Mediastinal Hemangioma Masquerading as a Simple Cyst.

ABSTRACT: This report presents imaging from a mediastinal mass in a patient with colon cancer. At baseline and surveillance chest computed tomography examinations, it was characterized as a pericardial cyst. However, during chemotherapy, complications arose and this mass was further characterized with a chest MRI. It was then decided to be removed, and histopathology confirmed the diagnosis of a hemangioma.

Predictors of persistent symptoms after mRNA SARS-CoV-2 vaccine-related myocarditis (myovacc registry).

Aims: Epidemiological surveillance has raised safety concerns for mRNA SARS-CoV-2-vaccination-related myocarditis. We aimed to analyze epidemiological, clinical and imaging findings associated with clinical outcomes in these patients in an international multi-center registry (NCT05268458). Methods and results: Patients with clinical and CMR diagnosis of acute myocarditis within 30 days after mRNA SARS-CoV-2-vaccination were included from five centers in Canada and Germany between 05/21 and 01/22. Clinical follow-up on persistent symptoms was collected. We enrolled 59 patients (80% males, mean age 29 years) with CMR-derived mild myocarditis (hs-Troponin-T 552 [249-1,193] ng/L, CRP 28 [13-51] mg/L; LVEF 57 ± 7%, LGE 3 [2-5] segments). Most common symptoms at baseline were chest pain (92%) and dyspnea (37%). Follow-up data from 50 patients showed overall symptomatic burden improvement. However, 12/50 patients (24%, 75% females, mean age 37 years) reported persisting symptoms (median interval 228 days) of chest pain (n = 8/12, 67%), dyspnea (n = 7/12, 58%), with increasing occurrence of fatigue (n = 5/12, 42%) and palpitations (n = 2/12, 17%). These patients had initial lower CRP, lower cardiac involvement in CMR, and fewer ECG changes. Significant predictors of persisting symptoms were female sex and dyspnea at initial presentation. Initial severity of myocarditis was not associated with persisting complaints. Conclusion: A relevant proportion of patients with mRNA SARS-CoV-2-vaccination-related myocarditis report persisting complaints. While young males are usually affected, patients with persisting symptoms were predominantly females and older. The severity of the initial cardiac involvement not predicting these symptoms may suggest an extracardiac origin.

Host Expression Profiling From Diagnostic Coronavirus Disease 2019 Swabs Associates Upper Respiratory Tract Immune Responses With Radiologic Lung Pathology and Clinical Severity.

Background: COVID-19 presents with a breadth of symptomatology including a spectrum of clinical severity requiring intensive care unit (ICU) admission. We investigated the mucosal host gene response at the time of gold standard COVID-19 diagnosis using clinical surplus RNA from upper respiratory tract swabs. Methods: Host response was evaluated by RNA-sequencing, and transcriptomic profiles of 44 unvaccinated patients including outpatients and in-patients with varying levels of oxygen supplementation were included. Additionally, chest X-rays were reviewed and scored for patients in each group. Results: Host transcriptomics revealed significant changes in the immune and inflammatory response. Patients destined for the ICU were distinguished by the significant upregulation of immune response pathways and inflammatory chemokines, including cxcl2 which has been linked to monocyte subsets associated with COVID-19 related lung damage. In order to temporally associate gene expression profiles in the upper respiratory tract at diagnosis of COVID-19 with lower respiratory tract sequalae, we correlated our findings with chest radiography scoring, showing nasopharygeal or mid-turbinate sampling can be a relevant surrogate for downstream COVID-19 pneumonia/ICU severity. Conclusions: This study demonstrates the potential and relevance for ongoing study of the mucosal site of infection of SARS-CoV-2 using a single sampling that remains standard of care in hospital settings. We highlight also the archival value of high quality clinical surplus specimens, especially with rapidly evolving COVID-19 variants and changing public health/vaccination measures.

A Case of Idiopathic First Bite Syndrome, Possibly Linked to Type I Diabetes Mellitus.

