Search or filter publications

Filter by type:

Filter by publication type

Filter by year:

to

Results

  • Showing results for:
  • Reset all filters

Search results

  • Conference paper
    Balaji K, Vicente PM, Kukran S, Mendoza M, Bharath AA, Lally PJ, Bangerter NKet al., 2025,

    COMPARING QDESS AND RAFO-4 PERFORMANCE IN 5-MINUTE, SIMULTANEOUS 3D T<sub>2</sub> MAPPING AND MORPHOLOGICAL MR IMAGING

    , OARSI World Congress on Osteoarthritis, Publisher: ELSEVIER SCI LTD, Pages: 792-793, ISSN: 1063-4584
  • Conference paper
    Balaji K, Mendoza M, Vicente PM, Galazis C, Kukran S, Bharath AA, Lally PJ, Bangerter NKet al., 2025,

    RAFO-4 MRI: SIMULTANEOUS CARTILAGE MORPHOLOGY AND 3D T<sub>2</sub> MAPPING WITH MACHINE LEARNING

    , OARSI World Congress on Osteoarthritis, Publisher: ELSEVIER SCI LTD, Pages: 791-792, ISSN: 1063-4584
  • Journal article
    Yang L, Huang J, Yang G, Zhang Det al., 2025,

    CT-SDM: A Sampling Diffusion Model for Sparse-View CT Reconstruction Across Various Sampling Rates

    , IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 44, Pages: 2581-2593, ISSN: 0278-0062
  • Journal article
    Ankolekar A, Boie S, Abdollahyan M, Gadaleta E, Hasheminasab SA, Yang G, Beauville C, Dikaios N, Kastis GA, Bussmann M, Chelala C, Khalid S, Kruger H, Lambin P, Papanastasiou Get al., 2025,

    Advancing breast, lung and prostate cancer research with federated learning. A systematic review

    , NPJ DIGITAL MEDICINE, Vol: 8, ISSN: 2398-6352
  • Journal article
    Hasan MK, Luo Y, Yang G, Yap CHet al., 2025,

    Feedback attention to enhance unsupervised deep learning image registration in 3D echocardiography

    , IEEE Transactions on Medical Imaging, Vol: 44, Pages: 2230-2243, ISSN: 0278-0062

    Cardiac motion estimation is important for assessing the contractile health of the heart, and performing this in 3D can provide advantages due to the complex 3D geometry and motions of the heart. Deep learning image registration (DLIR) is a robust way to achieve cardiac motion estimation in echocardiography, providing speed and precision benefits, but DLIR in 3D echo remains challenging. Successful unsupervised 2D DLIR strategies are often not effective in 3D, and there have been few 3D echo DLIR implementations. Here, we propose a new spatial feedback attention (FBA) module to enhance unsupervised 3D DLIR and enable it. The module uses the results of initial registration to generate a co-attention map that describes remaining registration errors spatially and feeds this back to the DLIR to minimize such errors and improve self-supervision. We show that FBA improves a range of promising 3D DLIR designs, including networks with and without transformer enhancements, and that it can be applied to both fetal and adult 3D echo, suggesting that it can be widely and flexibly applied. We further find that the optimal 3D DLIR configuration is when FBA is combined with a spatial transformer and a DLIR backbone modified with spatial and channel attention, which outperforms existing 3D DLIR approaches. FBA’s good performance suggests that spatial attention is a good way to enable scaling up from 2D DLIR to 3D and that a focus on the quality of the image after registration warping is a good way to enhance DLIR performance. Codes and data are available at: https://github.com/kamruleee51/Feedback_DLIR.
  • Journal article
    Nan Y, Zhou H, Xing X, Papanastasiou G, Zhu L, Gao Z, Frangi AF, Yang Get al., 2025,

    Revisiting medical image retrieval via knowledge consolidation

    , MEDICAL IMAGE ANALYSIS, Vol: 102, ISSN: 1361-8415
  • Journal article
    Zhang Z, Zhang H, Zeng T, Yang G, Shi Z, Gao Zet al., 2025,

    Bridging multi-level gaps: Bidirectional reciprocal cycle framework for text-guided label-efficient segmentation in echocardiography

    , MEDICAL IMAGE ANALYSIS, Vol: 102, ISSN: 1361-8415
  • Journal article
    Schweitzer R, de Marvao A, Shah M, Inglese P, Kellman P, Berry A, Statton B, O'Regan Det al., 2025,

    Establishing cardiac MRI reference ranges stratified by sex and age for cardiovascular function during exercise

    , Radiology: Cardiothoracic Imaging, ISSN: 2638-6135

    Purpose: To evaluate the effects of exercise on left ventricular parameters using exercise cardiac MRI in healthy adults without known cardiovascular disease, and establish reference ranges stratified by age and sex.Materials and Methods: This prospective study included healthy adult participants with no known cardiovascular disease or genetic variants associated with cardiomyopathy, enrolled between January 2018 and April 2021, who underwent exercise cardiac MRI evaluation. Participants were imaged at rest and after exercise, with parameters measured by two readers. Prediction intervals were calculated and compared across sex and age groups.Results: The study included 161 participants (mean age, 49±[SD]14 years; 85 female). Compared with the resting state, exercise caused an increase in heart rate (64±9 bpm vs 133±19 bpm, P < 0.001), left ventricular end-diastolic volume (140±32 ml vs 148±35 ml, P < 0.001), stroke volume (82±18 ml vs 102±25 ml, P < 0.001), ejection fraction (59±6% vs 69±7%, P < 0.001), and cardiac output (5.2±1.1 l/min vs 13.5±3.9 l/min, P < 0.001), and a decrease in left ventricular end-systolic volume (58±18 ml vs 46±15 ml, P < 0.001). There were significant differences in exercise response between groups stratified by sex and age for most parameters.Conclusion: In healthy adults, an increase in cardiac output after exercise is driven by a rise in heart rate with both increased ventricular filling and emptying. Normal ranges for exercise response, stratified by age and sex, are established as a reference for the use of exercise cardiac MRI in clinical practice.
  • Journal article
    Nan Y, Zhou H, Xing X, Yang Get al., 2025,

    Beyond the Hype: A Dispassionate Look at Vision-Language Models in Medical Scenario

    , IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, ISSN: 2162-237X
  • Journal article
    Inglese M, Boccato T, Ferrante M, Islam S, Williams M, Waldman AD, O'Neill K, Aboagye EO, Toschi Net al., 2025,

    Genotype Characterization in Primary Brain Gliomas via Unsupervised Clustering of Dynamic PET Imaging of Short-Chain Fatty Acid Metabolism

    , IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, Vol: 9, Pages: 460-467, ISSN: 2469-7311

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.

Request URL: http://www.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=1107&limit=10&resgrpMemberPubs=true&page=5&respub-action=search.html Current Millis: 1765818970220 Current Time: Mon Dec 15 17:16:10 GMT 2025

Contact

For enquiries about the MRI Physics Collective, please contact:

Mary Finnegan
Senior MR Physicist at the Imperial College Healthcare NHS Trust

Pete Lally
Assistant Professor in Magnetic Resonance (MR) Physics at Imperial College

Jan Sedlacik
MR Physicist at the Robert Steiner MR Unit, Hammersmith Hospital Campus