Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
1.
Lecture Notes in Networks and Systems ; 473:377-384, 2023.
Article in English | Scopus | ID: covidwho-2243546

ABSTRACT

A convolutional neural network (CNN) has one or more layers and is mainly used for image processing, classification, segmentation. CNN is commonly used for satellite image capturing or classifying hand written letters and digits. In this particular project, a convolutional neural network is trained to predict whether a person is wearing a mask or not. The training is done by using a set of masked and unmasked images which constitutes the training data. The performance of the trained model is evaluated on the test dataset, and the accuracy of the prediction is observed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

2.
International Conference on Innovative Computing and Communications, Icicc 2022, Vol 1 ; 473:377-384, 2023.
Article in English | Web of Science | ID: covidwho-2094513

ABSTRACT

A convolutional neural network (CNN) has one or more layers and is mainly used for image processing, classification, segmentation. CNN is commonly used for satellite image capturing or classifying hand written letters and digits. In this particular project, a convolutional neural network is trained to predict whether a person is wearing a mask or not. The training is done by using a set of masked and unmasked images which constitutes the training data. The performance of the trained model is evaluated on the test dataset, and the accuracy of the prediction is observed.

3.
Quantitative Biology ; 10(2):188-207, 2022.
Article in English | Scopus | ID: covidwho-1955124

ABSTRACT

Background: Due to the limited availability and high cost of the reverse transcription-polymerase chain reaction (RT-PCR) test, many studies have proposed machine learning techniques for detecting COVID-19 from medical imaging. The purpose of this study is to systematically review, assess and synthesize research articles that have used different machine learning techniques to detect and diagnose COVID-19 from chest X-ray and CT scan images. Methods: A structured literature search was conducted in the relevant bibliographic databases to ensure that the survey solely centered on reproducible and high-quality research. We selected papers based on our inclusion criteria. Results: In this survey, we reviewed 98 articles that fulfilled our inclusion criteria. We have surveyed a complete pipeline of chest imaging analysis techniques related to COVID-19, including data collection, pre-processing, feature extraction, classification, and visualization. We have considered CT scans and X-rays as both are widely used to describe the latest developments in medical imaging to detect COVID-19. Conclusions: This survey provides researchers with valuable insights into different machine learning techniques and their performance in the detection and diagnosis of COVID-19 from chest imaging. At the end, the challenges and limitations in detecting COVID-19 using machine learning techniques and the future direction of research are discussed. © The Author(s) 2022.

4.
Developmental Medicine and Child Neurology ; 64(SUPPL 1):24, 2022.
Article in English | EMBASE | ID: covidwho-1723130

ABSTRACT

Objective: To present paediatric cases of unusual neuroinflammatory conditions encountered during the COVID-19 pandemic in Trinidad & Tobago. Methods: Retrospective study design. Inpatient paediatric patients (aged 0-16 years) hospitalized for neurological complaints from June 2020 - August 2021 at EWMSC. Outcome measures were age at presentation, sex, ethnicity, diagnosis, radiological findings, blood/CSF findings, COVID-19 PCR and antibodies testing, treatment, outcomes and other systems involved. Results: Twenty (20) patients (aged 4-months-old to 15-years-old) had documented neurological involvement. 50% had a diagnosis of ADEM/ADS/AHNE;45% had a diagnosis of either CNS vasculitis (n=3), autoimmune encephalitis (n=3) or GBS (n=3);5% had a diagnosis of acute COVID-19 encephalitis. 70% were of African descent. The youngest age group (0-4 years) (n=11) constituted more males (82%) whereas the eldest age group (10-15 years) (n=3) were all females. Neuroimaging findings were corpus callosal lesions;deep white matter T2 hyperintensities;cerebellar involvement;area postrema and brainstem/C-spine involvement;microhaemorrhages and necrotizing/haemorrhagic lesions (peripheral/central). 70% of patients were either SARS-CoV-2 PCR or COVID-19 antibodies positive. Other systems were involved in 40% to 62.5% (n=5) had cardiac involvement (myocarditis, coronary arteries dilatation, valve regurgitation) and 37.5% (n=3) had pancreatic involvement (autoimmune pancreatitis, type 1 diabetes mellitus). Treatment modalities for CNS manifestations (n=17) were clinically based - 24% (n=4) 3rd line treatment, 29% (n=5) 2nd line treatment, 41% (n=7) 1st line treatment and 6% (n=1) requiring no treatment. All 3 patients with a diagnosis of GBS responded appropriately to IVIG. Developmental outcomes were worst in patients with a diagnosis of autoimmune encephalitis. Conclusion: We have had an explosion of neuro-inflammatory cases since the COVID-19 pandemic began. The range of neuroradiological diagnoses and other systemic involvement (including criteria for PIMS) are interesting, alluding to a neuroinflammatory mechanism. Effects on long-term sequelae and developmental outcomes are concerning in some cases, however, still unknown at this stage.

