Publications
274 results found
Wu Y, Hatipoglu S, Alonso-Álvarez D, et al., 2021, Fast and automated segmentation for the three-directional multi-slice cine myocardial velocity mapping, Diagnostics, Vol: 11, ISSN: 2075-4418
Three-directional cine multi-slice left ventricular myocardial velocity mapping (3Dir MVM) is a cardiac magnetic resonance (CMR) technique that allows the assessment of cardiac motion in three orthogonal directions. Accurate and reproducible delineation of the myocardium is crucial for accurate analysis of peak systolic and diastolic myocardial velocities. In addition to the conventionally available magnitude CMR data, 3Dir MVM also provides three orthogonal phase velocity mapping datasets, which are used to generate velocity maps. These velocity maps may also be used to facilitate and improve the myocardial delineation. Based on the success of deep learning in medical image processing, we propose a novel fast and automated framework that improves the standard U-Net-based methods on these CMR multi-channel data (magnitude and phase velocity mapping) by cross-channel fusion with an attention module and the shape information-based post-processing to achieve accurate delineation of both epicardial and endocardial contours. To evaluate the results, we employ the widely used Dice Scores and the quantification of myocardial longitudinal peak velocities. Our proposed network trained with multi-channel data shows superior performance compared to standard U-Net-based networks trained on single-channel data. The obtained results are promising and provide compelling evidence for the design and application of our multi-channel image analysis of the 3Dir MVM CMR data.
Wu Y, Hatipoglu S, Alonso-Álvarez D, et al., 2021, Automated multi-channel segmentation for the 4D myocardial velocity mapping cardiac MR, Medical Imaging 2021: Computer-Aided Diagnosis, Publisher: SPIE, Pages: 1-7
Four-dimensional (4D) left ventricular myocardial velocity mapping (MVM) is a cardiac magnetic resonance (CMR) technique that allows assessment of cardiac motion in three orthogonal directions. Accurate and reproducible delineation of the myocardium is crucial for accurate analysis of peak systolic and diastolic myocardial velocities. In addition to the conventionally available magnitude CMR data, 4D MVM also acquires three velocity-encoded phase datasets which are used to generate velocity maps. These can be used to facilitate and improve myocardial delineation. Based on the success of deep learning in medical image processing, we propose a novel automated framework that improves the standard U-Net based methods on these CMR multi-channel data (magnitude and phase) by cross-channel fusion with attention module and shape information based post-processing to achieve accurate delineation of both epicardium and endocardium contours. To evaluate the results, we employ the widely used Dice scores and the quantification of myocardial longitudinal peak velocities. Our proposed network trained with multi-channel data shows enhanced performance compared to standard UNet based networks trained with single-channel data. Based on the results, our method provides compelling evidence for the design and application for the multi-channel image analysis of the 4D MVM CMR data.
Yu C, Gao Z, Zhang W, et al., 2021, Multitask Learning for Estimating Multitype Cardiac Indices in MRI and CT Based on Adversarial Reverse Mapping, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, Vol: 32, Pages: 493-506, ISSN: 2162-237X
- Author Web Link
- Cite
- Citations: 42
Zhou Z, Wang R, Wang H, et al., 2021, Myocardial extracellular volume fraction quantification in an animal model of the doxorubicin-induced myocardial fibrosis: a synthetic hematocrit method using 3T cardiac magnetic resonance, Quantitative imaging in medicine and surgery, Vol: 11, Pages: 510-520, ISSN: 2223-4292
