skip to main content

Title: MAGIC: Multitask Automated Generation of Inter-modal CT Perfusion Maps via Generative Adversarial Network
Introduction: Computed tomography perfusion (CTP) imaging requires injection of an intravenous contrast agent and increased exposure to ionizing radiation. This process can be lengthy, costly, and potentially dangerous to patients, especially in emergency settings. We propose MAGIC, a multitask, generative adversarial network-based deep learning model to synthesize an entire CTP series from only a non-contrasted CT (NCCT) input. Materials and Methods: NCCT and CTP series were retrospectively retrieved from 493 patients at UF Health with IRB approval. The data were deidentified and all images were resized to 256x256 pixels. The collected perfusion data were analyzed using the RapidAI CT Perfusion analysis software (iSchemaView, Inc. CA) to generate each CTP map. For each subject, 10 CTP slices were selected. Each slice was paired with one NCCT slice at the same location and two NCCT slices at a predefined vertical offset, resulting in 4.3K CTP images and 12.9K NCCT images used for training. The incorporation of a spatial offset into the NCCT input allows MAGIC to more accurately synthesize cerebral perfusive structures, increasing the quality of the generated images. The studies included a variety of indications, including healthy tissue, mild infarction, and severe infarction. The proposed MAGIC model incorporates a novel multitask architecture, more » allowing for the simultaneous synthesis of four CTP modalities: mean transit time (MTT), cerebral blood flow (CBF), cerebral blood volume (CBV), and time to peak (TTP). We propose a novel Physicians-in-the-loop module in the model's architecture, acting as a tunable layer that allows physicians to manually adjust the amount of anatomic detail present in the synthesized CTP series. Additionally, we propose two novel loss terms: multi-modal connectivity loss and extrema loss. The multi-modal connectivity loss leverages the multi-task nature to assert that the mathematical relationship between MTT, CBF, and CBV is satisfied. The extrema loss aids in learning regions of elevated and decreased activity in each modality, allowing for MAGIC to accurately learn the characteristics of diagnostic regions of interest. Corresponding NCCT and CTP slices were paired along the vertical axis. The model was trained for 100 epochs on a NVIDIA TITAN X GPU. Results and Discussion: The MAGIC model’s performance was evaluated on a sample of 40 patients from the UF Health dataset. Across all CTP modalities, MAGIC was able to accurately produce images with high structural agreement between the entire synthesized and clinical perfusion images (SSIMmean=0.801 , UQImean=0.926). MAGIC was able to synthesize CTP images to accurately characterize cerebral circulatory structures and identify regions of infarct tissue, as shown in Figure 1. A blind binary evaluation was conducted to assess the presence of cerebral infarction in both the synthesized and clinical perfusion images, resulting in the synthesized images correctly predicting the presence of cerebral infarction with 87.5% accuracy. Conclusions: We proposed a MAGIC model whose novel deep learning structures and loss terms enable high-quality synthesis of CTP maps and characterization of circulatory structures solely from NCCT images, potentially eliminating the requirement for the injection of an intravenous contrast agent and elevated radiation exposure during perfusion imaging. This makes MAGIC a beneficial tool in a clinical scenario increasing the overall safety, accessibility, and efficiency of cerebral perfusion and facilitating better patient outcomes. Acknowledgements: This work was partially supported by the National Science Foundation, IIS-1908299 III: Small: Modeling Multi-Level Connectivity of Brain Dynamics + REU Supplement, to the University of Florida. « less
; ;
Award ID(s):
Publication Date:
Journal Name:
Biomedical Engineering Society Annual Meeting
Sponsoring Org:
National Science Foundation
More Like this
