Lung Cancer Screening with Low-Dose CT: What We Have Learned in Two Decades of ITALUNG and What Is Yet to Be Addressed.

The ITALUNG trial started in 2004 and compared lung cancer (LC) and other-causes mortality in 55-69 years-aged smokers and ex-smokers who were randomized to four annual chest low-dose CT (LDCT) or usual care. ITALUNG showed a lower LC and cardiovascular mortality in the screened subjects after 13 years of follow-up, especially in women, and produced many ancillary studies. They included recruitment results of a population-based mimicking approach, development of software for computer-aided diagnosis (CAD) and lung nodules volumetry, LDCT assessment of pulmonary emphysema and coronary artery calcifications (CAC) and their relevance to long-term mortality, results of a smoking-cessation intervention, assessment of the radiations dose associated with screening LDCT, and the results of biomarkers assays. Moreover, ITALUNG data indicated that screen-detected LCs are mostly already present at baseline LDCT, can present as lung cancer associated with cystic airspaces, and can be multiple. However, several issues of LC screening are still unaddressed. They include the annual vs. biennial pace of LDCT, choice between opportunistic or population-based recruitment. and between uni or multi-centre screening, implementation of CAD-assisted reading, containment of false positive and negative LDCT results, incorporation of emphysema. and CAC quantification in models of personalized LC and mortality risk, validation of ultra-LDCT acquisitions, optimization of the smoking-cessation intervention. and prospective validation of the biomarkers.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images.

Purpose: The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Approach: Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. Results: The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Conclusions: Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

Moderate-severe coronary calcification predicts long-term cardiovascular death in CT lung cancer screening: The ITALUNG trial.

PURPOSE: Coronary artery calcifications (CAC) are very strong indicators for increased cardio-vascular (CV) risk and can be evaluated also in low-dose computed tomography (LDCT) for lung cancer screening. We assessed whether a simple and fast CAC visual score is associated with CV mortality. METHODS: CAC were retrospectively assessed by two observers using a 4-score (absent, mild, moderate and severe) scale in baseline LDCT obtained in 1364 participants to the ITALUNG trial who had 55-69 years of age and a smoking history ≥20 pack-years. Correlations with CV risk factors at baseline and with CV mortality after 11 years of follow-up were investigated. RESULTS: CAC were absent in 470 (34.5%), mild in 433 (31.7%), moderate in 357 (26.2%) and severe in 104 (7.6%) subjects. CAC severity correlated (≤0.001) with age, male sex, pack-years, history of arterial hypertension or diabetes, obesity and treated hypercholesterolemia. Twenty-one CV deaths occurred. Moderate or severe CAC were significantly associated with higher CV mortality after adjustment for all other known risk factors (ARR = 2.72; 95 %CI:1.04-7.11). Notably, also in subjects with none or one only additional CV risk factor, the presence of moderate-severe CAC allowed to identify a subgroup of subjects with higher CV death risk (RR = 3.66; CI95%:1.06-12.6). CONCLUSIONS: Moderate or severe CAC visually assessed in LDCT examinations for lung cancer screening are independently associated with CV mortality.

The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission.

Triage is crucial for patient's management and estimation of the required intensive care unit (ICU) beds is fundamental for health systems during the COVID-19 pandemic. We assessed whether chest computed tomography (CT) of COVID-19 pneumonia has an incremental role in predicting patient's admission to ICU. We performed volumetric and texture analysis of the areas of the affected lung in CT of 115 outpatients with COVID-19 infection presenting to the emergency room with dyspnea and unresponsive hypoxyemia. Admission blood laboratory including lymphocyte count, serum lactate dehydrogenase, D-dimer and C-reactive protein and the ratio between the arterial partial pressure of oxygen and inspired oxygen were collected. By calculating the areas under the receiver-operating characteristic curves (AUC), we compared the performance of blood laboratory-arterial gas analyses features alone and combined with the CT features in two hybrid models (Hybrid radiological and Hybrid radiomics)for predicting ICU admission. Following a machine learning approach, 63 patients were allocated to the training and 52 to the validation set. Twenty-nine (25%) of patients were admitted to ICU. The Hybrid radiological model comprising the lung %consolidation performed significantly (p = 0.04) better in predicting ICU admission in the validation (AUC = 0.82; 95% confidence interval 0.73-0.97) set than the blood laboratory-arterial gas analyses features alone (AUC = 0.71; 95% confidence interval 0.56-0.86). A risk calculator for ICU admission was derived and is available at: https://github.com/cgplab/covidapp . The volume of the consolidated lung in CT of patients with COVID-19 pneumonia has a mild but significant incremental value in predicting ICU admission.

Multidetector computed tomography of the head in acute stroke: predictive value of different patterns of the dense artery sign revealed by maximum intensity projection reformations for location and extent of the infarcted area.

Maximum intensity projections reconstructions from 2.5 mm unenhanced multidetector computed tomography axial slices were obtained from 49 patients within the first 6 h of anterior-circulation cerebral strokes to identify different patterns of the dense artery sign and their prognostic implications for location and extent of the infarcted areas. The dense artery sign was found in 67.3% of cases. Increased density of the whole M1 segment with extension to M2 of the middle cerebral artery was associated with a wider extension of cerebral infarcts in comparison to M1 segment alone or distal M1 and M2. A dense sylvian branch of the middle cerebral artery pattern was associated with a more restricted extension of infarct territory. We found 62.5% of patients without a demonstrable dense artery to have a limited peripheral cortical or capsulonuclear lesion. In patients with a 7-10 points on the Alberta Stroke Early Programme Computed Tomography Score and a dense proximal MCA in the first hours of ictus the mean decrease in the score between baseline and follow-up was 5.09+/-1.92 points. In conclusion, maximum intensity projections from thin-slice images can be quickly obtained from standard computed tomography datasets using a multidetector scanner and are useful in identifying and correctly localizing the dense artery sign, with prognostic implications for the entity of cerebral damage.

Traumatic lesions of corpus callosum: early multidetector CT findings.

Corpus callosum is one of the common sites of brain lesion, whose involvement is an indicator of a more severe prognosis, produced by traumatic shearing stresses resulting in diffuse axonal injury (DAI). Computed tomography (CT) in acute phase is considered to have a limited role for the detection of non-hemorrhagic or petechial hemorrhagic DAI lesions. New generation multidetector CT scanners allow faster acquisition of thinner-slice images and post-processing reformations. Three patients with severe closed head trauma underwent CT examinations using a multidetector scanner, a few hours and the day after injury. The review of original images with narrow window width and integration with reconstruction of thinner slices from raw-data and post-processing multiplanar reformations (MPR) helped to detect the onset of hypodense or predominantly hypodense areas of corpus callosum, not present at admission and afterwards confirmed by MRI.