Background: Visualization of diffuse myocardial fibrosis is challenging and mainly relies on histology.Cardiac magnetic resonance (CMR), which uses extracellular contrast agents, is a rapidly developingtechnique for measuring the extracellular volume (ECV). The objective of this study was to evaluate thefeasibility of the synthetic myocardial ECV fraction based on 3.0 T CMR compared with the conventionalECV fraction.Methods: This study was approved by the local animal care and ethics committee. Fifteen beagle modelswith diffuse myocardial fibrosis, including 12 experimental and three control subjects, were generatedby injecting doxorubicin 30 mg/m2 intravenously every three weeks for 24 weeks. Short-axis (SAX) and4-chamber long-axis (LAX) T1 maps were acquired for both groups. The association between hematocrit(Hct) and native T1blood was derived from 9 non-contrast CMR T1 maps of 3 control beagles using regressionanalysis. Synthetic ECV was then calculated using the synthetic Hct and compared with conventional ECVat baseline and the 16th and 24th week after doxorubicin administration. The collagen volume fraction (CVF)value was measured on digital biopsy samples. Bland-Altman plots were used to analyze the agreementbetween conventional and synthetic ECV. Correlation analyses were performed to explore the associationamong conventional ECV, synthetic ECV, CVF, and left ventricular ejection fraction (LVEF).Results: The regression model synthetic Hct = 816.46*R1blood − 0.01 (R2=0.617; P=0.012) was used topredict the Hct from native T1blood values. The conventional and synthetic ECV fractions of experimentalanimals at the 16th and 24th week after modeling were significantly higher than those measured at the baseline(31.4%±2.2% and 36.3%±2.1% vs. 22.9%±1.7%; 29.9%±2.4% and 36.1%±2.6% vs. 22.0%±2.4%; all withP<0.05). Bland-Altman plots showed a bias (1.0%) between conventional and synthetic ECV with 95% limitsof agreement
Lv J, Wang C, Yang G, 2021, PIC-GAN: a parallel imaging coupled generative adversarial network for accelerated multi-channel MRI reconstruction, Diagnostics, Vol: 11, ISSN: 2075-4418
In this study, we proposed a model combing parallel imaging (PI) with generative adversarial network (GAN) architecture (PIC-GAN) for accelerated multi-channel magnetic resonance imaging (MRI) reconstruction. This model integrated data fidelity and regularization terms into the generator to benefit from multi-coils information and provide an “end-to-end” reconstruction. Besides, to better preserve image details during reconstruction, we combined the adversarial loss with pixel-wise loss in both image and frequency domains. The proposed PIC-GAN framework was evaluated on abdominal and knee MRI images using 2, 4 and 6-fold accelerations with different undersampling patterns. The performance of the PIC-GAN was compared to the sparsity-based parallel imaging (L1-ESPIRiT), the variational network (VN), and conventional GAN with single-channel images as input (zero-filled (ZF)-GAN). Experimental results show that our PIC-GAN can effectively reconstruct multi-channel MR images at a low noise level and improved structure similarity of the reconstructed images. PIC-GAN has yielded the lowest Normalized Mean Square Error (in ×10−5) (PIC-GAN: 0.58 ± 0.37, ZF-GAN: 1.93 ± 1.41, VN: 1.87 ± 1.28, L1-ESPIRiT: 2.49 ± 1.04 for abdominal MRI data and PIC-GAN: 0.80 ± 0.26, ZF-GAN: 0.93 ± 0.29, VN:1.18 ± 0.31, L1-ESPIRiT: 1.28 ± 0.24 for knee MRI data) and the highest Peak Signal to Noise Ratio (PIC-GAN: 34.43 ± 1.92, ZF-GAN: 31.45 ± 4.0, VN: 29.26 ± 2.98, L1-ESPIRiT: 25.40 ± 1.88 for abdominal MRI data and PIC-GAN: 34.10 ± 1.09, ZF-GAN: 31.47 ± 1.05, VN: 30.01 ± 1.01, L1-ESPIRiT: 28.01 ± 0.98 for knee MRI data) compared to ZF-GAN, VN and L1-ESPIRiT with an under-sampling factor of 6. The proposed PIC-GAN framework has shown superior reconstruction performance in terms of reducing aliasing artifacts and restoring tissue structures as compared to other c
Liang L, Yang G, Heinis T, et al., 2021, SOJA: A memory-efficent small-large outer join for MPI, Pages: 523-528
The join is a fundamental and widely used operation in data analytics but equally, it is also one of the most expensive ones. Considerable work has been carried out to improve and evaluate join approaches based on popular distributed processing systems such as Spark and Hadoop, however, it has not been widely studied on MPI. In this paper, we first implement, analyse and compare existing algorithms for the common small-large outer join operation and develop a novel approach, the swap-based outer join algorithm (SOJA). SOJA is designed to minimise the expensive communication between the distributed nodes while also reducing the cost of the local join operations. We demonstrate the benefits of SOJA experimentally, showing that it achieves at worst an execution time similar to its competitors. More importantly, SOJA requires substantially less memory (typically half the memory compared to the best competitor) and that memory usage scales very well.
