Yin Ziman, Ni Zhengze, Ren Yuxiang, Nie Dong, Tang Zhenyu
School of Computer, Beihang University, Beijing, China.
Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
Med Phys. 2025 Apr 28. doi: 10.1002/mp.17845.
The main task of deep learning (DL) based brain tumor segmentation is to get accurate projection from learned image features to their corresponding semantic labels (i.e., brain tumor sub-regions). To achieve this goal, segmentation networks are required to learn image features with high intra-class consistency. However, brain tumor are known to be heterogeneous, and it often causes high diversity in image gray values which further influences the learned image features. Therefore, projecting such diverse image features (i.e., low intra-class consistency) to the same semantic label is often difficult and inefficient.
The purpose of this study is to address the issue of low intra-class consistency of image features learned from heterogeneous brain tumor regions and ease the projection of image features to their corresponding semantic labels. In this way, accurate segmentation of brain tumor can be achieved.
We propose a new DL-based method for brain tumor segmentation, where a semantic feature module (SFM) is introduced to consolidate image features with meaningful semantic information and enhance their intra-class consistency. Specifically, in the SFM, deep semantic vectors are derived and used as prototypes to re-encode image features learned in the segmentation network. Since the relatively consistent deep semantic vectors, diversity of the resulting image features can be reduced; moreover, semantic information in the resulting image features can also be enriched, both facilitating accurate projection to the final semantic labels.
In the experiment, a public brain tumor dataset, BraTS2022 containing, multi-sequence MR images of 1251 patients is used to evaluate our method in the task of brain tumor sub-region segmentation, and the experimental results demonstrate that, benefiting from the SFM, our method outperforms the state-of-the-art methods with statistical significance ( using the Wilcoxon signed rank test). Further ablation study shows that the proposed SFM can yield an improvement in segmentation accuracy (Dice index) of up to 11% comparing with that without the SFM.
In DL-based segmentation, low intra-class consistency of learned image features degrades segmentation performance. The proposed SFM can effectively enhance the intra-class consistency with high-level semantic information, making the projection of image features to their corresponding semantic labels more accurate.
基于深度学习（DL）的脑肿瘤分割的主要任务是从学习到的图像特征中获得准确的投影，以对应其相应的语义标签（即脑肿瘤子区域）。为实现这一目标，分割网络需要学习具有高类内一致性的图像特征。然而，已知脑肿瘤具有异质性，这通常会导致图像灰度值的高度多样性，进而影响学习到的图像特征。因此，将这种多样的图像特征（即低类内一致性）投影到相同的语义标签上往往既困难又低效。
本研究的目的是解决从异质性脑肿瘤区域学习到的图像特征的低类内一致性问题，并简化图像特征到其相应语义标签的投影。通过这种方式，可以实现脑肿瘤的准确分割。
我们提出了一种基于深度学习的脑肿瘤分割新方法，其中引入了一个语义特征模块（SFM），以整合具有有意义语义信息的图像特征，并增强其类内一致性。具体而言，在SFM中，推导深度语义向量并将其用作原型，对在分割网络中学习到的图像特征进行重新编码。由于深度语义向量相对一致，因此可以降低所得图像特征的多样性；此外，所得图像特征中的语义信息也可以得到丰富，这两者都有助于准确投影到最终的语义标签上。
在实验中，使用一个包含1251名患者多序列磁共振图像的公共脑肿瘤数据集BraTS2022，在脑肿瘤子区域分割任务中评估我们的方法，实验结果表明，受益于SFM，我们的方法在统计学上显著优于现有方法（使用威尔科克森符号秩检验）。进一步的消融研究表明，与没有SFM的情况相比，所提出的SFM可以使分割准确率（骰子系数）提高多达11%。
在基于深度学习的分割中，学习到的图像特征的低类内一致性会降低分割性能。所提出的SFM可以有效地利用高级语义信息增强类内一致性，使图像特征到其相应语义标签的投影更加准确。
