This technical report proposes the use of a deep convolutional neural network as a preliminary diagnostic method in the analysis of chest computed tomography images from patients with symptoms of Severe Acute Respiratory Syndrome (SARS) and suspected COVID-19 disease, especially on occasions when the delay of the RT-PCR result and the absence of urgent care could result in serious temporary, long-term, or permanent health damage. The model was trained on 83,391 images, validated on 15,297, and tested on 22,185 figures, achieving an F1-Score of 98%, 97.59% in Cohen's Kappa, 98.4% in Accuracy, and 5.09% in Loss. Attesting a highly accurate automated classification and providing results in less time than the current gold-standard exam, Real-Time reverse-transcriptase Polymerase Chain Reaction (RT-PCR). -- O presente relat\'orio t\'ecnico prop\~oe a utiliza\c{c}\~ao de uma rede neural convolucional profunda como m\'etodo diagn\'ostico preliminar na an\'alise de imagens de tomografia computadorizada tor\'acica em pacientes com sintomas de S\'indrome Respirat\'oria Aguda Grave (SRAG) e suspeita de COVID-19, principalmente em ocasi\~oes em que a demora do resultado do RT-PCR e a aus\^encia de cuidados urgentes poderia acarretar graves danos tempor\'arios, \`a longo prazo, ou permanentes \`a sa\'ude. O modelo foi treinado em 83.391 imagens, validado em 15.297, e testado em 22.185 figuras, atingindo pontua\c{c}\~ao no F1-Score de 98%, 97,59% em Cohen's Kappa, 98,4% de Acur\'acia e 5,09% de Loss. Atestando uma classifica\c{c}\~ao automatizada r\'apida e de alta precis\~ao, e fornecendo resultado em tempo menor ao do exame padr\~ao-ouro atual, o Real-Time reverse-transcriptase Polymerase Chain Reaction (RT-PCR).
翻译:这份技术报告建议使用一个深层混血神经网络作为初步诊断方法,用于分析具有严重急性呼吸综合症(SARS)和疑似COVID-19症状的患者的胸部计算断层图像,特别是在RT-PCR结果的延迟和缺乏紧急护理可能导致严重的临时、长期或永久性健康损害的情况下。模型用83,391个图像进行了培训,15,297得到验证,22,185个数字进行了测试,达到98 %的F1-Score,97.59%的Cohen's Kappa,98.4%的Scure,和5.09%的损失。测试了高度准确的自动化分类,并且提供了比当前黄金标准测试、实时反向性聚合链反应(RT-PCRCR)更短的时间。