Qin Jiacheng, Xu Dan, Zhang Hao, Xiong Zhaoyu, Yuan Yejing, He Kangjian
School of Information Science and Engineering, Yunnan University, 650500, Kunming, China.
School of Information Science and Engineering, Yunnan University, 650500, Kunming, China.
Comput Biol Med. 2025 Mar;186:109694. doi: 10.1016/j.compbiomed.2025.109694. Epub 2025 Jan 21.
In the treatment of brain tumors, accurate diagnosis and treatment heavily rely on reliable brain tumor segmentation, where multimodal Magnetic Resonance Imaging (MRI) plays a pivotal role by providing valuable complementary information. This integration significantly enhances the performance of brain tumor segmentation. However, due to the uneven grayscale distribution, irregular shapes, and significant size variations in brain tumor images, this task remains highly challenging. In order to overcome these obstacles, we have introduced a novel framework for automated segmentation of brain tumors that leverages the diverse information from multi-modal MRI scans. Our proposed method is named BTSegDiff and it is based on a Diffusion Probability Model (DPM). First, we designed a dynamic conditional guidance module consisting of an encoder. This encoder is used to extract information from multimodal MRI images and guide the DPM in generating accurate and realistic segmentation masks. During the guidance process, we need to fuse the diffused generated features with the extracted multimodal features. However, diffusion process itself introduces a significant amount of Gaussian noise, which can affect the fusion results. Therefore, we designed a Fourier domain feature fusion module to transfer this fusion process to Euclidean space and reduce the impact of high-frequency noise on fusion. Lastly, we have taken into account that the DPM, as a generative model, produces non-unique results with each sampling. In the meticulous field of medicine, this is highly detrimental. Therefore, we have designed a Stepwise Uncertainty Sampling module based on Monte Carlo uncertainty calculation to generate unique outcomes and enhance segmentation accuracy simultaneously. To validate the effectiveness of our approach, we perform a validation on the popular BraTs2020 and BraTS2021 benchmarks. The experimental results show that our method outperforms many existing brain tumor segmentation methods. Our code is available at https://github.com/jaceqin/BTSegDiff.
在脑肿瘤治疗中，准确的诊断和治疗很大程度上依赖于可靠的脑肿瘤分割，其中多模态磁共振成像（MRI）通过提供有价值的补充信息发挥着关键作用。这种整合显著提高了脑肿瘤分割的性能。然而，由于脑肿瘤图像中灰度分布不均匀、形状不规则以及尺寸变化较大，这项任务仍然极具挑战性。为了克服这些障碍，我们引入了一种新颖的脑肿瘤自动分割框架，该框架利用多模态MRI扫描的多样信息。我们提出的方法名为BTSegDiff，它基于扩散概率模型（DPM）。首先，我们设计了一个由编码器组成的动态条件引导模块。该编码器用于从多模态MRI图像中提取信息，并引导DPM生成准确且逼真的分割掩码。在引导过程中，我们需要将扩散生成的特征与提取的多模态特征进行融合。然而，扩散过程本身会引入大量高斯噪声，这可能会影响融合结果。因此，我们设计了一个傅里叶域特征融合模块，将此融合过程转移到欧几里得空间，并减少高频噪声对融合的影响。最后，我们考虑到DPM作为一种生成模型，每次采样都会产生非唯一的结果。在医学这个严谨的领域中，这是非常不利的。因此，我们基于蒙特卡洛不确定性计算设计了一个逐步不确定性采样模块，以生成唯一结果并同时提高分割精度。为了验证我们方法的有效性，我们在流行的BraTs2020和BraTS2021基准上进行了验证。实验结果表明，我们的方法优于许多现有的脑肿瘤分割方法。我们的代码可在https://github.com/jaceqin/BTSegDiff获取。
