Two-step machine learning to diagnose and predict involvement of lungs in COVID-19 and pneumonia using CT radiomics.

OBJECTIVE: To develop a two-step machine learning (ML) based model to diagnose and predict involvement of lungs in COVID-19 and non COVID-19 pneumonia patients using CT chest radiomic features. METHODS: Three hundred CT scans (3-classes: 100 COVID-19, 100 pneumonia, and 100 healthy subjects) were enrolled in this study. Diagnostic task included 3-class classification. Severity prediction score for COVID-19 and pneumonia was considered as mild (0-25%), moderate (26-50%), and severe (>50%). Whole lungs were segmented utilizing deep learning-based segmentation. Altogether, 107 features including shape, first-order histogram, second and high order texture features were extracted. Pearson correlation coefficient (PCC≥90%) followed by different features selection algorithms were employed. ML-based supervised algorithms (Naïve Bays, Support Vector Machine, Bagging, Random Forest, K-nearest neighbors, Decision Tree and Ensemble Meta voting) were utilized. The optimal model was selected based on precision, recall and area-under-curve (AUC) by randomizing the training/validation, followed by testing using the test set. RESULTS: Nine pertinent features (2 shape, 1 first-order, and 6 second-order) were obtained after features selection for both phases. In diagnostic task, the performance of 3-class classification using Random Forest was 0.909±0.026, 0.907±0.056, 0.902±0.044, 0.939±0.031, and 0.982±0.010 for precision, recall, F1-score, accuracy, and AUC, respectively. The severity prediction task using Random Forest achieved 0.868±0.123 precision, 0.865±0.121 recall, 0.853±0.139 F1-score, 0.934±0.024 accuracy, and 0.969±0.022 AUC. CONCLUSION: The two-phase ML-based model accurately classified COVID-19 and pneumonia patients using CT radiomics, and adequately predicted severity of lungs involvement. This 2-steps model showed great potential in assessing COVID-19 CT images towards improved management of patients.

Monodisperse Gold Nanoparticles: A Review on Synthesis and Their Application in Modern Medicine.

Gold nanoparticles (AuNPs) are becoming increasingly popular as drug carriers due to their unique properties such as size tenability, multivalency, low toxicity and biocompatibility. AuNPs have physical features that distinguish them from bulk materials, small molecules and other nanoscale particles. Their unique combination of characteristics is just now being fully realized in various biomedical applications. In this review, we focus on the research accomplishments and new opportunities in this field, and we describe the rising developments in the use of monodisperse AuNPs for diagnostic and therapeutic applications. This study addresses the key principles and the most recent published data, focusing on monodisperse AuNP synthesis, surface modifications, and future theranostic applications. Moving forward, we also consider the possible development of functionalized monodisperse AuNPs for theranostic applications based on these efforts. We anticipate that as research advances, flexible AuNPs will become a crucial platform for medical applications.

Artificial intelligence-driven assessment of radiological images for COVID-19.

Artificial Intelligence (AI) methods have significant potential for diagnosis and prognosis of COVID-19 infections. Rapid identification of COVID-19 and its severity in individual patients is expected to enable better control of the disease individually and at-large. There has been remarkable interest by the scientific community in using imaging biomarkers to improve detection and management of COVID-19. Exploratory tools such as AI-based models may help explain the complex biological mechanisms and provide better understanding of the underlying pathophysiological processes. The present review focuses on AI-based COVID-19 studies as applies to chest x-ray (CXR) and computed tomography (CT) imaging modalities, and the associated challenges. Explicit radiomics, deep learning methods, and hybrid methods that combine both deep learning and explicit radiomics have the potential to enhance the ability and usefulness of radiological images to assist clinicians in the current COVID-19 pandemic. The aims of this review are: first, to outline COVID-19 AI-analysis workflows, including acquisition of data, feature selection, segmentation methods, feature extraction, and multi-variate model development and validation as appropriate for AI-based COVID-19 studies. Secondly, existing limitations of AI-based COVID-19 analyses are discussed, highlighting potential improvements that can be made. Finally, the impact of AI and radiomics methods and the associated clinical outcomes are summarized. In this review, pipelines that include the key steps for AI-based COVID-19 signatures identification are elaborated. Sample size, non-standard imaging protocols, segmentation, availability of public COVID-19 databases, combination of imaging and clinical information and full clinical validation remain major limitations and challenges. We conclude that AI-based assessment of CXR and CT images has significant potential as a viable pathway for the diagnosis, follow-up and prognosis of COVID-19.

Recent Advances in Synthesis, Medical Applications and Challenges for Gold-Coated Iron Oxide: Comprehensive Study.

Combining iron oxide nanoparticles (Fe3O4 NPs) and gold nanoparticles (Au NPs) in one nanostructure is a promising technique for various applications. Fe3O4 NPs have special supermagnetic attributes that allow them to be applied in different areas, and Au NPs stand out in biomaterials due to their oxidation resistance, chemical stability, and unique optical properties. Recent studies have generally defined the physicochemical properties of nanostructures without concentrating on a particular formation strategy. This detailed review provides a summary of the latest research on the formation strategy and applications of Fe3O4@Au. The diverse methods of synthesis of Fe3O4@Au NPs with different basic organic and inorganic improvements are introduced. The role and applicability of Au coating on the surface of Fe3O4 NPs schemes were explored. The 40 most relevant publications were identified and reviewed. The versatility of combining Fe3O4@Au NPs as an option for medical application is proven in catalysis, hyperthermia, biomedical imaging, drug delivery and protein separation.

