ABArian Beqiri

Arian Beqiri

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Arian Beqiri has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Echo from Noise: Synthetic Ultrasound Image Generation Using Diffusion Models for Real Image Segmentation

    by David Stojanovski, Uxio Hermida, Pablo Lamata, Arian Beqiri, Alberto Gomez

    We propose a novel pipeline for the generation of synthetic ultrasound images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for ultrasound image analysis tasks such as cardiac segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiograms and trained a neural network for segmenting the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of $$88.6 \pm 4.91$$ 88.6 ± 4.91 , $$91.9 \pm 4.22$$ 91.9 ± 4.22 , $$85.2 \pm 4.83$$ 85.2 ± 4.83 % for left ventricular endocardium, epicardium and left atrial segmentation respectively. This represents a relative increase of 9.2, 3.3 and 13.9% in Dice scores compared to the previous state-of-the-art. The proposed pipeline has potential for application to a wide range of other tasks across various medical imaging modalities.


  • Open Access

    Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography

    by Jamie M O’dRiscoll, William Hawkes, Arian Beqiri, Angela Mumith, Andrew Parker, Ross Upton, Annabelle McCourt, William Woodward, Cameron Dockerill, Nikant Sabharwal, et al.

    To evaluate whether left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), automatically calculated by artificial intelligence (AI), increases the diagnostic performance of stress echocardiography (SE) for coronary artery disease (CAD) detection. SEs from 512 participants who underwent a clinically indicated SE (with or without contrast) for the evaluation of CAD from seven hospitals in the UK and US were studied. Visual wall motion scoring (WMS) was performed to identify inducible ischaemia. In addition, SE images at rest and stress underwent AI contouring for automated calculation of AI-LVEF and AI-GLS (apical two and four chamber images only) with Ultromics EchoGo Core 1.0. Receiver operator characteristic curves and multivariable risk models were used to assess accuracy for identification of participants subsequently found to have CAD on angiography. Participants with significant CAD were more likely to have abnormal WMS, AI-LVEF, and AI-GLS values at rest and stress (all P < 0.001). The areas under the receiver operating characteristics for WMS index, AI-LVEF, and AI-GLS at peak stress were 0.92, 0.86, and 0.82, respectively, with cut-offs of 1.12, 64%, and −17.2%, respectively. Multivariable analysis demonstrated that addition of peak AI-LVEF or peak AI-GLS to WMS significantly improved model discrimination of CAD [C-statistic (bootstrapping 2.5th, 97.5th percentile)] from 0.78 (0.69–0.87) to 0.83 (0.74–0.91) or 0.84 (0.75–0.92), respectively. AI calculation of LVEF and GLS by contouring of contrast-enhanced and unenhanced SEs at rest and stress is feasible and independently improves the identification of obstructive CAD beyond conventional WMSI.


  • Open Access

    Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D Echo Views

    by David Stojanovski, Uxio Hermida, Marica Muffoletto, Pablo Lamata, Arian Beqiri, Alberto Gomez

    Accurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of new biomarkers and make imaging less dependent on operator expertise, however most ultrasound systems only have 2D imaging capabilities. We propose both a simple alteration to the Pix2Vox++ networks for a sizeable reduction in memory usage and computational complexity, and a pipeline to perform reconstruction of 3D anatomy from 2D standard cardiac views, effectively enabling 3D anatomical reconstruction from limited 2D data. We evaluate our pipeline using synthetically generated data achieving accurate 3D whole-heart reconstructions (peak intersection over union score $$> 0.88$$ > 0.88 ) from just two standard anatomical 2D views of the heart. We also show preliminary results using real echo images.


