MULTIVARIATE MATHEMATICAL MORPHOLOGY FOR DCE-MRI IMAGE ANALYSIS IN ANGIOGENESIS STUDIES
DOI:
https://doi.org/10.5566/ias.1109Keywords:
classification, DCE-MRI series, multivariate mathematical morphology, segmentation, stochastic watershed, tumoursAbstract
We propose a new computer aided detection framework for tumours acquired on DCE-MRI (Dynamic Contrast Enhanced Magnetic Resonance Imaging) series on small animals. To perform this approach, we consider DCE-MRI series as multivariate images. A full multivariate segmentation method based on dimensionality reduction, noise filtering, supervised classification and stochastic watershed is explained and tested on several data sets. The two main key-points introduced in this paper are noise reduction preserving contours and spatio temporal segmentation by stochastic watershed. Noise reduction is performed in a special way to select factorial axes of Factor Correspondence Analysis in order to preserves contours. Then a spatio-temporal approach based on stochastic watershed is used to segment tumours. The results obtained are in accordance with the diagnosis of the medical doctors.References
Angulo J, Jeulin D (2007). Stochastic watershed
segmentation. In: Mathematical morphology and
its applications to signal and image processing.
Proc. of the 8th Int. Symposium on Mathematical
Morphology. Instituto Nacional de Pesquisas
Espaciais (INPE), 265–76.
Balvay D, Frouin F, Calmon G, Bessoud B, Kahn
E, Siauve N, Clément O, Cuenod CA (2005).
New Criteria for assessing fit quality in dynamic contrast-enhanced T1-weighted MRI for perfusion
and permeability imaging. Magnet Reson Med
:868–77.
Balvay D, Kachenoura N, Espinoza S, Thomassin-
Naggara I, Fournier LS, Clément O, Cuenod
CA (2011). Signal-to-noise ratio improvement in
dynamic contrast-enhanced CT and MR imaging
with automated principal component analysis
filtering. Radiology 258(2):435–45.
Benediktsson JA, Palmason JA, Sveinsson JR (2005).
Classification of hyperspectral data from urban
areas based on extended morphological profiles.
IEEE T Geosci Remote 42:480–91.
Benzécri JP (1964). Sur l’Analyse Factorielle des
Proximités. Publications Institut de Statistique-
Université de Paris 13:235–82.
Benzécri JP (1973). L’Analyse Des Données,
L’Analyse des Correspondances. Dunod-Paris 2.
Berman M (1985). The statistical properties of three
noise removal procedures for multichannel
remotely sensed datas. CSIRO Div. of
Mathematics and Statistics-Australia. Consulting
Report NSW/85/31/MB9.
Beucher S, Lantuéjoul C (1979). Use of watersheds
in contour detection. In: Proc. Int. Workshop
on image processing, real-time edge and motion
detection-estimation 17–21.
Beucher S, Meyer F (1992). The morphological
approach to segmentation: The watershed
transformation. In: Mathematical morphology
in image processing. Marcel-Dekker, New York
–81.
Brasch RC, Li KCP, Husband JE, Keogan MT,
Neeman M, Padhani AR et al.(2000). In vivo
monitoring of tumor angiogenesis with MR
imaging. Acad Radiol 7(10):812–23.
Brix G, Ravesh MS, Zwick S, Griebel J, Delorme S
(2012). On impulse response functions computed
from dynamic contrast-enhanced image data
by algebraic deconvolution and compartmental
modeling. Phys Medica 28(2):119–28.
Brochot C, Bessoud B, Balvay D, Cuénod CA,
Siauve N, Bois FY. Evaluation of antiangiogenic
treatment effects on tumors’ microcirculation by
Bayesian physiological pharmacokinetic modeling
and magnetic resonance imaging (2006). Magn
Reson Imaging 24:1059—67.
Cattell RB (1966). The scree test for the number of
factors. Multivariate Behavioral Research 245–76.
Diday E (1971). Une nouvelle méthode en
classification automatique et reconnaissance
des formes la méthode des nuées dynamique.
Revue de statistique appliquée 19(2):19-33.
Ding Y, Chung YC, Raman SV, Simonetti OP (2009).
Application of the Karhunen-Loeve transform
temporal image filter to reduce noise in real-time
cardiac cine MRI. Phys Med Biol 54(12):3909.
Ding Y, Chung YC,Simonetti OP (2010). A method
to assess spatially variant noise in dynamic MR
image series. Magnet Reson Med 63(3):782–89.
Duda RO, Hart PE (1973). Pattern classification and
scene analysis.Wiley-New York.
Green A, Berman M, Switzer P, Craig MD (1988). A
transformation for ordering multispectral data in
terms of image quality with implications for noise
removal. IEEE T Geosci Remote 26(1):65—74.
Hanbury A, Serra J (2001). Morphological operators
on the unit circle. IEEE T Image Process
(12):1842–50.
Hartigan JA, Wong MA (1979). A K-means clustering
algorithm. Applied Statistic 28:100–08.
Hastie T, Tibshirani R, Friedman J (2003). The
elements of statistical learning: Data mining,
inference, and prediction. Springer.
