Post-Acute Sequelae of COVID-19 Pneumonia: Six-month Chest CT Follow-up.

Background The long-term post-acute pulmonary sequelae of COVID-19 remain unknown. Purpose To evaluate lung injury in patients affected by COVID-19 pneumonia at the 6-month follow-up CT examination compared with the baseline chest CT examination. Materials and Methods From March 19, 2020, to May 24, 2020, patients with moderate to severe COVID-19 pneumonia who had undergone baseline chest CT were prospectively enrolled at their 6-month follow-up. The CT qualitative findings, semiquantitative Lung Severity Score (LSS), and the well-aerated lung volume at quantitative chest CT (QCCT) analysis were analyzed. The performance of the baseline LSS and QCCT findings for predicting fibrosis-like changes (reticular pattern and/or honeycombing) at the 6-month follow-up chest CT examination was tested by using receiver operating characteristic curves. Univariable and multivariable logistic regression analyses were used to test clinical and radiologic features that were predictive of fibrosis-like changes. The multivariable analysis was performed with clinical parameters alone (clinical model), radiologic parameters alone (radiologic model), and the combination of clinical and radiologic parameters (combined model). Results One hundred eighteen patients who had undergone baseline chest CT and agreed to undergo follow-up chest CT at 6 months were included in the study (62 women; mean age, 65 years ± 12 [standard deviation]). At follow-up chest CT, 85 of 118 (72%) patients showed fibrosis-like changes and 49 of 118 (42%) showed ground-glass opacities. The baseline LSS (>14) and QCCT findings (≤3.75 L and ≤80%) showed excellent performance for predicting fibrosis-like changes at follow-up chest CT. In the multivariable analysis, the areas under the curve were 0.89 (95% CI: 0.77, 0.96) for the clinical model, 0.81 (95% CI: 0.68, 0.9) for the radiologic model, and 0.92 (95% CI: 0.81, 0.98) for the combined model. Conclusion At 6-month follow-up chest CT, 72% of patients showed late sequelae, in particular fibrosis-like changes. The baseline Lung Severity Score and the well-aerated lung volume at quantitative chest CT (QCCT) analysis showed excellent performance for predicting fibrosis-like changes at the 6-month chest CT (area under the curve, >0.88). Male sex, cough, lymphocytosis, and the well-aerated lung volume at QCCT analysis were significant predictors of fibrosis-like changes at 6 months, demonstrating an inverse correlation (area under the curve, 0.92). © RSNA, 2021 See also the editorial by Wells and Devaraj in this issue.

Radiomics in Oncology, Part 1: Technical Principles and Gastrointestinal Application in CT and MRI.

Radiomics has been playing a pivotal role in oncological translational imaging, particularly in cancer diagnosis, prediction prognosis, and therapy response assessment. Recently, promising results were achieved in management of cancer patients by extracting mineable high-dimensional data from medical images, supporting clinicians in decision-making process in the new era of target therapy and personalized medicine. Radiomics could provide quantitative data, extracted from medical images, that could reflect microenvironmental tumor heterogeneity, which might be a useful information for treatment tailoring. Thus, it could be helpful to overcome the main limitations of traditional tumor biopsy, often affected by bias in tumor sampling, lack of repeatability and possible procedure complications. This quantitative approach has been widely investigated as a non-invasive and an objective imaging biomarker in cancer patients; however, it is not applied as a clinical routine due to several limitations related to lack of standardization and validation of images acquisition protocols, features segmentation, extraction, processing, and data analysis. This field is in continuous evolution in each type of cancer, and results support the idea that in the future Radiomics might be a reliable application in oncologic imaging. The first part of this review aimed to describe some radiomic technical principles and clinical applications to gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy.

Radiomics in Oncology, Part 2: Thoracic, Genito-Urinary, Breast, Neurological, Hematologic and Musculoskeletal Applications.

Radiomics has the potential to play a pivotal role in oncological translational imaging, particularly in cancer detection, prognosis prediction and response to therapy evaluation. To date, several studies established Radiomics as a useful tool in oncologic imaging, able to support clinicians in practicing evidence-based medicine, uniquely tailored to each patient and tumor. Mineable data, extracted from medical images could be combined with clinical and survival parameters to develop models useful for the clinicians in cancer patients' assessment. As such, adding Radiomics to traditional subjective imaging may provide a quantitative and extensive cancer evaluation reflecting histologic architecture. In this Part II, we present an overview of radiomic applications in thoracic, genito-urinary, breast, neurological, hematologic and musculoskeletal oncologic applications.

Deep Learning Can Differentiate IDH-Mutant from IDH-Wild GBM.

Isocitrate dehydrogenase (IDH) mutant and wildtype glioblastoma multiforme (GBM) often show overlapping features on magnetic resonance imaging (MRI), representing a diagnostic challenge. Deep learning showed promising results for IDH identification in mixed low/high grade glioma populations; however, a GBM-specific model is still lacking in the literature. Our aim was to develop a GBM-tailored deep-learning model for IDH prediction by applying convoluted neural networks (CNN) on multiparametric MRI. We selected 100 adult patients with pathologically demonstrated WHO grade IV gliomas and IDH testing. MRI sequences included: MPRAGE, T1, T2, FLAIR, rCBV and ADC. The model consisted of a 4-block 2D CNN, applied to each MRI sequence. Probability of IDH mutation was obtained from the last dense layer of a softmax activation function. Model performance was evaluated in the test cohort considering categorical cross-entropy loss (CCEL) and accuracy. Calculated performance was: rCBV (accuracy 83%, CCEL 0.64), T1 (accuracy 77%, CCEL 1.4), FLAIR (accuracy 77%, CCEL 1.98), T2 (accuracy 67%, CCEL 2.41), MPRAGE (accuracy 66%, CCEL 2.55). Lower performance was achieved on ADC maps. We present a GBM-specific deep-learning model for IDH mutation prediction, with a maximal accuracy of 83% on rCBV maps. Highest predictivity achieved on perfusion images possibly reflects the known link between IDH and neoangiogenesis through the hypoxia inducible factor.

Typical and atypical COVID-19 computed tomography findings.

In December 2019 a novel coronavirus, named severe acute respiratory syndrome coronavirus 2 was identified and the disease associated was named coronavirus disease 2019 (COVID-19). Fever, cough, myalgia, fatigue associated to dyspnea represent most common clinical symptoms of the disease. The reference standard for diagnosis of severe acute respiratory syndrome coronavirus 2 infection is real time reverse-transcription polymerase chain reaction test applied on respiratory tract specimens. Despite of lower specificity, chest computed tomography (CT), as reported in manifold scientific studies, showed high sensitivity, therefore it may help in the early detection, management and follow-up of COVID-19 pneumonia. Patients affected by COVID-19 pneumonia usually showed on chest CT some typical features, such as: Bilateral ground glass opacities characterized by multilobe involvement with posterior and peripheral distribution; parenchymal consolidations with or without air bronchogram; interlobular septal thickening; crazy paving pattern, represented by interlobular and intralobular septal thickening surrounded by ground-glass opacities; subsegmental pulmonary vessels enlargement (> 3 mm). Halo sign, reversed halo sign, cavitation and pleural or pericardial effusion represent some of atypical findings of COVID-19 pneumonia. On the other hand lymphadenopathy's and bronchiectasis' frequency is unclear, indeed conflicting data emerged in literature. Radiologists play a key role in recognition of high suspicious findings of COVID-19 on chest CT, both typical and atypical ones. Thus, the aim of this review is to illustrate typical and atypical CT findings of COVID-19.