Publications

Search or filter publications

Search publications Search

Filter by type:

Filter by publication type

• Book
• Book chapter
• Conference paper
• Journal article
• Other
• Patent
• Poster
• Report
• Scholarly edition
• Software
• Thesis dissertation
• Working paper

Filter by year:

Filter from 2026202520242023202220212020201920182017201620152014201320122011201020092008200720062005200420032002 to Filter to 2026202520242023202220212020201920182017201620152014201320122011201020092008200720062005200420032002

---

Search results

• Journal article
  Jin W, Wang N, Tao T, Jiang M, Xing Y, Zhao B, Wu H, Duan H, Yang Get al., 2025,

  A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection

  , ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, Vol: 144, ISSN: 0952-1976
  • Cite
  • Citations: 3
• Journal article
  Ristic M, Chappell KE, Lanz H, McGinley JVM, Gupte C, Amiras Det al., 2025,

  First in-vivo magic angle directional imaging using dedicated low-field MRI

  , Magnetic Resonance in Medicine, Vol: 93, Pages: 1077-1089, ISSN: 0740-3194

  Purpose: To report the first in-vivo results from exploiting the magic angle effect, using a dedicated low-field MRI scanner that can be rotated about two axes. The Magic Angle Directional Imaging (MADI) method is used to depict collagen microstructures with 3D collagen tractography of knee ligaments and the meniscus. Methods: A novel low-field MRI system was developed, based on a transverse field open magnet, where the magnet can be rotated about two orthogonal. Sets of volume scans at various orientations were obtained in healthy volunteers. The experiments focused on the anterior cruciate ligament (ACL) and the meniscus of the knee. The images were co-registered, anatomical regions of interest (RoI) were selected and the collagen fiber orientations in each voxel were estimated from the observed image intensity variations. The 3D collagen tractography was superimposed on conventional volume images. Results: The MADI method was successfully employed for the first time producing in-vivo results comparable to those previously reported for excised animal specimens using conventional MRI. Tractography plots were generated for the ACL and the menisci. These results are consistent with the known microstructure of collagen fibers in these tissues. Conclusion: Images obtained using low-field MRI with 1 mm3 resolution were of sufficient quality for the MADI method, which was shown to produce high quality in-vivo information of collagen microstructures. This was achieved using a cost effective and sustainable low-field magnet making the technique potentially accessible and scalable, potentially changing the way we image injuries or disease in joints.

  • Abstract
  • Publisher Web Link
  • Cite
• Journal article
  Wang J, Ruan D, Li Y, Wang Z, Wu Y, Tan T, Yang G, Jiang Met al., 2025,

  Data augmentation strategies for semi-supervised medical image segmentation

  , PATTERN RECOGNITION, Vol: 159, ISSN: 0031-3203
  • Cite
• Journal article
  Wang C, Jiang M, Li Y, Wei B, Li Y, Wang P, Yang Get al., 2025,

  MP-FocalUNet: Multiscale parallel focal self-attention U-Net for medical image segmentation

  , COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, Vol: 260, ISSN: 0169-2607
  • Cite
  • Citations: 1
• Journal article
  Wang Z, Wang F, Qin C, Lyu J, Ouyang C, Wang S, Li Y, Yu M, Zhang H, Guo K, Shi Z, Li Q, Xu Z, Zhang Y, Li H, Hua S, Chen B, Sun L, Sun M, Li Q, Chu Y-H, Bai W, Qin J, Zhuang X, Prieto C, Young A, Markl M, Wang H, Wu L-M, Yang G, Qu X, Wang Cet al., 2025,

  CMRxRecon2024: A Multimodality, Multiview k-Space Dataset UniversalMachine for Accelerated Cardiac MRI

  , RADIOLOGY-ARTIFICIAL INTELLIGENCE, Vol: 7, ISSN: 2638-6100
  • Cite
  • Citations: 4
• Journal article
  Hasan MK, Zhu H, Yang G, Yap CHet al., 2025,

  Deep learning image registration for cardiac motion estimation in adult and fetal echocardiography via a focus on anatomic plausibility and texture quality of warped image.

  , Comput Biol Med, Vol: 187

  Temporal echocardiography image registration is important for cardiac motion estimation, myocardial strain assessments, and stroke volume quantifications. Deep learning image registration (DLIR) is a promising way to achieve consistent and accurate registration results with low computational time. DLIR seeks the image deformation that enables the moving image to be warped to match the fixed image. We propose that, during DLIR training, a greater focus on the warped moving image's anatomic plausibility and image texture can support robust results, and we show that it has sufficient robustness to be applied to both fetal and adult echocardiography. Our proposed framework includes (1) an anatomic shape-encoded constraint to preserve physiological myocardial and left ventricular anatomical topologies in the warped image, (2) a data-driven texture constraint to preserve good texture features in the warped image, and (3) a multi-scale training algorithm to improve accuracy. Our experiments demonstrate a strong correlation between the shape-encoded constraint and good anatomical topology and between the data-driven texture constraint and image textures. They improve different aspects of registration results in a non-overlapping way. We demonstrate that these methods can successfully register both fetal and adult echocardiography using our multi-demographic fetal dataset and the public CAMUS adult dataset, despite the inherent differences between adult and fetal echocardiography. Our approach also outperforms traditional non-DL gold standard registration approaches, including optical flow and Elastix, and could be translated into more accurate and precise clinical quantification of cardiac ejection fraction, demonstrating potential for clinical utility.

