Tomography Angiography Research Articles

Artificial neural networks analysis predicts long-term fistula function in hemodialysis patients following percutaneous transluminal angioplasty

Kidney failure is particularly common in the United States, where it affects over 700,000 individuals. It is typically treated through repeated sessions of hemodialysis to filter and clean the blood. Hemodialysis requires vascular access, in about 70% of cases through an arteriovenous fistula (AVF) surgically created by connecting an artery and vein. AVF take 6 weeks or more to mature. Mature fistulae often require intervention, most often percutaneous transluminal angioplasty (PTA), also known as fistulaplasty, to maintain the patency of the fistula. PTA is also the first-line intervention to restore blood flow and prolong the use of an AVF, and many patients undergo the procedure multiple times. Although PTA is important for AVF maturation and maintenance, research into predictive models of AVF function following PTA has been limited. Therefore, in this paper we hypothesize that based on patient-specific information collected during PTA, a predictive model can be created to help improve treatment planning. We test a set of rich, multimodal data from 28 patients that includes medical history, AVF blood flow, and interventional angiographic imaging (specifically excluding any post-PTA measurements) and build deep hybrid neural networks. A hybrid model combining a 3D convolutional neural network with a multi-layer perceptron to classify AVF was established. We found using this model that we were able to identify the association between different factors and evaluate whether the PTA procedure can maintain primary patency for more than 3 months. The testing accuracy achieved was 0.75 with a weighted F1-score of 0.75, and AUROC of 0.75. These results indicate that evaluating multimodal clinical data using artificial neural networks can predict the outcome of PTA. These initial findings suggest that the hybrid model combining clinical data, imaging and hemodynamic analysis can be useful to treatment planning for hemodialysis. Further study based on a large cohort is needed to refine the accuracy and model efficiency.

Patient-specific cerebral 3D vessel model reconstruction using deep learning.

Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. Time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.

Intra-procedural three-dimensional rotational angiography in cryoballoon ablation of atrial fibrillation - results from a randomised clinical trial

Abstract Introduction There are a variety of approaches for pre-procedural imaging to facilitate atrial fibrillation (AF) ablation. Intra-procedural three-dimensional rotational angiography (3DRA) is the least employed method and it can be advantageous regarding efficiency and procedural logistics (1). There is an open question whether LA imaging could improve safety and outcomes of cryoballoon (CB) ablation. Purpose The aim of this study is to evaluate possible benefits of 3DRA for procedural success, safety and long-term outcomes of CB ablation. Methods We designed a single-centre unblinded randomised clinical trial and recruited 134 patients (64.2% male, 59.0±11.6 years) with paroxysmal (93.3%) and early-persistent AF. Patients were randomised to no imaging or 3DRA which was performed intra-procedurally after trans-septal puncture. Angiographic images were segmented and overlaid to the fluoroscopy screen to guide the ablation procedure. Patients were scheduled for follow-up visits and twenty-four hour ECG recordings at 3, 6 and 12 months, and every 6 months thereafter. Results Of all the patients recruited, 66 (49.3%) were randomised to 3DRA and angiography was successfully performed in all but one patient (1.5%). Procedure time was significantly longer when 3DRA was performed (86.7±27.8 min compared to 67.2±22.1 in non-3DRA group, p<0.001). Total radiation dose (447.4±485.0 vs. 133.9±166.2 mGy, p<0.001) and contrast administration (131.8±28.3 vs. 40.8±26.5 ml, p<0.001) were significantly higher in the 3DRA group (Table 1). In patients who received no imaging one pulmonary vein (PV) couldn’t be isolated in 2 patients while this occurred in 3 patients in the 3DRA group (OR 1.57, 95% CI 0.25-9.72). Only minor complications were reported in both groups. Five patients developed large haematoma (4 in the 3DRA group vs. 1 in the control group). In each group there were 3 incidents of impending or transient phrenic nerve palsy. During 12 months of follow-up, 88.2% of patients in the control group and 81.8% in the 3DRA group were free of atrial fibrillation (OR 1.67, 95% CI 0.63-4.38). Two patients from the control group developed atrial flutter and were treated by ablation. In total, 10 patients underwent redo procedures (7 in the control and 3 in the 3DRA group respectively) and PV reconnections were detected in 9 cases. Conclusion 3DRA is a safe and efficient intra-procedural imaging method to guide CB ablation of AF. However, it significantly increases procedure duration, total radiation dose and contrast expenditure. In our trial it did not have any impact on the acute success rate of PV isolation or freedom from atrial fibrillation during 12-month follow-up.

