Vascular Maps Research Articles

Dynamic Contrast Enhanced MRI Mapping of Vascular Permeability for Evaluation of Breast Cancer Neoadjuvant Chemotherapy Response Using Image-to-Image Conditional Generative Adversarial Networks.

Dynamic contrast enhanced (DCE) MRI is a non-invasive imaging technique that has become a quantitative standard for assessing tumor microvascular permeability. Through the application of a pharmacokinetic (PK) model to a series of T1-weighed MR images acquired after an injection of a contrast agent, several vascular permeability parameters can be quantitatively estimated. These parameters, including Ktrans, a measure of capillary permeability, have been widely implemented for assessing tumor vascular function as well as tumor therapeutic response. However, conventional PK modeling for translation of DCE MRI to PK vascular permeability parameter maps is complex and time-consuming for dynamic scans with thousands of pixels per image. In recent years, image-to-image conditional generative adversarial network (cGAN) is emerging as a robust approach in computer vision for complex cross-domain translation tasks. Through a sophisticated adversarial training process between two neural networks, image-to-image cGANs learn to effectively translate images from one domain to another, producing images that are indistinguishable from those in the target domain. In the present study, we have developed a novel image-to-image cGAN approach for mapping DCE MRI data to PK vascular permeability parameter maps. The DCE-to-PK cGAN not only generates high-quality parameter maps that closely resemble the ground truth, but also significantly reduces computation time over 1000-fold. The utility of the cGAN approach to map vascular permeability is validated using open-source breast cancer patient DCE MRI data provided by The Cancer Imaging Archive (TCIA). This data collection includes images and pathological analyses of breast cancer patients acquired before and after the first cycle of neoadjuvant chemotherapy (NACT). Importantly, in good agreement with previous studies leveraging this dataset, the percentage change of vascular permeability Ktrans derived from the DCE-to-PK cGAN enables early prediction of responders to NACT.

Using Vascular Deserts as a Guide for Limb Preservation Outreach Programs Successfully Targets Underserved Populations

Vascular deserts, regions without vascular providers, previously described targets for limb salvage efforts. The Comprehensive Heart and Multidisciplinary Limb Preservation Outreach Networks (CHAMPIONS) programs targeted regions for outreach and evaluated the population using desert maps. At 2 events targeting underserved regions between 2022 and 2023, providers screened and educated participants on peripheral arterial and cardiovascular disease (PACD). Demographics and cardiovascular risk factors were collected. Using Arc geographic information system, vascular surgeons, and Vascular Quality Initiative (VQI) participating facilities were mapped with a 30-mile buffer. Participants were mapped with census data, and the healthy places index (HPI) was overlayed for population and social determinants of health data analysis in medical service study areas (MSSA), a geographical analysis unit. (Figure1) Results were compared to prior statewide deserts. Outreach program participants' mean age was 56 (range 6-88); 39% were male, and the majority were Hispanic (86%). 27% had no primary care provider (PCP). 30% had diabetes, 10% undiagnosed before the event, 38% had hypertension, 40% undiagnosed prior to the event, and 21% described intermittent claudication. 81% made <$30,000 annually, and 28% reported no health insurance. Similarities were observed when comparing program participant demographics to the population-level data from the targeted regions. Patients were more frequently Hispanic than other desert regions (68% vs. 36%, P<0.001). Compared to other vascular desert regions, the target population was more disadvantaged in all HPI domains, including economic (18 vs. 38%, P<0.001), education (21 vs. 39%, P<0.001), and transportation (30 vs. 40%, P<0.001). Worse education, financial, and transportation resources correspond to decreased care access due to poor literacy and travel burdens. CHAMPIONS programs successfully targeted populations needing care based on vascular care desert maps, demonstrating that at-risk populations can be successfully identified and screened for cardiovascular disease.

Imaging of the vascular distribution of the outer ear using optical coherence tomography angiography for highly accurate positioning of a hearable sensor.

