No abstract

Recent research on COVID-19 suggests that CT imaging provides useful information to assess disease progression and assist diagnosis, in addition to help understanding the disease. There is an increasing number of studies that propose to use deep learning to provide fast and accurate quantification of COVID-19 using chest CT scans. The main tasks of interest are the automatic segmentation of lung and lung lesions in chest CT scans of confirmed or suspected COVID-19 patients. In this study, we compare twelve deep learning algorithms using a multi-center dataset, including both open-source and in-house developed algorithms. Results show that ensembling different methods can boost the overall test set performance for lung segmentation, binary lesion segmentation and multiclass lesion segmentation, resulting in mean Dice scores of 0.982, 0.724 and 0.469, respectively. The resulting binary lesions were segmented with a mean absolute volume error of 91.3 ml. In general, the task of distinguishing different lesion types was more difficult, with a mean absolute volume difference of 152 ml and mean Dice scores of 0.369 and 0.523 for consolidation and ground glass opacity, respectively. All methods perform binary lesion segmentation with an average volume error that is better than visual assessment by human raters, suggesting these methods are mature enough for a large-scale evaluation for use in clinical practice. Code for all the methods developed in this paper will be made publicly available. List of abbreviationsCT = computed tomography; COVID-19 = coronavirus disease 2019; RT-PCR = reverse-transcription polymerase chain reaction; GGO = ground glass opacity; CON = mix of consolidation and linear opacity; CPP = crazy paving pattern; COM = combined pattern (mix of GGO, CON and CPP); OAT = other abnormal tissue; SEN = sensitivity; DSC = Dice score coefficient; HD95 = Hausdorff distance at 95% percentile; ASD = average surface difference; AVD = average volume difference; CNN = convolutional neural network; HU = Hounsfield units. * These authors contributed equally. Order was chosen randomly.

No abstract