The Phenomenon of Quiescent Tomographically-Detected Macular Neovascularization

Macular neovascularization (MNV) is a pathophysiological precursor to local tissue destruction. Age-related macular degeneration is the predominant disease for MNV incidence. The spectrum of macular neovascular morphologies can be studied with optical coherence tomography angiography (OCTA) imaging and observed for vision-threatening activity.

Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis

PurposeTo evaluate the capabilities and incapabilities of a GPT-4V(ision)-based chatbot in interpreting ocular multimodal images.MethodsWe developed a digital ophthalmologist app using GPT-4V and evaluated its performance with a dataset (60...

An enhanced and objective approach to advancing the classification system for left atrial appendage morphology in atrial fibrillation

Abstract The left atrial appendage (LAA) is an important part of the heart that can contribute to the formation of blood clots and the development of arrhythmias. Managing the LAA is crucial in clinical practice. Besides oral anticoagulation, one approach is LAA occlusion, which can reduce the risk of blood clots in selected patients. Another approach is LAA ablation, which has been proposed in addition to pulmonary vein isolation (PVI) and might improve the success of treating atrial fibrillation (AF). Different types of LAA morphology have been identified, and these differences can affect the choice of treatment and strategies for individual patients. To refine current classification system, a new approach has been proposed. The study utilized an observational single-center trial with blinded retrospective analysis of cardiac computed tomography angiography (CCTA) images from cryoballoon PVI patients. Statistical analysis included baseline characteristics and left atrium/LAA measurements. An LAA bounding box was introduced to enhance the current classification system, particularly focusing on distinguishing "chicken-wing" and "windsock," as well as "cauliflower" and "cactus" morphologies. From 2012 to 2016 a total of 1.103 patients underwent second generation cryoballoon PVI. Prior to PVI, CCTA was available for 725 (65.7%) patients with sufficient quality for measuring in 473 (65.2%). Mean age was 66.3±9.5 years; Paroxysmal AF was present in 277 (58.6%) participants. The distribution of LAA morphological types was as follows: "windsock" 51%, "chicken-wing" 20%, "cauliflower" 15%, and "cactus" 13%. Inter-rater reliability, assessed using Cohen's Kappa with Landis and Koch criteria, demonstrated substantial agreement (Kappa = 0.69; p<0.001). "Chicken-wing" morphology had the largest LAA volume at 9.9 (7.9; 12.8) mL, followed by "windsock" morphology with an LAA volume of 9.7 (7.7; 13.1) mL. "Cactus" and "cauliflower" morphologies had considerably smaller LAA volumes, measuring 5.4 (4.6; 7.5) mL and 5.6 (4.4; 7.6) mL, respectively. Bounding box parameters were utilized to distinguish between "windsock" and "chicken-wing" as well as "cauliflower" and "cactus" morphologies. "Windsock" had a maximal LAA depth of 44.3±7.1 mm, while "chicken-wing" measured 40.1±8.6 mm (p<0.001). The sinus values for the bounding box were 0.40±0.06 for "windsock" and 0.44±0.08 for "chicken-wing" (p<0.001). For "cauliflower," the LAA depth averaged 30.42±5.0 mm, whereas for "cactus," it measured 33.4±4.3 mm (p<0.001). The mean sinus of the bounding box was 0.48±0.08 for "cauliflower" and 0.44±0.07 for "cactus" (p<0.05). The utilization of novel bounding box parameters has the potential to aid in the differentiation between different LAA morphologies, such as 'chicken-wing' and 'windsock', as well as 'cactus' and 'cauliflower', especially in cases where the current classification system may not provide clear distinctions.