Zhang N, Yang G, Zhang W, et al., 2021, Fully automatic framework for comprehensive coronary artery calcium scores analysis on non-contrast cardiac-gated CT scan: Total and vessel-specific quantifications, European Journal of Radiology, Vol: 134, ISSN: 0720-048X
ObjectivesTo develop a fully automatic multiview shape constraint framework for comprehensive coronary artery calcium scores (CACS) quantification via deep learning on nonenhanced cardiac CT images.MethodsIn this retrospective single-centre study, a multi-task deep learning framework was proposed to detect and quantify coronary artery calcification from CT images collected between October 2018 and March 2019. A total of 232 non-contrast cardiac-gated CT scans were retrieved and studied (80 % for model training and 20 % for testing). CACS results of testing datasets (n = 46), including Agatston score, calcium volume score, calcium mass score, were calculated fully automatically and manually at total and vessel-specific levels, respectively.ResultsNo significant differences were found in CACS quantification obtained using automatic or manual methods at total and vessel-specific levels (Agatston score: automatic 535.3 vs. manual 542.0, P = 0.993; calcium volume score: automatic 454.2 vs. manual 460.6, P = 0.990; calcium mass score: automatic 128.9 vs. manual 129.5, P = 0.992). Compared to the ground truth, the number of calcified vessels can be accurate recognized automatically (total: automatic 107 vs. manual 102, P = 0.125; left main artery: automatic 15 vs. manual 14, P = 1.000 ; left ascending artery: automatic 37 vs. manual 37, P = 1.000; left circumflex artery: automatic 22 vs. manual 20, P = 0.625; right coronary artery: automatic 33 vs. manual 31, P = 0.500). At the patient’s level, there was no statistic difference existed in the classification of Agatston scoring (P = 0.317) and the number of calcified vessels (P = 0.102) between the automatic and manual results.ConclusionsThe proposed framework can achieve reliable and comprehensive quantification for the CACS, including the calcified extent and distr
Jin Y, Yang G, Fang Y, et al., 2021, 3D PBV-Net: An automated prostate MRI data segmentation method, COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 128, ISSN: 0010-4825
- Author Web Link
- Cite
- Citations: 43
Wang C, Yang G, Papanastasiou G, 2021, FIRE: Unsupervised bi-directional inter- and intra-modality registration using deep networks, 34th IEEE International Symposium on Computer-Based Medical Systems (IEEE CBMS), Publisher: IEEE, Pages: 510-514, ISSN: 2372-9198
- Author Web Link
- Cite
- Citations: 4
Cao Y, Wang Z, Liu Z, et al., 2021, Multiparameter Synchronous Measurement With IVUS Images for Intelligently Diagnosing Coronary Cardiac Disease, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, Vol: 70, ISSN: 0018-9456
Ye Q, Xia J, Yang G, 2021, EXPLAINABLE AI FOR COVID-19 CT CLASSIFIERS: AN INITIAL COMPARISON STUDY, 2021 IEEE 34TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), Pages: 521-526, ISSN: 2372-9198
- Author Web Link
- Cite
- Citations: 29
Ye Q, Shen X, Gao Y, et al., 2021, Temporal Cue Guided Video Highlight Detection with Low-Rank Audio-Visual Fusion, 18th IEEE/CVF International Conference on Computer Vision (ICCV), Publisher: IEEE, Pages: 7930-7939
Chen Y, Firmin D, Yang G, 2021, Wavelet Improved GAN for MRI reconstruction, Medical Imaging Conference - Physics of Medical Imaging, Publisher: SPIE-INT SOC OPTICAL ENGINEERING, ISSN: 0277-786X
- Author Web Link
- Cite
- Citations: 12
Haldar S, Khan HR, Boyalla V, et al., 2020, Catheter ablation vs. thoracoscopic surgical ablation in long-standing persistent atrial fibrillation: CASA-AF randomized controlled trial., European Heart Journal, Vol: 41, Pages: 4471-4480, ISSN: 0195-668X