We present a rare case of a 34-year-old male with poorly regulated type I diabetes and three-month history of excruciating pain in the right condylar process of the mandible, occurring only during the first bite of each meal. The patient had no history of surgery or trauma in the head and neck region. Clinical and imaging examination revealed no tumor or pathology deriving from the dentures, the temporomandibular joint (TMJ), or the salivary glands. Idiopathic first bite syndrome (FBS) was suspected and treated with pregabalin and glycemic control. This case highlights how a detailed pain history and clinical examination can lead to a rare diagnosis and indicates the potential involvement of diabetic neuropathy in idiopathic FBS, as well as the importance of glycemic regulation in treatment.

Robust framework for COVID-19 identication from a multicenter dataset of chest CT scans.

The main objective of this study is to develop a robust deep learning-based framework to distinguish COVID-19, Community-Acquired Pneumonia (CAP), and Normal cases based on volumetric chest CT scans, which are acquired in different imaging centers using different scanners and technical settings. We demonstrated that while our proposed model is trained on a relatively small dataset acquired from only one imaging center using a specific scanning protocol, it performs well on heterogeneous test sets obtained by multiple scanners using different technical parameters. We also showed that the model can be updated via an unsupervised approach to cope with the data shift between the train and test sets and enhance the robustness of the model upon receiving a new external dataset from a different center. More specifically, we extracted the subset of the test images for which the model generated a confident prediction and used the extracted subset along with the training set to retrain and update the benchmark model (the model trained on the initial train set). Finally, we adopted an ensemble architecture to aggregate the predictions from multiple versions of the model. For initial training and development purposes, an in-house dataset of 171 COVID-19, 60 CAP, and 76 Normal cases was used, which contained volumetric CT scans acquired from one imaging center using a single scanning protocol and standard radiation dose. To evaluate the model, we collected four different test sets retrospectively to investigate the effects of the shifts in the data characteristics on the model's performance. Among the test cases, there were CT scans with similar characteristics as the train set as well as noisy low-dose and ultra-low-dose CT scans. In addition, some test CT scans were obtained from patients with a history of cardiovascular diseases or surgeries. This dataset is referred to as the "SPGC-COVID" dataset. The entire test dataset used in this study contains 51 COVID-19, 28 CAP, and 51 Normal cases. Experimental results indicate that our proposed framework performs well on all test sets achieving total accuracy of 96.15% (95%CI: [91.25-98.74]), COVID-19 sensitivity of 96.08% (95%CI: [86.54-99.5]), CAP sensitivity of 92.86% (95%CI: [76.50-99.19]), Normal sensitivity of 98.04% (95%CI: [89.55-99.95]) while the confidence intervals are obtained using the significance level of 0.05. The obtained AUC values (One class vs Others) are 0.993 (95%CI: [0.977-1]), 0.989 (95%CI: [0.962-1]), and 0.990 (95%CI: [0.971-1]) for COVID-19, CAP, and Normal classes, respectively. The experimental results also demonstrate the capability of the proposed unsupervised enhancement approach in improving the performance and robustness of the model when being evaluated on varied external test sets.

Detection of solid and subsolid pulmonary nodules with lung MRI: performance of UTE, T1 gradient-echo, and single-shot T2 fast spin echo.

BACKGROUND: Although MRI is a radiation-free imaging modality, it has historically been limited in lung imaging due to inherent technical restrictions. The aim of this study is to explore the performance of lung MRI in detecting solid and subsolid pulmonary nodules using T1 gradient-echo (GRE) (VIBE, Volumetric interpolated breath-hold examination), ultrashort time echo (UTE) and T2 Fast Spin Echo (HASTE, Half fourier Single-shot Turbo spin-Echo). METHODS: Patients underwent a lung MRI in a 3 T scanner as part of a prospective research project. A baseline Chest CT was obtained as part of their standard of care. Nodules were identified and measured on the baseline CT and categorized according to their density (solid and subsolid) and size (> 4 mm/ ≤ 4 mm). Nodules seen on the baseline CT were classified as present or absent on the different MRI sequences by two thoracic radiologists independently. Interobserver agreement was determined using the simple Kappa coefficient. Paired differences were compared using nonparametric Mann-Whitney U tests. The McNemar test was used to evaluate paired differences in nodule detection between MRI sequences. RESULTS: Thirty-six patients were prospectively enrolled. One hundred forty-nine nodules (100 solid/49 subsolid) with mean size 10.8 mm (SD = 9.4) were included in the analysis. There was substantial interobserver agreement (k = 0.7, p = 0.05). Detection for all nodules, solid and subsolid nodules was respectively; UTE: 71.8%/71.0%/73.5%; VIBE: 61.6%/65%/55.1%; HASTE 72.4%/72.2%/72.7%. Detection rate was higher for nodules > 4 mm in all groups: UTE 90.2%/93.4%/85.4%, VIBE 78.4%/88.5%/63.4%, HASTE 89.4%/93.8%/83.8%. Detection of lesions ≤4 mm was low for all sequences. UTE and HASTE performed significantly better than VIBE for detection of all nodules and subsolid nodules (diff = 18.4 and 17.6%, p = < 0.01 and p = 0.03, respectively). There was no significant difference between UTE and HASTE. There were no significant differences amongst MRI sequences for solid nodules. CONCLUSIONS: Lung MRI shows adequate performance for the detection of solid and subsolid pulmonary nodules larger than 4 mm and can serve as a promising radiation-free alternative to CT.