Efficient 3D cone trajectory design for improved combined angiographic and perfusion imaging using arterial spin labeling.

To improve the spatial resolution and repeatability of a non-contrast MRI technique for simultaneous time resolved 3D angiography and perfusion imaging by developing an efficient 3D cone trajectory design. A novel parameterized 3D cone trajectory design incorporating the 3D golden angle was integrated into 4D combined angiography and perfusion using radial imaging and arterial spin labeling (CAPRIA) to achieve higher spatial resolution and sampling efficiency for both dynamic angiography and perfusion imaging with flexible spatiotemporal resolution. Numerical simulations and physical phantom scanning were used to optimize the cone design. Eight healthy volunteers were scanned to compare the original radial trajectory in 4D CAPRIA with our newly designed cone trajectory. A locally low rank reconstruction method was used to leverage the complementary k-space sampling across time. The improved sampling in the periphery of k-space obtained with the optimized 3D cone trajectory resulted in improved spatial resolution compared with the radial trajectory in phantom scans. Improved vessel sharpness and perfusion visualization were also achieved in vivo. Less dephasing was observed in the angiograms because of the short TE of our cone trajectory and the improved k-space sampling efficiency also resulted in higher repeatability compared to the original radial approach. The proposed 3D cone trajectory combined with 3D golden angle ordering resulted in improved spatial resolution and image quality for both angiography and perfusion imaging and could potentially benefit other applications that require an efficient sampling scheme with flexible spatial and temporal resolution.

Does delayed phase imaging in CT angiography provide additional information in patients with suspected active bleeding?

We hypothesize that delayed phase imaging does not provide additional diagnostic information in patients who undergo multi-phasic CTA for suspected active bleeding. Data on patients who underwent multiphasic CTA (pre-contrast, arterial, porto-venous, and delayed phases) for suspected acute bleed were retrospectively collected between January 2019 and November 2021. CTA images were reviewed by a general radiologist, an interventional radiologist, and a body imaging radiologist independently. Each reader evaluated if delayed phase images provided additional information that would change the final impression of the CTA report. Additional information regarding bleeding location, time needed for delayed image acquisition, and radiation exposure were also obtained. A total of 104 patients with CTAs were analyzed with an average age of 58 years ± 22. Studies rated with absent additional findings on delayed images were 102 (98.1%) by the interventional radiologist, 101 (97.1%) by the body imaging radiologist, and 100 (96.1%) by the general radiologist with percent agreement of 96.15% (kappa 0.54, p < 0.001). All the findings were characterized as unlikely to be clinically significant. Mean time added to complete a delayed phase images was 3.61 ± 3.4min. The average CT dose length product (DLP) for the total exam was 3621.78 ± 2129.57 mGy.cm with delayed acquisition adding a mean DLP of 847.75 ± 508.8 mGy.cm. Delayed phase imaging does not provide significant additional diagnostic information in evaluating patients with suspected active bleeding but is associated with increased examination time and radiation exposure.

First Thousand Cases of Intracranial Radiosurgery Treated with Gamma Knife at a Tertiary Care Hospital in India

Abstract Purpose We present the profile of first 1,000 cases of intracranial radiosurgery (IRS) treated with Gamma Knife system at a government-funded tertiary care hospital in India. In addition to the information on the indications treated, this study provides an idea of the relevance of the Gamma Knife Radiosurgery (GKRS) for IRS in the fast-changing technological scenario. This study also shows the disease indications for which GKRS was the primary treatment preference. Materials and Methods Leksell Gamma Knife model 4C was used for GKRS. Leksell G-frame-based stereotactic localization was used for all patients. Axial magnetic resonance imaging scans were used for treatment planning with additional two-dimensional angiography images for patients treated for arteriovenus malformations (AVM). The patient population treated with GKRS at our center mainly comprised of patients referred from across the country. Results Acoustic schwannoma formed the largest group of patients (27%) followed by meningioma (21%), AVM (18%), pituitary adenoma (16%), brain metastasis (5.3%), trigeminal neuralgia (3%), cavernoma (2.4%), glomus jugulare (1.8%), craniopharyngioma (1.1%) and “others” (5%). Conclusion The case mix at our center is similar to the overall Indian case mix. However, it is different from the Asian data of 2018 but interestingly similar to the data from Middle East and Africa for 2018. Among the various categories of cranial disorders treated by us, pituitary adenoma tumors had minimum (14/161) and cavernoma tumors had maximum (24/24) proportion of cases managed with GKRS as primary treatment modality.

