Benjamin P. Ziemer

An architecture that uses a variational autoencoder-enhanced, attention-aware, cycle-consistent generative adversarial network (A-CycleGAN) for MR-to-CT image translation is described; this is the ... PurposeTo suggest an attention-aware, cycle-consistent generative adversarial network (A-CycleGAN) enhanced with variational autoencoding (VAE) as a superior alternative to current state-of-the-art...

The first-pass analysis technique was retrospectively validated in a swine model and has the potential to be used for accurate, low-dose vessel-specific morphologic and physiologic assessment of coronary artery disease. PurposeTo retrospectively validate a first-pass analysis (FPA) technique that combines computed tomographic (CT) angiography and dynamic CT perfusion measurement into one low-dose examination.Materials and MethodsThe study was approved by the animal care committee. The FPA technique was retrospectively validated in six swine (mean weight, 37.3 kg ± 7.5 [standard deviation]) between April 2015 and October 2016. Four to five intermediate-severity stenoses were generated in the left anterior descending artery (LAD), and 20 contrast material–enhanced volume scans were acquired per stenosis. All volume scans were used for maximum slope model (MSM) perfusion measurement, but only two volume scans were used for FPA perfusion measurement. Perfusion measurements in the LAD, left circumflex artery (LCx), right coronary artery, and all three coronary arteries combined were compared with microsphere perfusion measurements by using regression, root-mean-square error, root-mean-square deviation, Lin concordance correla...

Purpose: Single‐isocenter, volumetric‐modulated arc therapy (VMAT) stereotactic radiosurgery (SRS) for multiple brain metastases (multimets) can deliver highly conformal dose distributions and reduce overall patient treatment time compared to other techniques. However, treatment planning for multimet cases is highly complex due to variability in numbers and sizes of brain metastases, as well as their relative proximity to organs‐at‐risk (OARs). The purpose of this study was to automate the VMAT planning of multimet cases through a knowledge‐based planning (KBP) approach that adapts single‐target SRS dose predictions to multiple target predictions.Methods: Using a previously published artificial neural network (ANN) KBP system trained on single‐target, linac‐based SRS plans, 3D dose distribution predictions for multimet patients were obtained by treating each brain lesion as a solitary target and subsequently combining individual dose predictions into a single distribution. Spatial dose distributions for each of the i = 1…N lesions were merged using the combination function . The optimal value of n was determined by minimizing root‐mean squared (RMS) difference between clinical multimet plans and predicted dose per unit length along the line profile joining each lesion in the clinical cohort. The gradient measure is the primary quality metric for SRS plan evaluation at our institution and served as the main comparative metric between clinical plans and the KBP results. A total of 41 previously treated multimet plans, with target numbers ranging from N = 2–10, were used to validate the ANN predictions and subsequent KBP auto‐planning routine. Fully deliverable KBP plans were developed by converting predicted dose distribution into patient‐specific optimization objectives for the clinical treatment planning system (TPS). Plan parity was maintained through identical arc configuration and target normalization. Overall plan quality improvements were quantified by calculating the difference between SRS quality metrics (QMs): ΔQM = QM_clinical − QM_KBP. In addition to GM, investigated QMs were: volume of brain receiving ≥ 10 Gy (V_10 Gy), volume of brain receiving ≥ 5 Gy (ΔV_5 Gy), heterogeneity index (HI), dose to 0.1 cc of the brainstem (D_0.1 cc), dose to 1% of the optic chiasm (D_1%), and interlesion dose (D_IL). In addition to this quantitative analysis, overall plan quality was assessed via blinded plan comparison of the manual and KBP treatment plans by SRS‐specializing physicians.Results: A dose combination factor of n = 8 yielded an integrated dose profile RMS difference of 2.9% across the 41‐patient cohort. Multimet dose predictions exhibited ΔGM = 0.07 ± 0.10 cm against the clinical sample, implying either further normal tissue sparing was possible or that dose predictions were slightly overestimating achievable dose gradients. The latter is the more likely explanation, as this bias vanished when dose predictions were converted to deliverable KBP plans ΔGM = 0.00 ± 0.08 cm. Remaining QMs were nearly identical or showed modest improvements in the KBP sample. Equivalent QMs included: ΔV_10 Gy = 0.37 ± 3.78 cc, ΔHI = 0.02 ± 0.08 and ΔD_IL = −2.22 ± 171.4 cGy. The KBP plans showed a greater degree of normal tissue sparing as indicated by brain ΔV_5 Gy = 4.11± 24.05 cc, brainstem ΔD_0.1 cc = 42.8 ± 121.4 cGy, and chiasm ΔD_1% = 50.8 ± 83.0 cGy. In blinded review by SRS‐specializing physicians, KBP‐generated plans were deemed equivalent or superior in 32/41(78.1%) of the cases.Conclusion: Heuristic KBP‐driven automated planning in linac‐based, single‐isocenter treatments for multiple brain metastases maintained or exceeded overall plan quality.

Background—: Computed tomographic (CT) angiography is an important tool for the evaluation of coronary artery disease but often correlates poorly with myocardial ischemia. Current dynamic CT perfusion techniques can assess ischemia but have limited accuracy and deliver high radiation dose. Therefore, an accurate, low-dose, dynamic CT perfusion technique is needed. Methods and Results—: A total of 20 contrast-enhanced CT volume scans were acquired in 5 swine (40±10 kg) to generate CT angiography and perfusion images. Varying degrees of stenosis were induced using a balloon catheter in the proximal left anterior descending coronary artery, and a pressure wire was used for reference fractional flow reserve (FFR) measurement. Perfusion measurements were made with only 2 volume scans using a new first-pass analysis (FPA) technique and with 20 volume scans using an existing maximum slope model (MSM) technique. Perfusion (P) and FFR measurements were related by P _FPA =1.01 FFR−0.03 ( R ² =0.85) and P _MSM =1.03 FFR−0.03 ( R ² =0.80) for FPA and MSM techniques, respectively. Additionally, the effective radiation doses were calculated to be 2.64 and 26.4 mSv for FPA and MSM techniques, respectively. Conclusions—: A new FPA-based dynamic CT perfusion technique was validated in a swine animal model. The results indicate that the FPA technique can potentially be used for improved anatomical and functional assessment of coronary artery disease at a relatively low radiation dose.