Novel hearable technology is securely and comfortably positioned within the ear canal minimizing inaccuracies caused by accessory movements during activities. Despite extensive research on hearable technologies within the outer ear, there is a lack of research in the field of vascular imaging and quantitative analysis in the outer ear in vivo, which is one of the crucial factors to select the appropriate sensor position. Therefore, in this paper, we introduced optical coherence tomography angiography (OCTA)-based qualitative and quantitative analyses to visualize the inner vasculature of the outer ear to acquire vascular maps for microvascular assessments in vivo. By generating maximum amplitude projection images from three-dimensional blood vascular volume, we identified variations of blood vessel signal caused by the different biological characteristics and curvature of the ear among individuals. The performance of micro-vascular mapping using the proposed method was validated through the comparison and analysis of individual vascular parameters using extracted 20 vascular-related variables. In addition, we extracted pulsatile blood flow signals, demonstrating its potential to provide photoplethysmographic signals and ear blood maps simultaneously. Therefore, our proposed OCTA-based method for ear vascular mapping successfully provides quantitative information about ear vasculature, which is potentially used for determining the position of system-on-chip sensors for health monitoring in hearable devices.

Phase contrast reflectance confocal brain imaging at 1650nm.

The imaging depth of microscopy techniques is limited by the ability of light to penetrate biological tissue. Recent research has addressed this limitation by combining a reflectance confocal microscope with the NIR-II (or shortwave infrared) spectrum. This approach offers significant imaging depth, is straightforward in design, and remains cost-effective. However, the imaging system, which relies on intrinsic signals, could benefit from adjustments in its optical design and post-processing methods to differentiate cortical cells, such as neurons and small blood vessels. We implemented a phase contrast detection scheme to a reflectance confocal microscope using NIR-II spectral range as illumination. We analyzed the features retrieved in the images while testing the imaging depth. Moreover, we introduce an acquisition method for distinguishing dynamic signals from the background, allowing the creation of vascular maps similar to those produced by optical coherence tomography. The phase contrast implementation is successful to retrieve deep images in the cortex up to using a cranial window. Vascular maps were retrieved at similar cortical depth and the possibility of combining multiple images can provide a vessel network. Phase contrast reflectance confocal microscopy can improve the outlining of cortical cell bodies. With the presented framework, angiograms can be retrieved from the dynamic signal in the biological tissue. Our work presents an optical implementation and analysis techniques from a former microscope design.

Equivalent-time-active-cavitation-imaging enables vascular-resolution blood-brain-barrier-opening-therapy planning

Objective. Linking cavitation and anatomy was found to be important for predictable outcomes in focused-ultrasound blood-brain-barrier-opening and requires high resolution cavitation mapping. However, cavitation mapping techniques for planning and monitoring of therapeutic procedures either (1) do not leverage the full resolution capabilities of ultrasound imaging or (2) place constraints on the length of the therapeutic pulse. This study aimed to develop a high-resolution technique that could resolve vascular anatomy in the cavitation map. Approach. Herein, we develop BandPass-sampled-equivalent-time-active-cavitation-imaging (BP-ETACI), derived from bandpass sampling and dual-frequency contrast imaging at 12.5 MHz to produce cavitation maps prior and during blood–brain barrier opening with long therapeutic bursts using a 1.5 MHz focused transducer in the brain of C57BL/6 mice. Main results. The BP-ETACI cavitation maps were found to correlate with the vascular anatomy in ultrasound localization microscopy vascular maps and in histological sections. Cavitation maps produced from non-blood-brain-barrier disrupting doses showed the same cavitation-bearing vasculature as maps produced over entire blood-brain-barrier opening procedures, allowing use for (1) monitoring focused-ultrasound blood-brain-barrier-opening (FUS-BBBO), but also for (2) therapy planning and target verification. Significance. BP-ETACI is versatile, created high resolution cavitation maps in the mouse brain and is easily translatable to existing FUS-BBBO experiments. As such, it provides a means to further study cavitation phenomena in FUS-BBBO.

Cervical spinal cord angiography and vessel-selective perfusion imaging in the rat.

