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
  • [1] Spatial-Temporal Asynchronous Normalization for Unsupervised 3D Action Representation Learning
    Liu, Mengyuan
    Bao, Youneng
    Liang, Yongsheng
    Meng, Fanyang
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 632 - 636
  • [2] Unsupervised Segmentation of 3D Medical Images Based on Clustering and Deep Representation Learning
    Moriya, Takayasu
    Roth, Holger R.
    Nakamura, Shota
    Oda, Hirohisa
    Nagara, Kai
    Oda, Masahiro
    Mori, Kensaku
    MEDICAL IMAGING 2018: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING, 2018, 10578
  • [3] An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation
    Wu, Qing
    Li, Yuwei
    Sun, Yawen
    Zhou, Yan
    Wei, Hongjiang
    Yu, Jingyi
    Zhang, Yuyao
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (02) : 1004 - 1015
  • [4] An Unsupervised Learning Approach to 3D Rectal MRI Volume Registration
    Ho, Chi-Jui
    Duong, Soan T. M.
    Wang, Yiqian
    Nguyen, Chanh D. Tr.
    Bui, Bieu Q.
    Truong, Steven Q. H.
    Nguyen, Truong Q.
    An, Cheolhong
    IEEE ACCESS, 2022, 10 : 87650 - 87660
  • [5] PointGLR: Unsupervised Structural Representation Learning of 3D Point Clouds
    Rao, Yongming
    Lu, Jiwen
    Zhou, Jie
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (02) : 2193 - 2207
  • [6] A Kernel-based Representation to Support 3D MRI Unsupervised Clustering
    Cardenas-Pena, D.
    Orbes-Arteaga, M.
    Castro-Ospina, A.
    Alvarez-Meza, A.
    Castellanos-Dominguez, G.
    2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 3203 - 3208
  • [7] MVCNet: Multiview Contrastive Network for Unsupervised Representation Learning for 3-D CT Lesions
    Zhai, Penghua
    Cong, Huaiwei
    Zhu, Enwei
    Zhao, Gangming
    Yu, Yizhou
    Li, Jinpeng
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (06) : 7376 - 7390
  • [8] 3D Interactive Segmentation With Semi-Implicit Representation and Active Learning
    Deng, Jingjing
    Xie, Xianghua
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 9402 - 9417
  • [9] Unsupervised Learning in Winner-Takes-All Neural Network Based on 3D NAND Flash
    Zhou, Wen
    Jin, Lei
    Jia, Xinlei
    Wang, Tingze
    Xu, Pengyu
    Zhang, An
    Huo, Zongliang
    IEEE ELECTRON DEVICE LETTERS, 2022, 43 (03) : 374 - 377
  • [10] Deep Learning on Object-Centric 3D Neural Fields
    Ramirez, Pierluigi Zama
    De Luigi, Luca
    Sirocchi, Daniele
    Cardace, Adriano
    Spezialetti, Riccardo
    Ballerini, Francesco
    Salti, Samuele
    Di Stefano, Luigi
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (12) : 9940 - 9956