Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 2 de 2
IEEE J Biomed Health Inform ; 24(10): 2787-2797, 2020 10.
Article in English | MEDLINE | ID: covidwho-724919


Coronavirus Disease 2019 (COVID-19) has rapidly spread worldwide since first reported. Timely diagnosis of COVID-19 is crucial both for disease control and patient care. Non-contrast thoracic computed tomography (CT) has been identified as an effective tool for the diagnosis, yet the disease outbreak has placed tremendous pressure on radiologists for reading the exams and may potentially lead to fatigue-related mis-diagnosis. Reliable automatic classification algorithms can be really helpful; however, they usually require a considerable number of COVID-19 cases for training, which is difficult to acquire in a timely manner. Meanwhile, how to effectively utilize the existing archive of non-COVID-19 data (the negative samples) in the presence of severe class imbalance is another challenge. In addition, the sudden disease outbreak necessitates fast algorithm development. In this work, we propose a novel approach for effective and efficient training of COVID-19 classification networks using a small number of COVID-19 CT exams and an archive of negative samples. Concretely, a novel self-supervised learning method is proposed to extract features from the COVID-19 and negative samples. Then, two kinds of soft-labels ('difficulty' and 'diversity') are generated for the negative samples by computing the earth mover's distances between the features of the negative and COVID-19 samples, from which data 'values' of the negative samples can be assessed. A pre-set number of negative samples are selected accordingly and fed to the neural network for training. Experimental results show that our approach can achieve superior performance using about half of the negative samples, substantially reducing model training time.

Betacoronavirus , Clinical Laboratory Techniques/statistics & numerical data , Coronavirus Infections/diagnostic imaging , Coronavirus Infections/diagnosis , Pandemics , Pneumonia, Viral/diagnostic imaging , Pneumonia, Viral/diagnosis , Radiographic Image Interpretation, Computer-Assisted/statistics & numerical data , Supervised Machine Learning , Tomography, X-Ray Computed/statistics & numerical data , Algorithms , Cohort Studies , Computational Biology , Coronavirus Infections/classification , Deep Learning , Diagnostic Errors/statistics & numerical data , Humans , Neural Networks, Computer , Pandemics/classification , Pneumonia, Viral/classification , Retrospective Studies
IEEE Trans Med Imaging ; 39(8): 2626-2637, 2020 Aug.
Article in English | MEDLINE | ID: covidwho-690465


Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net, a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.

Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Supervised Machine Learning , Tomography, X-Ray Computed/methods , Algorithms , Betacoronavirus , Humans , Lung/diagnostic imaging , Pandemics