AIMS: Long-standing persistent atrial fibrillation (LSPAF) is challenging to treat with suboptimal catheter ablation (CA) outcomes. Thoracoscopic surgical ablation (SA) has shown promising efficacy in atrial fibrillation (AF). This multicentre randomized controlled trial tested whether SA was superior to CA as the first interventional strategy in de novo LSPAF. METHODS AND RESULTS: We randomized 120 LSPAF patients to SA or CA. All patients underwent predetermined lesion sets and implantable loop recorder insertion. Primary outcome was single procedure freedom from AF/atrial tachycardia (AT) ≥30 s without anti-arrhythmic drugs at 12 months. Secondary outcomes included clinical success (≥75% reduction in AF/AT burden); procedure-related serious adverse events; changes in patients' symptoms and quality-of-life scores; and cost-effectiveness. At 12 months, freedom from AF/AT was recorded in 26% (14/54) of patients in SA vs. 28% (17/60) in the CA group [OR 1.128, 95% CI (0.46-2.83), P = 0.83]. Reduction in AF/AT burden ≥75% was recorded in 67% (36/54) vs. 77% (46/60) [OR 1.13, 95% CI (0.67-4.08), P = 0.3] in SA and CA groups, respectively. Procedure-related serious adverse events within 30 days of intervention were reported in 15% (8/55) of patients in SA vs. 10% (6/60) in CA, P = 0.46. One death was reported after SA. Improvements in AF symptoms were greater following CA. Over 12 months, SA was more expensive and provided fewer quality-adjusted life-years (QALYs) compared with CA (0.78 vs. 0.85, P = 0.02). CONCLUSION: Single procedure thoracoscopic SA is not superior to CA in treating LSPAF. Catheter ablation provided greater improvements in symptoms and accrued significantly more QALYs during follow-up than SA. CLINICAL TRIAL REGISTRATION: ISRCTN18250790 and ClinicalTrials.gov: NCT02755688.
Fang EF, Xie C, Schenkel JA, et al., 2020, A research agenda for ageing in China in the 21st century (2nd edition): Focusing on basic and translational research, long-term care, policy and social networks, AGEING RESEARCH REVIEWS, Vol: 64, ISSN: 1568-1637
- Author Web Link
- Cite
- Citations: 167
Zhang D, Yang G, Zhao S, et al., 2020, Direct Quantification of Coronary Artery Stenosis Through Hierarchical Attentive Multi-View Learning, IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 39, Pages: 4322-4334, ISSN: 0278-0062
- Author Web Link
- Cite
- Citations: 19
Zhou X, Ye Q, Jiang Y, et al., 2020, Systematic and comprehensive automated ventricle segmentation on ventricle images of the elderly patients: A retrospective study, Frontiers in Aging Neuroscience, Vol: 12, ISSN: 1663-4365
Background and Objective: Ventricle volume is closely related to hydrocephalus, brain atrophy, Alzheimer's, Parkinson's syndrome, and other diseases. To accurately measure the volume of the ventricles for elderly patients, we use deep learning to establish a systematic and comprehensive automated ventricle segmentation framework.Methods: The study participation included 20 normal elderly people, 20 patients with cerebral atrophy, 64 patients with normal pressure hydrocephalus, and 51 patients with acquired hydrocephalus. Second, get their imaging data through the picture archiving and communication systems (PACS) system. Then use ITK software to manually label participants' ventricular structures. Finally, extract imaging features through machine learning.Results: This automated ventricle segmentation method can be applied not only to CT and MRI images but also to images with different scan slice thicknesses. More importantly, it produces excellent segmentation results (Dice > 0.9).Conclusion: This automated ventricle segmentation method has wide applicability and clinical practicability. It can help clinicians find early disease, diagnose disease, understand the patient's disease progression, and evaluate the patient's treatment effect.