TAVR in a Patient With Anomalous Origin and Course of the Left Main Coronary Artery.

In patients with anomalous coronary arteries with high-risk features, corrective cardiac surgery should be considered. We report the first case of transcatheter aortic valve replacement using a self-expanding Evolut valve, in a patient with a single coronary artery arising from the right coronary cusp and an intramural course of the left main. (Level of Difficulty: Intermediate.).

CT patterns and serial CT Changes in lung Cancer patients post stereotactic body radiotherapy (SBRT).

BACKGROUND: To evaluate computed tomography (CT) patterns of post-SBRT lung injury in lung cancer and identify time points of serial CT changes. MATERIALS AND METHODS: One hundred eighty-three tumors in 170 patients were evaluated on sequential CTs within 29 months (median). Frequencies of post-SBRT CT patterns and time points of initiation and duration were assessed. Duration of increase of primary lesion or surrounding injury without evidence of local recurrence and time to stabilization or local recurrence were evaluated. RESULTS: Post-SBRT CT patterns could overlap in the same patient and were nodule-like pattern (69%), consolidation with ground glass opacity (GGO) (41%), modified conventional pattern (39%), peribronchial/patchy consolidation (42%), patchy GGO (24%), diffuse consolidation (16%), "orbit sign" (21%), mass-like pattern (19%), scar-like pattern (15%) and diffuse GGO (3%). Patchy GGO started at 4 months post-SBRT. Peribronchial/patchy consolidation and consolidation with GGO started at 4 and 5 months respectively. Diffuse consolidation, diffuse GGO and orbit sign started at 5, 6 and 8 months respectively. Mass-like, modified conventional and scar-like pattern started at 8, 12 and 12 months respectively. Primary lesion (n = 11) or surrounding injury (n = 85) increased up to 13 months. Primary lesion (n = 119) or surrounding injury (n = 115) started to decrease at 4 and 9 months respectively. Time to stabilization was 20 months. The most common CT pattern at stabilization was modified conventional pattern (49%), scar-like pattern (23%) and mass-like pattern (12%). Local recurrence (n = 15) occurred at a median time of 18 months. CONCLUSION: Different CT patterns of lung injury post-SBRT appear in predictable time points and have variable but predictable duration. Familiarity with these patterns and timeframes of appearance helps differentiate them from local recurrence.

Human-level COVID-19 diagnosis from low-dose CT scans using a two-stage time-distributed capsule network.

Reverse transcription-polymerase chain reaction is currently the gold standard in COVID-19 diagnosis. It can, however, take days to provide the diagnosis, and false negative rate is relatively high. Imaging, in particular chest computed tomography (CT), can assist with diagnosis and assessment of this disease. Nevertheless, it is shown that standard dose CT scan gives significant radiation burden to patients, especially those in need of multiple scans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT) scan protocols that reduce the radiation exposure close to that of a single X-ray, while maintaining an acceptable resolution for diagnosis purposes. Since thoracic radiology expertise may not be widely available during the pandemic, we develop an Artificial Intelligence (AI)-based framework using a collected dataset of LDCT/ULDCT scans, to study the hypothesis that the AI model can provide human-level performance. The AI model uses a two stage capsule network architecture and can rapidly classify COVID-19, community acquired pneumonia (CAP), and normal cases, using LDCT/ULDCT scans. Based on a cross validation, the AI model achieves COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text], and accuracy of [Formula: see text]. By incorporating clinical data (demographic and symptoms), the performance further improves to COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text] , and accuracy of [Formula: see text]. The proposed AI model achieves human-level diagnosis based on the LDCT/ULDCT scans with reduced radiation exposure. We believe that the proposed AI model has the potential to assist the radiologists to accurately and promptly diagnose COVID-19 infection and help control the transmission chain during the pandemic.

