Segmentation

Segmentation

Segmentation is a fundamental problem in medical image analysis, in which images are labeled by an automated or semi-automated way. Our group has a long-standing activity in this area, with late emphasis on two areas; 1) segmentation of pathologies, such as tumors or lesions, either by building abnormality-specific models [1, 2], or by viewing abnormalities as deviations from statistics of normal anatomy [3]; 2) multi-atlas consensus-based labeling, in which multiple transformations, atlases and parameter sets are used to provide an ensemble of estimates of an individual’s labels, and are subsequently integrated via some optimality criterion [4-10]. We have also developed deep learning segmentation models for brain tumors, brain structures, and kidney [11-13]

Current Projects:

— Deformable registration of brain tumor images

— GLISTR: GLioma Image SegmenTation and Registration
— GLISTRboost: Our proposed method for segmenting low- and high-grade gliomas in multimodal magnetic resonance imaging (MRI) volumes.

— Multi Atlas Skull Stripping — MASS

— MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection — MUSE

— Deep learning for image segmentation

Publications:

[1]          A. Gooya, K. M. Pohl, M. Bilello, L. Cirillo, G. Biros, E. R. Melhem, et al., "GLISTR: Glioma Image Segmentation and Registration," IEEE Trans Med Imaging, vol. 31, pp. 1941-54, Oct 2012.

[2]          S. Bakas, K. Zeng, A. Sotiras, S. Rathore, H. Akbari, B. Gaonkar, et al., "GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation," Brainlesion (2015), vol. 9556, pp. 144-155, 2016.

[3]          K. Zeng, G. Erus, A. Sotiras, R. T. Shinohara, and C. Davatzikos, "Abnormality detection via iterative deformable registration and basis-pursuit decomposition," IEEE Transactions on Medical Imaging, vol. PP, pp. 1-1, 2016.

[4]          J. Doshi, G. Erus, Y. Ou, S. Resnick, R. Gur, R. Gur, et al., "MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection," NeuroImage, vol. 127, pp. 186-95, 2016.

[5]          J. Doshi, G. Erus, Y. Ou, B. Gaonkar, and C. Davatzikos, "Multi-Atlas Skull-Stripping," Academic radiology, vol. 20, pp. 1566-1576, 2013.

[6]          J. Doshi, G. Erus, Y. Ou, and C. Davatzikos, "Ensemble-based medical image labeling via sampling morphological appearance manifold," presented at the MICCAI, Nagoya, Japan, 2013.

[7]          H. Zhu, Z. Tang, H. Cheng, Y. Wu, and Y. Fan, "Multi-atlas label fusion with random local binary pattern features: Application to hippocampus segmentation," Sci Rep, vol. 9, p. 16839, Nov 14 2019.

[8]          Q. Zheng, Y. Wu, and Y. Fan, "Integrating Semi-supervised and Supervised Learning Methods for Label Fusion in Multi-Atlas Based Image Segmentation," Front Neuroinform, vol. 12, p. 69, 2018.

[9]          H. Zhu, H. Cheng, X. Yang, Y. Fan, and I. Alzheimer's Disease Neuroimaging, "Metric Learning for Multi-atlas based Segmentation of Hippocampus," Neuroinformatics, vol. 15, pp. 41-50, Jan 2017.

[10]        Y. Hao, T. Wang, X. Zhang, Y. Duan, C. Yu, T. Jiang, et al., "Local label learning (LLL) for subcortical structure segmentation: application to hippocampus segmentation," Hum Brain Mapp, vol. 35, pp. 2674-97, Jun 2014.

[11]        Yuemeng Li, Hangfan Liu, Hongming Li, and Y. Fan, "Feature-Fused Context-Encoding Network for Neuroanatomy Segmentation," arXiv:1905.02686 pp. 1-10, May 2019 2019.

[12]        X. Zhao, Y. Wu, G. Song, Z. Li, Y. Zhang, and Y. Fan, "A deep learning model integrating FCNNs and CRFs for brain tumor segmentation," Med Image Anal, vol. 43, pp. 98-111, Jan 2018.

[13]        S. Yin, Q. Peng, H. Li, Z. Zhang, X. You, K. Fischer, et al., "Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks," Med Image Anal, vol. 60, p. 101602, Nov 8 2019.