100 likes | 115 Views
This research presents a model-based registration approach to locate lesions in X-ray mammograms and MR images, aiding in multimodal breast cancer diagnosis. By incorporating a biomechanical model to address issues like large deformation, the method achieves successful localization with approximately 5mm deviation, as demonstrated in clinical evaluations.
E N D
Model-Based Registration of X-ray Mammograms and MR Images of the Female Breast N.V. Ruiter, T.O. Müller, R. Stotzka, H. Gemmeke,Forschungszentrum Karlsruhe, Germany
Locate lesion in complementary modality Motivation Support multimodal breast cancer diagnosis: MR image ? O O X-ray mammogram Registration:Find geometric correspondence
MR image: • Volume image • Undeformed breast • Prone position Registration Problem Images not directly comparable ! • X-ray mammography: • 2D projection • Large deformation • Only one projection per deformation Add information using a biomechanical model
MR image Biomechanical model Deformed model Deformation process Projection of artificial MR image X-ray mammogram Process of Registration
Skin Fatty tissue Glandular tissue L‘ Problems of Deformation Model • Large deformation of soft tissue • Details of deformation process unknown: • Exact patient position • 3D shape of breast • Thickness of deformed breast • Compression force • Tissues of the breast: • Only large scale structures resolved in MR image • Material models in literature: • Inconclusive • Not plausible for large deformation Plate compression
Specification of Deformation Model • Adapt global parameters: • Projection angle by non-linear scaling • Volume is preserved estimate thickness • Finite Element Model • Large deformations (>>5%), (nearly) incompressible materials • Material model • Evaluation of models for breast tissue: Neo Hookean model, homogeneous tissues • Two step modeling of deformation 1st step: Mammographic deformation 2nd step: Fine tuning using mammogram Mammographicdeformation
Results with Clinical Datasets • Six clinical data sets: Lesion position in X-ray mammograms and MR image known • Smallest visible lesions in MR images: 5 mm • Prediction of lesion position • MRI X-ray: • Mean center distance: 4.3 mm (2.3 – 6 mm) • Mean area overlap: 81% • X-ray MRI: • Mean center distance: 3.9 mm (1.6 – 6.4 mm) • Mean volume overlap: 91%
24mm • Center lesion distance 2.3mm • Lesion overlap 100% MR projection after simulation Results with Clinical Datasets MRI X-ray : craniocaudal example Direct MR projection X-ray mammogram
Conclusions • Registration overcomes 3D deformation • Successful first evaluation: Localization with approx. 5 mm deviation(smallest visible lesion) • Clinical evaluation • Possible applications: • Support multimodal breast cancer diagnosis(also alternative 3D modalities) • Simulation of breast deformation