Tractography and machine learning: Current state and open challenges

被引:33
|
作者
Poulin, Philippe [1 ]
Jorgens, Daniel [2 ]
Jodoin, Pierre-Marc [1 ]
Descoteaux, Maxims [1 ]
机构
[1] Univ Sherbrooke, Dept Comp Sci, Sherbrooke, PQ, Canada
[2] KTH Royal Inst Technol, Dept Biomed Engn & Hlth Syst, Stockholm, Sweden
基金
加拿大自然科学与工程研究理事会;
关键词
Diffusion MRI; Tractography; Machine learning; Benchmark; STANDARDIZED EVALUATION; DIFFUSION; SEGMENTATION; CONNECTOME; RECONSTRUCTION; FRAMEWORK; PROTOCOL; RICIAN; NOISE;
D O I
10.1016/j.mri.2019.04.013
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Supervised machine learning (ML) algorithms have recently been proposed as an alternative to traditional tractography methods in order to address some of their weaknesses. They can be path-based and local-model-free, and easily incorporate anatomical priors to make contextual and non-local decisions that should help the tracking process. ML-based techniques have thus shown promising reconstructions of larger spatial extent of existing white matter bundles, promising reconstructions of less false positives, and promising robustness to known position and shape biases of current tractography techniques. But as of today, none of these ML-based methods have shown conclusive performances or have been adopted as a de facto solution to tractography. One reason for this might be the lack of well-defined and extensive frameworks to train, evaluate, and compare these methods. In this paper, we describe several datasets and evaluation tools that contain useful features for ML algorithms, along with the various methods proposed in the recent years. We then discuss the strategies that are used to evaluate and compare those methods, as well as their shortcomings. Finally, we describe the particular needs of ML tractography methods and discuss tangible solutions for future works.
引用
收藏
页码:37 / 48
页数:12
相关论文
共 50 条
  • [1] Quantum Machine Learning: Current State and Challenges
    Avramouli, Maria
    Savvas, Ilias K.
    Garani, Georgia
    Vasilaki, Anna
    [J]. 25TH PAN-HELLENIC CONFERENCE ON INFORMATICS WITH INTERNATIONAL PARTICIPATION (PCI2021), 2021, : 397 - 402
  • [2] Automated Machine Learning: State-of-The-Art and Open Challenges
    Elshawi, Radwa
    Sakr, Sherif
    [J]. RESEARCH CHALLENGES IN INFORMATION SCIENCE (RCIS 2020), 2020, 385 : 627 - 629
  • [3] Open Challenges in Federated Machine Learning
    Baresi, Luciano
    Quattrocchi, Giovanni
    Rasi, Nicholas
    [J]. IEEE INTERNET COMPUTING, 2023, 27 (02) : 20 - 27
  • [4] Big Data Machine Learning and Graph Analytics: Current State and Future Challenges
    Huang, H. Howie
    Liu, Hang
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2014,
  • [5] Diffusion MRI tractography for neurosurgery: the basics, current state, technical reliability and challenges
    Yang, Joseph Yuan-Mou
    Yeh, Chun-Hung
    Poupon, Cyril
    Calamante, Fernando
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2021, 66 (15):
  • [6] Microstructure Informed Tractography: Pitfalls and Open Challenges
    Daducci, Alessandro
    Dal Palu, Alessandro
    Descoteaux, Maxime
    Thiran, Jean-Philippe
    [J]. FRONTIERS IN NEUROSCIENCE, 2016, 10
  • [7] Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges
    Hussain, Fatima
    Hassan, Syed Ali
    Hussain, Rasheed
    Hossain, Ekram
    [J]. IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2020, 22 (02): : 1251 - 1275
  • [8] Fiber tractography using machine learning
    Neher, Peter F.
    Cote, Marc-Alexandre
    Houde, Jean-Christophe
    Descoteaux, Maxime
    Maier-Hein, Klaus H.
    [J]. NEUROIMAGE, 2017, 158 : 417 - 429
  • [9] Open forum on the current state and future challenges of econometrics
    Hsiao, C
    [J]. JOURNAL OF ECONOMETRICS, 2001, 100 (01) : 1 - 1
  • [10] The Current State and Challenges of Fairness in Federated Learning
    Vucinich, Sean
    Zhu, Qiang
    [J]. IEEE ACCESS, 2023, 11 : 80903 - 80914