# A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Images

arXiv: https://arxiv.org/abs/2109.12634 · HTML: https://mlsanity.com/paper/2109.12634/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 26 Sep 2021.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Understanding Convolution for Semantic Segmentation](https://mlsanity.com/paper/1702.08502/) (2017)
- [AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy](https://mlsanity.com/paper/1808.05238/) (2018)
- [3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes](https://mlsanity.com/paper/1711.08580/) (2017)
- [FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images](https://mlsanity.com/paper/1907.12056/) (2019)
- [Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search](https://mlsanity.com/paper/2004.08426/) (2020)
- [X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies](https://mlsanity.com/paper/1907.07000/) (2019)
- [Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation](https://mlsanity.com/paper/2012.09279/) (2020)
- [Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation](https://mlsanity.com/paper/1908.01997/) (2019)

## Built on by (most cited first, 7 of 7)

- [Tackling the Class Imbalance Problem of Deep Learning Based Head and Neck Organ Segmentation](https://mlsanity.com/paper/2201.01636/) (2022)
- [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)
- [Comparing Bayesian Models for Organ Contouring in Head and Neck Radiotherapy](https://mlsanity.com/paper/2111.01134/) (2021)
- [Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation](https://mlsanity.com/paper/2409.03470/) (2024)
- [MOSAIC: A Multi-View 2.5D Organ Slice Selector with Cross-Attentional Reasoning for Anatomically-Aware CT Localization in Medical Organ Segmentation](https://mlsanity.com/paper/2505.10672/) (2025)
- [HUR-MACL: High-Uncertainty Region-Guided Multi-Architecture Collaborative Learning for Head and Neck Multi-Organ Segmentation](https://mlsanity.com/paper/2601.04607/) (2026)

## Abstract (arXiv)

Radiation therapy (RT) is widely employed in the clinic for the treatment of head and neck (HaN) cancers. An essential step of RT planning is the accurate segmentation of various organs-at-risks (OARs) in HaN CT images. Nevertheless, segmenting OARs manually is time-consuming, tedious, and error-prone considering that typical HaN CT images contain tens to hundreds of slices. Automated segmentation algorithms are urgently required. Recently, convolutional neural networks (CNNs) have been extensively investigated on this task. Particularly, 3D CNNs are frequently adopted to process 3D HaN CT images. There are two issues with na"ive 3D CNNs. First, the depth resolution of 3D CT images is usually several times lower than the in-plane resolution. Direct employment of 3D CNNs without distinguishing this difference can lead to the extraction of distorted image features and influence the final segmentation performance. Second, a severe class imbalance problem exists, and large organs can be orders of times larger than small organs. It is difficult to simultaneously achieve accurate segmentation for all the organs. To address these issues, we propose a novel hybrid CNN that fuses 2D and 3D convolutions to combat the different spatial resolutions and extract effective edge and semantic features from 3D HaN CT images. To accommodate large and small organs, our final model, named OrganNet2.5D, consists of only two instead of the classic four downsampling operations, and hybrid dilated convolutions are introduced to maintain the respective field. Experiments on the MICCAI 2015 challenge dataset demonstrate that OrganNet2.5D achieves promising performance compared to state-of-the-art methods.