxon-Mann-Whitney test was applied to evaluate feature differences within scanners and voltages, whereas the impact of the reconstruction was established with the overall concordance correlation coefficient (OCCC). A multivariable mixed model was also applied to investigate the independent contribution of each acquisition/reconstruction parameter. Univariate and multivariable analyses were combined to analyse feature behaviour. RESULTS: Scanner model and voltage did not affect features significantly. The reconstruction blending level showed a significant impact at both univariate analysis (154/1414 features yielding an OCCC < 0.85) and multivariable analysis, with most features (1042/1414) revealing a systematic trend with the blending level (multiple comparisons adjusted p < 0.05). Reproducibility increased in association to image processing with smooth filters, nonetheless specific investigation in relation to clinical endpoints should be performed to ensure that textural information is not removed. CONCLUSIONS: Combining univariate and multivariable models is allowed to identify features for which corrections may be applied to reduce the trend with the algorithm and increase reproducibility. Subsequent clustering may be applied to eliminate residual redundancy.

Impact of image filtering and assessment of volume-confounding effects on CT radiomic features and derived survival models in non-small cell lung cancer.

Background: No evidence supports the choice of specific imaging filtering methodologies in radiomics. As the volume of the primary tumor is a well-recognized prognosticator, our purpose is to assess how filtering may impact the feature/volume dependency in computed tomography (CT) images of non-small cell lung cancer (NSCLC), and if such impact translates into differences in the performance of survival modeling. The role of lesion volume in model performances was also considered and discussed. Methods: Four-hundred seventeen CT images NSCLC patients were retrieved from the NSCLC-Radiomics public repository. Pre-processing and features extraction were implemented using Pyradiomics v3.0.1. Features showing high correlation with volume across original and filtered images were excluded. Cox proportional hazards (PH) with least absolute shrinkage and selection operator (LASSO) regularization and CatBoost models were built with and without volume, and their concordance (C-) indices were compared using Wilcoxon signed-ranked test. The Mann Whitney U test was used to assess model performances after stratification into two groups based on low- and high-volume lesions. Results: Radiomic models significantly outperformed models built on only clinical variables and volume. However, the exclusion/inclusion of volume did not generally alter the performances of radiomic models. Overall, performances were not substantially affected by the choice of either imaging filter (overall C-index 0.539-0.590 for Cox PH and 0.589-0.612 for CatBoost). The separation of patients with high-volume lesions resulted in significantly better performances in 2/10 and 7/10 cases for Cox PH and CatBoost models, respectively. Both low- and high-volume models performed significantly better with the inclusion of radiomic features (P<0.0001), but the improvement was largest in the high-volume group (+10.2% against +8.7% improvement for CatBoost models and +10.0% against +5.4% in Cox PH models). Conclusions: Radiomic features complement well-known prognostic factors such as volume, but their volume-dependency is high and should be managed with vigilance. The informative content of radiomic features may be diminished in small lesion volumes, which could limit the applicability of radiomics in early-stage NSCLC, where tumors tend to be small. Our results also suggest an advantage of CatBoost models over the Cox PH models.