3D U-Net for segmentation of COVID-19 associated pulmonary infiltrates using transfer learning: State-of-the-art results on affordable hardware
This work addresses the need for efficient and accessible segmentation tools for COVID-19 severity assessment, though it is incremental as it applies an existing method to new data with optimizations.
The paper tackled the problem of automating segmentation of COVID-19 pulmonary infiltrates from CT scans by using a 3D U-Net with transfer learning, achieving Dice scores of 0.679, 0.648, and 0.405 on different datasets while reducing training time and hardware requirements.
Segmentation of pulmonary infiltrates can help assess severity of COVID-19, but manual segmentation is labor and time-intensive. Using neural networks to segment pulmonary infiltrates would enable automation of this task. However, training a 3D U-Net from computed tomography (CT) data is time- and resource-intensive. In this work, we therefore developed and tested a solution on how transfer learning can be used to train state-of-the-art segmentation models on limited hardware and in shorter time. We use the recently published RSNA International COVID-19 Open Radiology Database (RICORD) to train a fully three-dimensional U-Net architecture using an 18-layer 3D ResNet, pretrained on the Kinetics-400 dataset as encoder. The generalization of the model was then tested on two openly available datasets of patients with COVID-19, who received chest CTs (Corona Cases and MosMed datasets). Our model performed comparable to previously published 3D U-Net architectures, achieving a mean Dice score of 0.679 on the tuning dataset, 0.648 on the Coronacases dataset and 0.405 on the MosMed dataset. Notably, these results were achieved with shorter training time on a single GPU with less memory available than the GPUs used in previous studies.