Hughes G (1968). On the mean accuracy of statistical
pattern recognizers. IEEE T Inform Theory 14:55–
Ivancevic MK, Zimine I, Lazeyras F, Foxall D,
Vallée JP (2001). FAST sequences optimization for
contrast media pharmacokinetic quantification in
tissue. JMRI-J Magn Reson Im 14(6):771–78.
Kaiser H (1960). The application of electronic
computers to factor analysis. Educational and
PsychologicalMeasurement 20:141–51.
Landgrebe D (2002). Hyperspectral image data
analysis. IEEE Signal Proc Mag 19(1):17-28.
Leach MO, Morgan B, Tofts PS, Buckley DL, Huang
W, Horsfield MA et al.(2012). Imaging vascular
function for early stage clinical trials using
dynamic contrast-enhanced magnetic resonance
imaging. European Radiology 22(7):1451-64.
Lennon M (2002). Méthodes d’analyse d’images
hyperspectrales. Exploitation du capteur aéroporté
CASI pour des applications de cartographie
agro-environnementale en Bretagne. Ph.d. Thesis-
Université de Rennes, France.
Matheron G (1970). La théorie des variables
régionalisées et ses applications. Les cahiers
du Centre de Morphologie Mathématique de
Fontainebleau. Mines-ParisTech, France. http:
//www.cg.ensmp.fr/bibliotheque/
index_byyear.html
Matheron G (1975). Random Sets and Integral Integral
Geometry. Wiley, New York.
Meyer F (2001). An overview of morphological
segmentation. Int J Pattern Recogn 15(7):1089–18.
Meyer F (2004). Levelings, image simplification filters
for segmentation. J Math Imaging Vis 20:59–72.
Noyel G, Angulo J, Jeulin D (2007). Random
germs and stochastic watershed for unsupervised
multispectral image segmentation. In: KES 2007/
WIRN 2007. Springer LNAI 4694 3:17–24.
Noyel G, Angulo J, Jeulin D (2007). Morphological
segmentation of hyperspectral images. In: Proc.
th International Congress for Stereology, ICS
XII. Saint Etienne France.
Noyel G, Angulo J, Jeulin D (2007). Morphological
segmentation of hyperspectral images. Image
Analysis and Stereology 26:101–09.
Noyel G, Angulo J, Jeulin D (2007). On distances,
paths and connections for hyperspectral image
segmentation. In: Mathematical morphology and
its applications to signal and image processing,
Proc. 8th Int. Symposium on Mathematical
Morphology. Instituto Nacional de Pesquisas
Espaciais (INPE) 1:399–10.
Noyel G, Angulo J, Jeulin D (2008). Classificationdriven
stochastic watershed. Application to
multispectral segmentation. In: Proc. IS&T’s
Fourth European Conference on Color in Graphics
Imaging and Vision CGIV 2008 471–76.
Noyel G, Angulo J, Jeulin D (2008). Filtering,
segmentation and region classification by
hyperspectral mathematical morphology of
DCE-MRI series for angiogenesis imaging.
In: Proc. IEEE International Symposium on
Biomedical Imaging ISBI 2008 1517–20.
Noyel G (2008). Filtrage, réduction de dimension,
classification et segmentation morphologique
hyperspectrale.Mines-ParisTech, France.
Noyel G, Angulo J, Jeulin D (2010). Regionalized
random germs by a classification for probabilistic
watershed. Application: angiogenesis imaging
segmentation. In: Progress in Industrial
Mathematics at ECMI 2008. Springer
Mathematics in Industry 15:211–16.
Noyel G, Angulo J, Jeulin D (2011). A new spatiospectral
morphological segmentation for multispectral
remote-sensing images. Int J Remote Sens
(22):5895–920.
O’Connor JPB, Jackson A, Asselin MC, Buckley
DL, Parker GJM, Jayson GC (2008). Quantitative
imaging biomarkers in the clinical development
of targeted therapeutics: current and future
perspectives. The Lancet Oncology 9(8):766–76.
Orfeuil JP (1973). Une méthode de filtrage des
données. CG, Mines-ParisTech. Report N-314.
Pradel C, Siauve N, Bruneteau G, et al (2003).
Reduced capillary perfusion and permeability in
human tumour xenografts treated with the VEGF
signalling inhibitor ZD4190: an in vivo assessment
using dynamic MR imaging and macromolecular
contrast media. Magn Reson Imaging 21(8):845—
Scheunders P (2002). A multivalued image wavelet
representation based on multiscale fundamental
forms. IEEE T Image Process 11(5):568–75.
Soille P (1999). Morphological image analysis.
Springer-Berlin.
Sourbron SP, Buckley DL (2012). Tracer kinetic
modelling in MRI: estimating perfusion and
capillary permeability. Phys Med Biol 57(2):R1.
Zvan Dijke CF, Brasch RC, Roberts TP, Weidner N,
Mathur A, Shames DM et al.(1996). Mammary
carcinoma model: correlation of macromolecular
contrast-enhanced MR imaging characterizations
of tumor microvasculature and histologic capillary
density. Radiology 198(3):813–18.
Zahra MA, Hollingsworth KG, Sala E, Lomas DJ, Tan
LT (2007). Dynamic contrast-enhanced MRI as a
predictor of tumour response to radiotherapy. The
Lancet Oncology 8(1):63–74.
