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

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 vivo prostate magnetic resonance (MR) images, 78 dynamic contrast enhanced breast MR images, and 21 3T in vivo T1-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.

[1]  A. Kraskov,et al.  Estimating mutual information. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Bostjan Likar,et al.  Multifeature mutual information , 2004, SPIE Medical Imaging.

[3]  Paul Suetens,et al.  Minimal Shape and Intensity Cost Path Segmentation , 2007, IEEE Transactions on Medical Imaging.

[4]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Anant Madabhushi,et al.  A COMBINED FEATURE ENSEMBLE BASED MUTUAL INFORMATION SCHEME FOR ROBUST INTER-MODAL, INTER-PROTOCOL IMAGE REGISTRATION , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[6]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[7]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[8]  Anant Madabhushi,et al.  A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery , 2008, SPIE Medical Imaging.

[9]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[10]  Alejandro F. Frangi,et al.  Active shape model segmentation with optimal features , 2002, IEEE Transactions on Medical Imaging.

[11]  Anant Madabhushi,et al.  A Boosting Cascade for Automated Detection of Prostate Cancer from Digitized Histology , 2006, MICCAI.

[12]  Dimitris N. Metaxas,et al.  Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions , 2003, IEEE Transactions on Medical Imaging.

[13]  Anant Madabhushi,et al.  A multi-modal prostate segmentation scheme by combining spectral clustering and active shape models , 2008, SPIE Medical Imaging.

[14]  Timothy F. Cootes,et al.  Active Shape Models: Evaluation of a Multi-Resolution Method for Improving Image Search , 1994, BMVC.

[15]  Dimitris N. Metaxas,et al.  Automated detection of prostatic adenocarcinoma from high-resolution ex vivo MRI , 2005, IEEE Transactions on Medical Imaging.

[16]  Lasse Riis Østergaard,et al.  Active Surface Approach for Extraction of the Human Cerebral Cortex from MRI , 2006, MICCAI.

[17]  Matsuda,et al.  Physical nature of higher-order mutual information: intrinsic correlations and frustration , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.