  1. Introduction Multi-series CT (MSCT) scans, including non-contrast CT (NCCT), CT Perfusion (CTP), and CT Angiography (CTA), are widely used in acute stroke imaging. While each scan has its advantage in disease diagnosis, the varying image resolution of different series hinders the ability of the radiologist to discern subtle suspicious findings. Besides, higher image quality requires high radiation doses, leading to increases in health risks such as cataract formation and cancer induction. Thus, it is highly crucial to develop an approach to improve MSCT resolution and to lower radiation exposure. Hypothesis MSCT imaging of the same patient is highly correlated in structural features, the transferring and integration of the shared and complementary information from different series are beneficial for achieving high image quality. Methods We propose TL-GAN, a learning-based method by using Transfer Learning (TL) and Generative Adversarial Network (GAN) to reconstruct high-quality diagnostic images. Our TL-GAN method is evaluated on 4,382 images collected from nine patients’ MSCT scans, including 415 NCCT slices, 3,696 CTP slices, and 271 CTA slices. We randomly split the nine patients into a training set (4 patients), a validation set (2 patients), and a testing set (3 patients). In preprocessing, we remove the background and skullmore »and visualize in brain window. The low-resolution images (1/4 of the original spatial size) are simulated by bicubic down-sampling. For training without TL, we train different series individually, and for with TL, we follow the scanning sequence (NCCT, CTP, and CTA) by finetuning. Results The performance of TL-GAN is evaluated by the peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) index on 184 NCCT, 882 CTP, and 107 CTA test images. Figure 1 provides both visual (a-c) and quantity (d-f) comparisons. Through TL-GAN, there is a significant improvement with TL than without TL (training from scratch) for NCCT, CTP, and CTA images, respectively. These significances of performance improvement are evaluated by one-tailed paired t-tests (p < 0.05). We enlarge the regions of interest for detail visual comparisons. Further, we evaluate the CTP performance by calculating the perfusion maps, including cerebral blood flow (CBF) and cerebral blood volume (CBV). The visual comparison of the perfusion maps in Figure 2 demonstrate that TL-GAN is beneficial for achieving high diagnostic image quality, which are comparable to the ground truth images for both CBF and CBV maps. Conclusion Utilizing TL-GAN can effectively improve the image resolution for MSCT, provides radiologists more image details for suspicious findings, which is a practical solution for MSCT image quality enhancement.« less
  2. Purpose: Parkinson’s Disease (PD) is the second most common form of neural degeneration and defined by the decay of dopaminergic cells in the substantia nigra. The current standard for diagnosing PD occurs once 80% of dopaminergic cells have decayed. The degradation of these cells has been shown to create thinning of the retina walls and retina microvasculature. This work serves to find machine learning techniques to provide PD diagnosis using non-invasive fundus eye images. Materials and Methods: Two age and gender matched datasets where constructed using data from the UK Biobank (UKB) and data collected at the University of Florida (UF). The first dataset consists of 476 fundus eye images, 238 CN and 238 PD, sourced entirely from the UKB database. The second dataset, UF-UKB, consist of 100 images, 28 CN and 72 PD, collected at UF and 44 CN images from UKB. A second set of datasets, UKB-Green and UF-UKB-Green, were created using the green color channels to improve vessel segmentation. Vessel segmentation was performed using U-Net segmentation network. The vessel maps served as inputs to SVM classifying networks. Saliency maps were created to assess areas of interest for the networks. Results: The top performing SVM network for themore »UKB and UKB-Green datasets were the sigmoid SVM networks which achieved accuracies of .698 and .719 respectively. Meanwhile the top performing networks for the UF-UKB and UF-UKB-Green datasets where the linear SVM networks which achieved accuracies of .821 and .857 respectively. The saliency maps indicate that the different networks focused on different vessel structures with the most successful networks focusing more on smaller vessels. Conclusion: The results indicate that the machine learning networks can classify PD based on retina vasculature, with the key features being smaller blood vessels. The proposed methods further support the idea that changes in brain physiology can be observed in the eye. Machine learning networks can be applied to clinically available data and still provide accurate predictions Clinical Relevance statement, not to exceed 200 characters: The work illustrates the feasibility of utilizing eye images as a potential method for diagnosing PD, opposed to the current method of using motor symptoms.« less
  3. Puyol Anton, E ; Pop, M ; Sermesant, M ; Campello, V ; Lalande, A ; Lekadir, K ; Suinesiaputra, A ; Camara, O ; Young, A (Ed.)
