This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Purpose: Physics-informed neural networks (PINNs) and computational fluid dynamics (CFD) have both demonstrated an ability to derive accurate hemodynamics if boundary conditions (BCs) are known. Unfortunately, patient-specific BCs are often unknown, and assumptions based upon previous investigations are used instead. High speed angiography (HSA) may allow extraction of these BCs due to the high temporal fidelity of the modality. We propose to investigate whether PINNs using convection and Navier-Stokes equations with BCs derived from HSA data may allow for extraction of accurate hemodynamics in the vasculature.
Materials and Methods: Imaging data generated from in vitro 1000 fps HSA, as well as simulated 1000 fps angiograms generated using CFD were utilized for this study. Calculations were performed on a 3D lattice comprised of 2D projections temporally stacked over the angiographic sequence. A PINN based on an objective function comprised of the Navier-Stokes equation, the convection equation, and angiography-based BCs was used for estimation of velocity, pressure and contrast flow at every point in the lattice.
Results: Imaging-based PINNs show an ability to capture such hemodynamic phenomena as vortices in aneurysms and regions of rapid transience, such as outlet vessel blood flow within a carotid artery bifurcation phantom. These networks work best with small solution spaces and high temporal resolution of the input angiographic data, meaning HSA image sequences represent an ideal medium for such solution spaces.
Conclusions: The study shows the feasibility of obtaining patient-specific velocity and pressure fields using an assumption-free data driven approach based purely on governing physical equations and imaging data.
Purpose: Identification of cardiomyocyte nuclei is of great importance when assessing heart tissue for cardiovascular disease. However, manual identification of cardiomyocyte nuclei in hematoxylin & eosin (H&E)-stained heart tissue is particularly complex due to extensive heterogeneity in morphology. While expensive and time-consuming staining processes can be utilized to identify cardiomyocyte nuclei, this study proposes to test the feasibility of using a cycle-consistent generative adversarial network (CycleGAN) to automate the identification of cardiomyocyte nuclei in H&E-stained heart tissue without the need for additional staining.
Materials and Methods: 100 H&E-stained heart tissue sample regions from cancer patients were manually labeled with the input from an expert pathologist. Sample regions were processed into 3,584 labeled tiles and 3,584 tiles without labels, and then sorted, augmented, and run through a CycleGAN to facilitate the identification of cardiomyocyte nuclei. Performance was assessed with Fréchet Inception Distance (FID), Fréchet ResNet-50 Distance (FRD), sensitivity, specificity, and accuracy.
Results: Sensitivity and specificity were 61.6% sensitivity, 96.3% specificity with an accuracy of 85.0% for 30 randomly selected samples. FID and FRD reached as low as 64.8 and 2.46, respectively, with downward trend for FID and high volatility with a slight downward trend for FRD. Notably, the best results were achieved when FRD was at its lowest value.
Conclusion: The results suggest cardiomyocyte nuclei can be identified by a CycleGAN. However, targeted improvements are necessary to ensure accurate identification. An enhanced version of this approach may facilitate the automation of identifying cardiomyocyte nuclei in H&E-stained heart tissue, facilitating cardiovascular research.
Use of a convolutional neural network for aneurysm identification in digital subtraction angiography
Materials and Methods: Twelve patients for whom catheter angiography was clinically indicated signed written informed consent to CT Angiography (CTA) before their standard care that included coronary angiography (ICA) and conventional FFR (Angio-FFR). The research CTA was used first to determine CT-derived FFR (Vital Images) and second to generate patient specific 3D printed models of the aortic root and three main coronary arteries that were connected to a programmable pulsatile pump. Benchtop FFR was derived from pressures measured proximal and distal to coronary stenosis using pressure transducers.
Results: All 12 patients completed the clinical study without any complication, and the three FFR techniques (Angio-FFR, CT-FFR, and Benchtop FFR) are reported for one or two main coronary arteries. The Pearson correlation among Benchtop FFR/ Angio-FFR, CT-FFR/ Benchtop FFR, and CT-FFR/ Angio-FFR are 0.871, 0.877, and 0.927 respectively.