Facile Synthesis of Rigid Binuclear Manganese Complexes for Magnetic Resonance Angiography and SLC39A14-Mediated Hepatic Imaging.

Manganese(II)-based contrast agents (MBCAs) are potential candidates for gadolinium-free enhanced magnetic resonance imaging (MRI). In this work, a rigid binuclear MBCA (Mn2-PhDTA2) with a zero-length linker was developed via facile synthetic routes, while the other dimer (Mn2-TPA-PhDTA2) with a longer rigid linker was also synthesized via more complex steps. Although the molecular weight of Mn2-PhDTA2 is lower than that of Mn2-TPA-PhDTA2, their T1 relaxivities are similar, being increased by over 71% compared to the mononuclear Mn-PhDTA. In the presence of serum albumin, the relaxivity of Mn2-PhDTA2 was slightly lower than that of Mn2-TPA-PhDTA2, possibly due to the lower affinity constant. The transmetalation reaction with copper(II) ions confirmed that Mn2-PhDTA2 has an ideal kinetic inertness with a dissociation half-life of approximately 10.4 h under physiological conditions. In the variable-temperature 17O NMR study, both Mn-PhDTA and Mn2-PhDTA2 demonstrated a similar estimated q close to 1, indicating the formation of monohydrated complexes with each manganese(II) ion. In addition, Mn2-PhDTA2 demonstrated a superior contrast enhancement to Mn-PhDTA in in vivo vascular and hepatic MRI and can be rapidly cleared through a dual hepatic and renal excretion pattern. The hepatic uptake mechanism of Mn2-PhDTA2 mediated by SLC39A14 was validated in cellular uptake studies.

Triplicated middle cerebral arteries (duplicated and ipsilateral accessory) associated with triplicated anterior cerebral arteries (accessory) diagnosed by magnetic resonance angiography.

To describe a case of duplicated middle cerebral artery (MCA) combined with ipsilateral accessory MCA, forming a triplicated MCA, associated with the accessory anterior cerebral artery (ACA), forming a triplicated A2 segment of the ACA detected incidentally on magnetic resonance (MR) angiography. A 70-year-old woman with internal carotid artery (ICA) stenosis at the origin, which was detected by ultrasound, underwent cranial MR imaging and MR angiography of the intracranial region for an evaluation of brain and cerebral arterial lesions. The MR machine was a 3-Tesla scanner. MR angiography was performed using a standard 3-dimensional time-of-flight technique. Multiple ischemic white matter lesions are observed. No significant stenotic lesions were observed in intracranial arteries. The right duplicated MCA was originated from right distal ICA. And main MCA was originated from right ICA bifurcation. Right accessory MCA was arisen from the A2 segment of the right ACA. Thus, the right MCA was triplicated. There was also an accessory ACA forming a triplicated ACA at its A2 segment. These findings were clearly identified on partial volume-rendering (VR) images. We herein report a case of triplicated MCA associated with triplicated ACA. MCA variations are relatively rare, and this is the third case of triplicated MCA reported in relevant English-language literature. To identify multiple cerebral arterial variations, creating partial VR images using MR angiographic source images is useful.

Improved stent sharpness evaluation with Super-Resolution deep learning reconstruction in coronary computed tomography angiography.

