# Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

arXiv: https://arxiv.org/abs/1909.09716 · HTML: https://mlsanity.com/paper/1909.09716/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 18 of 18)

- [SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities](https://mlsanity.com/paper/2204.02961/) (2022)
- [Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization](https://mlsanity.com/paper/2106.14662/) (2021)
- [Mimetic Models: Ethical Implications of AI that Acts Like You](https://mlsanity.com/paper/2207.09394/) (2022)
- [Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer](https://mlsanity.com/paper/2101.03711/) (2021)
- [Style Curriculum Learning for Robust Medical Image Segmentation](https://mlsanity.com/paper/2108.00402/) (2021)
- [Deep Learning for Breast MRI Style Transfer with Limited Training Data](https://mlsanity.com/paper/2301.02069/) (2023)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Feather-Light Fourier Domain Adaptation in Magnetic Resonance Imaging](https://mlsanity.com/paper/2208.00474/) (2022)
- [Domain generalization in deep learning for contrast-enhanced imaging](https://mlsanity.com/paper/2110.07360/) (2021)
- [Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach](https://mlsanity.com/paper/2202.02471/) (2022)
- [Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation](https://mlsanity.com/paper/2302.03296/) (2023)
- [MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization](https://mlsanity.com/paper/2309.02742/) (2023)
- [Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning](https://mlsanity.com/paper/2403.02566/) (2024)
- [Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions](https://mlsanity.com/paper/2107.11517/) (2021)
- [Automatic cerebral hemisphere segmentation in rat MRI with lesions via attention-based convolutional neural networks](https://mlsanity.com/paper/2108.01941/) (2021)
- [MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan](https://mlsanity.com/paper/2203.06363/) (2022)
- [Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning](https://mlsanity.com/paper/2207.14202/) (2022)
- [S3-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation](https://mlsanity.com/paper/2310.16783/) (2023)

## Abstract (arXiv)

Three-dimensional medical image segmentation is one of the most important problems in medical image analysis and plays a key role in downstream diagnosis and treatment. Recent years, deep neural networks have made groundbreaking success in medical image segmentation problem. However, due to the high variance in instrumental parameters, experimental protocols, and subject appearances, the generalization of deep learning models is often hindered by the inconsistency in medical images generated by different machines and hospitals. In this work, we present StyleSegor, an efficient and easy-to-use strategy to alleviate this inconsistency issue. Specifically, neural style transfer algorithm is applied to unlabeled data in order to minimize the differences in image properties including brightness, contrast, texture, etc. between the labeled and unlabeled data. We also apply probabilistic adjustment on the network output and integrate multiple predictions through ensemble learning. On a publicly available whole heart segmentation benchmarking dataset from MICCAI HVSMR 2016 challenge, we have demonstrated an elevated dice accuracy surpassing current state-of-the-art method and notably, an improvement of the total score by 29.91%. StyleSegor is thus corroborated to be an accurate tool for 3D whole heart segmentation especially on highly inconsistent data, and is available at https://github.com/horsepurve/StyleSegor.