Role of Chest Imaging in Viral Lung Diseases

Prediction of early-phase cytomegalovirus pneumonia in post-stem cell transplantation using a deep learning model

BACKGROUND

Diagnostic challenges exist for CMV pneumonia in post-hematopoietic stem cell transplantation (post-HSCT) patients, despite early-phase radiographic changes.

OBJECTIVE

The study aims to employ a deep learning model distinguishing CMV pneumonia from COVID-19 pneumonia, community-acquired pneumonia, and normal lungs post-HSCT.

METHODS

Initially, 6 neural network models were pre-trained with COVID-19 pneumonia, community-acquired pneumonia, and normal lung CT images from Kaggle's COVID multiclass dataset (Dataset A), then Dataset A was combined with the CMV pneumonia images from our center, forming Dataset B. We use a few-shot transfer learning strategy to fine-tune the pre-trained models and evaluate model performance in Dataset B.

RESULTS

34 cases of CMV pneumonia were found between January 2018 and December 2022 post-HSCT. Dataset A contained 1681 images of each subgroup from Kaggle. Combined with Dataset A, Dataset B was initially formed by 98 images of CMV pneumonia and normal lung. The optimal model (Xception) achieved an accuracy of 0.9034. Precision, recall, and F1-score all reached 0.9091, with an AUC of 0.9668 in the test set of Dataset B.

CONCLUSIONS

This framework demonstrates the deep learning model's ability to distinguish rare pneumonia types utilizing a small volume of CT images, facilitating early detection of CMV pneumonia post-HSCT.

Primary Lymphoproliferative Lung Diseases: Imaging and Multidisciplinary Approach

Lymphoproliferative lung diseases are a heterogeneous group of disorders characterized by primary or secondary involvement of the lung. Primary pulmonary lymphomas are the most common type, representing 0.5–1% of all primary malignancies of the lung. The radiological presentation is often heterogeneous and non-specific: consolidations, masses, and nodules are the most common findings, followed by ground-glass opacities and interstitial involvement, more common in secondary lung lymphomas. These findings usually show a prevalent perilymphatic spread along bronchovascular bundles, without a prevalence in the upper or lower lung lobes. An ancillary sign, such as a “halo sign”, “reverse halo sign”, air bronchogram, or CT angiogram sign, may be present and can help rule out a differential diagnosis. Since a wide spectrum of pulmonary parenchymal diseases may mimic lymphoma, a correct clinical evaluation and a multidisciplinary approach are mandatory. In this sense, despite High-Resolution Computer Tomography (HRCT) representing the gold standard, a tissue sample is needed for a certain and definitive diagnosis. Cryobiopsy is a relatively new technique that permits the obtaining of a larger amount of tissue without significant artifacts, and is less invasive and more precise than surgical biopsy.

Imaging Severity COVID-19 Assessment in Vaccinated and Unvaccinated Patients: Comparison of the Different Variants in a High Volume Italian Reference Center

