Radiomics-based machine learning differentiates "ground-glass" opacities due to COVID-19 from acute non-COVID-19 lung disease.

Ground-glass opacities (GGOs) are a non-specific high-resolution computed tomography (HRCT) finding tipically observed in early Coronavirus disesase 19 (COVID-19) pneumonia. However, GGOs are also seen in other acute lung diseases, thus making challenging the differential diagnosis. To this aim, we investigated the performance of a radiomics-based machine learning method to discriminate GGOs due to COVID-19 from those due to other acute lung diseases. Two sets of patients were included: a first set of 28 patients (COVID) diagnosed with COVID-19 infection confirmed by real-time polymerase chain reaction (RT-PCR) between March and April 2020 having (a) baseline HRCT at hospital admission and (b) predominant GGOs pattern on HRCT; a second set of 30 patients (nCOVID) showing (a) predominant GGOs pattern on HRCT performed between August 2019 and April 2020 and (b) availability of final diagnosis. Two readers independently segmented GGOs on HRCTs using a semi-automated approach, and radiomics features were extracted using a standard open source software (PyRadiomics). Partial least square (PLS) regression was used as the multivariate machine-learning algorithm. A leave-one-out nested cross-validation was implemented. PLS ß-weights of radiomics features, including the 5% features with the largest ß-weights in magnitude (top 5%), were obtained. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. The Youden's test assessed sensitivity and specificity of the classification. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The predictive model delivered an AUC of 0.868 (Youden's index = 0.68, sensitivity = 93%, specificity 75%, p = 4.2 × 10-7). Of the seven features included in the top 5% features, five were texture-related. A radiomics-based machine learning signature showed the potential to accurately differentiate GGOs due to COVID-19 pneumonia from those due to other acute lung diseases. Most of the discriminant radiomics features were texture-related. This approach may assist clinician to adopt the appropriate management early, while improving the triage of patients.

Weighing the role of skeletal muscle mass and muscle density in cancer patients receiving PD-1/PD-L1 checkpoint inhibitors: a multicenter real-life study.

Sarcopenia represents one of the hallmarks of all chronic diseases, including cancer, and was already investigated as a prognostic marker in the pre-immunotherapy era. Sarcopenia can be evaluated using cross-sectional image analysis of CT-scans, at the level of the third lumbar vertebra (L3), to estimate the skeletal muscle index (SMI), a surrogate of skeletal muscle mass, and to evaluate the skeletal muscle density (SMD). We performed a retrospective analysis of consecutive advanced cancer patient treated with PD-1/PD-L1 checkpoint inhibitors. Baseline SMI and SMD were evaluated and optimal cut-offs for survival, according to sex and BMI (+/-25) were computed. The evaluated clinical outcomes were: objective response rate (ORR), immune-related adverse events (irAEs), progression free survival (PFS) and overall survival (OS). From April 2015 to April 2019, 100 consecutive advanced cancer patients were evaluated. 50 (50%) patients had a baseline low SMI, while 51 (51%) had a baseline low SMD according to the established cut offs. We found a significant association between SMI and ECOG-PS (p = 0.0324), while no correlations were found regarding SMD and baseline clinical factors. The median follow-up was 20.3 months. Patients with low SMI had a significantly shorter PFS (HR = 1.66 [95% CI: 1.05-2.61]; p = 0.0291) at univariate analysis, but not at the multivariate analysis. They also had a significantly shorter OS (HR = 2.19 [95% CI: 1.31-3.64]; p = 0.0026). The multivariate analysis confirmed baseline SMI as an independent predictor for OS (HR = 2.19 [1.31-3.67]; p = 0.0027). We did not find significant relationships between baseline SMD and clinical outcomes, nor between ORR, irAEs and baseline SMI (data not shown). Low SMI is associated with shortened survival in advanced cancer patients treated with PD1/PDL1 checkpoint inhibitors. However, the lack of an association between SMI and clinical response suggests that sarcopenia may be generally prognostic in this setting rather than specifically predictive of response to immunotherapy.

