ABSTRACT
Background: The COVID-19 disease is putting unprecedented pressure on the global healthcare system. The CT examination as a auxiliary confirmed diagnostic method can help clinicians quickly detect lesions locations of COVID-19 once screening by PCR test. Furthermore, the lesion subtypes classification plays a critical role in the consequent treatment decision. Identifying the subtypes of lesions accurately can help doctors discover changes in lesions in time and better assess the severity of COVID-19. Method: The most four typical lesion subtypes of COVID-19 are discussed in this paper, which are ground-glass opacity (GGO), cord, solid and subsolid. A computer aided diagnosis approach of lesion subtype is proposed in this paper. The radiomics data of lesions are segmented from COVID-19 patients CT images with diagnosis and lesions annotations by radiologists. Then the three dimensional texture descriptors are applied on the volume data of lesions as well as shape and First order features. The massive feature data are selected by hybrid adaptive selection algorithm and a classification model is trained at the same time. The classifier is used to predict lesion subtypes as side decision information for radiologists. Results: There are 3734 lesions extracted from the dataset with 319 patients collection and then 189 radiomics features are obtained finally. The random forest classifier is trained with data augmentation that the number of different subtypes of lesions is imbalanced in initial dataset. The experimental results show that the accuracy of the four subtypes of lesions is (0.9306, 0.9684, 0.9958, and 0.9430), the recall is (0.9552, 0.9158, 0.9580 and 0.8075) and the f-score is (0.93.84, 0.92.37, 0.95.47, and 84.42). Conclusion: The method is evaluated in multiple sufficient experiments. The results show that the 3D radiomics features chosen by hybrid adaptive selection algorithm can better express the advanced information of the lesion data. The classification model obtains a good performance and is compared the models of COVID-19 in the stat of art, which can help clinicians more accurately identify the subtypes of COVID-19 lesions and provide help for further research.