Yuan Z, Jiang M, Wang Y, et al., 2020, SARA-GAN: self-attention and relative average discriminator based generative adversarial networks for fast compressed sensing MRI reconstruction, Frontiers in Neuroinformatics, Vol: 14, Pages: 1-12, ISSN: 1662-5196
Research on undersampled magnetic resonance image (MRI) reconstruction can increase the speed of MRI imaging and reduce patient suffering. In this paper, an undersampled MRI reconstruction method based on Generative Adversarial Networks with the Self-Attention mechanism and the Relative Average discriminator (SARA-GAN) is proposed. In our SARA-GAN, the relative average discriminator theory is applied to make full use of the prior knowledge, in which half of the input data of the discriminator is true and half is fake. At the same time, a self-attention mechanism is incorporated into the high-layer of the generator to build long-range dependence of the image, which can overcome the problem of limited convolution kernel size. Besides, spectral normalization is employed to stabilize the training process. Compared with three widely used GAN-based MRI reconstruction methods, i.e., DAGAN, DAWGAN, and DAWGAN-GP, the proposed method can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measure(SSIM), and the details of the reconstructed image are more abundant and more realistic for further clinical scrutinization and diagnostic tasks.
Ferreira PF, Martin RR, Scott AD, et al., 2020, Automating in vivo cardiac diffusion tensor postprocessing with deep learning-based segmentation, Magnetic Resonance in Medicine, Vol: 84, Pages: 2801-2814, ISSN: 0740-3194
PurposeIn this work we develop and validate a fully automated postprocessing framework for in vivo diffusion tensor cardiac magnetic resonance (DT‐CMR) data powered by deep learning.MethodsA U‐Net based convolutional neural network was developed and trained to segment the heart in short‐axis DT‐CMR images. This was used as the basis to automate and enhance several stages of the DT‐CMR tensor calculation workflow, including image registration and removal of data corrupted with artifacts, and to segment the left ventricle. Previously collected and analyzed scans (348 healthy scans and 144 cardiomyopathy patient scans) were used to train and validate the U‐Net. All data were acquired at 3 T with a STEAM‐EPI sequence. The DT‐CMR postprocessing and U‐Net training/testing were performed with MATLAB and Python TensorFlow, respectively.ResultsThe U‐Net achieved a median Dice coefficient of 0.93 [0.92, 0.94] for the segmentation of the left‐ventricular myocardial region. The image registration of diffusion images improved with the U‐Net segmentation (P < .0001), and the identification of corrupted images achieved an F1 score of 0.70 when compared with an experienced user. Finally, the resulting tensor measures showed good agreement between an experienced user and the fully automated method.ConclusionThe trained U‐Net successfully automated the DT‐CMR postprocessing, supporting real‐time results and reducing human workload. The automatic segmentation of the heart improved image registration, resulting in improvements of the calculated DT parameters.
