Full head-to-head comparison of ultrasonography and CT scan in volumetric quantification of pleural effusion: a systematic review and meta-analysis.

Pleural effusion is a very common clinical finding. Quantifying pleural effusion volume and its response to treatment over time has become increasingly important for clinicians, which is currently performed via computed tomography (CT) or drainage. To determine and compare ultrasonography (US), CT, and drainage agreements in pleural effusion volumetry. Protocol pre-registration was performed a priori at ( https://osf.io/rnugd/ ). We searched PubMed, Web of Science, Embase, and Cochrane Library for studies up to January 7, 2024. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), QUADAS-C, and Consensus-based Standards for the selection of health Measurement Instruments (COSMIN). Volumetric performances of CT, US, and drainage in assessment of pleural effusion volume were evaluated through both aggregated data (AD) and individual participant data (IPD) analyses. Certainty of evidence was evaluated using Grading of Recommendations, Assessment, Development, and Evaluations (GRADE). Six studies were included with 446 pleural effusion lesions. AD results showed a perfect level of agreement with pooled Pearson correlation and intraclass correlation coefficient (ICC) of 0.933 and 0.948 between US and CT. IPD results demonstrated a high level of agreement between US and CT, with Finn's coefficient, ICC, concordance correlation coefficient (CCC), and Pearson correlation coefficient values of 0.856, 0.855, 0.854, and 0.860, respectively. Also, both results showed an overall perfect level of agreement between US and drainage. As for comparing the three combinations, US vs. CT and US vs. drainage were both superior to CT vs. drainage, suggesting the US is a good option for pleural effusion volumetric assessment. Ultrasound provides a highly reliable, to-the-point, cost-effective, and noninvasive method for the assessment of pleural effusion volume and is a great alternative to CT or drainage.

Enhanced staging of extrahepatic hepatocellular carcinoma metastasis through dual-tracer PET/computed tomography: a systematic review and meta-analysis.

The aim of this study was to quantify the diagnostic value of dual-tracer PET/computed tomography (CT) with 11C-acetate and fluorodeoxyglucose (FDG) in per-lesion and per-patient and its effect on clinical decision-making for choosing the most appropriate management. The study protocol is registered a priori at https://osf.io/rvm75/. PubMed, Web of Science, Embase, and Cochrane Library were searched for relevant studies until 1 June 2023. Studies regarding the review question were included. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to assess bias risk. Per-lesion and per-patient diagnostic performance were calculated for: (1) 11C-acetate alone; (2) FDG alone; and (3) dual tracer of 11C-acetate and FDG. A direct comparison of these three combinations was made. The possible sources of statistical heterogeneity were also examined. We also calculated the percentage change in clinical decision-making when dual-tracer PET/CT was added to conventional imaging routinely used for metastatic evaluation (CT/MRI). Grading of Recommendations, Assessment, Development, and Evaluations tool was used to evaluate the certainty of evidence. Eight studies including 521 patients and 672 metastatic lesions were included. Dual-tracer PET/CT had a per-lesion sensitivity of 96.3% [95% confidence interval (CI), 91.8-98.4%] and per-patient sensitivity of 95.5% (95% CI, 89.1-98.2%) which were highly superior to either of tracers alone. Per-patient specificity was 98.5% (84.1-99.9%) which was similar to either of tracers alone. Overall, 9.3% (95% CI, 4.7-13.9%) of the patients had their management beneficially altered by adding dual-tracer PET/CT to their conventional CT/MRI results. Dual-tracer PET/CT substantially outperforms single-tracer methods in detecting extrahepatic hepatocellular carcinoma metastases, evidencing its reliability and significant role in refining clinical management strategies based on robust diagnostic performance.

AdaRes: A deep learning-based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies.