This study aimed to assess the impact of super-resolution deep learning reconstruction (SR-DLR) on coronary computed tomography angiography (CCTA) image quality and blooming artifacts from coronary artery stents in comparison to conventional methods, including hybrid iterative reconstruction (HIR) and deep learning-based reconstruction (DLR). A retrospective analysis included sixty-six CCTA patients from July to November 2022. Major coronary arteries were evaluated for image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Stent sharpness was quantified using 10-90% edge rise slope (ERS) and 10-90% edge rise distance (ERD). Qualitative analysis employed a 5-point scoring system to assess overall image quality, image noise, vessel wall, and stent structure. SR-DLR demonstrated significantly lower image noise compared to HIR and DLR. SNR and CNR were notably higher in SR-DLR. Stent ERS was significantly improved in SR-DLR, with mean ERD values of 0.70 ± 0.20 mm for SR-DLR, 1.13 ± 0.28 mm for HIR, and 0.85 ± 0.26 mm for DLR. Qualitatively, SR-DLR scored higher in all categories. SR-DLR produces images with lower image noise, leading to improved overall image quality, compared with HIR and DLR. SR-DLR is a valuable image reconstruction algorithm for enhancing the spatial resolution and sharpness of coronary artery stents without being constrained by hardware limitations. The overall image quality was significantly higher in SR-DLR, resulting in sharper coronary artery stents compared to HIR and DLR.

Deep learning-driven automated quality assessment of ultra-widefield optical coherence tomography angiography images for diabetic retinopathy

AbstractImage quality assessment (IQA) of fundus images constitutes a foundational step in automated disease analysis. This process is pivotal in supporting the automation of screening, diagnosis, follow-up, and related academic research for diabetic retinopathy (DR). This study introduced a deep learning-based approach for IQA of ultra-widefield optical coherence tomography angiography (UW-OCTA) images of patients with DR. Given the novelty of ultra-widefield technology, its limited prevalence, the high costs associated with equipment and operational training, and concerns regarding ethics and patient privacy, UW-OCTA datasets are notably scarce. To address this, we initially pre-train a vision transformer (ViT) model on a dataset comprising 6 mm × 6 mm OCTA images, enabling the model to acquire a fundamental understanding of OCTA image characteristics and quality indicators. Subsequent fine-tuning on 12 mm × 12 mm UW-OCTA images aims to enhance accuracy in quality assessment. This transfer learning strategy leverages the generic features learned during pre-training and adjusts the model to evaluate UW-OCTA image quality effectively. Experimental results demonstrate that our proposed method achieves superior performance compared to ResNet18, ResNet34, and ResNet50, with an AUC of 0.9026 and a Kappa value of 0.7310. Additionally, ablation studies, including the omission of pre-training on 6 mm × 6 mm OCTA images and the substitution of the backbone network with the ViT base version, resulted in varying degrees of decline in AUC and Kappa values, confirming the efficacy of each module within our methodology.

IN STENT RESTENOSIS (ISR) IN PATIENTS UNDERGOING PERCUTANEOUS CORONARY INTERVENTION (PCI) FOR CORONARY ARTERY DISEASE (CAD)

In-stent restenosis (ISR) remains a significant clinical challenge in patients undergoing percutaneous coronary intervention (PCI) for coronary artery disease (CAD). Objectives: The main aim of the study is to find the In-Stent Restenosis (ISR) in patients undergoing percutaneous coronary intervention (PCI) for coronary artery disease (CAD). Methods: This cross-sectional study was conducted at Prime Teaching Hospital Peshawar from January 2023 till December 2023. Data were collected from 80 patients from both genders. Patients who underwent PCI for CAD and developed ISR, as confirmed by angiographic or intravascular imaging studies, were included. Data were collected in a systematically designed performance. Information was collected from electronic medical records, angiographic reports, and procedural databases. Results: Data were collected from 80 patients according to inclusion criteria. The mean age of the patients was 65.09±8.5 years. There were 52 (65%) male and 48 (35%) female patients. Hypertension was present in 60 (75%), dyslipidemia in 48(60%) and DM in 36 (45%) patients. There was a significant association between older age and increased likelihood of ISR development post-PCI (Mean age ISR: 68.01 ± 7.2 years vs. No ISR: 62.39 ± 9.1 years, p=0.02). However, gender did not significantly influence ISR occurrence (71% male ISR vs. 62% male No ISR, p=0.42). Conclusion: It is concluded that ISR represents a significant challenge in patients post-PCI for CAD, with a substantial incidence observed in this study. Older age, diabetes mellitus, and DES implantation were identified as essential contributors to ISR development.

