TY - JOUR AB - PURPOSE: Deep generative models and synthetic data generation have become essential for advancing computer-assisted diagnosis and treatment. We explore one such emerging and particularly promising application of deep generative models, namely, the generation of virtual contrast enhancement. This allows to predict and simulate contrast enhancement in breast magnetic resonance imaging (MRI) without physical contrast agent injection, thereby unlocking lesion localization and categorization even in patient populations where the lengthy, costly, and invasive process of physical contrast agent injection is contraindicated. APPROACH: We define a framework for desirable properties of synthetic data, which leads us to propose the scaled aggregate measure (SAMe) consisting of a balanced set of scaled complementary metrics for generative model training and convergence evaluation. We further adopt a conditional generative adversarial network to translate from non-contrast-enhanced T 1 -weighted fat-saturated breast MRI slices to their dynamic contrast-enhanced (DCE) counterparts, thus learning to detect, localize, and adequately highlight breast cancer lesions. Next, we extend our model approach to jointly generate multiple DCE-MRI time points, enabling the simulation of contrast enhancement across temporal DCE-MRI acquisitions. In addition, three-dimensional U-Net tumor segmentation models are implemented and trained on combinations of synthetic and real DCE-MRI data to investigate the effect of data augmentation with synthetic DCE-MRI volumes. RESULTS: Conducting four main sets of experiments, (i) the variation across single metrics demonstrated the value of SAMe, and (ii) the quality and potential of virtual contrast injection for tumor detection and localization were shown. Segmentation models (iii) augmented with synthetic DCE-MRI data were more robust in the presence of domain shifts between pre-contrast and DCE-MRI domains. The joint synthesis approach of multi-sequence DCE-MRI (iv) resulted in temporally coherent synthetic DCE-MRI sequences and indicated the generative model's capability of learning complex contrast enhancement patterns. CONCLUSIONS: Virtual contrast injection can result in accurate synthetic DCE-MRI images, potentially enhancing breast cancer diagnosis and treatment protocols. We demonstrate that detecting, localizing, and segmenting tumors using synthetic DCE-MRI is feasible and promising, particularly considering patients where contrast agent injection is risky or contraindicated. Jointly generating multiple subsequent DCE-MRI sequences can increase image quality and unlock clinical applications assessing tumor characteristics related to its response to contrast media injection as a pillar for personalized treatment planning. AU - Osuala, R. AU - Joshi, S.* AU - Tsirikoglou, A.* AU - Garrucho, L.* AU - Pinaya, W.H.L.* AU - Lang, D.M. AU - Schnabel, J.A. AU - Diaz, O.* AU - Lekadir, K.* C1 - 75048 C2 - 57783 TI - Simulating dynamic tumor contrast enhancement in breast MRI using conditional generative adversarial networks. JO - J. Med. Imaging VL - 12 IS - Suppl 2 PY - 2025 SN - 2329-4302 ER - TY - JOUR AB - The accuracy of Monte Carlo (MC) simulations in estimating the computed tomography radiation dose is highly dependent on the proprietary x-ray source information. To address this, this study develops a method to precisely estimate the x-ray spectrum and bowtie (BT) filter thickness of the x-ray source based on physical measurements and calculations. The static x-ray source of the CT localizer radiograph was assessed to measure the total filtration at the isocenter for the x-ray spectrum characterization and the BT profile (air-kerma values as a function of fan angle). With these values, the utilized BT filter in the localizer radiograph was assessed by integrating the measured air kerma in a full 360-deg cycle. The consistency observed between the integrated BT filter profiles and the directly measured profiles pointed to the similarity in the utilized BT filter in terms of thickness and material between the static and rotating x-ray geometries. Subsequently, the measured air kerma was used to calculate the BT filter thickness and was verified using MC simulations by comparing the calculated and measured air-kerma values, where a very good agreement was observed. This would allow a more accurate computed tomography simulation and facilitate the estimation of the dose delivered to the patients. AU - Hassan, A.I.* AU - Skalej, M.* AU - Schlattl, H. AU - Hoeschen, C.* C1 - 52939 C2 - 44340 TI - Determination and verification of the x-ray spectrum of a CT scanner. JO - J. Med. Imaging VL - 5 IS - 1 PY - 2018 SN - 2329-4302 ER - TY - JOUR AB - Using numerical simulations, the influence of various imaging parameters on the resulting image can be determined for various imaging technologies. To achieve this, visualization of fine tissue structures needed to evaluate the image quality with different radiation quality and dose is essential. The present work examines a method that employs simulations of the imaging process using Monte Carlo methods and a combination of a standard and higher resolution voxel models. A hybrid model, based on nonlinear uniform rational B-spline and polygon mesh surfaces, was constructed from an existing voxel model of a female patient of a resolution in the range of millimeters. The resolution of the hybrid model was 500 μm, i.e., substantially finer than that of the original model. Furthermore, a high resolution lung voxel model [(0.11 mm)3 voxel volume, slice thickness: 114 μm] was developed from the specimen of a left lung lobe. This has been inserted into the hybrid model, substituting its left lung lobe and resulting in a dual-lattice geometry model. "Dual lattice" means, in this context, the combination of voxel models with different resolutions. Monte Carlo simulations of radiographic imaging were performed and the fine structure of the lung was easily recognizable. AU - Petoussi-Henß, N. AU - Schlattl, H. AU - Becker, J. AU - Greiter, M. AU - Zankl, M. AU - Hoeschen, C.* C1 - 50911 C2 - 42548 TI - Anthropomorphic dual-lattice voxel models for optimizing image quality and dose. JO - J. Med. Imaging VL - 4 IS - 1 PY - 2017 SN - 2329-4302 ER -