Accurate segmentation of neonatal brain MRI with deep learning

被引:6
作者
Richter, Leonie [1 ]
Fetit, Ahmed E. [1 ,2 ]
机构
[1] Imperial Coll London, Dept Comp, London, England
[2] Imperial Coll London, UKRI CDT Artificial Intelligence Healthcare, London, England
基金
英国科研创新办公室;
关键词
semantic segmentation; deep learning; transfer learning; neonates; MRI; label budget; IMAGE SEGMENTATION; U-NET;
D O I
10.3389/fninf.2022.1006532
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
An important step toward delivering an accurate connectome of the human brain is robust segmentation of 3D Magnetic Resonance Imaging (MRI) scans, which is particularly challenging when carried out on perinatal data. In this paper, we present an automated, deep learning-based pipeline for accurate segmentation of tissues from neonatal brain MRI and extend it by introducing an age prediction pathway. A major constraint to using deep learning techniques on developing brain data is the need to collect large numbers of ground truth labels. We therefore also investigate two practical approaches that can help alleviate the problem of label scarcity without loss of segmentation performance. First, we examine the efficiency of different strategies of distributing a limited budget of annotated 2D slices over 3D training images. In the second approach, we compare the segmentation performance of pre-trained models with different strategies of fine-tuning on a small subset of preterm infants. Our results indicate that distributing labels over a larger number of brain scans can improve segmentation performance. We also show that even partial fine-tuning can be superior in performance to a model trained from scratch, highlighting the relevance of transfer learning strategies under conditions of label scarcity. We illustrate our findings on large, publicly available T1- and T2-weighted MRI scans (n = 709, range of ages at scan: 26-45 weeks) obtained retrospectively from the Developing Human Connectome Project (dHCP) cohort.
引用
收藏
页数:18
相关论文
共 39 条
  • [1] Fine Tuning U-Net for Ultrasound Image Segmentation: Which Layers?
    Amiri, Mina
    Brooks, Rupert
    Rivaz, Hassan
    [J]. DOMAIN ADAPTATION AND REPRESENTATION TRANSFER AND MEDICAL IMAGE LEARNING WITH LESS LABELS AND IMPERFECT DATA, DART 2019, MIL3ID 2019, 2019, 11795 : 235 - 242
  • [2] Azizpour Hossein, 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), P36, DOI 10.1109/CVPRW.2015.7301270
  • [3] Bengio Y., 2012, P ICML WORKSH UNS TR, V7, P19
  • [4] Normal Myelination: A Practical Pictorial Review
    Branson, Helen M.
    [J]. NEUROIMAGING CLINICS OF NORTH AMERICA, 2013, 23 (02) : 183 - 195
  • [5] A review of the application of deep learning in medical image classification and segmentation
    Cai, Lei
    Gao, Jingyang
    Zhao, Di
    [J]. ANNALS OF TRANSLATIONAL MEDICINE, 2020, 8 (11)
  • [6] WHAT IS THE BEST DATA AUGMENTATION FOR 3D BRAIN TUMOR SEGMENTATION?
    Cirillo, Marco Domenico
    Abramian, David
    Eklund, Anders
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 36 - 40
  • [7] Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
    Cole, James H.
    Poudel, Rudra P. K.
    Tsagkrasoulis, Dimosthenis
    Caan, Matthan W. A.
    Steves, Claire
    Spector, Tim D.
    Montana, Giovanni
    [J]. NEUROIMAGE, 2017, 163 : 115 - 124
  • [8] Neonatal brain MRI segmentation: A review
    Devi, Chelli N.
    Chandrasekharan, Anupama
    Sundararaman, V. K.
    Alex, Zachariah C.
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2015, 64 : 163 - 178
  • [9] Magnetic resonance imaging of the newborn brain: Manual segmentation of labelled atlases in term-born and preterm infants
    Gousias, Ioannis S.
    Edwards, A. David
    Rutherford, Mary A.
    Counsell, Serena J.
    Hajnal, Jo V.
    Rueckert, Daniel
    Hammers, Alexander
    [J]. NEUROIMAGE, 2012, 62 (03) : 1499 - 1509
  • [10] The UNC/UMN Baby Connectome Project (BCP): An overview of the study design and protocol development
    Howell, Brittany R.
    Styner, Martin A.
    Gao, Wei
    Yap, Pew-Thian
    Wang, Li
    Baluyot, Kristine
    Yacoub, Essa
    Chen, Geng
    Potts, Taylor
    Salzwedel, Andrew
    Li, Gang
    Gilmore, John H.
    Piven, Joseph
    Smith, J. Keith
    Shen, Dinggang
    Ugurbil, Kamil
    Zhu, Hongtu
    Lin, Weili
    Elison, Jed T.
    [J]. NEUROIMAGE, 2019, 185 : 891 - 905