Fusion of full-field optical angiography images via gradient feature detection

Full-field optical angiography (FFOA)—a real-time non-invasive imaging technique for extracting biological blood microcirculation information—contributes to an in-depth understanding of the functional and pathological changes of biological tissues. However, owing to the limitation of the depth-of-field (DOF) of optical lenses, existing FFOA imaging methods cannot capture an image containing every blood-flow information. To address this problem, this study develops a long-DOF full-field optical angiography imaging system and proposes a novel multi-focus image fusion scheme to expand the DOF. First, FFOA images with different focal lengths are acquired by the absorption intensity fluctuation modulation effect. Second, an image fusion scheme based on gradient feature detection in a nonsubsampled contourlet transform domain is developed to capture focus features from FFOA images and synthesize an all-focused image. Specifically, FFOA images are decomposed by NSCT into coefficients and low-frequency difference images; thereafter, two gradient feature detection-based fusion rules are used to select the pre-fused coefficients. The experimental results of both phantom and animal cases show that the proposed fusion method can effectively extend the DOF and address practical FFOA image defocusing problems. The fused FFOA image can provide a more comprehensive description of blood information than a single FFOA image.

A deep learning system for the detection of optic disc neovascularization in diabetic retinopathy using optical coherence tomography angiography images

A deep learning system for the detection of optic disc neovascularization in diabetic retinopathy using optical coherence tomography angiography images

The factors associated with retinal pigment epithelium tear development in the early phase after treatment initiation for age-related macular degeneration.

This study aimed to evaluate the factors associated with retinal pigment epithelium (RPE) tear development in the early phase after anti-vascular endothelial growth factor (VEGF) drug initiation in eyes with neovascular age-related macular degeneration (nAMD) and retinal pigment epithelial detachment (PED). Treatment-naive eyes with nAMD and PED for which anti-VEGF drug injections had been initiated and followed up for at least 3months after the 1st anti-VEGF drug injection, were retrospectively investigated. Baseline characteristics of the PEDs, including type, height, and area, were evaluated using fundus photographs, fluorescein angiography, and optical coherence tomography images. The association between patient age, sex, medical history, PED characteristics, and the development of RPE tears within 3months of starting anti-VEGF therapy was examined. This study included 244 eyes (230 patients; mean age 75.0years, 159 males and 71 females). RPE tears occurred in 13 eyes (5.3%) within 3months of the start of anti-VEGF therapy. Multivariate analysis showed an association of the development of RPE tears with PED height (every 100µm, odds ratio [OR]: 1.50, 95% confidence interval [CI]: 1.07-2.12, p = 0.019), PED area (every 10 mm2, OR: 3.02, CI: 1.22-7.46, p = 0.016), and the presence of fibrovascular PED (OR: 59.22, CI: 4.12-850.59, p = 0.002). Eyes with cleft (the hypo-reflective space beneath the fibrovascular PED) were more likely to develop an RPE tear (p = 0.01, χ-square test). Fibrovascular PED, large PED area, high PED height, and the cleft finding are independent risk factors for the development of RPE tears early after the administration of anti-VEGF drugs.

Quantitative evaluation of the effects of flow diverter treatment on aneurysm hemodynamics using time-resolved rotational angiography.

