Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation

Overview

Journal Brainlesion

Publisher Springer

Date 2018 May 2

PMID 29714357

Citations 5

Authors

Greg M Fleishman

Alessandra Valcarcel

Dzung L Pham

Snehashis Roy

Peter A Calabresi

Paul Yushkevich

Russell T Shinohara

Ipek Oguz

Affiliations

Soon will be listed here.

Abstract

We propose a new approach to Multiple Sclerosis lesion segmentation that utilizes synthesized images. A new method of image synthesis is considered: joint intensity fusion (JIF). JIF synthesizes an image from a library of deformably registered and intensity normalized atlases. Each location in the synthesized image is a weighted average of the registered atlases; atlas weights vary spatially. The weights are determined using the joint label fusion (JLF) framework. The primary methodological contribution is the application of JLF to MRI signal directly rather than labels. Synthesized images are then used as additional features in a lesion segmentation task using the OASIS classifier, a logistic regression model on intensities from multiple modalities. The addition of JIF synthesized images improved the Dice-Sorensen coefficient (relative to manually drawn gold standards) of lesion segmentations over the standard model segmentations by 0.0462 ± 0.0050 (mean ± standard deviation) at optimal threshold over all subjects and 10 separate training/testing folds.

Citing Articles

Deep network and multi-atlas segmentation fusion for delineation of thigh muscle groups in three-dimensional water-fat separated MRI.

Annasamudram N, Okorie A, Spencer R, Kalyani R, Yang Q, Landman B J Med Imaging (Bellingham). 2024; 11(5):054003.

PMID: 39234425 PMC: 11369361. DOI: 10.1117/1.JMI.11.5.054003.

Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI.

Carass A, Greenman D, Dewey B, Calabresi P, Prince J, Pham D Neuroimage Rep. 2024; 4(1).

PMID: 38370461 PMC: 10871705. DOI: 10.1016/j.ynirp.2024.100195.

LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation.

Hu D, Cui C, Li H, Larson K, Tao Y, Oguz I Med Image Comput Comput Assist Interv. 2021; 12901:514-524.

PMID: 34950935 PMC: 8692169. DOI: 10.1007/978-3-030-87193-2_49.

Self-fusion for OCT noise reduction.

Oguz I, Malone J, Atay Y, Tao Y Proc SPIE Int Soc Opt Eng. 2021; 11313.

PMID: 34873356 PMC: 8643350. DOI: 10.1117/12.2549472.

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis.

Carass A, Roy S, Gherman A, Reinhold J, Jesson A, Arbel T Sci Rep. 2020; 10(1):8242.

PMID: 32427874 PMC: 7237671. DOI: 10.1038/s41598-020-64803-w.

References

Cardoso M, Sudre C, Modat M, Ourselin S . Template-Based Multimodal Joint Generative Model of Brain Data. Inf Process Med Imaging. 2015; 24():17-29. DOI: 10.1007/978-3-319-19992-4_2. View

Sweeney E, Shinohara R, Shiee N, Mateen F, Chudgar A, Cuzzocreo J . OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI. Neuroimage Clin. 2013; 2:402-13. PMC: 3777691. DOI: 10.1016/j.nicl.2013.03.002. View

Sled J, Zijdenbos A, Evans A . A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging. 1998; 17(1):87-97. DOI: 10.1109/42.668698. View

Suttner L, Mejia A, Dewey B, Sati P, Reich D, Shinohara R . Statistical estimation of white matter microstructure from conventional MRI. Neuroimage Clin. 2016; 12:615-623. PMC: 5048084. DOI: 10.1016/j.nicl.2016.09.010. View

Garcia-Lorenzo D, Francis S, Narayanan S, Arnold D, Collins D . Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med Image Anal. 2012; 17(1):1-18. DOI: 10.1016/j.media.2012.09.004. View

Iglesias J, Sabuncu M . Multi-atlas segmentation of biomedical images: A survey. Med Image Anal. 2015; 24(1):205-219. PMC: 4532640. DOI: 10.1016/j.media.2015.06.012. View