Medical imaging modalities using nanoprobes for cancer diagnosis: A literature review on recent findings.

Medical imaging modalities are used for different types of cancer detection and diagnosis. Recently, there have been a lot of studies on developing novel nanoparticles as new medical imaging contrast agents for the early detection of cancer. The aim of this review article is to categorize the medical imaging modalities accompanying with using nanoparticles to improve potential imaging for cancer detection and hence valuable therapy in the future. Nowadays, nanoparticles are becoming potentially transformative tools for cancer detection for a wide range of imaging modalities, including computed tomography (CT), magnetic resonance imaging, single photon emission CT, positron emission tomography, ultrasound, and optical imaging. The study results seen in the recent literature provided and discussed the diagnostic performance of imaging modalities for cancer detections and their future directions. With knowledge of the correlation between the application of nanoparticles and medical imaging modalities and with the development of targeted contrast agents or nanoprobes, they may provide better cancer diagnosis in the future.

Magnetic Iron Oxide Nanoparticles as T2 MR Imaging Contrast Agent for Detection of Breast Cancer (MCF-7) Cell.

BACKGROUND: Advances of nanotechnology have led to the development of nano-materials with both potential diagnostic and therapeutic applications. Among them, Super Paramagnetic Iron Oxide Nanoparticles (SPIONs) have received particular attention. Modified EDC coupling fraction was used to fabricate the SPION-C595 as an MR imaging contrast agent for breast cancer detection in early stages. METHODS: Nanoprobe characterization was confirmed using Fourier Transform Infrared Spectroscopy (FT-IR), Scanning Electron Microscopy with Energy Dispersive X-Ray Spectroscopy (SEM-EDAX), and Photon Correlation Spectroscopy (PCS). Protein and iron concentration of nanoprobe was examined by standard method. MTT assay was performed to evaluate the cytotoxicity of the nanoprobe in breast cancer cell line (MCF-7). T2-weighted MR imaging was performed to evaluate the signal enhancement on T2 relaxation time of nanoprobe using spin-echo pulse sequence. RESULTS: As results showed, SPIONs-C595 provided active targeting of breast cancer cell (MCF-7) at a final concentration of 600 µgFe/ml. The final concentration of protein was calculated to be at 0.78 µgprotein/ml. The hydrodynamic size of the nanoprobe was 87.4±0.7 nm. The MR imaging results showed a good reduction of T2 relaxation rates for the highest dose of SPIONs-C595. DISCUSSION: Based on the results, SPIONs-C595 nanoprobe has a potential in T2-weighted MR imaging contrast agent for breast cancer cell (MCF-7) detection.

In vitro Study of SPIONs-C595 as Molecular Imaging Probe for Specific Breast Cancer (MCF-7) Cells Detection

Background: Magnetic resonance imaging (MRI) plays an essential role in molecular imaging by delivering the contrast agent into targeted cancer cells. The aim of this study was to evaluate the C595 monoclonal antibody-conjugated superparamagnetic iron oxide nanoparticles (SPIONs-C595) for the detection of breast cancer cell (MCF-7). Methods: The conjugation of monoclonal antibody and nanoparticles was confirmed using X-ray diffraction, transmission electron microscopy, and photon correlation spectroscopy. The selectivity of the nanoprobe for breast cancer cells (MCF-7) was obtained by Prussian blue, atomic emission spectroscopy, and MRI relaxometry. Results: The in vitro MRI showed that T2 relaxation time will be reduced 76% when using T2-weighed magnetic resonance images compared to the control group (untreated cells) at the dose of 200 µg Fe/ml, as the optimum dose. In addition, the results showed the high uptake of nanoprobe into MCF-7 cancer cells. Conclusion: The SPIONs-C595 nanoprobe has potential for the detection of specific breast cancer.

Mutagenicity and preclinical safety assessment of the aqueous extract of Clinacanthus nutans leaves.

CONTEXT: Clinacanthus nutans (CN) is used traditionally for treating various illnesses. Robust safety data to support its use is lacking. OBJECTIVE: To evaluate the adverse effects of aqueous extract of CN leaves (AECNL). MATERIALS AND METHODS: The oral toxicity of the AECNL was tested following Organisation for Economic Co-operation and Development (OECD) guidelines. Mutagenicity (Ames test) of AECNL was evaluated using TA98 and TA100 Salmonella typhimurium strains. RESULTS: No mortality or morbidity was found in the animals upon single and repeated dose administration. However, significant body weight loss was observed at 2000 mg/kg during sub-chronic (90 d) exposure. In addition, increased eosinophil at 500 mg/kg and decreased serum alkaline phosphatase levels at 2000 mg/kg were observed in male rats. Variations in glucose and lipid profiles in treated groups were also observed compared to control. Ames test revealed no evidence of mutagenic or carcinogenic effects at 500 µg/well of AECNL. CONCLUSION: The median lethal dose (LD50) of the AECNL is >5000 mg/kg and the no-observed-adverse-effect level is identified to be greater than 2000 mg/kg/day in 90-d study.