Deep learning can provide rapid brain age estimation based on brain magnetic resonance imaging (MRI). However, most studies use one neural network to extract the global information from the whole input image, ignoring the local fine-grained details. In this paper, we propose a global-local transformer, which consists of a global-pathway to extract the global-context information from the whole input image and a local-pathway to extract the local fine-grained details from local patches. The fine-grained information from the local patches are fused with the global-context information by the attention mechanism, inspired by the transformer, to estimate the brain age. We evaluate the proposed method on 8 public datasets with 8,379 healthy brain MRIs with the age range of 0-97 years. 6 datasets are used for cross-validation and 2 datasets are used for evaluating the generality. Comparing with other state-of-the-art methods, the proposed global-local transformer reduces the mean absolute error of the estimated ages to 2.70 years and increases the correlation coefficient of the estimated age and the chronological age to 0.9853. In addition, our proposed method provides regional information of which local patches are most informative for brain age estimation. Our source code is available on: \url{https://github.com/shengfly/global-local-transformer}.
Brain Tumor Classification using Vision Transformer with Selective Cross-Attention Mechanism and Feature Calibration
K.N. Toosi University of Technology(霍梅尼国际大学(K.N. Toosi理工大学));Indiana University-Purdue University(印第安纳大学-普渡大学);Shahed university(沙希德大学);University of Cincinnati(辛辛那提大学)
Improving Across-Dataset Brain Tissue Segmentation Using Transformer
Columbia University(哥伦比亚大学);Mortimer B. Zuckerman Mind Brain Behavior Institute(Mortimer B. Zuckerman 心智与脑行为研究所)
脑组织分割在通过基于体素的形态学量化MRI数据和突出与脑内各种状况相关的细微结构变化方面具有很大的实用性。然而,手动分割是高度劳动密集型的,并且由于MRI采集的固有属性,自动化方法一直在努力,因此非常需要有效的分割工具。尽管最近深度卷积神经网络(CNN)在脑组织分割方面取得了成功,但许多此类解决方案并不能很好地推广到新的数据集,这对于可靠的解决方案至关重要。Transformers已经在自然图像分割中取得了成功,并且最近已被应用于3D医学图像分割任务,因为它们能够在CNN的局部感受野挣扎的输入中捕获长距离关系。这项研究介绍了一种新的CNN-Transformer混合架构,设计用于脑组织分割。我们在四个多站点T1 w MRI数据集上验证了我们模型的性能,这些数据集涵盖了不同的供应商、场强、扫描参数、时间点和神经精神疾病。在所有情况下,我们的模型实现了最大的通用性和可靠性。Out方法具有固有的鲁棒性,可以作为脑相关T1 w MRI研究的有价值的工具。TABS网络的代码可在https://github.com/raovish6/TABS上获得。
NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation
Tianjin University(天津大学);The University of Hong Kong(香港大学);Huanhu Hospital(环湖医院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学)
mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Tencent(腾讯);University of California, Los Angeles(加州大学洛杉矶分校);Lenovo Research(联想研究院)
View-Disentangled Transformer for Brain Lesion Detection
Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳)深圳大数据研究院);Sun Yat-sen University(中山大学);Pazhou Lab(琶洲实验室)
Unsupervised Anomaly Detection in 3D Brain MRI using Deep Learning with Multi-Task Brain Age Prediction
Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology(汉堡工业大学医疗技术与智能系统研究所);jung diagnostics GmbH(jung diagnostics GmbH公司);Hamburg University of Technology(汉堡工业大学)
SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions
Dept. of Math and Computer Science(数学与计算机科学系);Department of Neuroinflammation(神经炎症系);School of Physics, Engineering and CS(物理、工程与计算机科学学校);University of Hertfordshire(赫特福德大学)
Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School(马萨诸塞州总医院与哈佛医学院戈登医学影像中心);Korea Advanced Institute of Science and Technology(韩国科学技术院)
Estimating Brain Age with Global and Local Dependencies
Harbin Institute of Technology at Shenzhen(哈尔滨工业大学(深圳));Peng Cheng Laboratory(鹏城实验室);Capital Medical University(首都医科大学);Xuanwu Hospital Capital Medical University(首都医科大学宣武医院);MindsGo Life Science Co.Ltd(迈格生命科技有限公司)
Model and predict age and sex in healthy subjects using brain white matter features: A deep learning approach
Glasgow College, University of Electronic Science and Technology of China(电子科技大学格拉斯哥学院);Brigham and Women's Hospital, Harvard Medical School(哈佛医学院布莱根妇女医院)
Transformer based Models for Unsupervised Anomaly Segmentation in Brain MR Images
Univ. Rennes(雷恩大学);INSA Rennes(雷恩国立应用科学学院);CNRS(法国国家科学研究中心);University Hospital Bonn(波恩大学医院);Helmholtz Munich(亥姆霍兹慕尼黑中心);Technical University of Munich(慕尼黑工业大学)
Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation
Wellcome Centre for Human Neuroimaging, University College London(伦敦大学学院惠康人类神经成像中心);NVIDIA(英伟达);University of California, San Francisco(加州大学旧金山分校);Helen Wills Neuroscience Institute, University of California, Berkeley(加州大学伯克利分校海伦·威尔斯神经科学研究所);Stevens Institute for Neuroimaging and Informatics, University of Southern California(南加州大学史蒂文斯神经成像与信息学研究所)
针对 3D 脑病变分割,本文提出 U-Net 的全卷积 transformer 块变体,以大核注意力兼顾长程建模、CNN 参数效率与 transformer 归纳偏置,性能达到先进水平并开源代码。
Brain3D: Brain Report Automation via Inflated Vision Transformers in 3D
University of Naples Federico II, Department of Electrical Engineering and Information Technology(那不勒斯费德里科二世大学电子工程与信息技术系);Northwestern University, Dept. of Computer Science, McCormick School of Engineering and Applied Science(西北大学计算机科学系,工程与应用科学学院);Pegaso University, Department of Information Science and Technology(佩加索大学信息科学与技术系)
Residual Vision Transformer (ResViT) Based Self-Supervised Learning Model for Brain Tumor Classification
Center for Diabetes Technology(糖尿病技术中心);University of Virginia(弗吉尼亚大学);Erciyes University(埃尔齐耶斯大学);Biocomplexity Institute and Initiative(生物复杂性研究所与倡议项目)
Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4
The Center for Brains, Minds and Machines(大脑、心智与机器中心);Massachusetts Institute of Technology(麻省理工学院)
现代在大脑评分竞赛中获得高分的视觉模型并不源于Vision Transformers。然而,在本文中,我们通过展示双流Transformer,CrossViT $~\textit{a la}$ Chen et al.(2021),在联合旋转不变和对抗优化程序下,在2022年总Brain-Score竞赛中获得第二名,提供了反对Vision Transformers(ViT)在感知上与人类视觉表示不一致的意外趋势的证据(Schrimpf et al.,2020 b)在所有视觉类别中平均,并且在比赛时在V4区域的最高可解释方差中排名第一。此外,我们目前的基于变换器的模型还实现了区域V4、IT和行为的更大的可解释方差,而不是生物启发的CNN(ResNet 50),其集成了类似于额叶V1的计算模块(Dapello等人,2020年)。为了评估优化方案对CrossViT架构的贡献,我们对不同优化的CrossViT的对抗鲁棒性,常见的腐败基准,中腹部刺激解释和特征反转进行了几次额外的实验。与我们最初的预期,我们的家庭的结果提供了临时支持$\textit{"All roads lead to Rome"}$参数通过联合优化规则,即使是非生物学动机的模型,如Vision Transformers的视觉。代码可在https://github.com/williamberrios/BrainScore-T…
An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection
Ahsanullah University of Science and Technology(阿沙努拉科学与技术大学);Bangladesh University of Engineering and Technology(孟加拉工程与技术大学);Southeast University(东南大学)