Arterial spin labeling (ASL) has been widely used to evaluate arterial blood and perfusion dynamics, particularly in the brain, but its application to the spinal cord has been limited. The purpose of this study was to optimize vessel-selective pseudocontinuous arterial spin labeling (pCASL) for angiographic and perfusion imaging of the rat cervical spinal cord. A pCASL preparation module was combined with a train of gradient echoes for dynamic angiography. The effects of the echo train flip angle, label duration, and a Cartesian or radial readout were compared to examine their effects on visualizing the segmental arteries and anterior spinal artery (ASA) that supply the spinal cord. Lastly, vessel-selective encoding with either vessel-encoded pCASL (VE-pCASL) or super-selective pCASL (SS-pCASL) were compared. Vascular territory maps were obtained with VE-pCASL perfusion imaging of the spinal cord, and the interanimal variability was evaluated. The results demonstrated that longer label durations (200 ms) resulted in greater signal-to-noise ratio in the vertebral arteries, improved the conspicuity of the ASA, and produced better quality maps of blood arrival times. Cartesian and radial readouts demonstrated similar image quality. Both VE-pCASL and SS-pCASL adequately labeled the right or left vertebral arteries, which revealed the interanimal variability in the segmental artery with variations in their location, number, and laterality. VE-pCASL also demonstrated unique interanimal variations in spinal cord perfusion with a right-sided dominance across the six animals. Vessel-selective pCASL successfully achieved visualization of the arterial inflow dynamics and corresponding perfusion territories of the spinal cord. These methodological developments provide unique insights into the interanimal variations in the arterial anatomy and dynamics of spinal cord perfusion.

Diagnostic performance of wide-field optical coherence tomography angiography for high myopic glaucoma

Diagnosing and monitoring glaucoma in high myopic (HM) eyes are becoming very important; however, it is challenging to diagnose this condition. This study aimed to evaluate the diagnostic ability of wide-field optical coherence tomography angiography (WF-OCTA) maps for the detection of glaucomatous damage in eyes with HM and to compare the diagnostic ability of WF-OCTA maps with that of conventional imaging approaches, including swept-source optical coherence tomography (SS-OCT) wide-field maps. In this retrospective observational study, a total 62 HM-healthy eyes and 140 HM eyes with open-angle glaucoma were included. Patients underwent a comprehensive ocular examination, including SS-OCT wide-field and 12 × 12 WF-OCTA scans. The WF-OCTA map represents the peripapillary and macular superficial vascular density maps. Glaucoma specialists determined the presence of glaucomatous damage in HM eyes by reading the WF-OCTA map and comparing its sensitivity and specificity with those of conventional SS-OCT images. The sensitivity and specificity of 12 × 12 WF-OCTA scans for HM-glaucoma diagnosis were 87.28% and 86.94%, respectively, while, the sensitivity and specificity of SS-OCT wide-field maps for HM-glaucoma diagnosis were 87.49% and 80.51%, respectively. The specificity of the WF-OCTA map was significantly higher than that of the SS-OCT wide-field map (p < 0.05). The sensitivity of the WF-OCTA map was comparable with that of the SS-OCT wide-field map (p = 0.078). The WF-OCTA map showed good diagnostic ability for discriminating HM-glaucomatous eyes from HM-healthy eyes. As a complementary method to an alternative imaging modality, WF-OCTA mapping can be a useful tool for the detection of HM glaucoma.

CT angiography for characterization of advanced placenta accreta spectrum: indications, risks, and benefits.

Placenta accreta spectrum disorder (PASD) encompasses various types of abnormal placentation in which chorionic villi directly adhere to or invade the myometrium. The incidence of PASD has dramatically risen in the US over the past 3 decades owing to the increased rates of patients undergoing cesarean sections. While PASD remains a significant cause of maternal morbidity and mortality, accurate prenatal identification and characterization of PASD is associated with improved outcomes. Although ultrasound is the first-line imaging modality in the evaluation of PASD, with MRI serving as an adjunct, computed tomography angiography (CTA) may also offer unique diagnostic advantages in cases of advanced PASD by providing superior visualization of placental and abdominopelvic vasculature and enabling the creation of comprehensive vascular maps to roadmap complex surgical interventions. This paper represents the first evaluation of CTA as a diagnostic tool and operative planning aid in this context. Appropriate indications and diagnostic advantages of CTA in this setting are reviewed, and key multimodal imaging features of normal and abnormal placentation are highlighted.

