Search

Breast density, which is the ratio between fibroglandular tissue (FGT) and total breast volume, can be assessed qualitatively by radiologists and quantitatively by computer algorithms. These algorithms often rely on segmentation of breast and FGT volume. In this study, we propose a method to directly assess breast density on MRI, and provide interpretations of these assessments. We assessed breast density in 506 patients with breast cancer using a regression convolutional neural network (CNN). The input for the CNN were slices of breast MRI of 128 x 128 voxels, and the output was a continuous density value between 0 (fatty breast) and 1 (dense breast). We used 350 patients to train the CNN, 75 for validation, and 81 for independent testing. We investigated why the CNN came to its predicted density using Deep SHapley Additive exPlanations (SHAP). The density predicted by the CNN on the testing set was significantly correlated with the ground truth densities (N = 81 patients, Spearman's rho = 0.86, P < 0.001). When inspecting what the CNN based its predictions on, we found that voxels in FGT commonly had positive SHAP-values, voxels in fatty tissue commonly had negative SHAP-values, and voxels in non-breast tissue commonly had SHAP-values near zero. This means that the prediction of density is based on the structures we expect it to be based on, namely FGT and fatty tissue. To conclude, we presented an interpretable deep learning regression method for breast density estimation on MRI with promising results., This paper has been published as: Van der Velden, B.H.M., Ragusi, M.A.A., Janse, M.H.A., Loo, C.E., Gilhuijs, K.G.A. "Interpretable deep learning regression for breast density estimation on MRI." Medical Imaging 2020: Computer-Aided Diagnosis. Vol. 11314. International Society for Optics and Photonics, 2020

Image-guided navigation on the basis of pre-therapy images in a deformable organ, such as the breast, requires a survey of the factors that cause uncertainties. A deformable breast-tissue-mimicking phantom with simulated tumors was employed to investigate the accuracy of lesion localization with a needle instrument coupled to an optical measurement system. The RMS deviation was 1.1 mm with errors d 2.0 mm in 96% of the procedures. Ultrasonography data acquired during needle localization of breast tumors were analyzed in 20 patients (23 tumors; 12 benign, 11 malignant) to investigate the deformation due to presence of instruments. The overall RMS tumor shift was 2.3 mm after release of pressure on the needle. To establish an optimal strategy to correct for breast motion due to breathing experiments with a volunteer were performed. Tracking a single centre marker was found to be most effective to improve registration accuracy. Average deviations of 8.2 mm were reduced to 1.1 mm. The combined impact of these different uncertainties resulted in distributions defined by: μ = 2.5 mm, �1 = 1.4 mm (benign and malignant), μ = 3.1 mm, �1 = 1.8 mm (benign), μ = 1.7 mm, �1 = 0.9 mm (malignant).