COVID-rate: an automated framework for segmentation of COVID-19 lesions from chest CT images.

Novel Coronavirus disease (COVID-19) is a highly contagious respiratory infection that has had devastating effects on the world. Recently, new COVID-19 variants are emerging making the situation more challenging and threatening. Evaluation and quantification of COVID-19 lung abnormalities based on chest Computed Tomography (CT) images can help determining the disease stage, efficiently allocating limited healthcare resources, and making informed treatment decisions. During pandemic era, however, visual assessment and quantification of COVID-19 lung lesions by expert radiologists become expensive and prone to error, which raises an urgent quest to develop practical autonomous solutions. In this context, first, the paper introduces an open-access COVID-19 CT segmentation dataset containing 433 CT images from 82 patients that have been annotated by an expert radiologist. Second, a Deep Neural Network (DNN)-based framework is proposed, referred to as the [Formula: see text], that autonomously segments lung abnormalities associated with COVID-19 from chest CT images. Performance of the proposed [Formula: see text] framework is evaluated through several experiments based on the introduced and external datasets. Third, an unsupervised enhancement approach is introduced that can reduce the gap between the training set and test set and improve the model generalization. The enhanced results show a dice score of 0.8069 and specificity and sensitivity of 0.9969 and 0.8354, respectively. Furthermore, the results indicate that the [Formula: see text] model can efficiently segment COVID-19 lesions in both 2D CT images and whole lung volumes. Results on the external dataset illustrate generalization capabilities of the [Formula: see text] model to CT images obtained from a different scanner.

Survival analysis in lung cancer patients with interstitial lung disease.

OBJECTIVE: Lung cancer patients with interstitial lung disease (ILD) are prone for higher morbidity and mortality and their treatment is challenging. The purpose of this study is to investigate whether the survival of lung cancer patients is affected by the presence of ILD documented on CT. MATERIALS AND METHODS: 146 patients with ILD at initial chest CT were retrospectively included in the study. 146 lung cancer controls without ILD were selected. Chest CTs were evaluated for the presence of pulmonary fibrosis which was classified in 4 categories. Presence and type of emphysema, extent of ILD and emphysema, location and histologic type of cancer, clinical staging and treatment were evaluated. Kaplan-Meier estimates and Cox regression models were used to assess survival probability and hazard of death of different groups. P value < 0.05 was considered significant. RESULTS: 5-year survival for the study group was 41% versus 48% for the control group (log-rank test p = 0.0092). No significant difference in survival rate was found between the four different categories of ILD (log-rank test, p = 0.195) and the different histologic types (log-rank test, p = 0.4005). A cox proportional hazard model was used including presence of ILD, clinical stage and age. The hazard of death among patients with ILD was 1.522 times that among patients without ILD (95%CI, p = 0.029). CONCLUSION: Patients with lung cancer and CT evidence of ILD have a significantly shorter survival compared to patients with lung cancer only. Documenting the type and grading the severity of ILD in lung cancer patients will significantly contribute to their challenging management.

Right Ventricular Function at Cardiac MRI Predicts Cardiovascular Events in Patients with an Implantable Cardioverter-Defibrillator.

