Prostate cancer localization with multispectral MRI using cost-sensitive support vector machines and conditional random fields

Authors:
Yusuf Artan;Masoom A. Haider;Deanna L. Langer;Theodorus H. van der Kwast;Andrew J. Evans;Yongyi Yang;Miles N. Wernick;John Trachtenberg;Imam Samil Yetik
Affiliations:
Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL;Department of Medical Imaging, Princess Margaret and Mount Sinai Hospital, University Health Network, Toronto, ON, Canada and Institute of Medical Science, University of Toronto, Toronto, ON, Cana ...;Department of Medical Imaging, Princess Margaret and Mount Sinai Hospital, University Health Network, Toronto, ON, Canada and Institute of Medical Science, University of Toronto, Toronto, ON, Cana ...;Department of Pathology and Laboratory Medicine, Toronto General Hospital, University Health Network, Toronto, ON, Canada;Department of Pathology and Laboratory Medicine, Toronto General Hospital, University Health Network, Toronto, ON, Canada;Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL;Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL;Department of Medical Imaging, Princess Margaret and Mount Sinai Hospital, University Health Network, Toronto, ON, Canada and Department of Surgical Oncology, Princess Margaret Hospital, Universit ...;Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL
Venue:
IEEE Transactions on Image Processing
Year:
2010

Citing 12
Cited 3

Information Retrieval

Information Retrieval
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Simultaneous Relevant Feature Identification and Classification in High-Dimensional Spaces

WABI '02 Proceedings of the Second International Workshop on Algorithms in Bioinformatics
Simultaneous classification and relevant feature identification in high-dimensional spaces: application to molecular profiling data

Signal Processing - Special issue: Genomic signal processing
Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Experimentally optimal ν in support vector regression for different noise models and parameter settings

Neural Networks
A Comparison of Pharmacokinetic Models of Dynamic Contrast Enhanced MRI

CBMS '04 Proceedings of the 17th IEEE Symposium on Computer-Based Medical Systems
New Support Vector Algorithms

Neural Computation
Accelerated training of conditional random fields with stochastic gradient methods

ICML '06 Proceedings of the 23rd international conference on Machine learning
Prostate cancer segmentation with multispectral MRI using cost-sensitive conditional random fields

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Support vector random fields for spatial classification

PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
On the optimal parameter choice for ν-support vector machines

IEEE Transactions on Pattern Analysis and Machine Intelligence

Prostate cancer segmentation using multispectral random walks

MICCAI'10 Proceedings of the 2010 international conference on Prostate cancer imaging: computer-aided diagnosis, prognosis, and intervention
Robust classification using l2,1-norm based regression model

Pattern Recognition
Accurate Prediction of Coronary Artery Disease Using Reliable Diagnosis System

Journal of Medical Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

Prostate cancer is a leading cause of cancer death for men in the United States. Fortunately, the survival rate for early diagnosed patients is relatively high. Therefore, in vivo imaging plays an important role for the detection and treatment of the disease. Accurate prostate cancer localization with noninvasive imaging can be used to guide biopsy, radiotheraphy, and surgery as well as to monitor disease progression. Magnetic resonance imaging (MRI) performed with an endorectal coil provides higher prostate cancer localization accuracy, when compared to transrectal ultrasound (TRUS). However, in general, a single type of MRI is not sufficient for reliable tumor localization. As an alternative, multispectral MRI, i.e., the use of multiple MRI-derived datasets, has emerged as a promising noninvasive imaging technique for the localization of prostate cancer; however almost all studies are with human readers. There is a significant inter and intraobserver variability for human readers, and it is substantially difficult for humans to analyze the large dataset of multispectral MRI. To solve these problems, this study presents an automated localization method using cost-sensitive support vector machines (SVMs) and shows that this method results in improved localization accuracy than classical SVM. Additionally, we develop a new segmentation method by combining conditional random fields (CRF) with a cost-sensitive framework and show that our method further improves cost-sensitive SVM results by incorporating spatial information. We test SVM, cost-sensitive SVM, and the proposed cost-sensitive CRF on multispectral MRI datasets acquired from 21 biopsy-confirmed cancer patients. Our results show that multispectral MRI helps to increase the accuracy of prostate cancer localization when compared to single MR images; and that using advanced methods such as cost-sensitive SVM as well as the proposed cost-sensitive CRF can boost the performance significantly when compared to SVM.