Assessment of Dynamic Contrast Enhanced (DCE) MRI for Detection of Radiotherapy Induced Alteration in Mandibular Vasculature

We aim to determine the kinetics of DCE-MRI changes in various mandibular risk volumes based on radiation (RT) dose received. Eighty-eight head and neck cancer (HNC) patients (Pts) who underwent definitive RT were enrolled in this prospective study after IRB approval and informed consent. Images were acquired at pre-RT (Baseline), 3 weeks after RT start date (Mid-RT), 3 mos post-RT (PostRT1), and 6 mos post-RT (PostRT2). Manually segmented mandibular volumes on T2-weighted images were propagated to co-registered DCE-MRIs. Planning CTs and dose grids were also co-registered to corresponding baseline T2 images to create 3-D dose subvolumes. These were used to create 3 risk subvolumes; <30 Gy, 30-50 Gy, and >50 Gy ROIs. DCE images of different timepoints (TPs) were deformably co-registered and the dose subvolumes were propagated to each TP. We used the extended-Tofts model to generate the vascular quantitative maps (Ktrans and Ve). Each subvolume histogram parameters were extracted at each TP. Wilcoxon Signed Rank test was used to compare the changes at different TPs compared to baseline. We classified Pts' delta parameters at different TPs -based on our prior extensive QA assessment- into Pts with stable vascular profile (±25% change), Pts with significant increase (>25% change) and Pts with significant decrease (<-25%). Chi-square test was used to assess the change at different TPs. For <30 Gy subvolumes, there were no significant changes (p > 0.05) in the studied DCE parameters at all TPs except a significant decrease (p < 0.001) in median Ktrans at PostRT2. For 30-50 Gy subvolumes, there was a significant increase in median Ktrans that started at MidRT (p = 0.006) and continued at PostRT1 (p = 0.04) but recovered to baseline values at PostRT2. Median Ve on the other hand only showed significant increase at PostRT1 (p = 0.001), but other TPs were not significantly different compared to baseline. Similarly, subvolumes >50 Gy showed same kinetics as in 30-50 Gy with significant increase of Ktrans at MidRT and PostRT1 and significant increase in Ve in only PostRT1 (P <0.05). For <30 Gy, there was significant increase in the number of Pts with stable or decrease in Ktrans at PostRT2 compared to earlier TPs (70% vs. 60% at PostRT1 and 54% at MidRT p = 0.003). 30-50 Gy subvolumes showed similar profile like <30 Gy with significant increase in the percentage of Pts with recovery at PostRT2. However, for >50 Gy, there was no significant increase in the number of Pts who recovered at PostRT2 (p = 0.3). Ve showed no significant increase in the percentage of Pts with recovery at different TPs (p > 0.05). Results showed that for all dose mandibular subvolumes, there is an acute vascular insult that tends to recover at +6 months post-RT except for a selective group of patients who continue to have persistence of the vascular insult at high dose subvolumes. These findings are of importance for future selection of high risk population for prophylactic intervention against osteoradionecrosis.

Synthetic OCT-A blood vessel maps using fundus images and generative adversarial networks

Vessel segmentation in fundus images permits understanding retinal diseases and computing image-based biomarkers. However, manual vessel segmentation is a time-consuming process. Optical coherence tomography angiography (OCT-A) allows direct, non-invasive estimation of retinal vessels. Unfortunately, compared to fundus images, OCT-A cameras are more expensive, less portable, and have a reduced field of view. We present an automated strategy relying on generative adversarial networks to create vascular maps from fundus images without training using manual vessel segmentation maps. Further post-processing used for standard en face OCT-A allows obtaining a vessel segmentation map. We compare our approach to state-of-the-art vessel segmentation algorithms trained on manual vessel segmentation maps and vessel segmentations derived from OCT-A. We evaluate them from an automatic vascular segmentation perspective and as vessel density estimators, i.e., the most common imaging biomarker for OCT-A used in studies. Using OCT-A as a training target over manual vessel delineations yields improved vascular maps for the optic disc area and compares to the best-performing vessel segmentation algorithm in the macular region. This technique could reduce the cost and effort incurred when training vessel segmentation algorithms. To incentivize research in this field, we will make the dataset publicly available to the scientific community.

