# Transfer Learning U-Net Deep Learning for Lung Ultrasound Segmentation

arXiv: https://arxiv.org/abs/2110.02196 · HTML: https://mlsanity.com/paper/2110.02196/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 43 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Deep learning for cardiac image segmentation: A review](https://mlsanity.com/paper/1911.03723/) (2019)
- [Image Segmentation Algorithms Overview](https://mlsanity.com/paper/1707.02051/) (2017)

## Built on by (most cited first, 3 of 3)

- [Learning Generic Lung Ultrasound Biomarkers for Decoupling Feature Extraction from Downstream Tasks](https://mlsanity.com/paper/2206.08398/) (2022)
- [Segmenting Fetal Head with Efficient Fine-tuning Strategies in Low-resource Settings: an empirical study with U-Net](https://mlsanity.com/paper/2407.20086/) (2024)
- [Evaluate Fine-tuning Strategies for Fetal Head Ultrasound Image Segmentation with U-Net](https://mlsanity.com/paper/2307.09067/) (2023)

## Abstract (arXiv)

Transfer learning (TL) for medical image segmentation helps deep learning models achieve more accurate performances when there are scarce medical images. This study focuses on completing segmentation of the ribs from lung ultrasound images and finding the best TL technique with U-Net, a convolutional neural network for precise and fast image segmentation. Two approaches of TL were used, using a pre-trained VGG16 model to build the U-Net (V-Unet) and pre-training U-Net network with grayscale natural salient object dataset (X-Unet). Visual results and dice coefficients (DICE) of the models were compared. X-Unet showed more accurate and artifact-free visual performances on the actual mask prediction, despite its lower DICE than V-Unet. A partial-frozen network fine-tuning (FT) technique was also applied to X-Unet to compare results between different FT strategies, which FT all layers slightly outperformed freezing part of the network. The effect of dataset sizes was also evaluated, showing the importance of the combination between TL and data augmentation.