Angelica I. Aviles-Rivero
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Angelica I. Aviles-Rivero has a total of 312 co-authors. Here are the top co-authors by number of shared publications:
- Carola-Bibiane Schönlieb
University of Cambridge, UK
30 shared publications Chun-Wun Cheng
University of Cambridge
9 shared publicationsCarola-Bibiane Schönlieb
University of Cambridge
7 shared publicationsSamar M. Alsaleh
Department of Computer Science George Washington University Washington DC U.S.A
7 shared publications- Alicia Casals
Universitat Politecnica de Catalunya
6 shared publications - Lihao Liu
University of Cambridge, Cambridge, United Kingdom
6 shared publications
Latest Publications
- 27 September 2026
- Published by Springer Nature
- p. 405-415
ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
- 27 September 2026
- Published by Springer Nature
- p. 405-415
ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
- 7 September 2026
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 68 (5) , 69
You KAN do it in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
- 7 September 2026
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 68 (5) , 69
You KAN do it in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
- 19 August 2026
- Published by IOP Publishing in Inverse Problems
- Vol. 42 (8) , 085010
Inertial proximal difference-of-convex algorithm with convergent Bregman plug-and-play for nonconvex imaging
Imaging tasks are typically tackled using a structured optimization framework. This paper delves into a class of algorithms for difference-of-convex (DC) structured optimization, focusing on minimizing a DC function along with a possibly nonconvex function. Existing DC algorithms (DCAs) often fail to effectively handle nonconvex functions or exhibit slow convergence rates, hindering us from incorporating deep priors with theoretical guarantees in image processing tasks. We propose a novel inertial proximal DCA in Bregman geometry, named iBPDCA, designed to address nonconvex terms and enhance convergence speed through inertial techniques. We provide a detailed theoretical analysis, establishing both subsequential and global convergence of iBPDCA via the Kurdyka–Łojasiewicz property. Additionally, we introduce a plug-and-play (PnP) variant, PnP-iBPDCA, which employs a deep neural network-based prior for greater flexibility and robustness while ensuring theoretical convergence. We also establish that the Gaussian gradient step denoiser used in our method is equivalent to evaluating the Bregman proximal operator for an implicitly weakly convex functional. We extensively validate our method on Rician noise and phase retrieval. We demonstrate that iBPDCA surpasses existing state-of-the-art methods.
- 19 August 2026
- Published by IOP Publishing in Inverse Problems
- Vol. 42 (8) , 085010
Inertial proximal difference-of-convex algorithm with convergent Bregman plug-and-play for nonconvex imaging
Imaging tasks are typically tackled using a structured optimization framework. This paper delves into a class of algorithms for difference-of-convex (DC) structured optimization, focusing on minimizing a DC function along with a possibly nonconvex function. Existing DC algorithms (DCAs) often fail to effectively handle nonconvex functions or exhibit slow convergence rates, hindering us from incorporating deep priors with theoretical guarantees in image processing tasks. We propose a novel inertial proximal DCA in Bregman geometry, named iBPDCA, designed to address nonconvex terms and enhance convergence speed through inertial techniques. We provide a detailed theoretical analysis, establishing both subsequential and global convergence of iBPDCA via the Kurdyka–Łojasiewicz property. Additionally, we introduce a plug-and-play (PnP) variant, PnP-iBPDCA, which employs a deep neural network-based prior for greater flexibility and robustness while ensuring theoretical convergence. We also establish that the Gaussian gradient step denoiser used in our method is equivalent to evaluating the Bregman proximal operator for an implicitly weakly convex functional. We extensively validate our method on Rician noise and phase retrieval. We demonstrate that iBPDCA surpasses existing state-of-the-art methods.
- Open Access
- 29 July 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 371
MammoDG: Generalisable Deep Learning Advances Cross-Domain Multi-Center Breast Cancer Screening
Breast cancer is a major cause of cancer death among women, emphasising the importance of early detection for improved treatment outcomes and quality of life. Mammography, the primary diagnostic imaging test, poses challenges due to the high variability and patterns in mammograms. Double reading of mammograms is recommended in many screening programmes to improve diagnostic accuracy but increases the workload for radiologists. Therefore, researchers have explored Machine Learning models to support expert decision-making. Stand-alone models have shown comparable or superior performance to radiologists, but some studies observe decreased sensitivity when facing multiple datasets and sites, indicating the need for highly generalisable and robust models. This work devises MammoDG, a novel deep-learning framework for generalisable, robust, and reliable analysis of cross-domain multi-center mammography data. MammoDG introduces a cross-channel cross-view enhancement module to conduct information interaction among multi-view mammograms. Additionally, an instance-level contrastive regularisation is designed to mitigate the distribution gap between multi-center data and thus enhance generalisation capabilities. Extensive validation demonstrates the superiority of MammoDG over existing models, highlighting the critical importance of domain generalisation for trustworthy mammography analysis in the presence of imaging protocol variations.
