Deep Active Context Estimation for Automated COVID-19 Diagnosis

Many studies on automated COVID-19 diagnosis have advanced rapidly with the increasing availability of large-scale CT annotated datasets. Inevitably, there are still a large number of unlabeled CT slices in the existing data sources since it requires considerable consuming labor efforts. Notably, cinical experience indicates that the neighboring CT slices may present similar symptoms and signs. Inspired by such wisdom, we propose DACE, a novel CNN-based deep active context estimation framework, which leverages the unlabeled neighbors to progressively learn more robust feature representations and generate a well-performed classifier for COVID-19 diagnosis. Specifically, the backbone of the proposed DACE framework is constructed by a well-designed Long-Short Hierarchical Attention Network (LSHAN), which effectively incorporates two complementary attention mechanisms, i.e., short-range channel interactions (SCI) module and long-range spatial dependencies (LSD) module, to learn the most discriminative features from CT slices. To make full use of such available data, we design an efficient context estimation criterion to carefully assign the additional labels to these neighbors. Benefiting from two complementary types of informative annotations from K-nearest neighbors, i.e., the majority of high-confidence samples with pseudo labels and the minority of low-confidence samples with hand-annotated labels, the proposed LSHAN can be fine-tuned and optimized in an incremental learning manner. Extensive experiments on the Clean-CC-CCII dataset demonstrate the superior performance of our method compared with the state-of-the-art baselines.

Periphery-aware COVID-19 diagnosis with contrastive representation enhancement.

Computer-aided diagnosis has been extensively investigated for more rapid and accurate screening during the outbreak of COVID-19 epidemic. However, the challenge remains to distinguish COVID-19 in the complex scenario of multi-type pneumonia classification and improve the overall diagnostic performance. In this paper, we propose a novel periphery-aware COVID-19 diagnosis approach with contrastive representation enhancement to identify COVID-19 from influenza-A (H1N1) viral pneumonia, community acquired pneumonia (CAP), and healthy subjects using chest CT images. Our key contributions include: 1) an unsupervised Periphery-aware Spatial Prediction (PSP) task which is designed to introduce important spatial patterns into deep networks; 2) an adaptive Contrastive Representation Enhancement (CRE) mechanism which can effectively capture the intra-class similarity and inter-class difference of various types of pneumonia. We integrate PSP and CRE to obtain the representations which are highly discriminative in COVID-19 screening. We evaluate our approach comprehensively on our constructed large-scale dataset and two public datasets. Extensive experiments on both volume-level and slice-level CT images demonstrate the effectiveness of our proposed approach with PSP and CRE for COVID-19 diagnosis.