Zhang Guying, Zhou Jia, He Guanghua, Zhu Hancan
School of Mathematics, Physics and Information, Shaoxing University, Shaoxing, Zhejiang, 312000, China.
Cancer Center, Gamma Knife Treatment Center, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou, Zhejiang, 310014, China.
Heliyon. 2023 Aug 18;9(8):e19266. doi: 10.1016/j.heliyon.2023.e19266. eCollection 2023 Aug.
Accurate segmentation of pathological regions in brain magnetic resonance images (MRI) is essential for the diagnosis and treatment of brain tumors. Multi-modality MRIs, which offer diverse feature information, are commonly utilized in brain tumor image segmentation. Deep neural networks have become prevalent in this field; however, many approaches simply concatenate different modalities and input them directly into the neural network for segmentation, disregarding the unique characteristics and complementarity of each modality. In this study, we propose a brain tumor image segmentation method that leverages deep residual learning with multi-modality image feature fusion. Our approach involves extracting and fusing distinct and complementary features from various modalities, fully exploiting the multi-modality information within a deep convolutional neural network to enhance the performance of brain tumor image segmentation. We evaluate the effectiveness of our proposed method using the BraTS2021 dataset and demonstrate that deep residual learning with multi-modality image feature fusion significantly improves segmentation accuracy. Our method achieves competitive segmentation results, with Dice values of 83.3, 89.07, and 91.44 for enhanced tumor, tumor core, and whole tumor, respectively. These findings highlight the potential of our method in improving brain tumor diagnosis and treatment through accurate segmentation of pathological regions in brain MRIs.
准确分割脑磁共振成像（MRI）中的病理区域对于脑肿瘤的诊断和治疗至关重要。提供多种特征信息的多模态MRI通常用于脑肿瘤图像分割。深度神经网络在该领域已变得普遍；然而，许多方法只是简单地将不同模态连接起来并直接输入到神经网络中进行分割，而忽略了每种模态的独特特征和互补性。在本研究中，我们提出了一种利用深度残差学习和多模态图像特征融合的脑肿瘤图像分割方法。我们的方法包括从各种模态中提取和融合不同且互补的特征，在深度卷积神经网络中充分利用多模态信息以提高脑肿瘤图像分割的性能。我们使用BraTS2021数据集评估了我们提出的方法的有效性，并证明了具有多模态图像特征融合的深度残差学习显著提高了分割精度。我们的方法取得了具有竞争力的分割结果，增强肿瘤、肿瘤核心和全肿瘤的Dice值分别为83.3、89.07和91.44。这些发现突出了我们的方法通过准确分割脑MRI中的病理区域在改善脑肿瘤诊断和治疗方面的潜力。