Conclusions: 3D printed patient specific cardiovascular models successfully simulated hyperemic blood flow conditions, matching invasive Angio-FFR measurements. This benchtop flow system could be used to validate CTderived FFR diagnostic software, alleviating both cost and risk during invasive procedures.
The 3D model was connected to a pulsatile flow loop for simulating interventions using clinical devices such as catheters and stents. To validate the x-ray attenuation and establish clinical accuracy, the automatic exposure selection by a clinical c-arm system for the phantom was compared with that for a commercial anthropomorphic head phantom (SK-150, Phantom Labs). The percentage difference between automatic exposure selection for the neuro-intervention phantom and the SK-150 phantom was under 10%.
By changing 3D printed models, various patient diseased anatomies can be simulated accurately with the necessary x-ray attenuation. Using this platform various interventional procedures were performed using new imaging technologies such as a high-resolution x-ray fluoroscope and a dose-reduced region-of-interest attenuator and differential temporally filtered display for enhanced interventional imaging. Simulated clinical views from such phantom-based procedures were used to evaluate the potential clinical performance of such new technologies.
3DP idealized and patient specific vascular phantoms were manufactured using Stratasys Objet 500 Connex 3. The idealized phantoms were created using a sine wave shape, patient specific phantoms were based on CT- angiography volumes. The phantoms were coated with a hydrophilic material to mimic vascular surface properties. We tested various endovascular procedures using an Interventional Device Testing Equipment (IDTE) 2000 and measured push/pull force used to actuate endovascular devices during EIGIs.
The force needed to advance devices in neurovascular phantoms varied based on tortuosity, material and coating, ranging from -3 to 21 grams-force. Hydrophilic coating reduced maximum force from 21 to 4.8 grams-force in the same model. IDTE 2000 results of neurovascular models were compared to hand manipulation of guidewire access using a six-axis force sensor with forces ranging from -50 to 440 grams. The clot retriever tested in carotid models experienced most friction around tortuous bends ranging from -65 to -90 grams-force, with increasing rigidity of materials creating increased friction. Sine wave model forces varied from -2 to 105 grams.
3DP allows manufacturing of vascular phantoms with precise mechanical and surface properties which can be used for EIGI simulations for imaging protocol optimization and device behavior assessment.
To simulate the human neurovasculature in the Circle of Willis, patient-based phantoms with aneurysms were 3D printed using a Objet Eden 260V printer. Anthropomorphic head phantoms and a human skull combined with acrylic plates simulated human head bone anatomy and x-ray attenuation. For dynamic studies the 3D printed phantom was connected to a pulsatile flow loop with the anthropomorphic phantom underneath. By combining different 3D printed phantoms and the anthropomorphic phantoms, different patient pathologies can be simulated. For static studies a 3D printed neurovascular phantom was embedded inside a human skull and used as a positional reference for treatment devices such as stents. To simulate tissue attenuation acrylic layers were added. Different combinations can simulate different patient treatment procedures.
The Complementary-Metal-Oxide-Semiconductor (CMOS) based High Resolution Fluoroscope (HRF) with 75μm pixels offers an advantage over the state-of-the-art 200 μm pixel Flat Panel Detector (FPD) due to higher Nyquist frequency and better DQE performance. Whether this advantage is clinically useful during an actual clinical neurovascular intervention can be addressed by qualitatively evaluating images from a cohort of various cases performed using both detectors. The above-mentioned method can offer a realistic substitute for an actual clinical procedure. Also a large cohort of cases can be generated and used for a HRF clinical utility determination study.
First a model to simulate the aortic arch and its movement was built. A coronary stent was used to simulate a bioprosthetic valve used in TAVR procedures and was deployed under dose-reduced ROI fluoroscopy during the simulated heart motion. The images were then retrospectively processed for noise reduction in the periphery, using recursive temporal filtering, spatial filtering and a combination of both.
Quantitative metrics for all three noise reduction schemes are calculated and are presented as results. From these it can be concluded that with significant anatomical motion, a combination of spatial and recursive temporal filtering scheme is best suited for reducing the excess quantum noise in the periphery. This new noise-reduction technique in combination with ROI fluoroscopy has the potential for substantial patient-dose savings in cardiac interventions.