He W-J, Zhou X, Long J, et al., 2020, Idiopathic normal pressure hydrocephalus and elderly acquired hydrocephalus: evaluation with cerebrospinal fluid flow and ventricular volume parameters, Frontiers in Aging Neuroscience, Vol: 12, ISSN: 1663-4365
Purpose: To investigate differences in cerebrospinal fluid (CSF) flow through the aqueduct and to determine whether there is a relationship between CSF flow and ventricular volume parameters in idiopathic normal pressure hydrocephalus (iNPH) patients, elderly acquired hydrocephalus patients and age-matched healthy volunteers by phase-contrast MR (PC-MR).Methods: A total of 40 iNPH patients and 41 elderly acquired hydrocephalus patients and 26 age-matched healthy volunteers in the normal control (NC) group were included between November 2017 and October 2019 in this retrospective study. The following CSF flow parameters were measured with PC-MR: peak velocity, average velocity (AV), aqueductal stroke volume (ASV), net ASV, and net flow. The following ventricular volume parameters were measured: ventricular volume (VV), brain volume, total intracranial volume, and relative VV. Differences between the iNPH and acquired hydrocephalus groups were compared Mann–Whitney U test and correlations between CSF flow and ventricular volume parameters were assessed using the Spearman correlation coefficient.Results: Aqueductal stroke volume was significantly higher in the iNPH and acquired hydrocephalus groups than in the NC group, but did not differ significantly between the iNPH group and acquired hydrocephalus group. The AV, net ASV, and net flow in the iNPH and acquired hydrocephalus groups were significantly higher than those in the NC group (P < 0.0001), and those in the acquired hydrocephalus group were significantly higher than those in the iNPH group (P = 0.01, P = 0.007, P = 0.002, respectively). The direction of the AV and net ASV significantly differed among the three groups. There were no associations between the volume parameters and CSF flow according to PC-MR among the three groups.Conclusion: Compared with iNPH, elderly acquired hydrocephalus demonstrated higher CSF hyperdynamic flow. Although increased CSF flow may contribute to further changes in ventri
Guo Y, Wang C, Zhang H, et al., 2020, Deep attentive wasserstein generative adversarial networks for MRI reconstruction with recurrent context-awareness, International Conference on Medical Image Computing and Computer-Assisted Intervention, Publisher: Springer International Publishing, Pages: 167-177, ISSN: 0302-9743
The performance of traditional compressive sensing-based MRI (CS-MRI) reconstruction is affected by its slow iterative procedure and noise-induced artefacts. Although many deep learning-based CS-MRI methods have been proposed to mitigate the problems of traditional methods, they have not been able to achieve more robust results at higher acceleration factors. Most of the deep learning-based CS-MRI methods still can not fully mine the information from the k-space, which leads to unsatisfactory results in the MRI reconstruction. In this study, we propose a new deep learning-based CS-MRI reconstruction method to fully utilise the relationship among sequential MRI slices by coupling Wasserstein Generative Adversarial Networks (WGAN) with Recurrent Neural Networks. Further development of an attentive unit enables our model to reconstruct more accurate anatomical structures for the MRI data. By experimenting on different MRI datasets, we have demonstrated that our method can not only achieve better results compared to the state-of-the-arts but can also effectively reduce residual noise generated during the reconstruction process.
Wang F-B, Rong R, Xu J-J, et al., 2020, Impact of pelvic floor ultrasound in diagnosis of postpartum pelvic floor dysfunction A protocol of systematic review, MEDICINE, Vol: 99, ISSN: 0025-7974
Yang M, Xiao X, Liu Z, et al., 2020, Deep RetinaNet for Dynamic Left Ventricle Detection in Multiview Echocardiography Classification, SCIENTIFIC PROGRAMMING, Vol: 2020, ISSN: 1058-9244
- Author Web Link
- Cite
- Citations: 15
Hu C, Zaitseva TS, Alcazar C, et al., 2020, Delivery of Human Stromal Vascular Fraction Cells on Nanofibrillar Scaffolds for Treatment of Peripheral Arterial Disease, FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, Vol: 8, ISSN: 2296-4185
- Author Web Link
- Cite
- Citations: 5
Hu S, Gao Y, Niu Z, et al., 2020, Weakly supervised deep learning for COVID-19 infection detection and classification from CT images, IEEE Access, Vol: 8, Pages: 118869-18883, ISSN: 2169-3536
An outbreak of a novel coronavirus disease (i.e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world. Although COVID-19 is an acutely treated disease, it can also be fatal with a risk of fatality of 4.03% in China and the highest of 13.04% in Algeria and 12.67% Italy (as of 8th April 2020). The onset of serious illness may result in death as a consequence of substantial alveolar damage and progressive respiratory failure. Although laboratory testing, e.g., using reverse transcription polymerase chain reaction (RT-PCR), is the golden standard for clinical diagnosis, the tests may produce false negatives. Moreover, under the pandemic situation, shortage of RT-PCR testing resources may also delay the following clinical decision and treatment. Under such circumstances, chest CT imaging has become a valuable tool for both diagnosis and prognosis of COVID-19 patients. In this study, we propose a weakly supervised deep learning strategy for detecting and classifying COVID-19 infection from CT images. The proposed method can minimise the requirements of manual labelling of CT images but still be able to obtain accurate infection detection and distinguish COVID-19 from non-COVID-19 cases. Based on the promising results obtained qualitatively and quantitatively, we can envisage a wide deployment of our developed technique in large-scale clinical studies.
