Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleTang N, Liao Y, Chen Y, et 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 -
Journal articleOsugo M, Wall MB, Selvaggi P, et al., 2025,
Striatal dopamine D2/D3 receptor regulation of human reward processing and behaviour
, Nature Communications, Vol: 16, ISSN: 2041-1723Signalling 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.
-
Journal articleXing X, Shi F, Huang J, et al., 2025,
On the caveats of AI autophagy
, Nature Machine Intelligence, Vol: 7, Pages: 172-180, ISSN: 2522-5839Generative 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.
-
Journal articleRajakulasingam R, Ferreira P, Scott A, et 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: 0195-668XBackground 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.
-
Journal articleWu W, Long Y, Gao Z, et al., 2025,
Multi-Level Noise Sampling From Single Image for Low-Dose Tomography Reconstruction
, IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, Vol: 29, Pages: 1256-1268, ISSN: 2168-2194 -
Journal articleGuiot J, Henket M, Gester F, et al., 2025,
Automated AI-based image analysis for quantification and prediction of interstitial lung disease in systemic sclerosis patients.
, Respir Res, Vol: 26BACKGROUND: Systemic sclerosis (SSc) is a rare connective tissue disease associated with rapidly evolving interstitial lung disease (ILD), driving its mortality. Specific imaging-based biomarkers associated with the evolution of lung disease are needed to help predict and quantify ILD. METHODS: We evaluated the potential of an automated ILD quantification system (icolung®) from chest CT scans, to help in quantification and prediction of ILD progression in SSc-ILD. We used a retrospective cohort of 75 SSc-ILD patients to evaluate the potential of the AI-based quantification tool and to correlate image-based quantification with pulmonary function tests and their evolution over time. RESULTS: We evaluated a group of 75 patients suffering from SSc-ILD, either limited or diffuse, of whom 30 presented progressive pulmonary fibrosis (PPF). The patients presenting PPF exhibited more extensive lesions (in % of total lung volume (TLV)) based on image analysis than those without PPF: 3.93 (0.36-8.12)* vs. 0.59 (0.09-3.53) respectively, whereas pulmonary functional test showed a reduction in Force Vital Capacity (FVC)(pred%) in patients with PPF compared to the others : 77 ± 20% vs. 87 ± 19% (p < 0.05). Modifications of FVC and diffusing capacity of the lungs for carbon monoxide (DLCO) over time were correlated with longitudinal radiological ILD modifications (r=-0.40, p < 0.01; r=-0.40, p < 0.01 respectively). CONCLUSION: AI-based automatic quantification of lesions from chest-CT images in SSc-ILD is correlated with physiological parameters and can help in disease evaluation. Further clinical multicentric validation is necessary in order to confirm its potential in the prediction of patient's outcome and in treatment management.
-
Journal articleZhang S-Q, Niu Z, Anisimov A, et al., 2025,
NR1D1 Inhibition Enhances Autophagy and Mitophagy in Alzheimer's Disease Models
, Aging and Disease, ISSN: 2152-5250 -
Journal articleXing X, Tang C, Murdoch S, et al., 2025,
Artificial immunofluorescence in a flash: Rapid synthetic imaging from brightfield through residual diffusion
, NEUROCOMPUTING, Vol: 612, ISSN: 0925-2312 -
Conference paperWang S, Nan Y, Xing X, et al., 2025,
A Parallel Network for LRCT Segmentation and Uncertainty Mitigation with Fuzzy Sets
, Pages: 4443-4454Accurate segmentation of airways in LowResolution CT (LRCT) scans is vital for diagnostics in scenarios such as reduced radiation exposure, emergency response, or limited resources. Yet manual annotation is labor-intensive and prone to variability, while existing automated methods often fail to capture small airway branches in lowerresolution 3D data. To address this, we introduce FuzzySR, a parallel framework that merges superresolution (SR) and segmentation. By concurrently producing high-resolution reconstructions and precise airway masks, it enhances anatomic fidelity and captures delicate bronchi. FuzzySR employs a deep fuzzy set mechanism, leveraging learnable t-distribution and triangular membership functions via cross-attention. Through parameters μ, σ, and df, it preserves uncertain features and mitigates boundary noise. Extensive evaluations on lung cancer, COVID-19, and pulmonary fibrosis datasets confirm FuzzySR’s superior segmentation accuracy on LRCT, surpassing even high-resolution baselines. By uniting fuzzy-logic-driven uncertainty handling with SR-based resolution enhancement, FuzzySR effectively bridges the gap for robust airway delineation from LRCT data.
-
Journal articleHao P, Wang H, Yang G, et al., 2025,
Enhancing Visual Reasoning with LLM-Powered Knowledge Graphs for Visual Question Localized-Answering in Robotic Surgery
, IEEE Journal of Biomedical and Health Informatics, ISSN: 2168-2194Expert surgeons often have heavy workloads and cannot promptly respond to queries from medical students and junior doctors about surgical procedures. Thus, research on Visual Question Localized-Answering in Surgery (Surgical-VQLA) is essential to assist medical students and junior doctors in understanding surgical scenarios. Surgical-VQLA aims to generate accurate answers and locate relevant areas in the surgical scene, requiring models to identify and understand surgical instruments, operative organs, and procedures. A key issue is the model's ability to accurately distinguish surgical instruments. Current Surgical-VQLA models rely primarily on sparse textual information, limiting their visual reasoning capabilities. To address this issue, we propose a framework called Enhancing Visual Reasoning with LLM-Powered Knowledge Graphs (EnVR-LPKG) for the Surgical-VQLA task. This framework enhances the model's understanding of the surgical scenario by utilizing knowledge graphs of surgical instruments constructed by the Large Language Model (LLM). Specifically, we design a Fine-grained Knowledge Extractor (FKE) to extract the most relevant information from knowledge graphs and perform contrastive learning with the extracted knowledge graphs and local image. Furthermore, we design a Multi-attention-based Surgical Instrument Enhancer (MSIE) module, which employs knowledge graphs to obtain an enhanced representation of the corresponding surgical instrument in the global scene. Through the MSIE module, the model can learn how to fuse visual features with knowledge graph text features, thereby strengthening the understanding of surgical instruments and further improving visual reasoning capabilities. Extensive experimental results on the EndoVis-17-VQLA and EndoVis-18-VQLA datasets demonstrate that our proposed method outperforms other state-of-the-art methods. We will release our code for future research.
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.
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