PURPOSE: The quality of ultrasound images is degraded by speckle and Gaussian noises. This study aims to develop a deep-learning (DL)-based filter for ultrasound image denoising. METHODS: A novel DL-based filter using adaptive residual (AdaRes) learning was proposed. Five image quality metrics (IQMs) and 27 radiomics features were used to evaluate denoising results. The effect of our proposed filter, AdaRes, on four pre-trained convolutional neural network (CNN) classification models and three radiologists was assessed. RESULTS: AdaRes filter was tested on both natural and ultrasound image databases. IQMs results indicate that AdaRes could remove noises in three different noise levels with the highest performances. In addition, a radiomics study proved that AdaRes did not distort tissue textures and it could preserve most radiomics features. AdaRes could also improve the performance classification using CNNs in different settings. Finally, AdaRes also improved the mean overall performance (AUC) of three radiologists from 0.494 to 0.702 in the classification of benign and malignant lesions. CONCLUSIONS: AdaRes filtered out noises on ultrasound images more effectively and can be used as an auxiliary preprocessing step in computer-aided diagnosis systems. Radiologists may use it to remove unwanted noises and improve the ultrasound image quality before the interpretation.

Deep Radiomics Features of Median Nerves for Automated Diagnosis of Carpal Tunnel Syndrome With Ultrasound Images: A Multi-Center Study.

OBJECTIVES: Ultrasound is widely used in diagnosing carpal tunnel syndrome (CTS). However, the limitations of ultrasound in CTS detection are the lack of objective measures in the detection of nerve abnormality and the operator-dependent nature of ultrasound imaging. Therefore, in this study, we developed and proposed externally validated artificial intelligence (AI) models based on deep-radiomics features. METHODS: We have used 416 median nerves from 2 countries (Iran and Colombia) for the development (112 entrapped and 112 normal nerves from Iran) and validation (26 entrapped and 26 normal nerves from Iran, and 70 entrapped and 70 normal nerves from Columbia) of our models. Ultrasound images were fed to the SqueezNet architecture to extract deep-radiomics features. Then a ReliefF method was used to select the clinically significant features. The selected deep-radiomics features were fed to 9 common machine-learning algorithms to choose the best-performing classifier. The 2 best-performing AI models were then externally validated. RESULTS: Our developed model achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.910 (88.46% sensitivity, 88.46% specificity) and 0.908 (84.62% sensitivity, 88.46% specificity) with support vector machine and stochastic gradient descent (SGD), respectively using the internal validation dataset. Furthermore, both models consistently performed well in the external validation dataset, and achieved an AUC of 0.890 (85.71% sensitivity, 82.86% specificity) and 0.890 (84.29% sensitivity and 82.86% specificity), with SVM and SGD models, respectively. CONCLUSION: Our proposed AI models fed with deep-radiomics features performed consistently with internal and external datasets. This justifies that our proposed system can be employed for clinical use in hospitals and polyclinics.

An open-access breast lesion ultrasound image database : Applicable in artificial intelligence studies.

Breast cancer is one of the largest single contributors to the burden of disease worldwide. Early detection of breast cancer has been shown to be associated with better overall clinical outcomes. Ultrasonography is a vital imaging modality in managing breast lesions. In addition, the development of computer-aided diagnosis (CAD) systems has further enhanced the importance of this imaging modality. Proper development of robust and reproducible CAD systems depends on the inclusion of different data from different populations and centers to considerate all variations in breast cancer pathology and minimize confounding factors. The current database contains ultrasound images and radiologist-defined masks of two sets of histologically proven benign and malignant lesions. Using this and similar pieces of data can aid in the development of robust CAD systems.

Diagnosis of Metastatic Lymph Nodes in Patients With Papillary Thyroid Cancer: A Comparative Multi-Center Study of Semantic Features and Deep Learning-Based Models.

OBJECTIVES: Deep learning algorithms have shown potential in streamlining difficult clinical decisions. In the present study, we report the diagnostic profile of a deep learning model in differentiating malignant and benign lymph nodes in patients with papillary thyroid cancer. METHODS: An in-house deep learning-based model called "ClymphNet" was developed and tested using two datasets containing ultrasound images of 195 malignant and 178 benign lymph nodes. An expert radiologist also viewed these ultrasound images and extracted qualitative imaging features used in routine clinical practice. These signs were used to train three different machine learning algorithms. Then the deep learning model was compared with the machine learning models on internal and external validation datasets containing 22 and 82 malignant and 20 and 76 benign lymph nodes, respectively. RESULTS: Among the three machine learning algorithms, the support vector machine model (SVM) outperformed the best, reaching a sensitivity of 91.35%, specificity of 88.54%, accuracy of 90.00%, and an area under the curve (AUC) of 0.925 in all cohorts. The ClymphNet performed better than the SVM protocol in internal and external validation, achieving a sensitivity of 93.27%, specificity of 92.71%, and an accuracy of 93.00%, and an AUC of 0.948 in all cohorts. CONCLUSION: A deep learning model trained with ultrasound images outperformed three conventional machine learning algorithms fed with qualitative imaging features interpreted by radiologists. Our study provides evidence regarding the utility of ClymphNet in the early and accurate differentiation of benign and malignant lymphadenopathy.

