Multi-Attribute Non-initializing Texture Reconstruction Based Active Shape Model (MANTRA)

Authors:
Robert Toth;Jonathan Chappelow;Mark Rosen;Sona Pungavkar;Arjun Kalyanpur;Anant Madabhushi
Affiliations:
Rutgers, The State University of New Jersey, New Brunswick, USA;Rutgers, The State University of New Jersey, New Brunswick, USA;University of Pennsylvania, Philadelphia, USA;Dr. Balabhai Nanavati Hospital, Mumbai, India;Teleradiology Solutions, Bangalore, India;Rutgers, The State University of New Jersey, New Brunswick, USA
Venue:
MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
Year:
2008

Citing 3
Cited 1

Active shape models—their training and application

Computer Vision and Image Understanding
Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
A boosting cascade for automated detection of prostate cancer from digitized histology

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II

Facilitating 3D spectroscopic imaging through automatic prostate localization in MR images using random walker segmentation initialized via boosted classifiers

MICCAI'11 Proceedings of the 2011 international conference on Prostate cancer imaging: image analysis and image-guided interventions

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present MANTRA (Multi-Attribute, Non-Initializing, Texture Reconstruction Based Active Shape Model) which incorporates a number of features that improve on the the popular Active Shape Model (ASM) algorithm. MANTRA has the following advantages over the traditional ASM model. (1) It does not rely on image intensity information alone, as it incorporates multiple statistical texture features for boundary detection. (2) Unlike traditional ASMs, MANTRA finds the border by maximizing a higher dimensional version of mutual information (MI) called combined MI (CMI), which is estimated from kNN entropic graphs. The use of CMI helps to overcome limitations of the Mahalanobis distance, and allows multiple texture features to be intelligently combined. (3) MANTRA does not rely on the mean pixel intensity values to find the border; instead, it reconstructs potential image patches, and the image patch with the best reconstruction based on CMI is considered the object border. Our algorithm was quantitatively evaluated against expert ground truth on almost 230 clinical images (128 1.5 Tesla (T) T2 weighted in vivoprostate magnetic resonance (MR) images, 78 dynamic contrast enhanced breast MR images, and 21 3T in vivoT1-weighted prostate MR images) via 6 different quantitative metrics. Results from the more difficult prostate segmentation task (in which a second expert only had a 0.850 mean overlap with the first expert) show that the traditional ASM method had a mean overlap of 0.668, while the MANTRA model had a mean overlap of 0.840.