An ensemble learning method based on ordinal regression for COVID-19 diagnosis from chest CT.

Coronavirus disease 2019 (COVID-19) has brought huge losses to the world, and it remains a great threat to public health. X-ray computed tomography (CT) plays a central role in the management of COVID-19. Traditional diagnosis with pulmonary CT images is time-consuming and error-prone, which could not meet the need of precise and rapid COVID-19 screening. Nowadays, deep learning (DL) has been successfully applied to CT image analysis, which assists radiologists in workflow scheduling and treatment planning for patients with COVID-19. Traditional method uses Cross-Entropy (CE) as loss function with Softmax layer following fully-connected layer. Most DL-based classification methods target intraclass relationship in certain class (early, progressive, severe, or dissipative phases), ignoring the natural order of different phases of the disease progression; i.e., from an early stage and progress to a late stage. To learn both intraclass and interclass relationship among different stages and improve accuracy of classification, this paper proposes an ensemble learning method based on ordinal regression, which leverages the ordinal information on COVID-19 phases. The proposed method uses multi-binary, neuron stick-breaking (NSB) and soft labels (SL) techniques, and ensembles the ordinal outputs through a median selection. To evaluate our method, we collected 172 confirmed cases. In 2-fold cross-validation experiment, the accuracy is increased by 22% compared with traditional method when we use modified Resnet-18 as backbone. And precision, recall and F1-score are also improved. The experimental results show that our proposed method achieves a better performance than the traditional methods, which helps establish guidelines for classification of COVID-19 chest CT images.