A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time.

This work presents a data-driven method to simulate, in real-time, the biomechanical behavior of the breast tissues in some image-guided interventions such as biopsies or radiotherapy dose delivery as well as to speed up multimodal registration algorithms. Ten real breasts were used for this work. Their deformation due to the displacement of two compression plates was simulated off-line using the finite element (FE) method. Three machine learning models were trained with the data from those simulations. Then, they were used to predict in real-time the deformation of the breast tissues during the compression. The models were a decision tree and two tree-based ensemble methods (extremely randomized trees and random forest). Two different experimental setups were designed to validate and study the performance of these models under different conditions. The mean 3D Euclidean distance between nodes predicted by the models and those extracted from the FE simulations was calculated to assess the performance of the models in the validation set. The experiments proved that extremely randomized trees performed better than the other two models. The mean error committed by the three models in the prediction of the nodal displacements was under 2 mm, a threshold usually set for clinical applications. The time needed for breast compression prediction is sufficiently short to allow its use in real-time (<0.2 s).

A complete software application for automatic registration of x-ray mammography and magnetic resonance images.

PURPOSE: This work presents a complete and automatic software application to aid radiologists in breast cancer diagnosis. The application is a fully automated method that performs a complete registration of magnetic resonance (MR) images and x-ray (XR) images in both directions (from MR to XR and from XR to MR) and for both x-ray mammograms, craniocaudal (CC), and mediolateral oblique (MLO). This new approximation allows radiologists to mark points in the MR images and, without any manual intervention, it provides their corresponding points in both types of XR mammograms and vice versa. METHODS: The application automatically segments magnetic resonance images and x-ray images using the C-Means method and the Otsu method, respectively. It compresses the magnetic resonance images in both directions, CC and MLO, using a biomechanical model of the breast that distinguishes the specific biomechanical behavior of each one of its three tissues (skin, fat, and glandular tissue) separately. It makes a projection of both compressions and registers them with the original XR images using affine transformations and nonrigid registration methods. RESULTS: The application has been validated by two expert radiologists. This was carried out through a quantitative validation on 14 data sets in which the Euclidean distance between points marked by the radiologists and the corresponding points obtained by the application were measured. The results showed a mean error of 4.2 ± 1.9 mm for the MRI to CC registration, 4.8 ± 1.3 mm for the MRI to MLO registration, and 4.1 ± 1.3 mm for the CC and MLO to MRI registration. CONCLUSIONS: A complete software application that automatically registers XR and MR images of the breast has been implemented. The application permits radiologists to estimate the position of a lesion that is suspected of being a tumor in an imaging modality based on its position in another different modality with a clinically acceptable error. The results show that the application can accelerate the mammographic screening process for high risk populations or for dense breasts.

Segmentation of the breast skin and its influence in the simulation of the breast compression during an X-ray mammography.

A novel method of skin segmentation is presented aimed to obtain as many pixels belonging to the real skin as possible. This method is validated by experts in radiology. In addition, a biomechanical model of the breast, which considers the skin segmented in this way, is constructed to study the influence of considering real skin in the simulation of the breast compression during an X-ray mammography. The reaction forces of the plates are obtained and compared with the reaction forces obtained using classical methods that model the skin as a 2D membranes that cover all the breast. The results of this work show that, in most of the cases, the method of skin segmentation is accurate and that real skin should be considered in the simulation of the breast compression during the X-ray mammographies.

MRI skin segmentation for the virtual deformation of the breast under mammographic compression.

Breast Magnetic Resonance Image skin has similar intensity levels than dense tissue, and may produce segmentation errors if not managed correctly. In this work a novel skin segmentation method is presented and validated by experts, aimed to obtain as many pixels belonging to the real skin as possible. Segmented skin will be used to build a breast biomechanical model to register X-Ray Images with Magnetic Resonance Images in the future, using a virtually deformed Magnetic Resonance Image.