Mi Jiaqi, Zhang Xindong
College of Electronic Science and Engineering, Jilin University, Changchun, China.
Med Phys. 2025 Jan;52(1):219-231. doi: 10.1002/mp.17482. Epub 2024 Oct 30.
Accurate segmentation of gliomas is crucial for diagnosis, treatment planning, and evaluating therapeutic efficacy. Physicians typically analyze and delineate tumor regions in brain magnetic resonance imaging (MRI) images based on personal experience, which is often time-consuming and subject to individual interpretation. Despite advancements in deep learning technology for image segmentation, current techniques still face challenges in clearly defining tumor boundary contours and enhancing segmentation accuracy.
To address these issues, this paper proposes a conditional diffusion network (SF-Diff) with a spatial channel attention infusion (SCAI) module and a frequency spatial attention (FSA) mechanism to achieve accurate segmentation of the whole tumor (WT) region in brain tumors.
SF-Diff initially extracts multiscale information from multimodal MRI images and subsequently employs a diffusion model to restore boundaries and details, thereby enabling accurate brain tumor segmentation (BraTS). Specifically, a SCAI module is developed to capture multiscale information within and between encoder layers. A dual-channel upsampling block (DUB) is designed to assist in detail recovery during upsampling. A FSA mechanism is introduced to better match the conditional features with the diffusion probability distribution information. Furthermore, a cross-model loss function has been implemented to supervise the feature extraction of the conditional model and the noise distribution of the diffusion model.
The dataset used in this paper is publicly available and includes 369 patient cases from the Multimodal BraTS Challenge 2020 (BraTS2020). The conducted experiments on BraTS2020 demonstrate that SF-Diff performs better than other state-of-the-art models. The method achieved a Dice score of 91.87%, a Hausdorff 95 of 5.47 mm, an IoU of 84.96%, a sensitivity of 92.29%, and a specificity of 99.95% on BraTS2020.
The proposed SF-Diff performs well in identifying the WT region of the brain tumors compared to other state-of-the-art models, especially in terms of boundary contours and non-contiguous lesion regions, which is clinically significant. In the future, we will further develop this method for brain tumor three-class segmentation task.
胶质瘤的准确分割对于诊断、治疗规划和评估治疗效果至关重要。医生通常基于个人经验在脑磁共振成像（MRI）图像中分析和勾勒肿瘤区域，这往往耗时且存在个体差异。尽管深度学习技术在图像分割方面取得了进展，但当前技术在清晰定义肿瘤边界轮廓和提高分割准确性方面仍面临挑战。
为解决这些问题，本文提出一种具有空间通道注意力注入（SCAI）模块和频率空间注意力（FSA）机制的条件扩散网络（SF-Diff），以实现脑肿瘤全肿瘤（WT）区域的准确分割。
SF-Diff首先从多模态MRI图像中提取多尺度信息，随后采用扩散模型恢复边界和细节，从而实现准确的脑肿瘤分割（BraTS）。具体而言，开发了一个SCAI模块来捕捉编码器层内和层间的多尺度信息。设计了一个双通道上采样块（DUB）来协助上采样过程中的细节恢复。引入FSA机制以更好地使条件特征与扩散概率分布信息相匹配。此外，还实现了一个跨模型损失函数来监督条件模型的特征提取和扩散模型的噪声分布。
本文使用的数据集是公开可用的，包括来自2020年多模态BraTS挑战赛（BraTS2020）的369例患者病例。在BraTS2020上进行的实验表明，SF-Diff的性能优于其他现有先进模型。该方法在BraTS2020上的Dice分数为91.87%，Hausdorff 95为5.47毫米，交并比（IoU）为84.96%，灵敏度为92.29%，特异性为99.95%。
与其他现有先进模型相比，所提出的SF-Diff在识别脑肿瘤的WT区域方面表现良好，特别是在边界轮廓和非连续病变区域方面，具有临床意义。未来，我们将进一步开发此方法用于脑肿瘤的三类分割任务。
