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
  Papanastasiou G, Sanchez PP, Christodoulidis A, Yang G, Pinaya WHLet al., 2025,

  Confounder-aware foundation modeling for accurate phenotype profiling in cell imaging

  , npj Imaging, ISSN: 2948-197X

  Image-based profiling is rapidly transforming drug discovery, offering unprecedented insights into cellular responses. However, experimental variability hinders accurate identification of mechanisms of action (MoA) and compound targets. Existing methods commonly fail to generalize to novel compounds, limiting their utility in exploring uncharted chemical space. To address this, we present a confounder-aware foundation model integrating a causal mechanism within a latent diffusion model, enabling the generation of balanced synthetic datasets for robust biological effect estimation. Trained on over 13 million Cell Painting images and 107 thousand compounds, our model learns robust cellular phenotype representations, mitigating confounder impact. We achieve state-of-the-art MoA and target prediction for both seen (0.66 and 0.65 ROC-AUC) and unseen compounds (0.65 and 0.73 ROC-AUC), significantly surpassing real and batch-corrected data. This innovative framework advances drug discovery by delivering robust biological effect estimations for novel compounds, potentially accelerating hit expansion. Our model establishes a scalable and adaptable foundation for cell imaging, holding the potential to become a cornerstone in data-driven drug discovery.

  • Abstract
  • Cite
• Journal article
  Lally P, Jin Y, Huo Z, Beitone C, Chiew M, Matthews P, Miller K, Bangerter Net al., 2025,

  Steady-state free precession for T2* relaxometry: all echoes in every readout with k-space aliasing

  , Magnetic Resonance in Medicine, Vol: 94, Pages: 1563-1576, ISSN: 0740-3194

  PurposeMulti-echo gradient echo imaging is useful for a range of applications including relaxometry, susceptibility mapping, and quantifying relative proportions of fat and water. This relies primarily on long-TR multi-echo gradient echo sequences (FLASH), which by design isolate one signal component (i.e., echo) at a time per readout. In this work, we propose an alternative strategy that simultaneously measures all signal components at once in every readout event with an N-periodic SSFP sequence. Essentially, we Fourier encode the signals into an “F-k space” similar to the “TE-k space” of a multi-echo gradient echo acquisition. This enables an efficient, short-TR relaxometry experiment where signals benefit from averaging effects over multiple excitations.Theory and MethodsIn the presented approach, multiple echoes are recorded simultaneously and separated by their differing phase evolution over multiple TRs. At low flip angles the relative echo amplitudes and phases are equivalent to those acquired sequentially from a multi-echo FLASH, in terms of both T2* weighting and spatial phase distributions. The two approaches were compared for the example of R2* relaxometry in a phantom and in human volunteers.ResultsThe proposed approach shows close agreement in R2* estimation with multi-echo FLASH, with the advantage of more rapid temporal sampling.ConclusionThe proposed approach is a promising alternative to other relaxometry approaches, by measuring signals from multiple echo pathways simultaneously and separating them based on a simple analytical model.

  • Abstract
  • Publisher Web Link
  • Cite
• Journal article
  David MCB, Kolanko MA, Parker TD, Nilforooshan R, Zimmerman KA, Bonet Olivares C, Hoang K, Brandt J, Triantafyllou C, Lally PJ, Scott G, Sharp DJ, Malhotra PAet al., 2025,

  Catecholaminergic nucleus integrity and Alzheimer's pathology, symptoms, and progression

  , Alzheimer's and Dementia, Vol: 21, ISSN: 1552-5260

  BACKGROUNDThe noradrenergic locus coeruleus (LC) accumulates pathology early in Alzheimer's disease (AD), with LC dysfunction contributing to symptoms and disease progression. We investigated LC and substantia nigra (SN) integrity in healthy controls and AD participants.METHODSNinety-three AD participants and 29 controls underwent neuromelanin magnetic resonance imaging. LC and SN contrast, reflecting nucleus integrity, related to cognitive and neuropsychiatric symptoms, as well as cognitive decline and atrophy rates.RESULTSLC – but not SN – integrity was reduced in AD versus controls (b = −0.39, p = 0.001) and within AD was associated with global cognition (b = 8.53, p = 0.04) and neuropsychiatric symptoms, accounting for SN. An AD subgroup with reduced SN integrity had worse cognition. LC integrity predicted plasma phosphorylated tau protein 217 (b = −0.30, p = 0.03). Lower LC and SN integrities were both related to faster cognitive decline (LC: b = −4.74, p = 0.048; SN: b = −2.27, p = 0.03), accounting for one another.DISCUSSIONCatecholaminergic nucleus integrity plays an important role in AD. Both systems are relevant to cognitive performance and decline. LC, in particular, relates closely to symptoms, pathology, and rate of progression.HighlightsIn symptomatic AD, LC integrity reflects cortical AD pathology, measured by pTau217.LC integrity predicts cognitive function in AD, independent of cortical atrophy.LC and SN integrity independently relate to attentional performance.Symptoms of anxiety, depression, and apathy are associated with lower LC integrity.LC and SN relate to cognitive decline rate and left LC predicts atrophy rate.