Artificial intelligence, BI-RADS evaluation and morphometry: A novel combination to diagnose breast cancer using ultrasonography, results from multi-center cohorts.

PURPOSE: To develop and validate a machine learning (ML) model for the classification of breast lesions on ultrasound images. METHOD: In the present study, three separate data cohorts containing 1288 breast lesions from three countries (Malaysia, Iran, and Turkey) were utilized for MLmodel development and external validation. The model was trained on ultrasound images of 725 breast lesions, and validation was done separately on the remaining data. An expert radiologist and a radiology resident classified the lesions based on the BI-RADS lexicon. Thirteen morphometric features were selected from a contour of the lesion and underwent a three-step feature selection process. Five features were chosen to be fed into the model separately and combined with the imaging signs mentioned in the BI-RADS reference guide. A support vector classifier was trained and optimized. RESULTS: The diagnostic profile of the model with various input data was compared to the expert radiologist and radiology resident. The agreement of each approach with histopathologic specimens was also determined. Based on BI-RADS and morphometric features, the model achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.885, which is higher than the expert radiologist and radiology resident performances with AUC of 0.814 and 0.632, respectively in all cohorts. DeLong's test also showed that the AUC of the ML protocol was significantly different from that of the expert radiologist (ΔAUCs = 0.071, 95%CI: (0.056, 0.086), P = 0.005). CONCLUSIONS: These results support the possible role of morphometric features in enhancing the already well-excepted classification schemes.

Effect of Convalescent Plasma Therapy on Clinical Improvement of COVID-19 Patients: A Randomized Clinical Trial.

Background: Due to the critical condition of COVID-19, it is necessary to evaluate the efficacy of administrating convalescent plasma to COVID-19 patients. Therefore, we decided to design a clinical trial to investigate the effect of convalescent plasma of patients recovered from COVID-19 on the treatment outcome of COVID-19-infected patients. Materials and Methods: In this parallel randomized controlled clinical trial, patients in the intervention group received standard treatment plus convalescent plasma of patients recovered from COVID-19. We allocated 60 patients to each treatment group through balanced block randomization. Then, COVID-19 outcomes, vital signs, and biochemical parameters were compared between the two treatment groups by the independent t test and ANCOVA. Results: The mean age (SD) of the patients in the intervention and standard treatment groups was 52.84 (15.77) and 55.15 (14.34) years, respectively. Although patients in the intervention group reported more hospitalization days (11.45±5.86 vs. 10.42±6.79), death rates (26.67% vs. 18.13%), ICU admission (45 vs. 41.67%), and ARDS (11.67% vs. 3.33%), these differences were not statistically significant (P>0.05). Moreover, the two groups were homogenous in vital signs and biochemical parameters before and after treatment (P>0.05). Conclusion: The present study indicated that convalescent plasma therapy has no significant effect on the survival, hospitalization, and ICU admission of COVID-19 patients.

Tumor Microenvironment, Radiology, and Artificial Intelligence: Should We Consider Tumor Periphery?