Purpose: To analyze the vaccine effect by comparing five groups: unvaccinated patients with Alpha variant, unvaccinated patients with Delta variant, vaccinated patients with Delta variant, unvaccinated patients with Omicron variant, and vaccinated patients with Omicron variant, assessing the “gravity” of COVID-19 pulmonary involvement, based on CT findings in critically ill patients admitted to Intensive Care Unit (ICU). Methods: Patients were selected by ICU database considering the period from December 2021 to 23 March 2022, according to the following inclusion criteria: patients with proven Omicron variant COVID-19 infection with known COVID-19 vaccination with at least two doses and with chest Computed Tomography (CT) study during ICU hospitalization. Wee also evaluated the ICU database considering the period from March 2020 to December 2021, to select unvaccinated consecutive patients with Alpha variant, subjected to CT study, consecutive unvaccinated and vaccinated patients with Delta variant, subjected to CT study, and, consecutive unvaccinated patients with Omicron variant, subjected to CT study. CT images were evaluated qualitatively using a severity score scale of 5 levels (none involvement, mild: ≤25% of involvement, moderate: 26−50% of involvement, severe: 51−75% of involvement, and critical involvement: 76−100%) and quantitatively, using the Philips IntelliSpace Portal clinical application CT COPD computer tool. For each patient the lung volumetry was performed identifying the percentage value of aerated residual lung volume. Non-parametric tests for continuous and categorical variables were performed to assess statistically significant differences among groups. Results: The patient study group was composed of 13 vaccinated patients affected by the Omicron variant (Omicron V). As control groups we identified: 20 unvaccinated patients with Alpha variant (Alpha NV); 20 unvaccinated patients with Delta variant (Delta NV); 18 vaccinated patients with Delta variant (Delta V); and 20 unvaccinated patients affected by the Omicron variant (Omicron NV). No differences between the groups under examination were found (p value > 0.05 at Chi square test) in terms of risk factors (age, cardiovascular diseases, diabetes, immunosuppression, chronic kidney, cardiac, pulmonary, neurologic, and liver disease, etc.). A different median value of aerated residual lung volume was observed in the Delta variant groups: median value of aerated residual lung volume was 46.70% in unvaccinated patients compared to 67.10% in vaccinated patients. In addition, in patients with Delta variant every other extracted volume by automatic tool showed a statistically significant difference between vaccinated and unvaccinated group. Statistically significant differences were observed for each extracted volume by automatic tool between unvaccinated patients affected by Alpha variant and vaccinated patients affected by Delta variant of COVID-19. Good statistically significant correlations among volumes extracted by automatic tool for each lung lobe and overall radiological severity score were obtained (ICC range 0.71−0.86). GGO was the main sign of COVID-19 lesions on CT images found in 87 of the 91 (95.6%) patients. No statistically significant differences were observed in CT findings (ground glass opacities (GGO), consolidation or crazy paving sign) among patient groups. Conclusion: In our study, we showed that in critically ill patients no difference were observed in terms of severity of disease or exitus, between unvaccinated and vaccinated patients. The only statistically significant differences were observed, with regard to the severity of COVID-19 pulmonary parenchymal involvement, between unvaccinated patients affected by Alpha variant and vaccinated patients affected by Delta variant, and between unvaccinated patients with Delta variant and vaccinated patients with Delta variant.

Artificial Intelligence and COVID-19 Using Chest CT Scan and Chest X-ray Images: Machine Learning and Deep Learning Approaches for Diagnosis and Treatment

OBJECTIVE

To report an overview and update on Artificial Intelligence (AI) and COVID-19 using chest Computed Tomography (CT) scan and chest X-ray images (CXR). Machine Learning and Deep Learning Approaches for Diagnosis and Treatment were identified.

METHODS

Several electronic datasets were analyzed. The search covered the years from January 2019 to June 2021. The inclusion criteria were studied evaluating the use of AI methods in COVID-19 disease reporting performance results in terms of accuracy or precision or area under Receiver Operating Characteristic (ROC) curve (AUC).

RESULTS

Twenty-two studies met the inclusion criteria: 13 papers were based on AI in CXR and 10 based on AI in CT. The summarized mean value of the accuracy and precision of CXR in COVID-19 disease were 93.7% ± 10.0% of standard deviation (range 68.4-99.9%) and 95.7% ± 7.1% of standard deviation (range 83.0-100.0%), respectively. The summarized mean value of the accuracy and specificity of CT in COVID-19 disease were 89.1% ± 7.3% of standard deviation (range 78.0-99.9%) and 94.5 ± 6.4% of standard deviation (range 86.0-100.0%), respectively. No statistically significant difference in summarized accuracy mean value between CXR and CT was observed using the Chi square test (p value > 0.05).

CONCLUSIONS

Summarized accuracy of the selected papers is high but there was an important variability; however, less in CT studies compared to CXR studies. Nonetheless, AI approaches could be used in the identification of disease clusters, monitoring of cases, prediction of the future outbreaks, mortality risk, COVID-19 diagnosis, and disease management.