Background Right ventricular ejection fraction (RVEF) is an independent predictor of death and adverse cardiovascular outcomes in patients with various cardiac conditions. Purpose To investigate whether RVEF, measured with cardiac MRI, is a predictor of appropriate shock or death in implantable cardioverter-defibrillator (ICD) recipients for primary and secondary prevention of sudden cardiac death. Materials and Methods This retrospective, multicenter, observational study included patients who underwent cardiac MRI before ICD implantation between January 2007 and May 2017. Right ventricular end-diastolic and end-systolic volumes and RVEF were measured with cardiac MRI. The primary end point was a composite of all-cause mortality or appropriate ICD shock. The secondary end point was all-cause mortality. The association between RVEF and primary and secondary outcomes was evaluated by using multivariable Cox regression analysis. Potential interactions were tested between primary prevention, ischemic cause, left ventricular ejection fraction (LVEF), and RVEF. Results Among 411 patients (mean age ± standard deviation, 60 years; 315 men) during a median follow-up of 63 months, 143 (35%) patients experienced an appropriate ICD shock or died. In univariable analysis, lower RVEF was associated with greater risks for appropriate ICD shock or death and for death alone (log-rank trend test, P = .003 and .005 respectively). In multivariable Cox regression analysis adjusting for age at ICD implantation, LVEF, ICD indication (primary vs secondary), ischemic heart disease, and late gadolinium enhancement, RVEF was an independent predictor of the primary outcome (hazard ratio [HR], 1.21 per 10% lower RVEF; 95% CI: 1.04, 1.41; P = .01) and all-cause mortality (HR, 1.25 per 10% lower RVEF; 95% CI: 1.01, 1.55; P = .04). No evidence of significant interactions was found between RVEF and primary or secondary prevention (P = .49), ischemic heart disease (P = .78), and LVEF (P = .29). Conclusion Right ventricular ejection fraction measured with cardiac MRI was a predictor of appropriate implantable cardioverter-defibrillator shock or death. © RSNA, 2021 See also the editorial by Nazarian and Zghaib in this issue. An earlier incorrect version of this article appeared online. This article was corrected on August 24, 2021.

COVID-FACT: A Fully-Automated Capsule Network-Based Framework for Identification of COVID-19 Cases from Chest CT Scans.

The newly discovered Coronavirus Disease 2019 (COVID-19) has been globally spreading and causing hundreds of thousands of deaths around the world as of its first emergence in late 2019. The rapid outbreak of this disease has overwhelmed health care infrastructures and arises the need to allocate medical equipment and resources more efficiently. The early diagnosis of this disease will lead to the rapid separation of COVID-19 and non-COVID cases, which will be helpful for health care authorities to optimize resource allocation plans and early prevention of the disease. In this regard, a growing number of studies are investigating the capability of deep learning for early diagnosis of COVID-19. Computed tomography (CT) scans have shown distinctive features and higher sensitivity compared to other diagnostic tests, in particular the current gold standard, i.e., the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Current deep learning-based algorithms are mainly developed based on Convolutional Neural Networks (CNNs) to identify COVID-19 pneumonia cases. CNNs, however, require extensive data augmentation and large datasets to identify detailed spatial relations between image instances. Furthermore, existing algorithms utilizing CT scans, either extend slice-level predictions to patient-level ones using a simple thresholding mechanism or rely on a sophisticated infection segmentation to identify the disease. In this paper, we propose a two-stage fully automated CT-based framework for identification of COVID-19 positive cases referred to as the "COVID-FACT". COVID-FACT utilizes Capsule Networks, as its main building blocks and is, therefore, capable of capturing spatial information. In particular, to make the proposed COVID-FACT independent from sophisticated segmentations of the area of infection, slices demonstrating infection are detected at the first stage and the second stage is responsible for classifying patients into COVID and non-COVID cases. COVID-FACT detects slices with infection, and identifies positive COVID-19 cases using an in-house CT scan dataset, containing COVID-19, community acquired pneumonia, and normal cases. Based on our experiments, COVID-FACT achieves an accuracy of 90.82 % , a sensitivity of 94.55 % , a specificity of 86.04 % , and an Area Under the Curve (AUC) of 0.98, while depending on far less supervision and annotation, in comparison to its counterparts.

COVID-CT-MD, COVID-19 computed tomography scan dataset applicable in machine learning and deep learning.

Novel Coronavirus (COVID-19) has drastically overwhelmed more than 200 countries affecting millions and claiming almost 2 million lives, since its emergence in late 2019. This highly contagious disease can easily spread, and if not controlled in a timely fashion, can rapidly incapacitate healthcare systems. The current standard diagnosis method, the Reverse Transcription Polymerase Chain Reaction (RT- PCR), is time consuming, and subject to low sensitivity. Chest Radiograph (CXR), the first imaging modality to be used, is readily available and gives immediate results. However, it has notoriously lower sensitivity than Computed Tomography (CT), which can be used efficiently to complement other diagnostic methods. This paper introduces a new COVID-19 CT scan dataset, referred to as COVID-CT-MD, consisting of not only COVID-19 cases, but also healthy and participants infected by Community Acquired Pneumonia (CAP). COVID-CT-MD dataset, which is accompanied with lobe-level, slice-level and patient-level labels, has the potential to facilitate the COVID-19 research, in particular COVID-CT-MD can assist in development of advanced Machine Learning (ML) and Deep Neural Network (DNN) based solutions.