OBJECTIVES: The tumor microenvironment (TME) consists of cellular and noncellular components which enable the tumor to interact with its surroundings and plays an important role in the tumor progression and how the immune system reacts to the malignancy. In the present study, we investigate the diagnostic potential of the TME in differentiating benign and malignant lesions using image quantification and machine learning. METHODS: A total of 229 breast lesions and 220 cervical lymph nodes were included in the study. A group of expert radiologists first performed medical imaging and segmented the lesions, after which a rectangular mask was drawn, encompassing all of the contouring. The mask was extended in each axis up to 50%, and 29 radiomics features were extracted from each mask. Radiomics features that showed a significant difference in each contour were used to develop a support vector machine (SVM) classifier for benign and malignant lesions in breast and lymph node images separately. RESULTS: Single radiomics features extracted from extended contours outperformed radiologists' contours in both breast and lymph node lesions. Furthermore, when fed into the SVM model, the extended models also outperformed the radiologist's contour, achieving an area under the receiver operating characteristic curve of 0.887 and 0.970 in differentiating breast and lymph node lesions, respectively. CONCLUSIONS: Our results provide convincing evidence regarding the importance of the tumor periphery and TME in medical imaging diagnosis. We propose that the immediate tumor periphery should be considered for differentiating benign and malignant lesions in image quantification studies.

Radiofrequency ablation of parathyroid adenomas causing primary hyperparathyroidism: A report of 27 patients.

PURPOSE: To study treatment outcome of parathyroid adenomas using ultrasound-guided radiofrequency ablation. METHODS: Twenty-seven patients with a single adenoma of the parathyroid gland were included in the study. Using color Doppler ultrasonography, the lesion and its characteristics were determined, and dextrose was injected to dissect the gland from the surrounding structures. The ablation process was done with 6-12 watts of power. RESULTS: No complications were seen in any of the subjects. A significant reduction was seen in serum parathyroid hormone (PTH) and calcium levels after treatment. PTH levels showed a median decrease of 13.8%, and a median decrease of 8.2% was seen in serum calcium levels (p < 0.001). Phosphorus levels did not change significantly after treatment. In 1-month follow-up of patients, the lesion size had decreased considerably. In long-term follow-up, 11 of 20 patients having subsequent imaging had indistinguishable lesions. CONCLUSION: Our results showed that RFA of parathyroid adenomas caused a significant reduction in biomedical indicators of disease and resulted in a significant reduction or disappearance of the lesion in the majority of the patients while having no considerable complications.

Application of shear wave elastography and median nerve cross-section area in the diagnosis and staging of carpal tunnel syndrome: a case-control study.

PURPOSE: Imaging is gaining a more prominent role in the diagnosis of carpal tunnel syndrome (CTS), especially ultrasonography. Shear wave elastography (SWE) is a novel qualitative method to study mechanical changes in tissue. In this study, we aim to assess the role of SWE in diagnosing and staining of the disease. MATERIAL AND METHODS: A total of 124 wrists were included in the study. Seventy wrists had CTS, and 54 were included as the control group. All of the wrists with CTS had staging done with nerve conduction study. All patients underwent ultrasonography by an expert radiologist and had the SWE and cross-section of the median nerve determined. These values were compared among the 2 groups and different stages of CTS. The receiver operating characteristic curve was utilized to assess the diagnostic role of each of the variables. RESULTS: Cross-section area (CSA) and SWE were significantly different between the 2 groups (p = 0.0001). CSA was also significantly different among various stages of CTS. SWE was not significantly different among moderate and severe stages of CTS. Both of the variables had a good ability to distinguish mild CTS from healthy wrists (p = 0.0001). CONCLUSION: SWE can be used in diagnosing CTS and in the staging of the disease.

Expanding spontaneous pneumothorax in COVID-19 pneumonia: Case report and review of literature.

Coronavirus disease 2019 has presented itself with a variety of clinical signs and symptoms. One of these has been the accordance of spontaneous pneumothorax which in instances has caused rapid deterioration of patients. Furthermore pneumothorax may happen secondary to intubation and the resulting complications. Not enough is discussed regarding cases with COVID-19 related pneumothorax and proper management of these patients. The present article reports an elderly patient with spontaneous pneumothorax secondary to COVID-19 and reviews the existing literature.

A practical artificial intelligence system to diagnose COVID-19 using computed tomography: A multinational external validation study.

