Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleKe Z, Xu S, Wang G, et al., 2026,
SAFE-Det: Scale-Adaptive Feature Enhancement for Remote Sensing Small-Object Detection
, IEEE Geoscience and Remote Sensing Letters, Vol: 23, ISSN: 1545-598XDue to the minuscule size of objects and the presence of background noise in remote sensing images, the object detection in such images remains a challenging task. In an effort to enhance the detection accuracy of small objects, this letter proposes a novel scale-adaptive feature enhancement detection (SAFE-Det) framework named SAFE-Det. This framework is specifically designed for small-object detection in remote sensing images. SAFE-Det utilizes the residual connections and a multiscale parallel attention downsample (MPAD) module to dynamically preserve the features of small objects, thereby reducing the information loss. Moreover, it incorporates an adaptive perception core (APC) model that combines a triple-branch pyramid attention (TBPA) and microtarget augmentation (MTA). This module aims to highlight small objects while suppressing the background noise. In addition, SAFE-Det features a specialized small-object detection head that leverages high-resolution shallow features, thus overcoming the limitations of conventional methods. Experimental results on the VisDrone2019 and VEDAI datasets indicate that SAFE-Det achieves an mAP@0.5 of 41.3% and 73.0%, respectively. These results represent respective improvements of 7.9% and 6.7% over baseline models. Codes are available at: https://github.com/xjh1017/Reunion
-
Conference paperZhang Z, Lee K, Jing P, et al., 2026,
GEMA-Score: Granular Explainable Multi-Agent Scoring Framework for Radiology Report Evaluation
, Pages: 13025-13033, ISSN: 2159-5399Automatic medical report generation has the potential to support clinical diagnosis, reduce the workload of radiologists, and demonstrate potential for enhancing diagnostic consistency. However, current evaluation metrics often fail to reflect the clinical reliability of generated reports. Overlap-based methods overlook fine-grained details (e.g., location, sever-ity), diagnostic metrics are constrained by fixed vocabularies. Some diagnostic metrics are limited by fixed vocabularies or templates, reducing their ability to capture diverse clinical expressions. LLM-based metrics lack interpretable reasoning, limiting trust in clinical settings. Therefore, we propose a Granular Explainable Multi-Agent Score (GEMA-Score) in this paper, which conducts both objective quantification and subjective evaluation through a large language model-based multi-agent workflow. Our GEMA-Score parses structured reports and employs stable calculations through interactive exchanges of information among agents to assess disease diagnosis, location, severity, and uncertainty. Additionally, an LLM-based scoring agent evaluates completeness, readability, and clinical terminology while providing explanatory feedback. Extensive experiments show that GEMA-Score achieves the highest correlation with human experts on public datasets (Kendall = 0.69 on ReXVal; 0.45 on RadEvalX), demonstrating improved clinical scoring reliability.
-
Journal articleHalliday BP, Owen R, Ragavan A, et al., 2026,
A double-blind, randomized placebo-controlled trial examining the effect of MitoQ on myocardial energetics in patients with dilated cardiomyopathy
, European Heart Journal-Cardiovascular Imaging, Vol: 27, Pages: 74-77, ISSN: 2047-2404 -
Conference paperWang S, Fang Y, Li Y, et al., 2026,
ILLUMINATING UNCERTAINTY: A TRIFOCAL FINE-GRAINED AND TRANSFORMER-LIKE AXIAL ATTENTION FRAMEWORK FOR PULMONARY VASCULAR SEGMENTATION
, ISSN: 1945-7928Pulmonary artery segmentation has recently emerged as a novel biomarker for lung diseases, necessitating accurate and efficient automatic segmentation methods. However, in none contrast enhanced CT (NECT) scans, the low tissue contrast poses a persistent challenge for accurately delineating multibranch structures and small pulmonary arteries, particularly in complex pulmonary conditions. In this work, we introduce IFSAttUNet, a trifocal fine-grained attention framework enhanced by transformer-like triple-axis multi-head attention. This method provides an explicit measure for 'uncertain' or 'hard-to-recognize' regions, thereby guiding the network's focus toward artery boundaries. Moreover, IFSAttUNet features a lightweight architecture capable of capturing global dependencies effectively. Our empirical results demonstrate that IFSAttUNet outperforms state-of-the-art Gaussian-based fuzzy attention and transformer based models, offering a promising avenue for robust pulmonary vascular analysis.