Canadian Society of Thoracic Radiology/Canadian Association of Radiologists Clinical Practice Guidance for Non-Vascular Thoracic MRI.

Historically thoracic MRI has been limited by the lower proton density of lung parenchyma, cardiac and respiratory motion artifacts and long acquisition times. Recent technological advancements in MR hardware systems and improvement in MR pulse sequences have helped overcome these limitations and expand clinical opportunities for non-vascular thoracic MRI. Non-vascular thoracic MRI has been established as a problem-solving imaging modality for characterization of thymic, mediastinal, pleural chest wall and superior sulcus tumors and for detection of endometriosis. It is increasingly recognized as a powerful imaging tool for detection and characterization of lung nodules and for assessment of lung cancer staging. The lack of ionizing radiation makes thoracic MRI an invaluable imaging modality for young patients, pregnancy and for frequent serial follow-up imaging. Lack of familiarity and exposure to non-vascular thoracic MRI and lack of consistency in existing MRI protocols have called for clinical practice guidance. The purpose of this guide, which was developed by the Canadian Society of Thoracic Radiology and endorsed by the Canadian Association of Radiologists, is to familiarize radiologists, other interested clinicians and MR technologists with common and less common clinical indications for non-vascular thoracic MRI, discuss the fundamental imaging findings and focus on basic and more advanced MRI sequences tailored to specific clinical questions.

Radiological, epidemiological and clinical patterns of pulmonary viral infections.

Respiratory viruses are the most common causes of acute respiratory infections. However, identification of the underlying viral pathogen may not always be easy. Clinical presentations of respiratory viral infections usually overlap and may mimic those of diseases caused by bacteria. However, certain imaging morphologic patterns may suggest a particular viral pathogen as the cause of the infection. Although definitive diagnosis cannot be made on the basis of clinical or imaging features alone, the use of a combination of clinical and radiographic findings can substantially improve the accuracy of diagnosis. The purpose of this review is to present the clinical, epidemiological and radiological patterns of lower respiratory tract viral pathogens providing a comprehensive approach for their diagnosis and identification in hospitals and community outbreaks.

Pathological entities that may affect the lungs and the myocardium. Evaluation with chest CT and cardiac MR.

Certain entities may simultaneously involve the lungs and the myocardium. Knowing their cardiac and thoracic manifestations enhances the understanding of those conditions and increases awareness and suspicion for possible concurrent cardiothoracic involvement. Entities that can present with pulmonary and myocardial involvement include infiltrative diseases like sarcoidosis and amyloidosis, eosinophil-associated conditions including eosinophilic granulomatosis with polyangiitis (EGPA) and hypereosinophilic syndrome (HES), connective tissue diseases such as systemic sclerosis (SSc) and lupus erythematosus and genetic disorders like Fabry disease (FD). Lung involvement in sarcoidosis is almost universal. While cardiac involvement is less common, concurrent cardiothoracic involvement can often be seen. Pulmonary amyloidosis is more often a localized process and generally occurs separately from cardiac involvement, except for diffuse alveolar-septal amyloidosis. EGPA and HES can present with consolidative or ground glass opacities, cardiac inflammation and endomyocardial fibrosis. Manifestations of SSc include interstitial lung disease, pulmonary hypertension and cardiomyopathy. Lupus can present with serositis, pneumonitis and cardiac inflammation. FD causes left ventricular thickening and fibrosis, and small airways disease. This article aims to review the clinicopathological features of chest and cardiac involvement of these entities and describe their main findings on chest CT and cardiac MR.

COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images.

