# Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Net

arXiv: https://arxiv.org/abs/1809.00960 · HTML: https://mlsanity.com/paper/1809.00960/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2018.

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

- [Pyramid Medical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2104.14702/) (2021)
- [MediSee: Reasoning-based Pixel-level Perception in Medical Images](https://mlsanity.com/paper/2504.11008/) (2025)
- [Weaving Attention U-net: A Novel Hybrid CNN and Attention-based Method for Organs-at-risk Segmentation in Head and Neck CT Images](https://mlsanity.com/paper/2107.04847/) (2021)
- [Towards more precise automatic analysis: a comprehensive survey of deep learning-based multi-organ segmentation](https://mlsanity.com/paper/2303.00232/) (2023)
- [Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation](https://mlsanity.com/paper/2302.03296/) (2023)
- [Uncertainty Driven Bottleneck Attention U-net for Organ at Risk Segmentation](https://mlsanity.com/paper/2303.10796/) (2023)
- [MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images](https://mlsanity.com/paper/2511.12110/) (2025)
- [OARnet: Automated organs-at-risk delineation in Head and Neck CT images](https://mlsanity.com/paper/2108.13987/) (2021)
- [A novel shape-based loss function for machine learning-based seminal organ segmentation in medical imaging](https://mlsanity.com/paper/2203.03336/) (2022)

## Abstract (arXiv)

Accurate segmentation of organ at risk (OAR) play a critical role in the treatment planning of image guided radiation treatment of head and neck cancer. This segmentation task is challenging for both human and automatic algorithms because of the relatively large number of OARs to be segmented, the large variability of the size and morphology across different OARs, and the low contrast of between some OARs and the background. In this paper, we proposed a two-stage segmentation framework based on 3D U-Net. In this framework, the segmentation of each OAR is decomposed into two sub-tasks: locating a bounding box of the OAR and segment it from a small volume within the bounding box, and each sub-tasks is fulfilled by a dedicated 3D U-Net. The decomposition makes each of the two sub-tasks much easier, so that they can be better completed. We evaluated the proposed method and compared it to state-of-the-art methods by using the MICCAI 2015 Challenge dataset. In terms of the boundary-based metric 95HD, the proposed method ranked first in eight of all nine OARs and ranked second in the other OAR. In terms of the area-based metric DSC, the proposed method ranked first in six of the nine OARs and ranked second in the other three OARs with small difference with the first one.