CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation
CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation
复制标题
DOI：
10.1109/tmi.2023.3250474
复制
发表时间：
2023-08-01
影响因子：
10.6
通讯作者：
Han, Chu
中科院分区：
文献类型：
--
作者：
Lin, Jianwei;Lin, Jiatai;Han, Chu
磁共振成像（MRI）中的脑肿瘤分割（BTS）在脑肿瘤诊断、肿瘤管理和研究中具有重要意义。随着十年BraTS挑战赛的巨大成功以及CNN和Transformer算法的进步，人们提出了许多优秀的BTS模型来解决BTS在不同技术方面的困难。然而，现有的研究很少考虑如何合理地融合多模态图像。在本文中，我们利用放射科医生如何从多种MRI模式诊断脑肿瘤的临床知识，提出了一个临床知识驱动的脑肿瘤分割模型，称为CKD-TransBTS。我们不是直接连接所有的模态，而是根据MRI的成像原理将输入模态分成两组进行重新组织。设计了一种基于模态相关交叉注意块（MCCA）的双支路混合编码器，用于提取多模态图像特征。该模型继承了Transformer和CNN的优点，具有精确病灶边界的局部特征表示能力和三维体图像的远程特征提取能力。为了弥合Transformer和CNN特征之间的差距，我们在解码器中提出了Trans & CNN特征校准块（TCFC）。我们将提出的模型与BraTS 2021挑战数据集上的六个基于cnn的模型和六个基于变压器的模型进行了比较。大量的实验表明，与所有竞争对手相比，所提出的模型具有最先进的脑肿瘤分割性能。
Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities and propose a clinical knowledge-driven brain tumor segmentation model, called CKD-TransBTS. Instead of directly concatenating all the modalities, we re-organize the input modalities by separating them into two groups according to the imaging principle of MRI. A dual-branch hybrid encoder with the proposed modality-correlated cross-attention block (MCCA) is designed to extract the multi-modality image features. The proposed model inherits the strengths from both Transformer and CNN with the local feature representation ability for precise lesion boundaries and long-range feature extraction for 3D volumetric images. To bridge the gap between Transformer and CNN features, we propose a Trans & CNN Feature Calibration block (TCFC) in the decoder. We compare the proposed model with six CNN-based models and six transformer-based models on the BraTS 2021 challenge dataset. Extensive experiments demonstrate that the proposed model achieves state-of-the-art brain tumor segmentation performance compared with all the competitors.