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

• Conference paper
  Koutsoftidis S, Belgaid Y, Yang G, Barsakcioglu DY, Glaros KN, Farina Det al., 2024,

  A capacitorless, AC-coupled, monolithic input-stage optimized for multi-channel surface EMG acquisition

  , EMBC 2024 Conference, Publisher: IEEE, ISSN: 2694-0604

  An input-stage optimized for multi-channel surface electromyography applications has been designed and realized in 0.35 μm CMOS technology. MOS-based pseudo-resistors and MOS-capacitors were utilized at the input AC-coupling stage to minimize chip area. Measured performance and variability results are provided across 20 fabricated channels from five dies. Confirming biological measurements were performed using commercially-available electrodes.Clinical Relevance—The proposed input-stage could be utilized to miniaturize existing desktop-based >128 channel sEMG research setups into wearable products

  • Abstract
  • Cite
• Journal article
  Chen J, Li X, Zhang H, Cho Y, Hwang SH, Gao Z, Yang Get al., 2024,

  Adaptive dynamic inference for few-shot left atrium segmentation

  , MEDICAL IMAGE ANALYSIS, Vol: 98, ISSN: 1361-8415
  • Cite
• Journal article
  Ankolekar A, Eppings L, Bottari F, Pinho IF, Howard K, Baker R, Nan Y, Xing X, Walsh SLF, Vos W, Yang G, Lambin Pet al., 2024,

  Using artificial intelligence and predictive modelling to enable learning healthcare systems (LHS) for pandemic preparedness

  , COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, Vol: 24, Pages: 412-419, ISSN: 2001-0370
  • Cite
• Journal article
  Zhang D, Liu X, Wang A, Zhang H, Yang G, Zhang H, Gao Zet al., 2024,

  Constraint-Aware Learning for Fractional Flow Reserve Pullback Curve Estimation From Invasive Coronary Imaging

  , IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 43, Pages: 4091-4104, ISSN: 0278-0062
  • Cite
• Journal article
  Wang H, Yang G, Zhang S, Qin J, Guo Y, Xu B, Jin Y, Zhu Let al., 2024,

  Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery

  , IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 43, Pages: 4457-4469, ISSN: 0278-0062
  • Cite
• Journal article
  Patel KHK, Bajaj N, Statton BK, Bishop MJ, Herath NS, Stoks J, Li X, Sau A, Nyamakope K, Davidson R, Savvidou S, Agha-Jaffar D, Coghlin JA, Brezitski M, Bergman H, Berry A, Ardissino M, de Marvao A, Cousins J, Ware JS, Purkayastha S, Volders P, Peters NS, O'Regan DP, Coronel R, Cluitmans M, Lambiase PD, Ng FSet al., 2024,

  Bariatric surgery partially reverses subclinical proarrhythmic structural, electrophysiological, and autonomic changes in obesity

  , Heart Rhythm, Vol: 21, Pages: 2282-2294, ISSN: 1547-5271

  BackgroundObesity confers higher risks of cardiac arrhythmias. The extent to which weight loss reverses subclinical proarrhythmic adaptations in arrhythmia-free obese individuals is unknown.ObjectiveThe purpose of this study was to study structural, electrophysiological, and autonomic remodeling in arrhythmia-free obese patients and their reversibility with bariatric surgery using electrocardiographic imaging (ECGi).MethodsSixteen arrhythmia-free obese patients (mean age 43 ± 12 years; 13 (81%) female participants; BMI 46.7 ± 5.5 kg/m2) had ECGi pre–bariatric surgery, of whom 12 (75%) had ECGi postsurgery (BMI 36.8 ± 6.5 kg/m2). Sixteen age- and sex-matched lean healthy individuals (mean age 42 ± 11 years; BMI 22.8 ± 2.6 kg/m2) acted as controls and had ECGi only once.ResultsObesity was associated with structural (increased epicardial fat volumes and left ventricular mass), autonomic (blunted heart rate variability), and electrophysiological (slower atrial conduction and steeper ventricular repolarization time gradients) remodeling. After bariatric surgery, there was partial structural reverse remodeling, with a reduction in epicardial fat volumes (68.7 cm3 vs 64.5 cm3; P = .0010) and left ventricular mass (33 g/m2.7 vs 25 g/m2.7; P < .0005). There was also partial electrophysiological reverse remodeling with a reduction in mean spatial ventricular repolarization gradients (26 mm/ms vs 19 mm/ms; P = .0009), although atrial activation remained prolonged. Heart rate variability, quantified by standard deviation of successive differences in R-R intervals, was also partially improved after bariatric surgery (18.7 ms vs 25.9 ms; P = .017). Computational modeling showed that presurgical obese hearts had a larger window of vulnerability to unidirectional block and had an earlier spiral-wave breakup with more complex reentry patterns than did postsurgery counterparts.ConclusionObesity is associated with adverse electrophysiologica

  • Abstract
  • Publisher Web Link
  • Cite
• Journal article
  Li Z, Li D, Du W, Du Y, Yang Get al., 2024,

  Facile preparation of fluorescent tartaric acid-modified polymer dots for Fe3+detection

  , JOURNAL OF PHOTOCHEMISTRY AND PHOTOBIOLOGY A-CHEMISTRY, Vol: 456, ISSN: 1010-6030
  • Cite
• Journal article
  Ferrante M, Inglese M, Brusaferri L, Whitehead AC, Maccioni L, Turkheimer FE, Nettis MA, Mondelli V, Howes O, Loggia ML, Veronese M, Toschi Net al., 2024,

  Physically informed deep neural networks for metabolite-corrected plasma input function estimation in dynamic PET imaging.