  • Open Access

    Whole‐brain 3DFLAIR at 7T using direct signal control

    by Arian Beqiri, Hans Hoogduin, Alessandro Sbrizzi, Joseph V. Hajnal, Shaihan J. Malik

    Purpose: Image quality obtained for brain imaging at 7T can be hampered by inhomogeneities in the static magnetic field, B0, and the RF electromagnetic field, B1. In imaging sequences such as fluid‐attenuated inversion recovery (FLAIR), which is used to assess neurological disorders, these inhomogeneities cause spatial variations in signal that can reduce clinical efficacy. In this work, we aim to correct for signal inhomogeneities to ensure whole‐brain coverage with 3D FLAIR at 7T.Methods: The direct signal control (DSC) framework was used to optimize channel weightings applied to the 8 transmit channels used in this work on a pulse‐by‐pulse basis through the echo train in the FLAIR sequences. 3D FLAIR brain images were acquired on 5 different subjects and compared with imaging using a quadrature‐like mode of the transmit array. Precomputed “universal” DSC solutions calculated from a separate set of 5 subjects were also explored.Results: DSC consistently enabled improved imaging across all subjects, with no dropouts in signal seen over the entire brain volume, which contrasted with imaging in quadrature mode. Further, the universal DSC solutions also consistently improved imaging despite not being optimized specifically for the subject being imaged.Conclusion: 3D FLAIR brain imaging at 7T is substantially improved using DSC and is able to recover regions of low signal without increasing imaging time or interecho spacing.


  • Open Access

    Extended RF shimming: Sequence‐level parallel transmission optimization applied to steady‐state free precession MRI of the heart

    by Arian Beqiri, Anthony N. Price, Francesco Padormo, Joseph V. Hajnal, Shaihan J. Malik

    Cardiac magnetic resonance imaging (MRI) at high field presents challenges because of the high specific absorption rate and significant transmit field (B1+) inhomogeneities. Parallel transmission MRI offers the ability to correct for both issues at the level of individual radiofrequency (RF) pulses, but must operate within strict hardware and safety constraints. The constraints are themselves affected by sequence parameters, such as the RF pulse duration and TR, meaning that an overall optimal operating point exists for a given sequence. This work seeks to obtain optimal performance by performing a ‘sequence‐level’ optimization in which pulse sequence parameters are included as part of an RF shimming calculation. The method is applied to balanced steady‐state free precession cardiac MRI with the objective of minimizing TR, hence reducing the imaging duration. Results are demonstrated using an eight‐channel parallel transmit system operating at 3 T, with an in vivo study carried out on seven male subjects of varying body mass index (BMI). Compared with single‐channel operation, a mean‐squared‐error shimming approach leads to reduced imaging durations of 32 ± 3% with simultaneous improvement in flip angle homogeneity of 32 ± 8% within the myocardium.


  • Open Access

    RF system calibration for global Q matrix determination

    by Francesco Padormo, Arian Beqiri, Shaihan J. Malik, Joseph V. Hajnal


  • Open Access

    Parallel transmission for ultrahigh‐field imaging

    by Francesco Padormo, Arian Beqiri, Joseph V. Hajnal, Shaihan J. Malik

    The development of MRI systems operating at or above 7 T has provided researchers with a new window into the human body, yielding improved imaging speed, resolution and signal‐to‐noise ratio. In order to fully realise the potential of ultrahigh‐field MRI, a range of technical hurdles must be overcome. The non‐uniformity of the transmit field is one of such issues, as it leads to non‐uniform images with spatially varying contrast. Parallel transmission (i.e. the use of multiple independent transmission channels) provides previously unavailable degrees of freedom that allow full spatial and temporal control of the radiofrequency (RF) fields. This review discusses the many ways in which these degrees of freedom can be used, ranging from making more uniform transmit fields to the design of subject‐tailored RF pulses for both uniform excitation and spatial selection, and also the control of the specific absorption rate. © 2015 The Authors. NMR in Biomedicine published by John Wiley & Sons Ltd.


