Tags

Type your tag names separated by a space and hit enter

Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study.
Comput Med Imaging Graph 2019; 75:14-23CM

Abstract

Dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is a method of temporal imaging that is commonly used to aid in prostate cancer (PCa) diagnosis and staging. Typically, machine learning models designed for the segmentation and detection of PCa will use an engineered scalar image called Ktrans to summarize the information in the DCE time-series images. This work proposes a new model that amalgamates the U-net and the convGRU neural network architectures for the purpose of interpreting DCE time-series in a temporal and spatial basis for segmenting PCa in MR images. Ultimately, experiments show that the proposed model using the DCE time-series images can outperform a baseline U-net segmentation model using Ktrans. However, when other types of scalar MR images are considered by the models, no significant advantage is observed for the proposed model.

Authors+Show Affiliations

Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada.Biomedical Translational Imaging Centre, Nova Scotia Health Authority and IWK Health Centre, Halifax, NS, Canada.Nova Scotia Health Research Foundation, Halifax, NS, Canada.Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada.Biomedical Translational Imaging Centre, Nova Scotia Health Authority and IWK Health Centre, Halifax, NS, Canada; Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, Canada.Biomedical Translational Imaging Centre, Nova Scotia Health Authority and IWK Health Centre, Halifax, NS, Canada; Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, Canada.Department of Pathology, Dalhousie University, Halifax, NS, Canada.Department of Pathology, Dalhousie University, Halifax, NS, Canada.Biomedical Translational Imaging Centre, Nova Scotia Health Authority and IWK Health Centre, Halifax, NS, Canada; Department of Physics & Atmospheric Science, Dalhousie University, Halifax, NS, Canada; Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, Canada. Electronic address: sharon.clarke@dal.ca.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31117012

Citation

Lee, Peter Q., et al. "Model-free Prostate Cancer Segmentation From Dynamic Contrast-enhanced MRI With Recurrent Convolutional Networks: a Feasibility Study." Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society, vol. 75, 2019, pp. 14-23.
Lee PQ, Guida A, Patterson S, et al. Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study. Comput Med Imaging Graph. 2019;75:14-23.
Lee, P. Q., Guida, A., Patterson, S., Trappenberg, T., Bowen, C., Beyea, S. D., ... Clarke, S. E. (2019). Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study. Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society, 75, pp. 14-23. doi:10.1016/j.compmedimag.2019.04.006.
Lee PQ, et al. Model-free Prostate Cancer Segmentation From Dynamic Contrast-enhanced MRI With Recurrent Convolutional Networks: a Feasibility Study. Comput Med Imaging Graph. 2019;75:14-23. PubMed PMID: 31117012.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study. AU - Lee,Peter Q, AU - Guida,Alessandro, AU - Patterson,Steve, AU - Trappenberg,Thomas, AU - Bowen,Chris, AU - Beyea,Steven D, AU - Merrimen,Jennifer, AU - Wang,Cheng, AU - Clarke,Sharon E, Y1 - 2019/05/19/ PY - 2018/09/08/received PY - 2019/04/15/revised PY - 2019/04/26/accepted PY - 2019/5/23/pubmed PY - 2019/5/23/medline PY - 2019/5/23/entrez KW - Dynamic contrast enhancement KW - Magnetic resonance imaging KW - Prostate cancer KW - Recurrent convolutional networks SP - 14 EP - 23 JF - Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society JO - Comput Med Imaging Graph VL - 75 N2 - Dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is a method of temporal imaging that is commonly used to aid in prostate cancer (PCa) diagnosis and staging. Typically, machine learning models designed for the segmentation and detection of PCa will use an engineered scalar image called Ktrans to summarize the information in the DCE time-series images. This work proposes a new model that amalgamates the U-net and the convGRU neural network architectures for the purpose of interpreting DCE time-series in a temporal and spatial basis for segmenting PCa in MR images. Ultimately, experiments show that the proposed model using the DCE time-series images can outperform a baseline U-net segmentation model using Ktrans. However, when other types of scalar MR images are considered by the models, no significant advantage is observed for the proposed model. SN - 1879-0771 UR - https://www.unboundmedicine.com/medline/citation/31117012/Model-free_prostate_cancer_segmentation_from_dynamic_contrast-enhanced_MRI_with_recurrent_convolutional_networks:_A_feasibility_study L2 - https://linkinghub.elsevier.com/retrieve/pii/S0895-6111(18)30533-0 DB - PRIME DP - Unbound Medicine ER -