Computed tomography has gained an important role in the early diagnosis of COVID-19 pneumonia. However, the ever-increasing number of patients has overwhelmed radiology departments and has caused a reduction in quality of services. Artificial intelligence (AI) systems are the remedy to the current situation. However, the lack of application in real-world conditions has limited their consideration in clinical settings. This study validated a clinical AI system, COVIDiag, to aid radiologists in accurate and rapid evaluation of COVID-19 cases. 50 COVID-19 and 50 non-COVID-19 pneumonia cases were included from each of five centers: Argentina, Turkey, Iran, Netherlands, and Italy. The Dutch database included only 50 COVID-19 cases. The performance parameters namely sensitivity, specificity, accuracy, and area under the ROC curve (AUC) were computed for each database using COVIDiag model. The most common pattern of involvement among COVID-19 cases in all databases were bilateral involvement of upper and lower lobes with ground-glass opacities. The best sensitivity of 92.0% was recorded for the Italian database. The system achieved an AUC of 0.983, 0.914, 0.910, and 0.882 for Argentina, Turkey, Iran, and Italy, respectively. The model obtained a sensitivity of 86.0% for the Dutch database. COVIDiag model could diagnose COVID-19 pneumonia in all of cohorts with AUC of 0.921 (sensitivity, specificity, and accuracy of 88.8%, 87.0%, and 88.0%, respectively). Our study confirmed the accuracy of our proposed AI model (COVIDiag) in the diagnosis of COVID-19 cases. Furthermore, the system demonstrated consistent optimal diagnostic performance on multinational databases, which is critical to determine the generalizability and objectivity of the proposed COVIDiag model. Our results are significant as they provide real-world evidence regarding the applicability of AI systems in clinical medicine.

The effect of vitamin D supplementation on flow-mediated dilatation, oxidized LDL and intracellular adhesion molecule 1 on type 2 diabetic patients with hypertension: A randomized, placebo-controlled, double-blind trial.

AIMS: Current study aimed to evaluate the effect of vitamin D supplementation on flow-mediated dilatation (FMD), oxidized LDL (oxLDL) and intracellular adhesion molecule 1 (ICAM1) in type 2 diabetic patients with hypertension. METHODS: In a double-blinded, placebo-controlled trial, 44 patients were randomly divided into vitamin D group (2000 IU/d, n = 23) and placebo group (control, n = 21) for 12 weeks. Vascular function with FMD, Serum 25-OH vitamin D, oxLDL and ICAM1 were assessed at the baseline and after the intervention. This clinical trial was registered at Iranian Registry of Clinical Trials (IRCT20191223045861N1). RESULTS: In intervention group serum level of vitamin D increased from 32.42 ± 10.56 to 40.45 ± 12.94 (p < 0.001). In the vitamin D group, oxLDL and ICAM1 significantly decreased and FMD increased significantly in both groups (p < 0.001). The level of oxLDL (p = 0.017) and ICAM1 (p < 0.001) were significantly lower in the vitamin D group than the placebo group and FMD (p < 0.001) was significantly higher in the vitamin D group. CONCLUSIONS: Vitamin D supplementation of 2000 IU/d for 12 weeks can improve endothelial function and decrease ICAM1 and oxLDL in type 2 diabetic patients with hypertension.

Alveolar hemorrhage in the setting of COVID-19: Report of a successful vascular intervention and embolization.

The coronavirus disease 2019 (COVID-19) is characterized by viral pneumonia with mild to moderate symptoms. Emerging studies suggest that some patients may experience uncommon complications, such as thrombotic or hemorrhagic episodes. Here we present a 59-year-old male patient who had a hemorrhage episode from a branch of the pulmonary arteries and was treated by interventional embolization. Our case report demonstrates the importance of early diagnosis of hemorrhagic complications of COVID-19 and the possible benefits of early vascular intervention.

Hydrodissection: A Novel Approach for Safe Core Needle Biopsy of Small High-Risk Subcapsular Thyroid Nodules.

PURPOSE: To evaluate the safety and effectiveness of core needle biopsy (CNB) under the assistance of hydrodissection (HDS). MATERIALS AND METHODS: Of 2325 patients requiring biopsy of thyroid lesions, 21 high-risk patients with subcapsular nodules smaller than 10 mm were recruited into this study. All patients underwent HDS with 0.9% saline solution followed by ultrasound (US)-guided CNB with an 18-gauge semi-automated biopsy needle. The separation success rate (SSR) of the HDS, technical success rate (TSR) of CNB, histopathologic success rate (HSR), and complications were assessed. RESULTS: Both the SSR of HDS and TSR of CNB were 100% (21/21). The HSR of the thyroid nodules was 85.7% (18/21). No major complications were recorded. CONCLUSION: HDS before CNB can successfully lead to safe biopsy of small subcapsular thyroid nodules. LEVEL OF EVIDENCE: Level 4, Case Series.