Backscattering amplitude in ultrasound localization microscopy

In the last decade, Ultrafast ultrasound localisation microscopy has taken non-invasive deep vascular imaging down to the microscopic level. By imaging diluted suspensions of circulating microbubbles in the blood stream at kHz frame rate and localizing the center of their individual point spread function with a sub-resolution precision, it enabled to break the unvanquished trade-off between depth of imaging and resolution by microscopically mapping the microbubbles flux and velocities deep into tissue. However, ULM also suffers limitations. Many small vessels are not visible in the ULM images due to the noise level in areas dimly explored by the microbubbles. Moreover, as the vast majority of studies are performed using 2D imaging, quantification is limited to in-plane velocity or flux measurements which hinders the accurate velocity determination and quantification. Here we show that the backscattering amplitude of each individual microbubble can also be exploited to produce backscattering images of the vascularization with a higher sensitivity compared to conventional ULM images. By providing valuable information about the relative distance of the microbubble to the 2D imaging plane in the out-of-plane direction, backscattering ULM images introduces a physically relevant 3D rendering perception in the vascular maps. It also retrieves the missing information about the out-of-plane motion of microbubbles and provides a way to improve 3D flow and velocity quantification using 2D ULM. These results pave the way to improved visualization and quantification for 2D and 3D ULM.

Comparing the volume of vascular intersection of two femoral neck fracture fixation implants using an In silico technique.

Three dimensional (3D) µCT angiograms of 9 cadaveric proximal femora were produced. Three segmented volumes-porous or cancellous bone, filled or cortical bone, and intraosseous vasculature-were converted to surface files. 3D in silico models of the fixation systems were sized and implanted in silico without visibility of the vascular maps. The volume of vasculature that overlapped with the devices was determined. The ratio of the vascular intersection to the comparator device was calculated, and the mean ratio was determined. A paired design, noninferiority test was used to compare the devices. Results indicate both significant (P < 0.001) superiority and noninferiority of the hip screw with an integrated antirotation screw when compared with a dynamic hip screw and antirotation screw for the volume of vasculature that overlapped with each device in the femoral neck. Combining established methods of vascular visualization with newer methods enables an implant's impact on vascular intersection to be assessed in silico. This methodology suggests that when used for femoral neck fracture management, the new device intersects fewer blood vessels than the comparator. Comparative clinical studies are needed to investigate whether these findings correlate with the incidence of avascular necrosis and clinical outcomes.

3-Dimensional Subcortical Vascular Maps (P11-5.003)

<h3>Objective:</h3> Create accessible and accurate 3-dimensional subcortical vascular maps. <h3>Background:</h3> Accurate knowledge of cerebral vascular territories forms the basis of all stroke care, yet there are major shortcomings in how neurology residents learn these vascular territories. The current standard maps are (a) difficult to interpret, especially with regard to subcortical territories, (b) 2-dimensional, which limit their structural precision and clinical applicability, and (c) difficult to access, which prompts learners to hunt through online searches that frequently result in inaccurate images. These shortcomings undermine both education and clinical practice. To address this, we constructed 3-dimensional vascular maps of the lenticulostriate vascular distribution. <h3>Design/Methods:</h3> Using the free software MRIcroGL,12 lenticulostriate strokes were manually drawn on acute DWI scans and then normalized to a standard brain template (MNI-152). We only included strokes that precisely matched the topography of the lenticulostriate territory, based on the vascular atlas of Takahashi. The stroke volumes were then superimposed to create stroke density maps in which color denotes the frequency of infarction at each voxel. <h3>Results:</h3> The resultant 3-dimensional map shows the spatial distribution of infarct frequency within the lenticulostriate territory. The map displays the most commonly affected core, as well as the territory’s typical shape, boundaries, and variability. <h3>Conclusions:</h3> The lenticulostriate territory map can be used for teaching or clinical reference. The map can be explored 3-dimensionally online or can be downloaded for viewing on MRIcroGL. Consistent with multi-modal learning theory, trainees’ learning and understanding of vascular territories will be optimized when exposed to maps that allow for 3-dimensional visual and kinesthetic exploration. Thus, the maps will improve the trainee’s ability to master vascular territory knowledge and also provide a valuable and accessible reference map for practicing neurologists. <b>Disclosure:</b> Dr. Ladsaria has nothing to disclose. Ms. Islam has nothing to disclose. Dr. Antoniello has nothing to disclose.

