TY - CHAP
T1 - Morphological change forecasting for prostate glands using feature-based registration and kernel density extrapolation
AU - Yang, Qianye
AU - Vercauteren, Tom
AU - Fu, Yunguan
AU - Giganti, Francesco
AU - Ghavami, Nooshin
AU - Stavrinides, Vasilis
AU - Moore, Caroline
AU - Clarkson, Matt
AU - Barratt, Dean
AU - Hu, Yipeng
N1 - Funding Information:
This work is supported by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (203145Z/16/Z), Centre for Medical Engineering (203148/Z/16/Z; NS/A000049/1), the EPSRC-funded UCL Centre for Doctoral Training in Intelligent, Integrated Imaging in Healthcare (EP/S021930/1), the Department of Health’s NIHR-funded Biomedical Research Centre at UCLH, and CRUK (C28070/A30912; C73666/A31378). Francesco Giganti is funded by the UCL Graduate Research Scholarship and the Brahm Ph.D. scholarship in memory of Chris Adams.
Publisher Copyright:
© 2021 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/4/13
Y1 - 2021/4/13
N2 - Organ morphology is a key indicator for prostate disease diagnosis and prognosis. For instance, In longitudinal study of prostate cancer patients under active surveillance, the volume, boundary smoothness and their changes are closely monitored on time-series MR image data. In this paper, we describe a new framework for forecasting prostate morphological changes, as the ability to detect such changes earlier than what is currently possible may enable timely treatment or avoiding unnecessary confirmatory biopsies. In this work, an efficient feature-based MR image registration is first developed to align delineated prostate gland capsules to quantify the morphological changes using the inferred dense displacement fields (DDFs). We then propose to use kernel density estimation (KDE) of the probability density of the DDF-represented future morphology changes, between current and future time points, before the future data become available. The KDE utilises a novel distance function that takes into account morphology, stage-of-progression and duration-of-change, which are considered factors in such subject-specific forecasting. We validate the proposed approach on image masks unseen to registration network training, without using any data acquired at the future target time points. The experiment results are presented on a longitudinal data set with 331 images from 73 patients, yielding an average Dice score of 0.865 on a holdout set, between the ground-truth and the image masks warped by the KDE-predicted-DDFs.
AB - Organ morphology is a key indicator for prostate disease diagnosis and prognosis. For instance, In longitudinal study of prostate cancer patients under active surveillance, the volume, boundary smoothness and their changes are closely monitored on time-series MR image data. In this paper, we describe a new framework for forecasting prostate morphological changes, as the ability to detect such changes earlier than what is currently possible may enable timely treatment or avoiding unnecessary confirmatory biopsies. In this work, an efficient feature-based MR image registration is first developed to align delineated prostate gland capsules to quantify the morphological changes using the inferred dense displacement fields (DDFs). We then propose to use kernel density estimation (KDE) of the probability density of the DDF-represented future morphology changes, between current and future time points, before the future data become available. The KDE utilises a novel distance function that takes into account morphology, stage-of-progression and duration-of-change, which are considered factors in such subject-specific forecasting. We validate the proposed approach on image masks unseen to registration network training, without using any data acquired at the future target time points. The experiment results are presented on a longitudinal data set with 331 images from 73 patients, yielding an average Dice score of 0.865 on a holdout set, between the ground-truth and the image masks warped by the KDE-predicted-DDFs.
KW - Active surveillance
KW - Deep learning
KW - Feature-based registration
KW - Kernel density estimation
KW - Longitudinal data
UR - http://www.scopus.com/inward/record.url?scp=85107187299&partnerID=8YFLogxK
U2 - 10.1109/ISBI48211.2021.9433798
DO - 10.1109/ISBI48211.2021.9433798
M3 - Conference paper
AN - SCOPUS:85107187299
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1072
EP - 1076
BT - 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
PB - IEEE Computer Society
T2 - 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Y2 - 13 April 2021 through 16 April 2021
ER -