Successful vascular interventional management of superior mesenteric vein thrombosis in a patient with COVID-19: A case report and review of literature.

Coronavirus disease (COVID-19) is associated with thrombosis formation in various vessels, including those in the abdomen. In this case report, we present a COVID-19 infected patient who had developed abdominal discomfort. The patient underwent magnetic resonance imaging, which showed signs of thrombosis formation in the superior mesenteric vein (SMV). After conservative treatment failed, the patient was considered for vascular intervention. The SMV clot underwent thrombolysis via the infusion of reteplase (dose 6 mg stat, followed by 1 mg every hour) through a 5F perfusion Cather (Cragg-McNamara, 20 cm). Control venography showed near-complete recanalization. The patient was discharged with oral anticoagulants. Our case report is one of the first incidents of successful vascular intervention in SMV thrombosis in the setting of COVID-19.

Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists' assessment.

PURPOSE: Ultrasonography is the most common imaging modality used to diagnose carpal tunnel syndrome (CTS). Recently artificial intelligence algorithms have been used to diagnose musculoskeletal diseases accurately without human errors using medical images. In this work, a computer-aided diagnosis (CAD) system is developed using radiomics features extracted from median nerves (MN) to diagnose CTS accurately. METHOD: This study is performed on 228 wrists from 65 patients and 57 controls, with an equal number of control and CTS wrists. Nerve conduction study (NCS) is considered as the gold standard in this study. Two radiologists used two guides to evaluate and categorize the pattern and echogenicity of MNs. Radiomics features are extracted from B-mode ultrasound images (Ultrasomics), and the robust features are fed into support vector machine classifier for automated classification. The diagnostic performances of two radiologists and the CAD system are evaluated using ROC analysis. RESULTS: The agreement of two radiologists was excellent for both guide 1 and 2. The honey-comb pattern clearly appeared in control wrists (based on guide 1). In addition, CTS wrists indicated significantly lower number of fascicles in MNs (based on guide 2). The area under ROC curve (AUC) of the radiologist 1 and 2 are 0.658 and 0.667 based on guide 1 and 0.736 and 0.721 based on guide 2, respectively. The CAD system indicated higher performance than two radiologists with AUC of 0.926. CONCLUSION: The proposed CAD system shows the benefit of using ultrasomics features and can assist radiologists to diagnose CTS accurately.

COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

OBJECTIVES: CT findings of COVID-19 look similar to other atypical and viral (non-COVID-19) pneumonia diseases. This study proposes a clinical computer-aided diagnosis (CAD) system using CT features to automatically discriminate COVID-19 from non-COVID-19 pneumonia patients. METHODS: Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesions of patients in both groups. All significant CT features were fed in five classifiers namely decision tree, K-nearest neighbor, naïve Bayes, support vector machine, and ensemble to evaluate the best performing CAD system in classifying COVID-19 and non-COVID-19 cases. RESULTS: Location and distribution pattern of involvement, number of the lesion, ground-glass opacity (GGO) and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features to classify COVID-19 from non-COVID-19 groups. Our proposed CAD system obtained the sensitivity, specificity, and accuracy of 0.965, 93.54%, 90.32%, and 91.94%, respectively, using ensemble (COVIDiag) classifier. CONCLUSIONS: This study proposed a COVIDiag model obtained promising results using CT radiological routine features. It can be considered an adjunct tool by the radiologists during the current COVID-19 pandemic to make an accurate diagnosis. KEY POINTS: • Location and distribution of involvement, number of lesions, GGO and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features between COVID-19 from non-COVID-19 groups. • The proposed CAD system, COVIDiag, could diagnose COVID-19 pneumonia cases with an AUC of 0.965 (sensitivity = 93.54%; specificity = 90.32%; and accuracy = 91.94%). • The AUC, sensitivity, specificity, and accuracy obtained by radiologist diagnosis are 0.879, 87.10%, 88.71%, and 87.90%, respectively.