arXiv 2311.030742023-11-06eess.IVcs.CV

结合CycleGAN与联合扩散的两阶段生成模型用于基于MRI的脑肿瘤检测

A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Peking University Shenzhen Hospital（北京大学深圳医院）；National Center for Applied Mathematics Shenzhen（深圳国家应用数学中心）

Wenxin Wang, Zhuo-Xu Cui, Guanxun Cheng, Chentao Cao, Xi Xu, Ziwei Liu, Haifeng Wang, Yulong Qi, Dong Liang, Yanjie Zhu

备注：: 11 pages,9 figures,3 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对脑肿瘤检测中监督方法需大量标注、无监督生成模型分布覆盖不足的问题，提出结合CycleGAN与联合扩散的两阶段生成模型，通过异常生成、健康重建及残差分割实现无监督脑肿瘤分割，在三个数据集上取得更优性能与泛化性。

摘要：

脑肿瘤的精准检测与分割对医学诊断至关重要。然而，当前的监督学习方法需要大量带标注图像，而无监督方法中所用的主流生成模型往往在覆盖完整数据分布方面存在局限。本文提出了一种新型框架两阶段生成模型（Two-Stage Generative Model，TSGM），该框架结合循环生成对抗网络（Cycle Generative Adversarial Network，CycleGAN）与基于联合概率的方差爆炸随机微分方程（Variance Exploding stochastic differential equation using joint probability，VE-JP），以提升脑肿瘤检测与分割效果。首先在未配对数据上训练CycleGAN，从健康图像生成异常图像作为数据先验；随后引入VE-JP，以合成的配对异常图像为引导重建健康图像，该过程仅改变病理区域，不影响健康区域。值得注意的是，本方法直接学习联合概率分布以实现条件生成。输入图像与重建图像的残差可指示异常区域，随后采用阈值法得到分割结果；此外，对多模态结果赋予不同权重进行融合，以进一步提升分割精度。我们在三个数据集上验证了本方法，并与其他无监督异常检测与分割方法进行对比。在BraTs2020数据集上DSC得分为0.8590，ITCS数据集上为0.6226，内部数据集上为0.7403，结果表明本方法具备更优的分割性能与更好的泛化能力。

英文摘要：

Accurate detection and segmentation of brain tumors is critical for medical diagnosis. However, current supervised learning methods require extensively annotated images and the state-of-the-art generative models used in unsupervised methods often have limitations in covering the whole data distribution. In this paper, we propose a novel framework Two-Stage Generative Model (TSGM) that combines Cycle Generative Adversarial Network (CycleGAN) and Variance Exploding stochastic differential equation using joint probability (VE-JP) to improve brain tumor detection and segmentation. The CycleGAN is trained on unpaired data to generate abnormal images from healthy images as data prior. Then VE-JP is implemented to reconstruct healthy images using synthetic paired abnormal images as a guide, which alters only pathological regions but not regions of healthy. Notably, our method directly learned the joint probability distribution for conditional generation. The residual between input and reconstructed images suggests the abnormalities and a thresholding method is subsequently applied to obtain segmentation results. Furthermore, the multimodal results are weighted with different weights to improve the segmentation accuracy further. We validated our method on three datasets, and compared with other unsupervised methods for anomaly detection and segmentation. The DSC score of 0.8590 in BraTs2020 dataset, 0.6226 in ITCS dataset and 0.7403 in In-house dataset show that our method achieves better segmentation performance and has better generalization.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。