  , Comput Methods Programs Biomed, Vol: 256

  INTRODUCTION: We propose a novel approach for the non-invasive quantification of dynamic PET imaging data, focusing on the arterial input function (AIF) without the need for invasive arterial cannulation. METHODS: Our method utilizes a combination of three-dimensional depth-wise separable convolutional layers and a physically informed deep neural network to incorporatea priori knowledge about the AIF's functional form and shape, enabling precise predictions of the concentrations of [11C]PBR28 in whole blood and the free tracer in metabolite-corrected plasma. RESULTS: We found a robust linear correlation between our model's predicted AIF curves and those obtained through traditional, invasive measurements. We achieved an average cross-validated Pearson correlation of 0.86 for whole blood and 0.89 for parent plasma curves. Moreover, our method's ability to estimate the volumes of distribution across several key brain regions - without significant differences between the use of predicted versus actual AIFs in a two-tissue compartmental model - successfully captures the intrinsic variability related to sex, the binding affinity of the translocator protein (18 kDa), and age. CONCLUSIONS: These results not only validate our method's accuracy and reliability but also establish a foundation for a streamlined, non-invasive approach to dynamic PET data quantification. By offering a precise and less invasive alternative to traditional quantification methods, our technique holds significant promise for expanding the applicability of PET imaging across a wider range of tracers, thereby enhancing its utility in both clinical research and diagnostic settings.

  • Abstract
  • Author Web Link
  • Cite
• Journal article
  Xing X, Murdoch S, Tang C, Papanastasiou G, Cross-Zamirski J, Guo Y, Xiao X, Schönlieb C-B, Wang Y, Yang Get al., 2024,

  Can generative AI replace immunofluorescent staining processes? A comparison study of synthetically generated cellpainting images from brightfield.

  , Comput Biol Med, Vol: 182

  Cell imaging assays utilising fluorescence stains are essential for observing sub-cellular organelles and their responses to perturbations. Immunofluorescent staining process is routinely in labs, however the recent innovations in generative AI is challenging the idea of wet lab immunofluorescence (IF) staining. This is especially true when the availability and cost of specific fluorescence dyes is a problem to some labs. Furthermore, staining process takes time and leads to inter-intra-technician and hinders downstream image and data analysis, and the reusability of image data for other projects. Recent studies showed the use of generated synthetic IF images from brightfield (BF) images using generative AI algorithms in the literature. Therefore, in this study, we benchmark and compare five models from three types of IF generation backbones-CNN, GAN, and diffusion models-using a publicly available dataset. This paper not only serves as a comparative study to determine the best-performing model but also proposes a comprehensive analysis pipeline for evaluating the efficacy of generators in IF image synthesis. We highlighted the potential of deep learning-based generators for IF image synthesis, while also discussed potential issues and future research directions. Although generative AI shows promise in simplifying cell phenotyping using only BF images with IF staining, further research and validations are needed to address the key challenges of model generalisability, batch effects, feature relevance and computational costs.

  • Abstract
  • Author Web Link
  • Cite
• Journal article
  Kumar S, Chauhan AR, Akhil, Kumar A, Yang G, Yang Get al., 2024,

  Resp-BoostNet: mental stress detection from biomarkers measurable by smartwatches using boosting neural network technique

  , IEEE Access, Vol: 12, Pages: 149861-149874, ISSN: 2169-3536

  To maintain overall health and well-being, it is crucial to manage mental stress. This studyfocuses on developing a deep learning model for recognizing mental stress levels using the sensors ofsmartwatches. Most related research with notable performance has focused on mental stress detectionusing various physiological biomarkers obtained through sophisticated IoMT (Internet of Medical Things)devices. However, the ones using only the smartwatch’s measurable physiological biomarkers, whichdo not include respiration rate, have comparatively lower performance because of a limited number ofphysiological biomarkers. In this paper, we introduce an improved model for mental stress detection usingboosting neural network that can be integrated into a smartwatch. The proposed model consists of twophases. In the first phase, we introduce a boosting neural network technique that predicts the respiration rateby utilizing the biomarkers measurable by a smartwatch. The second phase uses the In the second phase,the modified set of biomarkers, which includes both the original biomarkers and the predicted respirationrate, is used for stress level classification via an artificial neural network. The necessary hyperparametertuning is performed to obtain the optimal values of various model parameters. The training of the modelis performed for fifteen different subjects of the publicly available multimodal WESAD (Wearable Stressand Affect Detection) dataset using various biomarkers measured by smartwatches. The proposed modelpredicts respiration rate with low error (0.035 MSE (Mean Squared Error)) and achieves high mental stressdetection accuracy of 94% using smartwatch measurable biomarkers which is a ∼2% improvement over thecurrent contemporary technique.

  • 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.