Novel Coronavirus disease (COVID-19) has abruptly and undoubtedly changed the world as we know it at the end of the 2nd decade of the 21st century. COVID-19 is extremely contagious and quickly spreading globally making its early diagnosis of paramount importance. Early diagnosis of COVID-19 enables health care professionals and government authorities to break the chain of transition and flatten the epidemic curve. The common type of COVID-19 diagnosis test, however, requires specific equipment and has relatively low sensitivity. Computed tomography (CT) scans and X-ray images, on the other hand, reveal specific manifestations associated with this disease. Overlap with other lung infections makes human-centered diagnosis of COVID-19 challenging. Consequently, there has been an urgent surge of interest to develop Deep Neural Network (DNN)-based diagnosis solutions, mainly based on Convolutional Neural Networks (CNNs), to facilitate identification of positive COVID-19 cases. CNNs, however, are prone to lose spatial information between image instances and require large datasets. The paper presents an alternative modeling framework based on Capsule Networks, referred to as the COVID-CAPS, being capable of handling small datasets, which is of significant importance due to sudden and rapid emergence of COVID-19. Our results based on a dataset of X-ray images show that COVID-CAPS has advantage over previous CNN-based models. COVID-CAPS achieved an Accuracy of 95.7%, Sensitivity of 90%, Specificity of 95.8%, and Area Under the Curve (AUC) of 0.97, while having far less number of trainable parameters in comparison to its counterparts. To potentially and further improve diagnosis capabilities of the COVID-CAPS, pre-training and transfer learning are utilized based on a new dataset constructed from an external dataset of X-ray images. This is in contrary to existing works on COVID-19 detection where pre-training is performed based on natural images. Pre-training with a dataset of similar nature further improved accuracy to 98.3% and specificity to 98.6%.

Assessing invasiveness of subsolid lung adenocarcinomas with combined attenuation and geometric feature models.

The aim of this study was to develop and test multiclass predictive models for assessing the invasiveness of individual lung adenocarcinomas presenting as subsolid nodules on computed tomography (CT). 227 lung adenocarcinomas were included: 31 atypical adenomatous hyperplasia and adenocarcinomas in situ (class H1), 64 minimally invasive adenocarcinomas (class H2) and 132 invasive adenocarcinomas (class H3). Nodules were segmented, and geometric and CT attenuation features including functional principal component analysis features (FPC1 and FPC2) were extracted. After a feature selection step, two predictive models were built with ordinal regression: Model 1 based on volume (log) (logarithm of the nodule volume) and FPC1, and Model 2 based on volume (log) and Q.875 (CT attenuation value at the 87.5% percentile). Using the 200-repeats Monte-Carlo cross-validation method, these models provided a multiclass classification of invasiveness with discriminative power AUCs of 0.83 to 0.87 and predicted the class probabilities with less than a 10% average error. The predictive modelling approach adopted in this paper provides a detailed insight on how the value of the main predictors contribute to the probability of nodule invasiveness and underlines the role of nodule CT attenuation features in the nodule invasiveness classification.

[Formula: see text]: deep learning-based radiomics for the time-to-event outcome prediction in lung cancer.

Hand-crafted radiomics has been used for developing models in order to predict time-to-event clinical outcomes in patients with lung cancer. Hand-crafted features, however, are pre-defined and extracted without taking the desired target into account. Furthermore, accurate segmentation of the tumor is required for development of a reliable predictive model, which may be objective and a time-consuming task. To address these drawbacks, we propose a deep learning-based radiomics model for the time-to-event outcome prediction, referred to as DRTOP that takes raw images as inputs, and calculates the image-based risk of death or recurrence, for each patient. Our experiments on an in-house dataset of 132 lung cancer patients show that the obtained image-based risks are significant predictors of the time-to-event outcomes. Computed Tomography (CT)-based features are predictors of the overall survival (OS), with the hazard ratio (HR) of 1.35, distant control (DC), with HR of 1.06, and local control (LC), with HR of 2.66. The Positron Emission Tomography (PET)-based features are predictors of OS and recurrence free survival (RFS), with hazard ratios of 1.67 and 1.18, respectively. The concordance indices of [Formula: see text], [Formula: see text], and [Formula: see text] for predicting the OS, DC, and RFS show that the deep learning-based radiomics model is as accurate or better in predicting predefined clinical outcomes compared to hand-crafted radiomics, with concordance indices of [Formula: see text], [Formula: see text], and [Formula: see text], for predicting the OS, DC, and RFS, respectively. Deep learning-based radiomics has the potential to offer complimentary predictive information in the personalized management of lung cancer patients.