- 29 July 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 371
Open AccessMammoDG: Generalisable Deep Learning Advances Cross-Domain Multi-Center Breast Cancer Screening
Breast cancer is a major cause of cancer death among women, emphasising the importance of early detection for improved treatment outcomes and quality of life. Mammography, the primary diagnostic imaging test, poses challenges due to the high variability and patterns in mammograms. Double reading of mammograms is recommended in many screening programmes to improve diagnostic accuracy but increases the workload for radiologists. Therefore, researchers have explored Machine Learning models to support expert decision-making. Stand-alone models have shown comparable or superior performance to radiologists, but some studies observe decreased sensitivity when facing multiple datasets and sites, indicating the need for highly generalisable and robust models. This work devises MammoDG, a novel deep-learning framework for generalisable, robust, and reliable analysis of cross-domain multi-center mammography data. MammoDG introduces a cross-channel cross-view enhancement module to conduct information interaction among multi-view mammograms. Additionally, an instance-level contrastive regularisation is designed to mitigate the distribution gap between multi-center data and thus enhance generalisation capabilities. Extensive validation demonstrates the superiority of MammoDG over existing models, highlighting the critical importance of domain generalisation for trustworthy mammography analysis in the presence of imaging protocol variations.
- 14 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 328
MF2MR2: Multi-frequency fusion for accelerated multi-contrast MRI reconstruction
- 14 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 328
MF2MR2: Multi-frequency fusion for accelerated multi-contrast MRI reconstruction
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 3550-3565
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
n 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 ( 4 x and 8 x ) 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.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 3550-3565
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
n 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 ( 4 x and 8 x ) 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.
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 5450-5460
Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
Recent research in Vision-Language Models (VLMs) has significantly advanced our capabilities in cross-modal reasoning. However, existing methods suffer from performance degradation with domain changes or require substantial computational resources for fine-tuning in new domains. To address this issue, we develop a new adaptation method for large vision-language models, called Training-free Dual Hyperbolic Adapters (T-DHA). We characterize vision-language relationship between semantic concepts, which typically has a hierarchical tree structure, in the hyperbolic space instead of the traditional Euclidean space. Hyperbolic spaces exhibit exponential volume growth with radius, unlike the polynomial growth in Euclidean space. We find that this unique property is particularly effective for embedding hierarchical data structures using the Poincaré ball model, achieving significantly improved representation and discrimination power. Coupled with negative learning, it provides more accurate and robust classifications with fewer feature dimensions. Our extensive experimental results on various datasets demonstrate that the T-DHA method significantly outperforms existing state-of-the-art methods in few-shot image recognition and domain generalization tasks.
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 5450-5460
Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
Recent research in Vision-Language Models (VLMs) has significantly advanced our capabilities in cross-modal reasoning. However, existing methods suffer from performance degradation with domain changes or require substantial computational resources for fine-tuning in new domains. To address this issue, we develop a new adaptation method for large vision-language models, called Training-free Dual Hyperbolic Adapters (T-DHA). We characterize vision-language relationship between semantic concepts, which typically has a hierarchical tree structure, in the hyperbolic space instead of the traditional Euclidean space. Hyperbolic spaces exhibit exponential volume growth with radius, unlike the polynomial growth in Euclidean space. We find that this unique property is particularly effective for embedding hierarchical data structures using the Poincaré ball model, achieving significantly improved representation and discrimination power. Coupled with negative learning, it provides more accurate and robust classifications with fewer feature dimensions. Our extensive experimental results on various datasets demonstrate that the T-DHA method significantly outperforms existing state-of-the-art methods in few-shot image recognition and domain generalization tasks.
- Open Access
Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals. However, most existing methods rely on functional connectivity (FC) via Pearson correlation, which reduces 4D BOLD signals to static 2D matrices, discarding temporal dynamics and capturing only linear inter-regional relationships. In this work, we benchmark state-of-the-art temporal models (e.g., time-series models such as PatchTST, TimesNet, and TimeMixer) on raw BOLD signals across five public datasets. Results show these models consistently outperform traditional FC-based approaches, highlighting the value of directly modeling temporal information such as cycle-like oscillatory fluctuations and drift-like slow baseline trends. Building on this insight, we propose DeCI, a simple yet effective framework that integrates two key principles: (i) Cycle and Drift Decomposition to disentangle cycle and drift within each ROI (Region of Interest); and (ii) Channel-Independence to model each ROI separately, improving robustness and reducing overfitting. Extensive experiments demonstrate that DeCI achieves superior classification accuracy and generalization compared to both FC-based and temporal baselines. Our findings advocate for a shift toward end-to-end temporal modeling in fMRI analysis to better capture complex brain dynamics. The code is available at https://github.com/Levi-Ackman/DeCI.
