AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning

被引:0
作者
Mohan, Kadri Aditya [1 ]
Kaplan, Alan D. [1 ]
机构
[1] Lawrence Livermore Natl Lab, Computat Engn Div CED, Livermore, CA 94551 USA
关键词
Three-dimensional displays; Magnetic resonance imaging; Biological neural networks; Task analysis; Image segmentation; Brain; Image reconstruction; Brain imaging; MRI; representation learning; deep learning; CNN; MRI SCANS; BRAIN; SEGMENTATION; PARCELLATION; MODEL; FMRI;
D O I
10.1109/JBHI.2021.3124733
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present a novel neural network architecture called AutoAtlas for fully unsupervised partitioning and representation learning of 3D brain Magnetic Resonance Imaging (MRI) volumes. AutoAtlas consists of two neural network components: one neural network to perform multi-label partitioning based on local texture in the volume, and a second neural network to compress the information contained within each partition. We train both of these components simultaneously by optimizing a loss function that is designed to promote accurate reconstruction of each partition, while encouraging spatially smooth and contiguous partitioning, and discouraging relatively small partitions. We show that the partitions adapt to the subject specific structural variations of brain tissue while consistently appearing at similar spatial locations across subjects. AutoAtlas also produces very low dimensional features that represent local texture of each partition. We demonstrate prediction of metadata associated with each subject using the derived feature representations and compare the results to prediction using features derived from FreeSurfer anatomical parcellation. Since our features are intrinsically linked to distinct partitions, we can then map values of interest, such as partition-specific feature importance scores onto the brain for visualization.
引用
收藏
页码:2180 / 2191
页数:12
相关论文
共 50 条
[31]   Masked Autoencoders in 3D Point Cloud Representation Learning [J].
Jiang, Jincen ;
Lu, Xuequan ;
Zhao, Lizhi ;
Dazeley, Richard ;
Wang, Meili .
IEEE TRANSACTIONS ON MULTIMEDIA, 2025, 27 :820-831
[32]   Multi-Scale Representation Learning on Hypergraph for 3D Shape Retrieval and Recognition [J].
Bai, Junjie ;
Gong, Biao ;
Zhao, Yining ;
Lei, Fuqiang ;
Yan, Chenggang ;
Gao, Yue .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 (30) :5327-5338
[33]   A Comparison of Neural Network Methods for Unsupervised Representation Learning on the Zero Resource Speech Challenge [J].
Renshaw, Daniel ;
Kamper, Herman ;
Jansen, Area ;
Goldwater, Sharon .
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, :3199-3203
[34]   Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement [J].
Nie, Qiang ;
Liu, Ziwei ;
Liu, Yunhui .
COMPUTER VISION - ECCV 2020, PT XIX, 2020, 12364 :102-118
[35]   MULTI-CLASS BRAIN TUMOR SEGMENTATION VIA 3D AND 2D NEURAL NETWORKS [J].
Pnev, Sergey ;
Groza, Vladimir ;
Tuchinov, Bair ;
Amelina, Evgeniya ;
Pavlovskiy, Evgeniy ;
Tolstokulakov, Nikolay ;
Amelin, Mihail ;
Golushko, Sergey ;
Letyagin, Andrey .
2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,
[36]   Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging [J].
Liu, Fang ;
Zhou, Zhaoye ;
Jang, Hyungseok ;
Samsonov, Alexey ;
Zhao, Gengyan ;
Kijowski, Richard .
MAGNETIC RESONANCE IN MEDICINE, 2018, 79 (04) :2379-2391
[37]   Deep Learning for 3D Point Clouds: A Survey [J].
Guo, Yulan ;
Wang, Hanyun ;
Hu, Qingyong ;
Liu, Hao ;
Liu, Li ;
Bennamoun, Mohammed .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) :4338-4364
[38]   Transcoding across 3D shape representations for unsupervised learning of 3D shape feature [J].
Furuya, Takahiko ;
Ohbuchi, Ryutarou .
PATTERN RECOGNITION LETTERS, 2020, 138 :146-154
[39]   Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging [J].
Zahia, Sofia ;
Garcia-Zapirain, Begonya ;
Saralegui, Ibone ;
Fernandez-Ruanova, Begona .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2020, 197
[40]   ShapeMed-Knee: A Dataset and Neural Shape Model Benchmark for Modeling 3D Femurs [J].
Gatti, Anthony A. ;
Blankemeier, Louis ;
Van Veen, Dave ;
Hargreaves, Brian ;
Delp, Scott L. ;
Gold, Garry E. ;
Kogan, Feliks ;
Chaudhari, Akshay S. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2025, 44 (03) :1140-1152