  • Abstract
  • Publisher Web Link
  • Cite
• Journal article
  Nan Y, Felder FN, Humphries S, Mackintosh JA, Grainge C, Jo HE, Goh N, Reynolds PN, Hopkins PMA, Navaratnam V, Moodley Y, Walters H, Ellis S, Keir G, Zappala C, Corte T, Glaspole I, Wells AU, Yang G, Walsh SLFet al., 2025,

  Prognostication in patients with idiopathic pulmonary fibrosis using quantitative airway analysis from HRCT: a retrospective study

  , EUROPEAN RESPIRATORY JOURNAL, Vol: 66, ISSN: 0903-1936
  • Cite
  • Citations: 3
• Journal article
  Xing Z, Wan L, Fu H, Yang G, Yang Y, Yu L, Lei B, Zhu Let al., 2025,

  Diff-UNet: A diffusion embedded network for robust 3D medical image segmentation

  , MEDICAL IMAGE ANALYSIS, Vol: 105, ISSN: 1361-8415
  • Cite
  • Citations: 2
• Journal article
  Jiang L, Ma L, Yang G, 2025,

  Shadow defense against gradient inversion attack in federated learning☆

  , MEDICAL IMAGE ANALYSIS, Vol: 105, ISSN: 1361-8415
  • Cite
• Journal article
  Zeyu T, Xing X, Wang G, Yang Get al., 2025,

  Enhancing super-resolution network efficacy in CT imaging: cost-effective simulation of training data

  , IEEE Open Journal of Engineering in Medicine and Biology, ISSN: 2644-1276

  Deep learning-based Generative Models have the potential to convert low-resolution CT images into high-resolution counterparts without long acquisition times and increased radiation exposure in thin-slice CT imaging. However, procuring appropriate training data for these Super-Resolution (SR) models is challenging. Previous SR research has simulated thick-slice CT images from thin-slice CT images to create training pairs. However, these methods either rely on simplistic interpolation techniques that lack realism or on sinogram reconstruction, which requires the release of raw data and complex reconstruction algorithms. Thus, we introduce a simple yet realistic method to generate thick CT images from thin-slice CT images, facilitating the creation of training pairs for SR algorithms. The training pairs produced by our method closely resemble real data distributions (PSNR=49.74 vs. 40.66, p<0.05). A multivariate Cox regression analysis involving thick slice CT images with lung fibrosis revealed that only the radiomics features extracted using our method demonstrated a significant correlation with mortality (HR=1.19 and HR=1.14, p<0.005). This paper represents the first to identify and address the challenge of generating appropriate paired training data for Deep Learning-based CT SR models, which enhances the efficacy and applicability of SR models in real-world scenarios.

  • Abstract
  • Cite
• Journal article
  Vano LJ, McCutcheon RA, Sedlacik J, Rutigliano G, Kaar SJ, Finelli V, Lobo MC, Berry A, Statton B, Fazlollahi A, Everall IP, Howes ODet al., 2025,

  The role of low subcortical iron, white matter myelin, and oligodendrocytes in schizophrenia: a quantitative susceptibility mapping and diffusion tensor imaging study

  , MOLECULAR PSYCHIATRY, ISSN: 1359-4184
  • Cite
• Journal article
  Ai R, Xiao X, Deng S, Yang N, Xing X, Watne LO, Wedatilake Y, Xie C, Selback G, Rubinsztein DC, Neerland BE, Palmer JE, Chen H, Niu Z, Yang G, Fang EFet al., 2025,

  Artificial intelligence in drug development for delirium and Alzheimer's disease

  , Acta Pharmaceutica Sinica B, Vol: 15, Pages: 4386-4410, ISSN: 2211-3835

  Delirium is a common cause and complication of hospitalization in the elderly and is associated with higher risk of future dementia and progression of existing dementia, of which 70% is Alzheimer’s disease (AD). AD and delirium, which are known to be aggravated by one another, represent significant societal challenges, especially in light of the absence of effective treatments. The intricate biological mechanisms have led to numerous clinical trial setbacks and likely contribute to the limited efficacy of existing therapeutics. Artificial intelligence (AI) presents a promising avenue for overcoming these hurdles by deploying algorithms to uncover hidden patterns across diverse data types. This review explores the pivotal role of AI in revolutionizing drug discovery for AD and delirium from target identification to the development of small molecule and protein-based therapies. Recent advances in deep learning, particularly in accurate protein structure prediction, are facilitating novel approaches to drug design and expediting the discovery pipeline for biological and small molecule therapeutics. This review concludes with an appraisal of current achievements and limitations, and touches on prospects for the use of AI in advancing drug discovery in AD and delirium, emphasizing its transformative potential in addressing these two and possibly other neurodegenerative conditions.

  • Abstract
  • Cite
• Journal article
  Li S, Zhuang B, Cui C, He J, Ren Y, Wang H, Francone M, Yang G, Mohiaddin R, Lu M, Xu Let al., 2025,

  Prognostic significance of myocardial fibrosis in men with alcoholic cardiomyopathy: insights from cardiac MRI

  , EUROPEAN RADIOLOGY, Vol: 35, Pages: 5594-5603, ISSN: 0938-7994
  • Cite
  • Citations: 1

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.