Dendrou C, Fugger L, Friese M . Immunopathology of multiple sclerosis. Nat Rev Immunol. 2015; 15(9):545-58. DOI: 10.1038/nri3871. View

Shiee N, Bazin P, Ozturk A, Reich D, Calabresi P, Pham D . A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. Neuroimage. 2009; 49(2):1524-35. PMC: 2806481. DOI: 10.1016/j.neuroimage.2009.09.005. View

Carass A, Roy S, Jog A, Cuzzocreo J, Magrath E, Gherman A . Longitudinal multiple sclerosis lesion segmentation: Resource and challenge. Neuroimage. 2017; 148:77-102. PMC: 5344762. DOI: 10.1016/j.neuroimage.2016.12.064. View

10.

Carass A, Cuzzocreo J, Wheeler M, Bazin P, Resnick S, Prince J . Simple paradigm for extra-cerebral tissue removal: algorithm and analysis. Neuroimage. 2011; 56(4):1982-92. PMC: 3105165. DOI: 10.1016/j.neuroimage.2011.03.045. View

11.

Mazziotta J, Toga A, Evans A, Fox P, Lancaster J . A probabilistic atlas of the human brain: theory and rationale for its development. The International Consortium for Brain Mapping (ICBM). Neuroimage. 1995; 2(2):89-101. DOI: 10.1006/nimg.1995.1012. View

12.

DeLong E, Delong D, Clarke-Pearson D . Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988; 44(3):837-45. View

13.

Roy S, Agarwal H, Carass A, Bai Y, Pham D, Prince J . FUZZY C-MEANS WITH VARIABLE COMPACTNESS. Proc IEEE Int Symp Biomed Imaging. 2011; 4541030:452. PMC: 2814437. DOI: 10.1109/ISBI.2008.4541030. View

14.

Roy S, Carass A, Prince J, Pham D . Subject Specific Sparse Dictionary Learning for Atlas based Brain MRI Segmentation. Mach Learn Med Imaging. 2014; 8679:248-255. PMC: 4220547. DOI: 10.1007/978-3-319-10581-9_31. View

15.

Subbanna N, Precup D, Arnold D, Arbel T . IMaGe: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI. Inf Process Med Imaging. 2015; 24:514-26. DOI: 10.1007/978-3-319-19992-4_40. View

16.

Wang H, Suh J, Das S, Pluta J, Craige C, Yushkevich P . Multi-Atlas Segmentation with Joint Label Fusion. IEEE Trans Pattern Anal Mach Intell. 2012; 35(3):611-23. PMC: 3864549. DOI: 10.1109/TPAMI.2012.143. View

17.

Jog A, Roy S, Carass A, Prince J . MAGNETIC RESONANCE IMAGE SYNTHESIS THROUGH PATCH REGRESSION. Proc IEEE Int Symp Biomed Imaging. 2014; 2013:350-353. PMC: 3892700. DOI: 10.1109/ISBI.2013.6556484. View

18.

Tristan-Vega A, Garcia-Perez V, Aja-Fernandez S, Westin C . Efficient and robust nonlocal means denoising of MR data based on salient features matching. Comput Methods Programs Biomed. 2011; 105(2):131-44. PMC: 4102134. DOI: 10.1016/j.cmpb.2011.07.014. View

19.

Awate S, Whitaker R . Unsupervised, information-theoretic, adaptive image filtering for image restoration. IEEE Trans Pattern Anal Mach Intell. 2006; 28(3):364-76. DOI: 10.1109/TPAMI.2006.64. View

20.

Mejia A, Sweeney E, Dewey B, Nair G, Sati P, Shea C . Statistical estimation of T1 relaxation times using conventional magnetic resonance imaging. Neuroimage. 2016; 133:176-188. PMC: 4889526. DOI: 10.1016/j.neuroimage.2015.12.037. View