    Cardiac cine magnetic resonance imaging (CMRI) is the reference standard for assessing cardiac structure as well as function. However, CMRI data presents large variations among different centers, vendors, and patients with various cardiovascular diseases. Since typical deep-learning-based segmentation methods are usually trained using a limited number of ground truth annotations, they may not generalize well to unseen MR images, due to the variations between the training and testing data. In this study, we proposed an approach towards building a generalizable deep-learning-based model for cardiac structure segmentations from multi-vendor,multi-center and multi-diseases CMRI data. We used a novel combination of image augmentation and a consistency loss function to improve model robustness to typical variations in CMRI data. The proposed image augmentation strategy leverages un-labeled data by a) using CycleGAN to generate images in different styles and b) exchanging the low-frequency features of images from different vendors. Our model architecture was based on an attention-gated U-Net model that learns to focus on cardiac structures of varying shapes and sizes while suppressing irrelevant regions. The proposed augmentation and consistency training method demonstrated improved performance on CMRI images from new vendors and centers. When evaluated using CMRI data from 4 vendors and 6 clinical center,more »our method was generally able to produce accurate segmentations of cardiac structures.« less
  4. Image synthesis from corrupted contrasts increases the diver- sity of diagnostic information available for many neurological diseases. Recently the image-to-image translation has experienced signi cant lev- els of interest within medical research, beginning with the successful use of the Generative Adversarial Network (GAN) to the introduction of cyclic constraint extended to multiple domains. However, in current ap- proaches, there is no guarantee that the mapping between the two image domains would be unique or one-to-one. In this paper, we introduce a novel approach to unpaired image-to-image translation based on the invertible architecture. The invertible property of the ow-based architecture assures a cycle-consistency of image-to-image translation without additional loss functions. We utilize the temporal informa- tion between consecutive slices to provide more constraints to the optimization for transforming one domain to another in un- paired volumetric medical images. To capture temporal structures in the medical images, we explore the displacement between the consec- utive slices using a deformation eld. In our approach, the deformation eld is used as a guidance to keep the translated slides realistic and con- sistent across the translation. The experimental results have shown that the synthesized images using our proposed approach are able to archive a competitivemore »performance in terms of mean squared error, peak signal- to-noise ratio, and structural similarity index when compared with the existing deep learning-based methods on three standard datasets, i.e. HCP, MRBrainS13 and Brats2019.« less
  5. The standard of clinical care in many pediatric and neonatal neurocritical care units involves continuous monitoring of cerebral hemodynamics using hard-wired devices that physically adhere to the skin and connect to base stations that commonly mount on an adjacent wall or stand. Risks of iatrogenic skin injuries associated with adhesives that bond such systems to the skin and entanglements of the patients and/or the healthcare professionals with the wires can impede clinical procedures and natural movements that are critical to the care, development, and recovery of pediatric patients. This paper presents a wireless, miniaturized, and mechanically soft, flexible device that supports measurements quantitatively comparable to existing clinical standards. The system features a multiphotodiode array and pair of light-emitting diodes for simultaneous monitoring of systemic and cerebral hemodynamics, with ability to measure cerebral oxygenation, heart rate, peripheral oxygenation, and potentially cerebral pulse pressure and vascular tone, through the utilization of multiwavelength reflectance-mode photoplethysmography and functional near-infrared spectroscopy. Monte Carlo optical simulations define the tissue-probing depths for source–detector distances and operating wavelengths of these systems using magnetic resonance images of the head of a representative pediatric patient to define the relevant geometries. Clinical studies on pediatric subjects with and without congenital centralmore »hypoventilation syndrome validate the feasibility for using this system in operating hospitals and define its advantages relative to established technologies. This platform has the potential to substantially enhance the quality of pediatric care across a wide range of conditions and use scenarios, not only in advanced hospital settings but also in clinics of lower- and middle-income countries.« less