  • Open Access

    Specific absorption rate in neonates undergoing magnetic resonance procedures at 1.5 T and 3 T

    by Shaihan J. Malik, Arian Beqiri, Anthony N. Price, Jose Nuno Teixeira, Jeffrey W. Hand, Joseph V. Hajnal

    MRI is finding increased clinical use in neonatal populations; the extent to which electromagnetic models used for quantification of specific absorption rate (SAR) by commercial MRI scanners accurately reflect this alternative scenario is unclear. This study investigates how SAR predictions relating to adults can be related to neonates under differing conditions when imaged using 1.5 T and 3 T MRI scanners. Electromagnetic simulations were produced in neonatal subjects of different sizes and positions within a generic MRI body transmit device operating at both 64 MHz and 128 MHz, corresponding to 1.5 T and 3 T MRI scanners, respectively. An adult model was also simulated, as was a spherical salt‐water phantom, which was also used in a calorimetry experiment. The SAR in neonatal subjects was found to be less than that experienced in an adult in all scenarios; however, the overestimation factor was variable. For example a 3 T body scan resulting in local 10 g SAR of 10.1 W kg−1 in an adult would deposit 2.6 W kg−1 in a neonate: an approximately fourfold difference. The SAR experienced by neonatal subjects undergoing MRI is lower than that in adults in equivalent situations. If the safety of such procedures is assessed using adult‐appropriate models then the result is a conservative estimate. © 2015 The Authors. NMR in Biomedicine published by John Wiley & Sons, Ltd.


  • Open Access

    Comparison between simulated decoupling regimes for specific absorption rate prediction in parallel transmit MRI

    by Arian Beqiri, Jeffrey W. Hand, Joseph V. Hajnal, Shaihan J. Malik

    Purpose: The use of electromagnetic (EM) modeling is critical for specific absorption rate (SAR) characterization in parallel transmission MRI. Radiofrequency arrays that include decoupling networks can be difficult to characterize accurately in simulation. A practical method of simplifying modeling is to exclude the decoupling networks and model each transmit element in isolation. Results from this type of model can be related to a real device by applying “active decoupling” to the real device to suppress residual coupling when in use. Here, we compare this approach with a full model that includes decoupling networks.Methods: EM simulations for a variety of adult male voxel models placed within an eight‐channel transverse electromagnetic (TEM) array tuned for 3 Tesla operation were run with and without decoupling networks included. The resulting EM fields and SAR estimates were compared using basic normalization, and simulated active decoupling.Results: Modeling the transmit elements independently leads to variations which have significantly different SAR estimates of ∼20% on average compared with the full model if not normalized appropriately. After “active decoupling,” SAR was still generally seen to be overestimated by ∼7% with independent channel modeling; despite having similar B1+ field distributions.Conclusion: Modeling transmission elements independently may lead to substantially incorrect SAR estimates if the corresponding MRI system is not run in an analogous manner. Magn Reson Med 74:1423–1434, 2015.


  • Open Access

    PRIMO: Precise radiofrequency inference from multiple observations

    by Francesco Padormo, Arian Beqiri, Shaihan J. Malik, Joseph V. Hajnal

    Purpose: This paper presents Precise Radiofrequency Inference from Multiple Observations (PRIMO), a comprehensive reconstruction framework for calibrating MRI systems with parallel transmit and parallel receive radiofrequency capabilities.Theory and Methods: To date, the vast majority of radiofrequency (RF) calibration methods have considered transmit and receive calibration separately, without acknowledging that transmit field calibration sequences measure sufficient data for receive calibration. PRIMO provides a method of extracting both transmit and receive fields from transmit calibration data without presuming knowledge of either. The method is tested for accuracy through simulation, comparison to a gold standard dataset, and is demonstrated on in‐vivo data acquired at 3T.Results: PRIMO is shown to produce RF fields faithful to the gold standard with errors of less than 3% in realistic noise conditions. The in‐vivo reconstructions demonstrate the method's ability to produce high quality transmit and receive maps, with an 8 transmit/8 receive channel system being fully calibrated in three dimensions in approximately 2 minutes.Conclusion: PRIMO provides a unified framework for estimating all transmit and receive fields in a single calibration step. This is becoming increasingly relevant in an era of MRI systems with highly parallel RF architectures. Magn Reson Med 74:372–383, 2015.