Automatic vessel crossing and bifurcation detection based on multi-attention network vessel segmentation and directed graph search

Analysis of the vascular tree is the basic premise to automatically diagnose retinal biomarkers associated with ophthalmic and systemic diseases, among which accurate identification of intersection and bifurcation points is quite challenging but important for disentangling complex vascular network and tracking vessel morphology. In this paper, we present a novel directed graph search-based multi-attentive neural network approach to automatically segment the vascular network and separate intersections and bifurcations from color fundus images. Our approach uses multi-dimensional attention to adaptively integrate local features and their global dependencies while learning to focus on target structures at different scales to generate binary vascular maps. A directed graphical representation of the vascular network is constructed to represent the topology and spatial connectivity of the vascular structures. Using local geometric information including color difference, diameter, and angle, the complex vascular tree is decomposed into multiple sub-trees to finally classify and label vascular feature points. The proposed method has been tested on the DRIVE dataset and the IOSTAR dataset containing 40 images and 30 images, respectively, with 0.863 and 0.764 F1-score of detection points and average accuracy of 0.914 and 0.854 for classification points. These results demonstrate the superiority of our proposed method outperforming state-of-the-art methods in feature point detection and classification.

Design and Implementation of Embedded-Based Vein Image Processing System with Enhanced Denoising Capabilities.

In general, it is very difficult to visually locate blood vessels for intravenous injection or surgery. In addition, if vein detection fails, physical and mental pain occurs to the patient and leads to financial loss in the hospital. In order to prevent this problem, NIR-based vein detection technology is developing. The proposed study combines vein detection and digital hair removal to eliminate body hair, a noise that hinders the accuracy of detection, improving the performance of the entire algorithm by about 10.38% over existing systems. In addition, as a result of performing venous detection of patients without body hair, 5.04% higher performance than the existing system was detected, and the proposed study results were verified. It is expected that the use of devices to which the proposed study is applied will provide more accurate vascular maps in general situations.

Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps.

The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm. OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm. The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR. The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.

Guiding and monitoring focused ultrasound mediated blood–brain barrier opening in rats using power Doppler imaging and passive acoustic mapping

The blood–brain barrier (BBB) prevents harmful toxins from entering brain but can also inhibit therapeutic molecules designed to treat neurodegenerative diseases. Focused ultrasound (FUS) combined with microbubbles can enhance permeability of BBB and is often performed under MRI guidance. We present an all-ultrasound system capable of targeting desired regions to open BBB with millimeter-scale accuracy in two dimensions based on Doppler images. We registered imaging coordinates to FUS coordinates with target registration error of 0.6 ± 0.3 mm and used the system to target microbubbles flowing in cellulose tube in two in vitro scenarios (agarose-embedded and through a rat skull), while receiving echoes on imaging transducer. We created passive acoustic maps from received echoes and found error between intended location in imaging plane and location of pixel with maximum intensity after passive acoustic maps reconstruction to be within 2 mm in 5/6 cases. We validated ultrasound-guided procedure in three in vivo rat brains by delivering MRI contrast agent to cortical regions of rat brains after BBB opening. Landmark-based registration of vascular maps created with MRI and Doppler ultrasound revealed BBB opening inside the intended focus with targeting accuracy within 1.5 mm. Combined use of power Doppler imaging with passive acoustic mapping demonstrates an ultrasound-based solution to guide focused ultrasound with high precision in rodents.

