A Superpixel-Based Framework for Automatic Tumor Segmentation on Breast DCE-MRI

SPIE Medical Imaging 2015 (oral, best student paper finalist)


Ning Yu      Jia Wu      Susan Weinstein      Bilwaj Gaonkar      Brad Keller      Ahmed Ashraf      YunQing Jiang     
Christos Davatzikos      Emily Conant      Despina Kontos
University of Pennsylvania

Abstract


Accurate and efficient automated tumor segmentation in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is highly desirable for computer-aided tumor diagnosis. We propose a novel automatic segmentation framework which incorporates mean-shift smoothing, superpixel-wise classification, pixel-wise graph-cuts partitioning, and morphological refinement. A set of 15 breast DCE-MR images, obtained from the American College of Radiology Imaging Network (ACRIN) 6657 I-SPY trial, were manually segmented to generate tumor masks (as ground truth) and breast masks (as regions of interest). Four state-of-the-art segmentation approaches based on diverse models were also utilized for comparison. Based on five standard evaluation metrics for segmentation, the proposed framework consistently outperformed all other approaches. The performance of the proposed framework was: 1) 0.83 for Dice similarity coefficient, 2) 0.96 for pixel-wise accuracy, 3) 0.72 for VOC score, 4) 0.79 mm for mean absolute difference, and 5) 11.71 mm for maximum Hausdorff distance, which surpassed the second best method (i.e., adaptive geodesic transformation), a semi-automatic algorithm depending on precise initialization. Our results suggest promising potential applications of our segmentation framework in assisting analysis of breast carcinomas.

Demos

Breast tumor segmentation

Accuracy and comparisons

Materials




Paper



Slides

Press coverage


SPIE News

Citation

@inproceedings{yu2015superpixel,
  author = {Yu, Ning and Wu, Jia and Weinstein, Susan and Gaonkar, Bilwaj and Keller, Brad and Ashraf, Ahmed and Jiang, YunQing and Davatzikos, Christos and Conant, Emily and Kontos, Despina},
  title = {A Superpixel-Based Framework for Automatic Tumor Segmentation on Breast DCE-MRI},
  booktitle = {SPIE Medical Imaging Conference},
  year = {2015}
}

Acknowledgement


This project is supported by funding from the University of Pennsylvania Abramson Cancer Center 2-PREVENT Center of Excellence Program and the Center for Biomedical Image Computing and Analytics (CBICA). We thank Dr. Nola Hylton from UCSF for the permission to use the I-SPY data and the useful discussions on this research work.

Related Work


R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Süsstrunk. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. PAMI 2012.
Comment: The SLIC algorithm that is used in our work for superpixel oversegmentation.
Y. Boykov, O. Veksler, R. Zabih. Fast Approximate Energy Minimization via Graph Cuts. PAMI 2001.
Comment: The graph-cuts algorithm that is used in our work to solve segmentation.
B. Keller, D. Nathan, Y. Wang, Y. Zheng, J. Gee, E. Conant, D. Kontos. Estimation of Breast Percent Density in Raw and Processed Full Field Digital Mammography Images via Adaptive Fuzzy C-Means Clustering and Support Vector mMchine Segmentation. Medical physics 2012.
Comment: A baseline method that uses adaptive fuzzy C-means algorithm for tumor pxiel clustering and classification.
K. Parvati, B. Rao, M. Das. Image Segmentation Using Gray-Scale Morphology and Marker-Controlled Watershed Transformation. Discrete Dynamics in Nature and Society 2008.
Comment: A baseline method that applies watershed transformation on the gradient image superimposed with markers for tumor segmentation.
B. Gaonkar, L. Shu, G. Hermosillo, Y. Zhan. Adaptive Geodesic Transform for Segmentation of Vertebrae on CT Images. SPIE Medical Imaging 2014.
Comment: A baseline method that applies geodesic transformation on the geodesic distance map fused with pixel intensity and gradient for tumor segmentation.
A. Ashraf, S. Gavenonis, D. Daye, C. Mies, M. Feldman, M. Rosen, D. Kontos. A Multichannel Markov Random Field Approach for Automated Segmentation of Breast Cancer Tumor in DCE-MRI Data Using Kinetic Observation Model. MICCAI 2011.
Comment: A baseline method that models the topology of superpixels as a multi-channel Markov random field and converges the superpixel segementation through loopy belief propagation.