相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Engineering, Biomedical
Juncheng Tong et al.
Summary: The research on CNN-based automated brain tumor segmentation systems has advanced rapidly. To ensure practical application, the systems need to have good processing quality and reliability. The proposed system has a unique structure and is able to extract comprehensive feature information from multi-modality input, as well as distinguish pixels in different tumor classes. Extensive testing has shown that the system consistently produces high-quality segmentation results with extremely low computation complexity.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Zhiqin Zhu et al.
Summary: In this paper, a brain tumor segmentation method based on the fusion of deep semantics and edge information in multimodal MRI is proposed. The method utilizes Swin Transformer for semantic feature extraction, introduces a shifted patch tokenization strategy, and designs an edge spatial attention block and a multi-feature inference block based on graph convolution for feature enhancement and fusion. The experimental results demonstrate that the proposed method outperforms other methods in brain tumor segmentation.
INFORMATION FUSION
(2023)
Article
Engineering, Biomedical
Yanjun Peng et al.
Summary: In this study, an automatic weighted dilated convolutional network (AD-Net) is proposed to extract multimodal brain tumor features through channel feature separation learning. The method achieved good performance on the BraTS20 dataset.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Dongwei Liu et al.
Summary: In this study, a novel self-calibrated attention U-Net (SCAU-Net) model was proposed, which introduced external attention module and self-calibrated convolution module into a single U-Net for brain tumor segmentation. Experimental results showed that SCAU-Net achieved outstanding segmentation performance on various validation datasets and outperformed other representative brain tumor models.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Agus Subhan Akbar et al.
Summary: This paper proposes a new UNet architecture with the addition of attention in the skip connection and two atrous convolution sequences connected to the attention unit. The results show that this architecture outperforms existing methods for brain tumor segmentation and shows potential for clinical application.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Neurosciences
Yun Jiang et al.
Summary: Brain tumor semantic segmentation is a critical task in medical image processing. This research proposes SwinBTS, a new approach that combines transformer, convolutional neural network, and encoder-decoder structure for 3D brain tumor segmentation. Experimental results demonstrate that SwinBTS outperforms state-of-the-art 3D algorithms for brain tumor segmentation on 3D MRI scanned images.
Article
Neurosciences
Yang Xu et al.
Summary: In the field of medical image segmentation, traditional solutions mainly adopt convolutional neural networks (CNNs). This paper proposes a hybrid feature extraction network that combines CNNs and Transformer to better utilize global information for feature extraction and improve the segmentation performance of medical images. Additionally, a multi-dimensional statistical feature extraction module is also introduced to enhance low-dimensional texture features and further improve the segmentation results.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Mathematical & Computational Biology
Dongwei Liu et al.
Summary: This study proposes a novel 3D U-Net model called SGEResU-Net for brain tumor segmentation. The model utilizes residual blocks, spatial group-wise enhance attention blocks, and self-ensemble module to improve the accuracy of tumor segmentation. Evaluation experiments demonstrate the effectiveness of the proposed model for this medical application.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Editorial Material
Oncology
Patrick Y. Wen et al.
Article
Multidisciplinary Sciences
Ramin Ranjbarzadeh et al.
Summary: This paper proposes an effective brain tumor segmentation system, which solves the problems of brain tumor localization and segmentation in MRI images through methods like preprocessing, Cascade Deep Learning model, and Cascade Convolutional Neural Network. The proposed model achieves competitive results on the BRATS 2018 dataset.
SCIENTIFIC REPORTS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jindong Sun et al.
Summary: Gliomas are the most common brain tumors with a high mortality rate, and accurate segmentation of multimodal brain tissues is crucial for diagnosis. A novel network using residual neural blocks and U-Net architecture has been proposed to address this, achieving effective segmentation in evaluation sets with high Dice Similarity Coefficients. The residual convolutional block is key in improving model performance, making this method a powerful tool for medical image studies of brain tumors.
BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2020), PT I
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kun Cheng et al.
Summary: In this study, a patch-based 3D UNet model was trained using a hybrid loss function, which achieved good performance in brain tumor segmentation. Additionally, a label dropout process was introduced to address the issue of class imbalance effectively.
BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2020), PT II
(2021)
Proceedings Paper
Acoustics
Qing-Long Zhang et al.
Summary: Attention mechanisms are crucial in enhancing the performance of deep neural networks, with the Shuffle Attention (SA) module effectively combining two types of attention mechanisms to achieve better performance while reducing computational complexity.
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
(2021)
Article
Computer Science, Information Systems
Jianxin Zhang et al.
Article
Multidisciplinary Sciences
Spyridon Bakas et al.
Article
Computer Science, Interdisciplinary Applications
Sergio Pereira et al.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2016)