There have been immense advancements in the hardware and software of digital subtraction angiography systems over the last several years. These advancements continue to make progress toward the goals of offering better visualization and reducing radiation exposure. A newer advancement in this arena is presenting three-dimension data over time resulting in four-dimensional-digital subtracted angiography visualization. We have evaluated these protocols related to the evaluation of the treatment of intracranial aneurysms with pipeline flow diversion. Four-dimensional-digital subtracted angiography imaging was acquired on an Artis Q Biplane angiographic system (Siemens Healthcare AG, Forchheim, Germany). A six second four-dimensional-digital subtracted angiography protocol was performed pre and post flow diverter placement. Pre and post reconstructed images were sent through a dedicated prototype research workstation (Syngo X-Workplace; Siemens Healthineers AG) for further flow evaluation. The treatment of an aneurysm with flow diversion led to a filling delay of 0.278 ± 0.422 s inside the aneurysms, whereas distal to the aneurysms the filling of the vessel segment occurred earlier post procedural (negative filling delay of -0.15 ± 0.31 s. The flow ratio inside the aneurysm decreased to 63.6 ± 23% of its pre-treatment value and distal to the aneurysm the flow remained substantially the same (flow ratio: 95.6 ± 0.29%). Data showed a relative filling delay of the aneurysm normalized to the distal vessel of 0.43 ± 0.36 s. The relative flow ratio of the aneurysm in comparison to the distal parent vessel was 72.2 ± 31%. Analysis of a four-dimensional-digital subtracted angiography acquisition allows assessment of the effects of flow diversion treatment on aneurysm hemodynamic parameters and shows a significant decrease in flow inside the aneurysm compared to the parent vessel distal to the aneurysm.

Glaucoma detection using non-perfused areas in OCTA

Multiple ophthalmic diseases lead to decreased capillary perfusion that can be visualized using optical coherence tomography angiography images. To quantify the decrease in perfusion, past studies have often used the vessel density, which is the percentage of vessel pixels in the image. However, this method is often not sensitive enough to detect subtle changes in early pathology. More recent methods are based on quantifying non-perfused or intercapillary areas between the vessels. These methods rely upon the accuracy of vessel segmentation, which is a challenging task and therefore a limiting factor for reliability. Intercapillary areas computed from perfusion-distance measures are less sensitive to errors in the vessel segmentation since the distance to the next vessel is only slightly changing if gaps are present in the segmentation. We present a novel method for distinguishing between glaucoma patients and healthy controls based on features computed from the probability density function of these perfusion-distance areas. The proposed approach is evaluated on different capillary plexuses and outperforms previously proposed methods that use handcrafted features for classification. Moreover the results of the proposed method are in the same range as the ones of convolutional neural networks trained on the raw input images and is therefore a computationally efficient, simple to implement and explainable alternative to deep learning-based approaches.

Prediction model based on artificial intelligence for identifying risk of coronary atherosclerotic heart disease in computed tomography

ObjectiveTo analyze the application value of artificial intelligence (AI) in coronary computed tomography angiography (CCTA) image processing and diagnosis of coronary atherosclerotic heart disease (CHD). MethodsA total of 80 patients with suspected CHD in our hospital were selected for CCTA examination and blood lipid examination. The convolutional neural networks (CNN) model of coronary artery plaque detection was constructed, and the data set was randomly divided into training set and test set after pretreatment of lipid characteristics and image characteristics. The prediction efficiency and accuracy of the model were evaluated. ResultsIn the data set, the lipid indexes LDL-C, TC, and TG of patients in the CHD group were significantly higher than those in the Non-CHD group (P < 0.05). The average processing and diagnosis time of the AI model was (187.19 ± 18.79) s, which was significantly shorter than the average time of doctors (989.07 ± 50.40) s, and the difference was statistically significant (P < 0.05). There was no significant difference in the detection of calcified plaque, non-calcified plaque, and mixed plaque between doctors and AI models (P > 0.05). However, 5 plaques were misdiagnosed in the AI model (3.38%). The area under the curve (AUC) value of the CNN recognition model-based AI and manual recognition of doctors for the CHD were 0.870 (95% CI: 0.698–0.931) and 0.870 (95% CI: 0.691–0.926) (P < 0.001). ConclusionAI integrated with lipid parameters has certain clinical value in CCTA image processing efficiency and plaque diagnosis, and can be used as an effective auxiliary tool to analyze and diagnose CHD.