Infant Brain Age Classification: 2D CNN Outperforms 3D CNN in Small Dataset

被引:0
作者
Shabanian, Mahdieh [1 ]
Wenzel, Markus [2 ]
DeVincenzo, John P. [3 ]
机构
[1] Univ Tennessee, Ctr Hlth Sci, Dept Biomed Engn, Memphis, TN 38163 USA
[2] Fraunhofer Inst Digital Med MEVIS, Bremen, Germany
[3] Enanta Pharmaceut, Watertown, MA USA
来源
MEDICAL IMAGING 2022: IMAGE PROCESSING | 2022年 / 12032卷
关键词
Deep learning; CNN; neurodevelopmental; age estimation; infant diseases; MACHINE; MRI;
D O I
10.1117/12.2612887
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Determining if the brain is developing normally is a key component of pediatric neuroradiology and neurology. Brain magnetic resonance imaging (MRI) of infants demonstrates a specific pattern of development beyond simply myelination. While radiologists have used myelination patterns, brain morphology and size characteristics to determine age-adequate brain maturity, this requires years of experience in pediatric neuroradiology. With no standardized criteria, visual estimation of the structural maturity of the brain from MRI before three years of age remains dominated by inter-observer and intra-observer variability. A more objective estimation of brain developmental age could help physicians identify many neurodevelopmental conditions and diseases earlier and more reliably. Such data, however, is naturally hard to obtain, and the observer ground truth not much of a gold standard due to subjectivity of assessment. In this light, we explore the general feasibility to tackle this task, and the utility of different approaches, including two- and three-dimensional convolutional neural networks (CNN) that were trained on a fusion of T1-weighted, T2-weighted, and proton density (PD) weighted sequences from 84 individual subjects divided into four age groups from birth to 3 years of age. In the best performing approach, we achieved an accuracy of 0.90 [95% CI:0.86-0.94] using a 2D CNN on a central axial thick slab. We discuss the comparison to 3D networks and show how the performance compares to the use of only one sequence (T1w). In conclusion, despite the theoretical superiority of 3D CNN approaches, in limited-data situations, such approaches are inferior to simpler architectures. The code can be found in https://github.com/shabanian2018/Age_MRI-Classification
引用
收藏
页数:8
相关论文
共 50 条
[31]   Off-the-shelf CNN features for 3D object retrieval [J].
Dong Wang ;
Bin Wang ;
Sicheng Zhao ;
Hongxun Yao ;
Hong Liu .
Multimedia Tools and Applications, 2018, 77 :19833-19849
[32]   A MULTIPLE DECODER CNN FOR INVERSE CONSISTENT 3D IMAGE REGISTRATION [J].
Nazib, Abdullah ;
Fookes, Clinton ;
Salvado, Olivier ;
Perrin, Dimitri .
2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2021, :904-907
[33]   Off-the-shelf CNN features for 3D object retrieval [J].
Wang, Dong ;
Wang, Bin ;
Zhao, Sicheng ;
Yao, Hongxun ;
Liu, Hong .
MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (15) :19833-19849
[34]   HybridSN: Exploring 3-D-2-D CNN Feature Hierarchy for Hyperspectral Image Classification [J].
Roy, Swalpa Kumar ;
Krishna, Gopal ;
Dubey, Shiv Ram ;
Chaudhuri, Bidyut B. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (02) :277-281
[35]   Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification [J].
Hiba Mzoughi ;
Ines Njeh ;
Ali Wali ;
Mohamed Ben Slima ;
Ahmed BenHamida ;
Chokri Mhiri ;
Kharedine Ben Mahfoudhe .
Journal of Digital Imaging, 2020, 33 :903-915
[36]   Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification [J].
Mzoughi, Hiba ;
Njeh, Ines ;
Wali, Ali ;
Ben Slima, Mohamed ;
BenHamida, Ahmed ;
Mhiri, Chokri ;
Ben Mahfoudhe, Kharedine .
JOURNAL OF DIGITAL IMAGING, 2020, 33 (04) :903-915
[37]   Enhancement the DOA for 2D Coprime Array Using CNN [J].
Mubarak, Sura M. ;
Sabar, Bayan M. .
INTERNATIONAL JOURNAL OF MULTIPHYSICS, 2024, 18 (03) :1524-1533
[38]   Systolic-based 2D convolver for CNN in FPGA [J].
Hrabovsky, J. ;
Segec, P. ;
Moravcik, M. ;
Papan, J. .
2017 15TH IEEE INTERNATIONAL CONFERENCE ON EMERGING ELEARNING TECHNOLOGIES AND APPLICATIONS (ICETA 2017), 2017, :147-153
[39]   CNN based 2D object detection techniques: a review [J].
Lamichhane, Badri Raj ;
Srijuntongsiri, Gun ;
Horanont, Teerayut .
FRONTIERS IN COMPUTER SCIENCE, 2025, 7
[40]   Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data [J].
Islam N.U. ;
Khanam R. ;
Kumar A. .
Journal of Engineering and Applied Science, 2023, 70 (01)