# 3D U-Net for segmentation of COVID-19 associated pulmonary infiltrates using transfer learning: State-of-the-art results on affordable hardware

arXiv: https://arxiv.org/abs/2101.09976 · HTML: https://mlsanity.com/paper/2101.09976/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 25 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy](https://mlsanity.com/paper/1809.04430/) (2018)
- [Towards Data-Efficient Learning: A Benchmark for COVID-19 CT Lung and Infection Segmentation](https://mlsanity.com/paper/2004.12537/) (2020)
- [COVID-19 Chest CT Image Segmentation -- A Deep Convolutional Neural Network Solution](https://mlsanity.com/paper/2004.10987/) (2020)
- [Automated Chest CT Image Segmentation of COVID-19 Lung Infection based on 3D U-Net](https://mlsanity.com/paper/2007.04774/) (2020)

## Built on by (most cited first, 1 of 1)

- [INSIGHT: Explainable Weakly-Supervised Medical Image Analysis](https://mlsanity.com/paper/2412.02012/) (2024)

## Abstract (arXiv)

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.