Deep-learning convolutional neural network-based scatter correction for contrast enhanced digital breast tomosynthesis in both cranio-caudal and mediolateral-oblique views

Abstract

Purpose: Scatter radiation in contrast-enhanced digital breast tomosynthesis (CEDBT) reduces the image quality and iodinated lesion contrast. Monte Carlo simulation can provide accurate scatter estimation at the cost of computational burden. A model-based convolutional method trades off accuracy for processing speed. The purpose of this study is to develop a fast and robust deep-learning (DL) convolutional neural network (CNN)-based scatter correction method for CEDBT.Approach: Projection images and scatter maps of digital anthropomorphic breast phantoms were generated using Monte Carlo simulations. Experiments were conducted to validate the simulated scatter-to-primary ratio (SPR) at different locations of a breast phantom. Simulated projection images were used for CNN training and testing. Two separate U-Nets [low-energy (LE)-CNN and high-energy (HE)-CNN] were trained for LE and HE spectrum, respectively. CNN-based scatter correction was applied to a clinical case with a malignant iodinated mass to evaluate the influence on the lesion detection. Results:The average and standard deviation of mean absolute percentage error of LE-CNN and HE-CNN estimated scatter map are 2% AE 0.4% and 2.4% AE 0.8%, respectively. For clinical cases, the lesion signal difference to noise ratio average improvement was 190% after CNNbased scatter correction. To conduct scatter correction on clinical CEDBT images, the whole process of loading CNNs parameters and scatter correction for LE and HE images took <4 s, with 9 GB GPU computational cost. The SPR variation across the breast agrees between experimental measurements and Monte Carlo simulations. Conclusions:We developed a CNN-based scatter correction method for CEDBT in both CC view and mediolateral-oblique view with high accuracy and fast speed.

Task-based transferable deep-learning scatter correction in cone beam computed tomography: a simulation study

“…Furthermore, it was noted that the SR predictions from pCNN are smoother than the actual training targets, suggesting that CNN-based methods do not contribute additional noise to the reconstructed image. 30 The accuracy of SR predictions was further improved after TL (see Fig. 9).…”

Experimental results of the first prototype direct-indirect dual-layer flat-panel detector for contrast-enhanced digital mammography and contrast-enhanced digital breast tomosynthesis

“…[1][2][3][4] In conventional clinical situation, low-energy (LE) and high-energy (HE) images are acquired with two separate exposures, referred to as the dual-shot (DS) method in this study. [5][6][7][8][9][10] Patient motion between two exposures occurs frequently with DS method, which could result in residual breast tissue structure in recombined DE images, which impacts the image quality and iodinated lesion conspicuity. 5,[11][12][13][14][15][16][17][18] Studies have shown that for cases with gross patient motion, the artifact cannot be completely eliminated with image registration algorithms.…”