RESUMEN
BACKGROUND: Despite the globally reducing hospitalization rates and the much lower risks of Covid-19 mortality, accurate diagnosis of the infection stage and prediction of outcomes are clinically of interest. Advanced current technology can facilitate automating the process and help identifying those who are at higher risks of developing severe illness. This work explores and represents deep-learning-based schemes for predicting clinical outcomes in Covid-19 infected patients, using Visual Transformer and Convolutional Neural Networks (CNNs), fed with 3D data fusion of CT scan images and patients' clinical data. METHODS: We report on the efficiency of Video Swin Transformers and several CNN models fed with fusion datasets and CT scans only vs. a set of conventional classifiers fed with patients' clinical data only. A relatively large clinical dataset from 380 Covid-19 diagnosed patients was used to train/test the models. RESULTS: Results show that the 3D Video Swin Transformers fed with the fusion datasets of 64 sectional CT scans + 67 clinical labels outperformed all other approaches for predicting outcomes in Covid-19-infected patients amongst all techniques (i.e., TPR = 0.95, FPR = 0.40, F0.5 score = 0.82, AUC = 0.77, Kappa = 0.6). CONCLUSIONS: We demonstrate how the utility of our proposed novel 3D data fusion approach through concatenating CT scan images with patients' clinical data can remarkably improve the performance of the models in predicting Covid-19 infection outcomes. SIGNIFICANCE: Findings indicate possibilities of predicting the severity of outcome using patients' CT images and clinical data collected at the time of admission to hospital.
Asunto(s)
COVID-19 , Humanos , COVID-19/diagnóstico por imagen , Hospitalización , Hospitales , Redes Neurales de la Computación , Tomografía Computarizada por Rayos XRESUMEN
BACKGROUND: Chronic stress increases the production of pro-inflammatory cytokines and oxidative stress in the brain, which underlay cognitive and psychological problems. In addition to the anti-depressants, vitamin D is known to act as an anti-inflammatory and anti-oxidative agent. This study investigates the specific effects of vitamin D in protecting hippocampus and pre-frontal cortex (PFC) against chronic mild stress (CMS)-induced activation of pro-inflammatory cytokines IL-6 and TNF-α and decreasing the activation of anti-oxidative enzymes super oxide dismutase (SOD) and glutathione peroxidase (GPx). METHODS AND RESULTS: Rats were exposed to CMS for 3 weeks. Two groups of rats received vitamin D (5 and 10 µg/kg) and another received fluoxetine (5 mg/kg) along with CMS. Control groups were not exposed to CMS, but received treatments similar to CMS groups. Serum corticosterone and IL-6, TNF-α and SOD and GPx levels in the hippocampus and PFC were measured at the end of three weeks. CMS significantly increased corticosterone, IL-6, TNF-α and decreased SOD and GPx levels (P < 0.0001) in hippocampus and PFC. Vitamin D treatment reduced corticosterone levels (P < 0.01), increased SOD (P < 0.0001) and GPx (P < 0.01) and decreased IL-6 and TNF-α (P < 0.0001) levels in the hippocampus and PFC compared to rats treated with vitamin D vehicle. Vitamin D-10 regulation of SOD and IL-6 levels was more effective than fluoxetine (P < 0.0001 and P < 0.01, respectively, in hippocampus). CONCLUSION: This study suggests that vitamin D effectively protects the key regions of the brain related to cognition and affective behavior, against the inflammation and oxidative stress caused by the chronic stress.
Asunto(s)
Estrés Psicológico/tratamiento farmacológico , Vitamina D/farmacología , Animales , Antioxidantes/metabolismo , Conducta Animal/efectos de los fármacos , Encéfalo/metabolismo , Citocinas/metabolismo , Glutatión Peroxidasa/metabolismo , Hipocampo/efectos de los fármacos , Hipocampo/metabolismo , Inflamación , Interleucina-6/metabolismo , Masculino , Estrés Oxidativo/efectos de los fármacos , Estrés Oxidativo/fisiología , Corteza Prefrontal/efectos de los fármacos , Corteza Prefrontal/metabolismo , Ratas , Ratas Wistar , Estrés Psicológico/metabolismo , Estrés Psicológico/fisiopatología , Superóxido Dismutasa/metabolismo , Factor de Necrosis Tumoral alfa/metabolismo , Vitamina D/metabolismoRESUMEN
BACKGROUND: Mitotic activity index is considered as the most important grading component to predict prognosis in invasive breast carcinoma. But it is believed that it is also the cause of discordance in grade estimation based on Bloom-Richardson system. Thus, reproducible methods such as immunohistochemistry (IHC) based analysis methods appears to be of great value in facilitating mitotic count. MATERIALS AND METHODS: In the present study, we examined the utility of Phosphohistone H3 by IHC in various grades of breast carcinoma and compared it with traditional mitotic count by hematoxylin and eosin (H and E) staining and probable changes in tumor grading. RESULTS: Total 90 cases of invasive breast carcinoma were evaluated. Mean mitotic count were 8.6 and 6.4/10HPF in IHC and HandE groups, respectively. Although , mean average count was higher by IHC method , good correlation was observed(R=0.914). Using PHH3 IHC, two out of 33 cases of grade I tumors were upgraded in to grade II and three cases of grade II were upgraded in to grade III. None of the tumors were down graded. CONCLUSION: Similar to some other previous studies, we found PHH3 a robust sensitive and practical marker for mitotic count in breast carcinoma. Especially it is helpful to identify the most proliferating area. However, further studies are required to confirm the superiority of this biomarker for including in grading system.
.