Under-reporting of cardiovascular findings on chest CT.

PURPOSE: It is unclear whether (and, to what extent) radiologists look at and report cardiovascular abnormalities on non-cardio-synchronized standard chest computed tomography (CT). In this study, the frequency and the reporting rate of cardiovascular findings in chest CT examinations were retrospectively assessed. MATERIALS AND METHODS: This study was approved by the institutional review board of each participating center. Four academic centers provided data on 447 subjects who underwent non-ECG-synchronized chest CT examinations for evaluating pulmonary fibrosis (161/447, 36 %), suspected pulmonary embolism (140/447, 31.3 %), or lung cancer staging (146/447, 32.7 %). A total of 220/447 (53.7 %) and 227/447 CT (46.3 %) examinations were evaluated and reported by junior and senior chest radiologists, respectively. Two radiologists with training in cardiac imaging reviewed the same chest CT images looking for the presence of incidental cardiovascular abnormalities using a preformatted score sheet. Inter-observer agreement was assessed using the kappa coefficient of agreement (k). RESULTS: Inter-observer agreement between the study reviewers was moderate to good (0.4-0.73) for most of the incidental cardiovascular findings. At least one incidental cardiovascular finding not documented in the original report was identified by the study reviewers in 225/409 (55 %) of chest CT examinations. A total of 168/266 (63.2 %) potentially clinically significant cardiovascular findings were unreported in the original reports of 177/447 (39.6 %) subjects (p < 0.0001). Senior radiologists tended to more frequently report coronary artery calcification (p = 0.0006), cardiac valves calcification (p = 0.0003), and ascending aorta enlargement (p = 0.01) compared to junior radiologists. CONCLUSIONS: Several cardiovascular abnormalities can be reliably identified on standard chest CT. Yet, they are often under-reported, even when they might be relevant to the patient's work-up.

Imaging in occupational and environmental lung disease.

PURPOSE OF REVIEW: Work-related and environmental lung disease is increasing over time and new antigens causing pulmonary response are described in medical literature every year with more or less specific imaging findings. The purposes of this review are to highlight the current role of imaging, describe classic as well as uncommon high-resolution computed tomography (HRCT) patterns helpful in guiding diagnosis and update the recent literature on this topic. RECENT FINDINGS: Recent literature on imaging of occupational and environmental lung disease is scarce and is predominantly based on the HRCT appearance related to specific antigen exposure and on prognostic significance of findings. SUMMARY: Knowledge of imaging modality potential and radiologic appearance may guide identification, characterization and follow-up of old and new occupational and environmental lung diseases. HRCT plays a key role in this context, having radiation exposure as a major limitation, especially in asymptomatic patients. Low-dose HRCT has the potential to be employed for screening and surveillance of the exposed individuals. However, future research is needed to further this field.

Regenerative treatment of an immature, traumatized tooth with apical periodontitis: report of a case.

This case report describes the treatment of a necrotic immature permanent central incisor with complete crown fracture, suspected root fracture, and sinus tract, which was not treated with conventional apexification techniques. Instead, a regenerative approach based on the trauma literature's methods for revascularization was provided. The root canal was gently debrided of necrotic tissue with a sharp spoon excavator and irrigated for only one third of its length with NaOCl and then medicated with calcium hydroxide. After 15 days the sinus tract had healed, and the tooth was asymptomatic. The tooth was accessed, calcium hydroxide was removed, bleeding was stimulated to form an intracanal blood clot, and mineral trioxide aggregate was placed coronally to the blood clot. After 8 months, a coronal calcified barrier was radiographically evident and accompanied with progressive thickening of the root wall and apical closure. Two and a half years after treatment was initiated, the tooth remained asymptomatic, and the sinus tract had not reappeared. The progressive increase in the thickness of the dentinal walls and subsequent apical development suggest that appropriate biologic responses can occur with this type of treatment of the necrotic immature permanent tooth with sinus tract.