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.

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.

The association of sleep and late-night cell phone use among adolescents / Associação entre o sono e o uso noturno de celular entre adolescentes

Abstract Objective: This study aims to assess the relationship of late-night cell phone use with sleep duration and quality in a sample of Iranian adolescents. Methods: The study population consisted of 2400 adolescents, aged 12-18 years, living in Isfahan, Iran. Age, body mass index, sleep duration, cell phone use after 9 p.m., and physical activity were documented. For sleep assessment, the Pittsburgh Sleep Quality Index questionnaire was used. Results: The participation rate was 90.4% (n = 2257 adolescents). The mean (SD) age of participants was 15.44 (1.55) years; 1270 participants reported to use cell phone after 9 p.m. Overall, 56.1% of girls and 38.9% of boys reported poor quality sleep, respectively. Wake-up time was 8:17 a.m. (2.33), among late-night cell phone users and 8:03 a.m. (2.11) among non-users. Most (52%) late-night cell phone users had poor sleep quality. Sedentary participants had higher sleep latency than their peers. Adjusted binary and multinomial logistic regression models showed that late-night cell users were 1.39 times more likely to have a poor sleep quality than non-users (p-value < 0.001). Conclusion: Late-night cell phone use by adolescents was associated with poorer sleep quality. Participants who were physically active had better sleep quality and quantity. As part of healthy lifestyle recommendations, avoidance of late-night cell phone use should be encouraged in adolescents.

Resumo Objetivo: Avaliar a relação entre o uso de celular à noite e a duração e a qualidade do sono em uma amostra de adolescentes iranianos. Métodos: A população estudada consistiu em 2.400 adolescentes, entre 12 e 18 anos, que residem em Isfahan, Irã. Foram documentados a idade, o índice de massa corporal, a duração do sono, o uso de celular após as 21h e prática de atividade física. Para avaliação do sono, usamos o Índice de Qualidade do Sono de Pittsburgh (PSQI). Resultados: A taxa de participação foi de 90,4% (n = 2.257). A idade média (DP) foi de 15,44 ± (1,55) anos; 1.270 relataram o uso do celular após as 21h. Em geral, 56,1% das meninas e 38,9% dos meninos relataram sono de má qualidade, respectivamente. Os indivíduos que usaram celular à noite acordaram às 8h17 (2,33) e os que não usaram acordaram às 8h03 (2,11). A maior parte (52%) dos usuários de celular à noite apresentou má qualidade de sono. Aqueles sem algum tipo de atividade física apresentaram maior latência do sono do que seus pares. Os modelos ajustados de regressão logística binária e multinomial mostraram que os usuários de celular à noite foram 1,39 vez mais propensos a ter má qualidade do sono do que seus pares (p < 0,001). Conclusão: O uso de celular à noite por adolescentes foi associado a pior qualidade do sono. Os participantes fisicamente ativos apresentaram melhor qualidade e maior tempo de sono. Como parte das recomendações de estilo de vida saudável, os adolescentes devem ser incentivados a evitar o uso de celular à noite.

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.

The association of sleep and late-night cell phone use among adolescents.

OBJECTIVE: This study aims to assess the relationship of late-night cell phone use with sleep duration and quality in a sample of Iranian adolescents. METHODS: The study population consisted of 2400 adolescents, aged 12-18 years, living in Isfahan, Iran. Age, body mass index, sleep duration, cell phone use after 9p.m., and physical activity were documented. For sleep assessment, the Pittsburgh Sleep Quality Index questionnaire was used. RESULTS: The participation rate was 90.4% (n=2257 adolescents). The mean (SD) age of participants was 15.44 (1.55) years; 1270 participants reported to use cell phone after 9p.m. Overall, 56.1% of girls and 38.9% of boys reported poor quality sleep, respectively. Wake-up time was 8:17 a.m. (2.33), among late-night cell phone users and 8:03a.m. (2.11) among non-users. Most (52%) late-night cell phone users had poor sleep quality. Sedentary participants had higher sleep latency than their peers. Adjusted binary and multinomial logistic regression models showed that late-night cell users were 1.39 times more likely to have a poor sleep quality than non-users (p-value<0.001). CONCLUSION: Late-night cell phone use by adolescents was associated with poorer sleep quality. Participants who were physically active had better sleep quality and quantity. As part of healthy lifestyle recommendations, avoidance of late-night cell phone use should be encouraged in adolescents.