5.
Archives of Disease in Childhood ; 106(SUPPL 1):A35, 2021.
Article in English | EMBASE | ID: covidwho-1495034

ABSTRACT

Background Neuromyelitis Optica Spectrum Disorder (NMOSD) is an inflammatory demyelinating disease of the central nervous system (CNS) primarily affecting the optic nerves and spinal cord, but also involving other regions of the CNS including the area postrema, periaqueductal gray matter, and hypothalamus. There are limited cases describing the development of NMOSD post SARSCOV- 2. Objectives We present a case of seronegative NMOSD meeting the diagnostic criteria with coronary artery involvement and the probable association of Paediatric Multisystem Inflammatory Syndrome (PIMS)/SARS-COV-2. Methods A 13-year-old female of Chinese descent met the diagnostic criteria for sero-negative NMOSD: . Optic neuritis (presented initially with decreased vision right eye, progressed to complete blindness involving both eyes;optic discs swelling bilaterally) + enhancing focus in left parieto-occipital region . Area postrema syndrome (intractable vomiting) + enhancing lesion in the left aspect of the dorsal medulla . Acute brainstem syndrome (autonomic dysfunction, respiratory distress with new-onset squint) + enhancing foci in medulla . Symptomatic cerebral syndrome (left arm weakness, headache, behaviour change) + several enhancing foci within the cerebral hemisphere and sulcal thickening/oedema enhancement in the right fronto-temporal lobe She presented initially with headache and behaviour change x8 days;weakness left arm x6 days;loss of vision right eye x6 days;facial numbness x6 days;vomiting x2 days but no preceding viral illness/vaccine. She was initially managed as ADEM/ADS with steroids (imaging at this time revealed cerebral lesions). However, a protracted illness persisted with intractable nausea/vomiting, and development of new symptoms (squint, autonomic dysfunction, respiratory distress). Repeat imaging showed new involvement of the dorsal and ventral medulla. IVIG and rituximab treatment were then commenced. Results CSF pleocytosis (22 white cells) and elevated protein concentration (131mg/dL) were present. Anti-MOG and Aquaporin-4 antibodies testing post steroids were negative. ESR increased to 82 mm/hr and ANA titre was mildly elevated during her illness. ENA, dsDNA titres normal. COVID-19 IgM antibody level rose to 0.921. Infectious screen negative (Hepatitis studies, HIV, HSV, ASOT). Neoplastic workup negative (Antineuronal antibodies, CEA, CA-125, AFP, Blood film). MRI pelvis was normal. Anticardiolipin and lupus anticoagulant antibodies negative. Interestingly, ECHO done post steroids, IVIG and during rituximab treatment showed moderately dilated left middle coronary artery and severely dilated left anterior descending artery. Her neurological function has improved post IVIG and rituximab. Conclusions Due to the evidence of inflammation and neurological and cardiac dysfunction, we question whether this could be a post SARS-COV-2 related presentation of PIMS. This is our 3rd case in Trinidad & Tobago linking coronary artery and neurological involvement in the same patients possibly in relation to SARS-COV-2. The other cases: 1) 20-month-old with corpus callosal lesions and right coronary artery ectasia post-treatment 2) 2-year 7-months-old with long segment of cord enlargement with heterogenous appearance from C1 to C6 and dilated coronary arteries/mild mitral regurgitation/pericardial effusion.

6.
Developmental Medicine and Child Neurology ; 63(SUPPL 1):102, 2021.
Article in English | EMBASE | ID: covidwho-1109522

ABSTRACT

Clinical findings: NC, a 20-month-old male presented in July 2020 with new-onset focal motor seizures, drowsiness and developmental regression. There was a preceding history of fever, vomiting and diarrhoea about 1 to 2 weeks prior to presenting. On examination, he was noted to have erythema nodosum over his shins, unable to fix and follow even to light stimulus, no head nor trunk control with generalized increased tone, hyperreflexia and upgoing plantar responses bilaterally. Investigations: Blood investigations: lymphopenia, mild increase in ESR 16mm/hr, transaminases elevated, CK elevated. CSF investigations: CSF protein 143mg/dL, glucose 88mg/dL, CSF cell count 28 white cells, 17 red cells. EEG: background slowing right > left. MRI brain (initial): transient lesions along corpus callosum, petechial haemorrhages within superior aspect of cerebellar vermis Treatment: He was treated with 5 days IV methylprednisolone 30mg/kg/day followed by oral prednisolone. He was treated as a protracted ADEM illness with IVIG (2g/kg over 2 days) when he clinically deteriorated. Steroids were slowly tapered over 8 weeks. Progress: 2 weeks post IVIG-speech and language milestones improved to baseline, started cruising. 6 weeks post IVIG-able to walk independently however, not able to climb/run. Follow-up investigations: 2 months post admission: 2019-CoV IgM Antibodies (blood): 1.123 (range 0-1). Of note, we have had a total of 4 patients managed for ADEM within the past 3 months. 3 presented with preceding viral GE symptoms. Most recently the other was initially managed for Kawasaki disease and is also COVID 19 IgM positive. We are awaiting COVID-19 antibody testing for these patients to determine whether they are linked. Unfortunately, in our resource-limited setting, PCR testing was initially only performed on patients with a travel history and respiratory symptoms.

SELECTION OF CITATIONS
SEARCH DETAIL