Open AccessMoving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals. However, most existing methods rely on functional connectivity (FC) via Pearson correlation, which reduces 4D BOLD signals to static 2D matrices, discarding temporal dynamics and capturing only linear inter-regional relationships. In this work, we benchmark state-of-the-art temporal models (e.g., time-series models such as PatchTST, TimesNet, and TimeMixer) on raw BOLD signals across five public datasets. Results show these models consistently outperform traditional FC-based approaches, highlighting the value of directly modeling temporal information such as cycle-like oscillatory fluctuations and drift-like slow baseline trends. Building on this insight, we propose DeCI, a simple yet effective framework that integrates two key principles: (i) Cycle and Drift Decomposition to disentangle cycle and drift within each ROI (Region of Interest); and (ii) Channel-Independence to model each ROI separately, improving robustness and reducing overfitting. Extensive experiments demonstrate that DeCI achieves superior classification accuracy and generalization compared to both FC-based and temporal baselines. Our findings advocate for a shift toward end-to-end temporal modeling in fMRI analysis to better capture complex brain dynamics. The code is available at https://github.com/Levi-Ackman/DeCI.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (6) , 2764-2779
Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals. However, most existing methods rely on functional connectivity (FC) via Pearson correlation, which reduces 4D BOLD signals to static 2D matrices—discarding temporal dynamics and capturing only linear inter-regional relationships. In this work, we benchmark state-of-the-art temporal models (e.g., time-series models: PatchTST, TimesNet, TimeMixer) on raw BOLD signals across five public datasets. Results show these models consistently outperform traditional FC-based approaches, highlighting the value of directly modeling temporal information such as cycle-like oscillatory fluctuations and drift-like slow baseline trends. Building on this insight, we propose DeCI, a simple yet effective framework that integrates two key principles: (i) Cycle and Drift Decomposition to disentangle cycle and drift within each ROI (Region of Interest); and (ii) Channel-Independence to model each ROI separately, improving robustness and reducing overfitting. Extensive experiments demonstrate that DeCI achieves superior classification accuracy and generalization compared to both FC-based and temporal baselines. Our findings advocate for a shift toward end-to-end temporal modeling in fMRI analysis to better capture complex brain dynamics. The code is available at https://github.com/Levi-Ackman/DeCI.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (6) , 2764-2779
Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals. However, most existing methods rely on functional connectivity (FC) via Pearson correlation, which reduces 4D BOLD signals to static 2D matrices—discarding temporal dynamics and capturing only linear inter-regional relationships. In this work, we benchmark state-of-the-art temporal models (e.g., time-series models: PatchTST, TimesNet, TimeMixer) on raw BOLD signals across five public datasets. Results show these models consistently outperform traditional FC-based approaches, highlighting the value of directly modeling temporal information such as cycle-like oscillatory fluctuations and drift-like slow baseline trends. Building on this insight, we propose DeCI, a simple yet effective framework that integrates two key principles: (i) Cycle and Drift Decomposition to disentangle cycle and drift within each ROI (Region of Interest); and (ii) Channel-Independence to model each ROI separately, improving robustness and reducing overfitting. Extensive experiments demonstrate that DeCI achieves superior classification accuracy and generalization compared to both FC-based and temporal baselines. Our findings advocate for a shift toward end-to-end temporal modeling in fMRI analysis to better capture complex brain dynamics. The code is available at https://github.com/Levi-Ackman/DeCI.
- Open Access
SpectraKAN: Conditioning Spectral Operators
Spectral neural operators, particularly Fourier Neural Operators (FNO), are a powerful framework for learning solution operators of partial differential equations (PDEs) due to their efficient global mixing in the frequency domain. However, existing spectral operators rely on static Fourier kernels applied uniformly across inputs, limiting their ability to capture multi-scale, regime-dependent, and anisotropic dynamics governed by the global state of the system. We introduce SpectraKAN, a neural operator that conditions the spectral operator on the input itself, turning static spectral convolution into an input-conditioned integral operator. This is achieved by extracting a compact global representation from spatio-temporal history and using it to modulate a multi-scale Fourier trunk via single-query cross-attention, enabling the operator to adapt its behaviour while retaining the efficiency of spectral mixing. We provide theoretical justification showing that this modulation converges to a resolution-independent continuous operator under mesh refinement and KAN gives smooth, Lipschitz-controlled global modulation. Across diverse PDE benchmarks, SpectraKAN achieves state-of-the-art performance, reducing RMSE by up to 49% over strong baselines, with particularly large gains on challenging spatio-temporal prediction tasks.
Open AccessSpectraKAN: Conditioning Spectral Operators
Spectral neural operators, particularly Fourier Neural Operators (FNO), are a powerful framework for learning solution operators of partial differential equations (PDEs) due to their efficient global mixing in the frequency domain. However, existing spectral operators rely on static Fourier kernels applied uniformly across inputs, limiting their ability to capture multi-scale, regime-dependent, and anisotropic dynamics governed by the global state of the system. We introduce SpectraKAN, a neural operator that conditions the spectral operator on the input itself, turning static spectral convolution into an input-conditioned integral operator. This is achieved by extracting a compact global representation from spatio-temporal history and using it to modulate a multi-scale Fourier trunk via single-query cross-attention, enabling the operator to adapt its behaviour while retaining the efficiency of spectral mixing. We provide theoretical justification showing that this modulation converges to a resolution-independent continuous operator under mesh refinement and KAN gives smooth, Lipschitz-controlled global modulation. Across diverse PDE benchmarks, SpectraKAN achieves state-of-the-art performance, reducing RMSE by up to 49% over strong baselines, with particularly large gains on challenging spatio-temporal prediction tasks.