-
Conference paperHasan MK, Yang G, Yap CH, 2026,
Motion-Enhanced Cardiac Anatomy Segmentation via an Insertable Temporal Attention Module
, Pages: 143-153, ISSN: 0302-9743Cardiac anatomy segmentation is useful for clinical assessment of cardiac morphology to inform diagnosis and intervention. Deep learning (DL), especially with motion information, has improved segmentation accuracy. However, existing techniques for motion enhancement are not yet optimal, and they have high computational costs due to increased dimensionality or reduced robustness due to suboptimal approaches that use non-DL motion registration, non-attention models, or single-headed attention. They further have limited adaptability and are inconvenient for incorporation into existing networks where motion awareness is desired. Here, we propose a novel, computationally efficient Temporal Attention Module (TAM) that offers robust motion enhancement, modeled as a small, multi-headed, cross-temporal attention module. TAM’s uniqueness is that it is a lightweight, plug-and-play module that can be inserted into a broad range of segmentation networks (CNN-based, Transformer-based, or hybrid) for motion enhancement without requiring substantial changes in the network’s backbone. This feature enables high adaptability and ease of integration for enhancing both existing and future networks. Extensive experiments on multiple 2D and 3D cardiac ultrasound and MRI datasets confirm that TAM consistently improves segmentation across a range of networks while maintaining computational efficiency and improving on currently reported performance. The evidence demonstrates that it is a robust, generalizable solution for motion-awareness enhancement that is scalable (such as from 2D to 3D). The code is available at https://github.com/kamruleee51/TAM.
-
Journal articleWang N, Jin W, Bi H, et al., 2026,
RectMamba: Exploring state space models with entropy-divergence framework for noisy label rectification
, Neurocomputing, Vol: 663, Pages: 131998-131998, ISSN: 0925-2312 -
Journal articleYu Q, Zhang C, Jin G, et al., 2026,
StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors.
, IEEE Trans Image Process, Vol: 35, Pages: 1290-1304Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive patient information. As a result, well-trained medical segmentation models on private datasets constitute valuable intellectual property requiring robust protection mechanisms. Existing model protection techniques primarily focus on classification and generative tasks, while segmentation models-crucial to medical image analysis-remain largely underexplored. In this paper, we propose a novel, stealthy, and harmless method, StealthMark, for verifying the ownership of medical segmentation models under closed-box conditions. Our approach subtly modulates model uncertainty without altering the final segmentation outputs, thereby preserving the model's performance. To enable ownership verification, we incorporate model-agnostic explanation methods, e.g. LIME, to extract feature attributions from the model outputs. Under specific triggering conditions, these explanations reveal a distinct and verifiable watermark. We further design the watermark as a QR code to facilitate robust and recognizable ownership claims. We conducted extensive experiments across four medical imaging datasets (CMR dataset from UK Biobank, the SEG fundus dataset, the EchoNet echocardiography dataset, and the PraNet colonoscopy dataset) and five mainstream segmentation models. The results demonstrate the effectiveness, stealthiness, and harmlessness of our method on the original model's segmentation performance. For example, when applied to the SAM model, StealthMark consistently achieved attack success rates (ASR) above 95% across various datasets while maintaining less than a 1% drop in Dice and AUC scores-significantly outperforming backdoor-based watermarking methods and highlighting its strong potential for practical deployment. Our implementation code is made
-
Journal articleZhang Z, Zhang L, Cheng Y, et al., 2026,
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction.
, IEEE Trans Image Process, Vol: 35, Pages: 3550-3565In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially under accelerated acquisitions or patient motion. However, this task remains challenging due to hierarchical structural disruptions. It includes local detail loss from k-space undersampling, global structural aliasing caused by motion, and volumetric anisotropy. Therefore, we propose a progressive refinement implicit neural representation (PR-INR) framework. Our PR-INR unifies motion correction, structural refinement, and volumetric synthesis within a geometry-aware coordinate space. Specifically, a motion-aware diffusion module is first employed to generate coarse volumetric reconstructions that suppress motion artifacts and preserve global anatomical structures. Then, we introduce an implicit detail restoration module that performs residual refinement by aligning spatial coordinates with visual features. It corrects local structures and enhances boundary precision. Further, a voxel continuous-aware representation module represents the image as a continuous function over 3D coordinates. It enables accurate inter-slice completion and high-frequency detail recovery. We evaluate PR-INR on five public MRI datasets under various motion conditions (3% and 5% displacement), undersampling rates (4x and 8x) and slice resolutions (scale = 5). Experimental results demonstrate that PR-INR outperforms state-of-the-art methods in both quantitative reconstruction metrics and visual quality. It further shows generalization and robustness across diverse unseen domains.
-
Journal articleGeng C, Jiang M, Ruan D, et al., 2026,
TTP-SSFL: Test-Time Personalization Self-Supervised Federated Learning for Accelerating MR Image Reconstruction
, IEEE Transactions on Neural Networks and Learning Systems, Pages: 1-12, ISSN: 2162-237X -
Journal articleMarkus JE, Cristinacce PLH, Punwani S, et al., 2025,
Steps on the Path to Clinical Translation-A British and Irish Chapter ISMRM Workshop Survey of the UK MRI Community
, MAGNETIC RESONANCE IN MEDICINE, ISSN: 0740-3194
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