# Improving the Segmentation of Anatomical Structures in Chest Radiographs using U-Net with an ImageNet Pre-trained Encoder

arXiv: https://arxiv.org/abs/1810.02113 · HTML: https://mlsanity.com/paper/1810.02113/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential](https://mlsanity.com/paper/2206.04425/) (2022)
- [Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images](https://mlsanity.com/paper/2106.10605/) (2021)
- [Modality specific U-Net variants for biomedical image segmentation: A survey](https://mlsanity.com/paper/2107.04537/) (2021)
- [Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising](https://mlsanity.com/paper/2302.13546/) (2023)
- [AxonCallosumEM Dataset: Axon Semantic Segmentation of Whole Corpus Callosum cross section from EM Images](https://mlsanity.com/paper/2307.02464/) (2023)
- [Synthetic Image Data for Deep Learning](https://mlsanity.com/paper/2212.06232/) (2022)
- [An Automated Approach for Timely Diagnosis and Prognosis of Coronavirus Disease](https://mlsanity.com/paper/2104.14116/) (2021)
- [Out-of-distribution data supervision towards biomedical semantic segmentation](https://mlsanity.com/paper/2507.12105/) (2025)

## Abstract (arXiv)

Accurate segmentation of anatomical structures in chest radiographs is essential for many computer-aided diagnosis tasks. In this paper we investigate the latest fully-convolutional architectures for the task of multi-class segmentation of the lungs field, heart and clavicles in a chest radiograph. In addition, we explore the influence of using different loss functions in the training process of a neural network for semantic segmentation. We evaluate all models on a common benchmark of 247 X-ray images from the JSRT database and ground-truth segmentation masks from the SCR dataset. Our best performing architecture, is a modified U-Net that benefits from pre-trained encoder weights. This model outperformed the current state-of-the-art methods tested on the same benchmark, with Jaccard overlap scores of 96.1% for lung fields, 90.6% for heart and 85.5% for clavicles.