Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how pre-trained deep learning models can be adopted to perform COVID-19 detection using X-Ray images. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent image classification models. We highlight the challenges (including dataset size and quality) in utilising current publicly available COVID-19 datasets for developing useful deep learning models. We propose a semi-automated image pre-processing model to create a trustworthy image dataset for developing and testing deep learning models. The new approach is aimed to reduce unwanted noise from X-Ray images so that deep learning models can focus on detecting diseases with specific features from them. Next, we devise a deep learning experimental framework, where we utilise the processed dataset to perform comparative testing for several popular and widely available deep learning model families such as VGG, Inception, Xception, and Resnet. The experimental results highlight the suitability of these models for current available dataset and indicates that models with simpler networks such as VGG19 performs relatively better with up to 83% precision. This will provide a solid pathway for researchers and practitioners to develop improved models in the future.
Inhibition of the AT1R selectively improved baroreflex control of sSNA and peripheral chemoreflex control of all three sympathetic nerve outflows in the LPK rat, suggesting these anomalies in reflex function are driven in part by angiotensin II.
Spinal arteriovenous fistulas are rare entities. They often present with congestive myelopathy but are infrequently diagnosed as the cause of the patients’ symptoms. Only one such case has been described previously in Indian literature. We describe one such case who presented to us after a gap of 3 years since symptom onset and following a failed laminectomy where the cause was later diagnosed to be an intradural fistula in the filum terminale fed by the anterior spinal artery and review the available literature.
A 7-year-old male child presented with poorly controlled generalized tonic-clonic seizures. On examination, he was mentally retarded, deaf and had a swelling at the root on the nose. Computed tomography scan done previously revealed a left temporal arachnoid cyst (AC) due to which he was referred for surgery. However, magnetic resonance imaging revealed a constellation of abnormalities – all of which could be responsible for his seizures. The combination of periventricular nodular heterotopias with encepaholcele is rarely described in the literature, and more infrequently so its combination with AC and callosal dysgenesis – the Chudley-Mccullough syndrome. We describe the case and review relevant literature on this subject.
This paper presents an original methodology for extracting semantic features from X-rays images that correlate to severity from a data set with patient ICU admission labels through interpretable models. The validation is partially performed by a proposed method that correlates the extracted features with a separate larger data set that does not contain the ICU-outcome labels. The analysis points out that a few features explain most of the variance between patients admitted in ICUs or not. The methods herein can be viewed as a statistical approach highlighting the importance of features related to ICU admission that may have been only qualitatively reported. In between features shown to be over-represented in the external data set were ones like 'Consolidation' (1.67), 'Alveolar' (1.33), and 'Effusion' (1.3). A brief analysis on the locations also showed higher frequency in labels like 'Bilateral' (1.58) and Peripheral (1.28) in patients labelled with higher chances to be admitted in ICU. To properly handle the limited data sets, a state-of-the-art lung segmentation network was also trained and presented, together with the use of lowcomplexity and interpretable models to avoid overfitting.
Although Japanese Encephalitis (JE) and Wilson's disease (WD) are different entities, MR findings in both these conditions are quite similar. The purpose of this retrospective study was to find out the similarities and differences between JE and WD on MR imaging. The study group comprised 25 proven cases of JE and 10 cases of WD. Spin echo (SE) TI- and T2-weighted imaging was performed on a 1.5-T MR system. Fourteen of these 35 cases (10 JE, 4 WD) were also examined using T1-weighted magnetization transfer (MT) SE sequence before and after contrast administration. Although both JE and WD showed similar topographical distribution of lesions, predominant involvement of the basal ganglia and thalami, there were some differences. Brain stem lesion was more frequent for WD than for JE, and posteromedial part of the thalami was spared in WD. The lesion characteristics were also different between both; in WD mixed intensity in the basal ganglia and hyperintense linear rim at the peripheral putamen was observed frequently, whereas hyperintense basal ganglia on T2-weighted images, subacute hemorrhage in the thalami and meningeal enhancement were seen only in the patients with JE. These characteristic lesion criteria may help in differentiation of JE from WD on MR imaging.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.