TY - JOUR
T1 - Multi-resolution super learner for voxel-wise classification of prostate cancer using multi-parametric MRI
AU - Jin, Jin
AU - Zhang, Lin
AU - Leng, Ethan
AU - Metzger, Gregory J.
AU - Koopmeiners, Joseph S.
N1 - Publisher Copyright:
© 2021 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2023
Y1 - 2023
N2 - Multi-parametric MRI (mpMRI) is a critical tool in prostate cancer (PCa) diagnosis and management. To further advance the use of mpMRI in patient care, computer aided diagnostic methods are under continuous development for supporting/supplanting standard radiological interpretation. While voxel-wise PCa classification models are the gold standard, few if any approaches have incorporated the inherent structure of the mpMRI data, such as spatial heterogeneity and between-voxel correlation, into PCa classification. We propose a machine learning-based method to fill in this gap. Our method uses an ensemble learning approach to capture regional heterogeneity in the data, where classifiers are developed at multiple resolutions and combined using the super learner algorithm, and further account for between-voxel correlation through a Gaussian kernel smoother. It allows any type of classifier to be the base learner and can be extended to further classify PCa sub-categories. We introduce the algorithms for binary PCa classification, as well as for classifying the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to improve the detection of less prevalent cancer categories. The proposed method has shown important advantages over conventional modeling and machine learning approaches in simulations and application to our motivating patient data.
AB - Multi-parametric MRI (mpMRI) is a critical tool in prostate cancer (PCa) diagnosis and management. To further advance the use of mpMRI in patient care, computer aided diagnostic methods are under continuous development for supporting/supplanting standard radiological interpretation. While voxel-wise PCa classification models are the gold standard, few if any approaches have incorporated the inherent structure of the mpMRI data, such as spatial heterogeneity and between-voxel correlation, into PCa classification. We propose a machine learning-based method to fill in this gap. Our method uses an ensemble learning approach to capture regional heterogeneity in the data, where classifiers are developed at multiple resolutions and combined using the super learner algorithm, and further account for between-voxel correlation through a Gaussian kernel smoother. It allows any type of classifier to be the base learner and can be extended to further classify PCa sub-categories. We introduce the algorithms for binary PCa classification, as well as for classifying the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to improve the detection of less prevalent cancer categories. The proposed method has shown important advantages over conventional modeling and machine learning approaches in simulations and application to our motivating patient data.
KW - Multi-parametric MRI
KW - multi-resolution modeling
KW - ordinal clinical significance of PCa
KW - super learner
KW - voxel-wise PCa classification
UR - http://www.scopus.com/inward/record.url?scp=85121718957&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121718957&partnerID=8YFLogxK
U2 - 10.1080/02664763.2021.2017411
DO - 10.1080/02664763.2021.2017411
M3 - Article
C2 - 36819087
AN - SCOPUS:85121718957
SN - 0266-4763
VL - 50
SP - 805
EP - 826
JO - Journal of Applied Statistics
JF - Journal of Applied Statistics
IS - 3
ER -