  • Abstract
  • Author Web Link
  • Cite
• Journal article
  Tang N, Liao Y, Chen Y, Yang G, Lai X, Chen Jet al., 2025,

  RVM plus : An AI-Driven Vision Sensor Framework for High-Precision, Real-Time Video Portrait Segmentation with Enhanced Temporal Consistency and Optimized Model Design

  , SENSORS, Vol: 25
  • Cite
• Journal article
  Osugo M, Wall MB, Selvaggi P, Zahid U, Finelli V, Chapman GE, Whitehurst T, Onwordi EC, Statton B, McCutcheon RA, Murray RM, Marques TR, Mehta MA, Howes Oet al., 2025,

  Striatal dopamine D2/D3 receptor regulation of human reward processing and behaviour

  , Nature Communications, Vol: 16, ISSN: 2041-1723

  Signalling at dopamine D2/D3 receptors is thought to underlie motivated behaviour, pleasure experiences and emotional expression based on animal studies, but it is unclear if this is the case in humans or how this relates to neural processing of reward stimuli. Using a randomised, double-blind, placebo-controlled, crossover neuroimaging study, we show in healthy humans that sustained dopamine D2/D3 receptor antagonism for 7 days results in negative symptoms (impairments in motivated behaviour, hedonic experience, verbal and emotional expression) and that this is related to blunted striatal response to reward stimuli. In contrast, 7 days of partial D2/D3 agonism does not disrupt reward signalling, motivated behaviour or hedonic experience. Both D2/D3 antagonism and partial agonism induce motor impairments, which are not related to striatal reward response. These findings identify a central role for D2/D3 signalling and reward processing in the mechanism underlying motivated behaviour and emotional responses in humans, with implications for understanding neuropsychiatric disorders such as schizophrenia and Parkinson’s disease.

  • Abstract
  • Publisher Web Link
  • Cite
• Journal article
  Xing X, Shi F, Huang J, Wu Y, Nan Y, Zhang S, Fang Y, Roberts M, Schonlieb C-B, Del Ser J, Yang Get al., 2025,

  On the caveats of AI autophagy

  , Nature Machine Intelligence, Vol: 7, Pages: 172-180, ISSN: 2522-5839

  Generative artificial intelligence (AI) technologies and large models are producing realistic outputs across various domains, such as images, text, speech and music. Creating these advanced generative models requires significant resources, particularly large and high-quality datasets. To minimize training expenses, many algorithm developers use data created by the models themselves as a cost-effective training solution. However, not all synthetic data effectively improve model performance, necessitating a strategic balance in the use of real versus synthetic data to optimize outcomes. Currently, the previously well-controlled integration of real and synthetic data is becoming uncontrollable. The widespread and unregulated dissemination of synthetic data online leads to the contamination of datasets traditionally compiled through web scraping, now mixed with unlabelled synthetic data. This trend, known as the AI autophagy phenomenon, suggests a future where generative AI systems may increasingly consume their own outputs without discernment, raising concerns about model performance, reliability and ethical implications. What will happen if generative AI continuously consumes itself without discernment? What measures can we take to mitigate the potential adverse effects? To address these research questions, this Perspective examines the existing literature, delving into the consequences of AI autophagy, analysing the associated risks and exploring strategies to mitigate its impact. Our aim is to provide a comprehensive perspective on this phenomenon advocating for a balanced approach that promotes the sustainable development of generative AI technologies in the era of large models.

  • Abstract
  • Cite
• Journal article
  Rajakulasingam R, Ferreira P, Scott A, Khalique Z, Azzu A, Molto M, Conway M, Falaschetti E, Cheng K, Hammersley D, Cantor E, Tindale A, Beattie C, Banerjee A, Wage R, Soundarajan RK, Dalby M, Nielles-Vallespin S, Pennell D, De Silva Pet al., 2025,

  Characterization of dynamic changes in cardiac microstructure after reperfused ST-elevation myocardial infarction by biphasic diffusion tensor cardiovascular magnetic resonance

  , European Heart Journal, Vol: 46, Pages: 454-469, ISSN: 0195-668X

  Background and Aims: Microstructural disturbances underlie dysfunctional contraction and adverse left ventricular (LV) remodelling after ST-elevation myocardial infarction (STEMI). Biphasic diffusion tensor cardiovascular magnetic resonance (DT-CMR) quantifies dynamic reorientation of sheetlets (E2A) from diastole to systole during myocardial thickening, and markers of tissue integrity (mean diffusivity [MD] and fractional anisotropy [FA]). This study investigated whether microstructural alterations identified by biphasic DT-CMR: (i) enable contrast-free detection of acute myocardial infarction (MI); (ii) associate with severity of myocardial injury and contractile dysfunction; and (iii) predict adverse LV remodelling. Methods: Biphasic DT-CMR was acquired 4 days (n=70) and 4 months (n=66) after reperfused STEMI and in healthy volunteers (HVOLs) (n=22). Adverse LV remodelling was defined as an increase in LV end-diastolic volume ≥20% at 4 months. MD and FA maps were compared with late gadolinium enhancement images. Results: Widespread microstructural disturbances were detected post-STEMI. In the acute MI zone, diastolic E2A was raised and systolic E2A reduced, resulting in reduced E2A mobility (all p<0.001 vs adjacent and remote zones and HVOLs). Acute global E2A mobility was the only independent predictor of adverse LV remodelling (odds ratio 0.77; 95% confidence interval 0.63–0.94; p=0.010). MD and FA maps had excellent sensitivity and specificity (all >90%) and inter-observer agreement for detecting MI presence and location.Conclusions: Biphasic DT-CMR identifies microstructural alterations in both diastole and systole after STEMI, enabling detection of MI presence and location as well as predicting adverse LV remodelling. DT-CMR has potential to provide a single contrast-free modality for MI detection and prognostication of patients after acute STEMI.

  • Abstract
  • Publisher Web Link
  • Cite

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.