用合成数据提升脑瘤分割精度，实现在治疗后和放疗规划中的表现。
Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation
- 通过生成合成医学影像数据增强训练，改进深度模型对胶质瘤与脑膜瘤的分割能力。
- 在任务1中，六类肿瘤分割的DSC最高达0.8938，平均HD95为28.46，性能优异。
- 适合关注医学图像分割、数据增强及临床落地的科研与医疗工程师参考。
本文介绍了在BraTS挑战赛任务1中获得第一名、任务3中获得第三名的解决方案。随着算法日益复杂且可靠，自动化工具在临床中的应用不断增长，但要达到临床标准并适应真实场景仍具挑战。为此，BraTS组织了多项任务以发掘最先进的解决方案。本文提出利用合成数据训练当前最先进框架，以改善治疗后成人胶质瘤的分割以及用于放疗规划的脑膜瘤分割。结果显示，合成数据可使算法更具鲁棒性，尽管其生成流程对脑膜瘤任务适配度较低。在任务1中，各结构（ET、NETC、RC、SNFH、TC、WT）的DSC分别为0.7900、0.8076、0.7760、0.8926、0.7874、0.8938，对应的HD95为35.63、30.35、44.58、16.87、38.19、17.95；任务3测试阶段取得DSC 0.801，HD95 38.26。代码已开源：https://github.com/ShadowTwin41/BraTS_2023_2024_solutions。
原文摘要 · Abstract (English)
This paper presents the winning solution of task 1 and the third-placed solution of task 3 of the BraTS challenge. The use of automated tools in clinical practice has increased due to the development of more and more sophisticated and reliable algorithms. However, achieving clinical standards and developing tools for real-life scenarios is a major challenge. To this end, BraTS has organised tasks to find the most advanced solutions for specific purposes. In this paper, we propose the use of synthetic data to train state-of-the-art frameworks in order to improve the segmentation of adult gliomas in a post-treatment scenario, and the segmentation of meningioma for radiotherapy planning. Our results suggest that the use of synthetic data leads to more robust algorithms, although the synthetic data generation pipeline is not directly suited to the meningioma task. In task 1, we achieved a DSC of 0.7900, 0.8076, 0.7760, 0.8926, 0.7874, 0.8938 and a HD95 of 35.63, 30.35, 44.58, 16.87, 38.19, 17.95 for ET, NETC, RC, SNFH, TC and WT, respectively and, in task 3, we achieved a DSC of 0.801 and HD95 of 38.26, in the testing phase. The code for these tasks is available at https://github.com/ShadowTwin41/BraTS_2023_2024_solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。