TY - JOUR
T1 - Learning-based 3T brain MRI segmentation with guidance from 7T MRI labeling
AU - Alzheimer's Disease Neuroimaging Initiative
AU - Deng, Minghui
AU - Yu, Renping
AU - Wang, Li
AU - Shi, Feng
AU - Yap, Pew Thian
AU - Shen, Dinggang
N1 - Funding Information:
This work was supported in part by the 2013 Natural Science Program of Heilongjiang Province Educational Committee (No. 12531011), the Abroad Research Project of Heilongjiang Province University Strategic Reserve Talent, the Research Fund for the Doctoral Program of Higher Education of China (RFDP) (No. 20133219110029), and the China Scholarship Council (No. 201506840071). This work was also supported in part by National Institutes of Health Grant Nos. MH100217, MH070890, EB006733, EB008374, EB009634, AG041721, AG042599, and MH088520. ADNI Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.Loni.ucla.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.Loni.ucla.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_ List.pdf.
Publisher Copyright:
© 2016 American Association of Physicists in Medicine.
PY - 2016/12/1
Y1 - 2016/12/1
N2 - Purpose: Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. Methods: In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. Results: The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. Conclusions: The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.
AB - Purpose: Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. Methods: In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. Results: The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. Conclusions: The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.
UR - http://www.scopus.com/inward/record.url?scp=84998961886&partnerID=8YFLogxK
U2 - 10.1118/1.4967487
DO - 10.1118/1.4967487
M3 - Article
C2 - 27908163
AN - SCOPUS:84998961886
SN - 0094-2405
VL - 43
SP - 6588
EP - 6597
JO - Medical physics
JF - Medical physics
IS - 12
ER -