In vivo whole brain microvascular imaging in mice using transcranial 3D Ultrasound Localization Microscopy

SummaryBackgroundNon-invasive high-resolution imaging of the cerebral vascular anatomy and function is key for the study of intracranial aneurysms, stenosis, arteriovenous malformations, and stroke, but also neurological pathologies, such as degenerative diseases. Direct visualization of the microvascular networks in the whole brain remains however challenging in vivo.MethodsIn this work, we performed 3D ultrafast ultrasound localization microscopy (ULM) using a 2D ultrasound matrix array and mapped the whole-brain microvasculature and flow at microscopic resolution in C57Bl6 mice in vivo.FindingsWe demonstrated that the mouse brain vasculature can be imaged directly through the intact skull at a spatial resolution of 20 µm and over the whole brain depth and at high temporal resolution (750 volumes.s−1). Individual microbubbles were tracked to estimate the flow velocities that ranged from 2 mm.s−1 in arterioles and venules up to 100 mm.s−1 in large vessels. The vascular maps were registered automatically with the Allen atlas in order to extract quantitative vascular parameters such as local flow rates and velocities in regions of interest.InterpretationWe show the potential of 3D ULM to provide new insights into whole-brain vascular flow in mice models at unprecedented vascular scale for an in vivo technique. This technology is highly translational and has the potential to become a major tool for the clinical investigation of the cerebral microcirculation.FundingThis study was supported by the European Research Council under the European Union's Seventh Framework Program (FP/2007-2013) / ERC Grant Agreement n° 311025 and by the Fondation Bettencourt-Schueller under the program “Physics for Medicine”. We acknowledge the ART (Technological Research Accelerator) biomedical ultrasound program of INSERM.

Multistage DPIRef-Net: An effective network for semantic segmentation of arteries and veins from retinal surface

Retinal vascular changes are the early indicators for many progressive diseases like diabetes, hypertension, etc. However, the manual procedure in detecting these vascular changes is a time-consuming process and may cause a large variance, especially when dealing with a large dataset. Therefore, computer-aided diagnosis of the retinal vascular network plays a crucial role in analyzing the patients effectively with high precision. As a result, this paper presents a robust deep learning Multistage Dual-Path Interactive Refinement Network (DPIRef-Net) for segmenting the vascular maps of arteries and veins from the retinal surface. The main novelty of the proposed model lies in segmenting both the regional and edge salient feature maps that will reduce the degeneration problems of pooling and striding. This eventually preserves the edges of vascular branches and suppresses the false positive rate. In addition to this, a novel guided filtering technique is employed to segment the final accurate arteries and veins vascular networks from predicted regional and edge feature maps. The proposed Multistage DPIRef-Net is trained and tested on different benchmark datasets like DRIVE, HRF, AVRDB, INSPIRE AVR, VICAVR, and Dual-Mode datasets. The proposed model illustrated superior performance in segmenting the vascular maps on all datasets by achieving an average accuracy of 97%, a sensitivity of 96%, a specificity of 98%, and a dice coefficient of 98%.

Deep learning quantification of vascular pharmacokinetic parameters in mouse brain tumor models.

Background:Dynamic contrast-enhanced (DCE) MRI is widely used to assess vascular perfusion and permeability in cancer. In small animal applications, conventional modeling of pharmacokinetic (PK) parameters from DCE MRI images is complex and time consuming. This study is aimed at developing a deep learning approach to fully automate the generation of kinetic parameter maps, Ktrans (volume transfer coefficient) and Vp (blood plasma volume ratio), as a potential surrogate to conventional PK modeling in mouse brain tumor models based on DCE MRI.Methods:Using a 7T MRI, DCE MRI was conducted in U87 glioma xenografts growing orthotopically in nude mice. Vascular permeability Ktrans and Vp maps were generated using the classical Tofts model as well as the extended-Tofts model. These vascular permeability maps were then processed as target images to a twenty-four layer convolutional neural network (CNN). The CNN was trained on T1-weighted DCE images as source images and designed with parallel dual pathways to capture multiscale features. Furthermore, we performed a transfer study of this glioma trained CNN on a breast cancer brain metastasis (BCBM) mouse model to assess the potential of the network for alternative brain tumors.Results:Our data showed a good match for both Ktrans and Vp maps generated between the target PK parameter maps and the respective CNN maps for gliomas. Pixel-by-pixel analysis revealed intratumoral heterogeneous permeability, which was consistent between the CNN and PK models. The utility of the deep learning approach was further demonstrated in the transfer study of BCBM.Conclusions:Because of its rapid and accurate estimation of vascular PK parameters directly from the DCE dynamic images without complex mathematical modeling, the deep learning approach can serve as an efficient tool to assess tumor vascular permeability to facilitate small animal brain tumor research.