Ali A-R, Li J, Kanwal S, et al., 2020, A Novel Fuzzy Multilayer Perceptron (F-MLP) for the Detection of Irregularity in Skin Lesion Border Using Dermoscopic Images, FRONTIERS IN MEDICINE, Vol: 7
- Author Web Link
- Cite
- Citations: 12
Ali A-R, Li J, Yang G, et al., 2020, A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images, PEERJ COMPUTER SCIENCE, ISSN: 2376-5992
- Author Web Link
- Cite
- Citations: 23
Yang G, Chen J, Gao Z, et al., 2020, Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention, Future Generation Computer Systems: the international journal of grid computing: theory, methods and applications, Vol: 107, Pages: 215-228, ISSN: 0167-739X
Three-dimensional late gadolinium enhanced (LGE) cardiac MR (CMR) of left atrial scar in patients with atrial fibrillation (AF) has recently emerged as a promising technique to stratify patients, to guide ablation therapy and to predict treatment success. This requires a segmentation of the high intensity scar tissue and also a segmentation of the left atrium (LA) anatomy, the latter usually being derived from a separate bright-blood acquisition. Performing both segmentations automatically from a single 3D LGE CMR acquisition would eliminate the need for an additional acquisition and avoid subsequent registration issues. In this paper, we propose a joint segmentation method based on multiview two-task (MVTT) recursive attention model working directly on 3D LGE CMR images to segment the LA (and proximal pulmonary veins) and to delineate the scar on the same dataset. Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently (0.27 s to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60–68 2D slices). Compared to conventional unsupervised learning and other state-of-the-art deep learning based methods, the proposed MVTT model achieved excellent results, leading to an automatic generation of a patient-specific anatomical model combined with scar segmentation for patients in AF.
Li M, Wang C, Zhang H, et al., 2020, MV-RAN: Multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis, Computers in Biology and Medicine, Vol: 120, ISSN: 0010-4825
Multiview based learning has generally returned dividends in performance because additional information can be extracted for the representation of the diversity of different views. The advantage of multiview based learning fits the purpose of segmenting cardiac anatomy from multiview echocardiography, which is a non-invasive, low-cost and low-risk imaging modality. Nevertheless, it is still challenging because of limited training data, a poor signal-to-noise ratio of the echocardiographic data, and large variances across views for a joint learning. In addition, for a better interpretation of pathophysiological processes, clinical decision-making and prognosis, such cardiac anatomy segmentation and quantitative analysis of various clinical indices should ideally be performed for the data covering the full cardiac cycle. To tackle these challenges, a multiview recurrent aggregation network (MV-RAN) has been developed for the echocardiographic sequences segmentation with the full cardiac cycle analysis. Experiments have been carried out on multicentre and multi-scanner clinical studies consisting of spatio-temporal (2D + t) datasets. Compared to other state-of-the-art deep learning based methods, the MV-RAN method has achieved significantly superior results (0.92 ± 0.04 Dice scores) for the segmentation of the left ventricle on the independent testing datasets. For the estimation of clinical indices, our MV-RAN method has also demonstrated great promise and will undoubtedly propel forward the understanding of pathophysiological processes, computer-aided diagnosis and personalised prognosis using echocardiography.
Huang NF, Zaitseva T, Yang G, et al., 2020, Biomaterials-based Delivery of Angiogenic Messenger RNA Enhances Arteriogenesis in a Porcine Model of Limb Ischemia, American-Heart-Association's Scientific Sessions on Vascular Discovery - From Genes to Medicine, Publisher: LIPPINCOTT WILLIAMS & WILKINS, ISSN: 1079-5642
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.