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
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
  • [11] REAL-TIME 2D/3D REGISTRATION VIA CNN REGRESSION
    Miao, Shun
    Wang, Z. Jane
    Zheng, Yefeng
    Liao, Rui
    2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2016, : 1430 - 1434
  • [12] A CNN Regression Approach for Real-Time 2D/3D Registration
    Miao, Shun
    Wang, Z. Jane
    Liao, Rui
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (05) : 1352 - 1363
  • [13] Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
    Kumar, Amit
    Chellappa, Rama
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 430 - 439
  • [14] Polyp detection on video colonoscopy using a hybrid 2D/3D CNN
    Puyal, Juana Gonzalez-Bueno
    Brandao, Patrick
    Ahmad, Omer F.
    Bhatia, Kanwal K.
    Toth, Daniel
    Kader, Rawen
    Lovat, Laurence
    Mountney, Peter
    Stoyanov, Danail
    MEDICAL IMAGE ANALYSIS, 2022, 82
  • [15] A 3D CNN APPROACH FOR CHANGE DETECTION IN HR SATELLITE IMAGE TIME SERIES BASED ON A PRETRAINED 2D CNN
    Meshkini, K.
    Bovolo, F.
    Bruzzone, L.
    XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III, 2022, 43-B3 : 143 - 150
  • [16] Combined 3D CNN for Brain Tumor Segmentation
    Ahmad, Parvez
    Jin, Hai
    Qamar, Saqib
    Zheng, Ran
    Jiang, Wenbin
    THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020), 2020, : 113 - 116
  • [17] Classification of hyperspectral remote sensing images using different dimension reduction methods with 3D/2D CNN
    Firat, Huseyin
    Asker, Mehmet Emin
    Hanbay, Davut
    REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT, 2022, 25
  • [18] Hyperspectral Brain Tissue Classification using a Fast and Compact 3D CNN Approach
    Ayaz, Hamail
    Tormey, David
    McLoughlin, Ian
    Ahmad, Muhammad
    Unnikrishnan, Saritha
    2022 IEEE 5TH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING APPLICATIONS AND SYSTEMS, IPAS, 2022,
  • [19] An Anatomically-Informed 3D CNN for Brain Aneurysm Classification with Weak Labels
    Di Noto, Tommaso
    Marie, Guillaume
    Tourbier, Sebastian
    Aleman-Gomez, Yasser
    Saliou, Guillaume
    Cuadra, Meritxell Bach
    Hagmann, Patric
    Richiardi, Jonas
    MACHINE LEARNING IN CLINICAL NEUROIMAGING AND RADIOGENOMICS IN NEURO-ONCOLOGY, MLCN 2020, RNO-AI 2020, 2020, 12449 : 56 - 66
  • [20] A GRAPH-CNN FOR 3D POINT CLOUD CLASSIFICATION
    Zhang, Yingxue
    Rabbat, Michael
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 6279 - 6283