A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke

Research output: Contribution to journalJournal article – Annual report year: 2016Researchpeer-review

Standard

A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke. / Menze, Bjoern H.; Van Leemput, Koen; Lashkari, Danial; Riklin-Raviv, Tammy; Geremia, Ezequiel; Alberts, Esther; Gruber, Philipp; Wegener, Susanne; Weber, Marc-André; Székely, Gabor; Ayache, Nicholas; Golland, Polina.

In: I E E E Transactions on Medical Imaging, Vol. 35, No. 4, 2016, p. 933-946.

Research output: Contribution to journalJournal article – Annual report year: 2016Researchpeer-review

Harvard

Menze, BH, Van Leemput, K, Lashkari, D, Riklin-Raviv, T, Geremia, E, Alberts, E, Gruber, P, Wegener, S, Weber, M-A, Székely, G, Ayache, N & Golland, P 2016, 'A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke', I E E E Transactions on Medical Imaging, vol. 35, no. 4, pp. 933-946. https://doi.org/10.1109/TMI.2015.2502596

APA

CBE

Menze BH, Van Leemput K, Lashkari D, Riklin-Raviv T, Geremia E, Alberts E, Gruber P, Wegener S, Weber M-A, Székely G, Ayache N, Golland P. 2016. A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke. I E E E Transactions on Medical Imaging. 35(4):933-946. https://doi.org/10.1109/TMI.2015.2502596

MLA

Vancouver

Author

Menze, Bjoern H. ; Van Leemput, Koen ; Lashkari, Danial ; Riklin-Raviv, Tammy ; Geremia, Ezequiel ; Alberts, Esther ; Gruber, Philipp ; Wegener, Susanne ; Weber, Marc-André ; Székely, Gabor ; Ayache, Nicholas ; Golland, Polina. / A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke. In: I E E E Transactions on Medical Imaging. 2016 ; Vol. 35, No. 4. pp. 933-946.

Bibtex

@article{c69205b20c4549af8edf08aa3ce499fa,
title = "A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke",
abstract = "We introduce a generative probabilistic model for segmentation of brain lesions in multi-dimensional images that generalizes the EM segmenter, a common approach for modelling brain images using Gaussian mixtures and a probabilistic tissue atlas that employs expectation-maximization (EM), to estimate the label map for a new image. Our model augments the probabilistic atlas of the healthy tissues with a latent atlas of the lesion. We derive an estimation algorithm with closed-form EM update equations. The method extracts a latent atlas prior distribution and the lesion posterior distributions jointly from the image data. It delineates lesion areas individually in each channel, allowing for differences in lesion appearance across modalities, an important feature of many brain tumor imaging sequences. We also propose discriminative model extensions to map the output of the generative model to arbitrary labels with semantic and biological meaning, such as {"}tumor core{"} or {"}fluid-filled structure{"}, but without a one-to-one correspondence to the hypo- or hyper-intense lesion areas identified by the generative model. We test the approach in two image sets: the publicly available BRATS set of glioma patient scans, and multimodal brain images of patients with acute and subacute ischemic stroke. We find the generative model that has been designed for tumor lesions to generalize well to stroke images, and the extended discriminative-discriminative model to be one of the top ranking methods in the BRATS evaluation.",
keywords = "Medical diagnostic imaging, Anatomical structure, Tumors, Image segmentation, Object segmentation, Bayes methods",
author = "Menze, {Bjoern H.} and {Van Leemput}, Koen and Danial Lashkari and Tammy Riklin-Raviv and Ezequiel Geremia and Esther Alberts and Philipp Gruber and Susanne Wegener and Marc-Andr{\'e} Weber and Gabor Sz{\'e}kely and Nicholas Ayache and Polina Golland",
note = "This work is licensed under a Creative Commons Attribution 3.0 License.",
year = "2016",
doi = "10.1109/TMI.2015.2502596",
language = "English",
volume = "35",
pages = "933--946",
journal = "I E E E Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers",
number = "4",

}

RIS

TY - JOUR

T1 - A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation - With Application to Tumor and Stroke

AU - Menze, Bjoern H.

AU - Van Leemput, Koen

AU - Lashkari, Danial

AU - Riklin-Raviv, Tammy

AU - Geremia, Ezequiel

AU - Alberts, Esther

AU - Gruber, Philipp

AU - Wegener, Susanne

AU - Weber, Marc-André

AU - Székely, Gabor

AU - Ayache, Nicholas

AU - Golland, Polina

N1 - This work is licensed under a Creative Commons Attribution 3.0 License.

PY - 2016

Y1 - 2016

N2 - We introduce a generative probabilistic model for segmentation of brain lesions in multi-dimensional images that generalizes the EM segmenter, a common approach for modelling brain images using Gaussian mixtures and a probabilistic tissue atlas that employs expectation-maximization (EM), to estimate the label map for a new image. Our model augments the probabilistic atlas of the healthy tissues with a latent atlas of the lesion. We derive an estimation algorithm with closed-form EM update equations. The method extracts a latent atlas prior distribution and the lesion posterior distributions jointly from the image data. It delineates lesion areas individually in each channel, allowing for differences in lesion appearance across modalities, an important feature of many brain tumor imaging sequences. We also propose discriminative model extensions to map the output of the generative model to arbitrary labels with semantic and biological meaning, such as "tumor core" or "fluid-filled structure", but without a one-to-one correspondence to the hypo- or hyper-intense lesion areas identified by the generative model. We test the approach in two image sets: the publicly available BRATS set of glioma patient scans, and multimodal brain images of patients with acute and subacute ischemic stroke. We find the generative model that has been designed for tumor lesions to generalize well to stroke images, and the extended discriminative-discriminative model to be one of the top ranking methods in the BRATS evaluation.

AB - We introduce a generative probabilistic model for segmentation of brain lesions in multi-dimensional images that generalizes the EM segmenter, a common approach for modelling brain images using Gaussian mixtures and a probabilistic tissue atlas that employs expectation-maximization (EM), to estimate the label map for a new image. Our model augments the probabilistic atlas of the healthy tissues with a latent atlas of the lesion. We derive an estimation algorithm with closed-form EM update equations. The method extracts a latent atlas prior distribution and the lesion posterior distributions jointly from the image data. It delineates lesion areas individually in each channel, allowing for differences in lesion appearance across modalities, an important feature of many brain tumor imaging sequences. We also propose discriminative model extensions to map the output of the generative model to arbitrary labels with semantic and biological meaning, such as "tumor core" or "fluid-filled structure", but without a one-to-one correspondence to the hypo- or hyper-intense lesion areas identified by the generative model. We test the approach in two image sets: the publicly available BRATS set of glioma patient scans, and multimodal brain images of patients with acute and subacute ischemic stroke. We find the generative model that has been designed for tumor lesions to generalize well to stroke images, and the extended discriminative-discriminative model to be one of the top ranking methods in the BRATS evaluation.

KW - Medical diagnostic imaging

KW - Anatomical structure

KW - Tumors

KW - Image segmentation

KW - Object segmentation

KW - Bayes methods

U2 - 10.1109/TMI.2015.2502596

DO - 10.1109/TMI.2015.2502596

M3 - Journal article

VL - 35

SP - 933

EP - 946

JO - I E E E Transactions on Medical Imaging

JF - I E E E Transactions on Medical Imaging

SN - 0278-0062

IS - 4

ER -