Share Email Print

Proceedings Paper

Improving supervised classification accuracy using non-rigid multimodal image registration: detecting prostate cancer
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Computer-aided diagnosis (CAD) systems for the detection of cancer in medical images require precise labeling of training data. For magnetic resonance (MR) imaging (MRI) of the prostate, training labels define the spatial extent of prostate cancer (CaP); the most common source for these labels is expert segmentations. When ancillary data such as whole mount histology (WMH) sections, which provide the gold standard for cancer ground truth, are available, the manual labeling of CaP can be improved by referencing WMH. However, manual segmentation is error prone, time consuming and not reproducible. Therefore, we present the use of multimodal image registration to automatically and accurately transcribe CaP from histology onto MRI following alignment of the two modalities, in order to improve the quality of training data and hence classifier performance. We quantitatively demonstrate the superiority of this registration-based methodology by comparing its results to the manual CaP annotation of expert radiologists. Five supervised CAD classifiers were trained using the labels for CaP extent on MRI obtained by the expert and 4 different registration techniques. Two of the registration methods were affi;ne schemes; one based on maximization of mutual information (MI) and the other method that we previously developed, Combined Feature Ensemble Mutual Information (COFEMI), which incorporates high-order statistical features for robust multimodal registration. Two non-rigid schemes were obtained by succeeding the two affine registration methods with an elastic deformation step using thin-plate splines (TPS). In the absence of definitive ground truth for CaP extent on MRI, classifier accuracy was evaluated against 7 ground truth surrogates obtained by different combinations of the expert and registration segmentations. For 26 multimodal MRI-WMH image pairs, all four registration methods produced a higher area under the receiver operating characteristic curve compared to that obtained from expert annotation. These results suggest that in the presence of additional multimodal image information one can obtain more accurate object annotations than achievable via expert delineation despite vast differences between modalities that hinder image registration.

Paper Details

Date Published: 17 March 2008
PDF: 12 pages
Proc. SPIE 6915, Medical Imaging 2008: Computer-Aided Diagnosis, 69150V (17 March 2008); doi: 10.1117/12.770703
Show Author Affiliations
Jonathan Chappelow, Rutgers Univ. (United States)
Satish Viswanath, Rutgers Univ. (United States)
James Monaco, Rutgers Univ. (United States)
Mark Rosen, Univ. of Pennsylvania (United States)
John Tomaszewski, Univ. of Pennsylvania (United States)
Michael Feldman, Univ. of Pennsylvania (United States)
Anant Madabhushi, Rutgers Univ. (United States)

Published in SPIE Proceedings Vol. 6915:
Medical Imaging 2008: Computer-Aided Diagnosis
Maryellen L. Giger; Nico Karssemeijer, Editor(s)

© SPIE. Terms of Use
Back to Top