The 29th edition of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) took place in Strasbourg, France, from the 27th of September to the 1^st of  October 2026. The conference brings together international researchers, engineers and clinicians working at the intersection of artificial intelligence, medical imaging and biomedical engineering.

Several members of ViCOROB participated in this year’s edition, contributing to scientific presentations and activities within the international research community. Their participation covered different aspects of medical image computing, from automated lesion detection to research on medical image simulation and synthesis.

Automated skin lesion detection

Anup Saha presented the work entitled “Automated Skin Lesion Detection in Total Body Photography: A Multi-Architecture Benchmark” (Yamin, M. et al.) as a spotlight, at the ISIC workshop held in conjunction with MICCAI 2026.

The study is part of the European project iToBoS (Intelligent Total Body Scanner for Early Detection of Melanoma), coordinated by Prof. Rafael Garcia (ViCOROB). It addresses the automated detection of skin lesions in total body photography, an approach that involves analysing images covering the entire body to support the assessment of skin lesions. The research compares different model architectures to evaluate their performance in this task.

Contributions to the international research community

ViCOROB’s participation also involved scientific activities beyond the presentation of research findings, including contributions to conference sessions and initiatives within the MICCAI community.

Mariano Cabezas Grebol served as Session Chair for the 05A oral session titled Image Segmentation III from the main conference. The session focused on different segmentation approaches, including contributions based on foundation models. Together with Neslihan Bayramoglu, they introduced all 5 speakers and mediated during the Q&A after the presentation. He was also part of the organizing committee for the Ischemic Stroke Lesion Segmentation Challenge (ISLES’26), which focuses on the segmentation of lesions associated with ischaemic stroke and was held on the first day of the satellite events. During the satellite events, he also volunteered with the RISE ambassador program to present two posters for authors that could not attend the conference.

Adrià Casamitjana Díaz was a member of the organising committee for the 11th edition of the Simulation and Synthesis in Medical Imaging (SASHIMI) workshop, which focuses on research into the simulation and synthesis of medical images. A total of 36 out of 57 outstanding contributions were presented during the workshop, with focus on advances in image-to-image translation and image synthesis as well as discussion on the downstream applications of generative models.

Scientific posters and ongoing research

Poster sessions provided an additional opportunity to present research and exchange ideas with the international scientific community. Hasna R. Hamadache, Agustin Cartaya Lathulerie and Hadeel Awwad presented posters showcasing their ongoing research.

– A. Cartaya et al., Latent Conditional Rectified Flow for MRI Synthesis Across Modalities and Field Strengths in the MRIxFields2026 Challenge.
This work explores the consistent translation across scanners of different quality, improving the generalizability of downstream tasks such as image segmentation across hospitals.

– R.E. Hamadache et al., nnU-Net and Domain Randomization for Automated Segmentation of Moderate-to-Severe Traumatic Brain Injury.
This work studies the use of synthetic data to complement real cases in small sample size studies, improving the performance in small lesion detection.

Advancing research in medical image computing

The presence and active participation of ViCOROB members at MICCAI 2026, the leading international conference on medical image computing, reflects the quality of research conducted in our group. It has provided a unique opportunity to network, exchange ideas, and connect with frontier research labs in the field.

The current focus of the community is on learning robust and generalizable representations that deliver practical clinical value. This aligns closely with our work at ViCOROB: building generalizable normative models, leveraging domain randomization and image synthesis to train robust segmentation and registration architectures, and integrating longitudinal data to enrich clinical findings. As the MICCAI community gradually shifts toward world models, ViCOROB is well positioned to lead and contribute to this evolving paradigm.

The post ViCOROB presents its research in medical image computing at MICCAI 2026 appeared first on Vicorob.

By: Ricardo Montoya del Angel
Supervised by:  Dr. Robert Martí Marly

Thesis Overview

Artificial intelligence (AI) holds high potential for automated medical diagnosis, but relies heavily on vast, well-annotated datasets. In specialized fields like Contrast-Enhanced Mammography (CEM) or point-of-care echocardiography, data scarcity remains a critical bottleneck for clinical deployment. This thesis investigates probabilistic generative modeling strategies to synthesize realistic, clinically valid medical data across three levels of complexity:

1. Physically-Informed Uncertainty: Maps acquisition and annotation uncertainties into bounded generative variance, enhancing radiomic biomarker prediction in small CEM cohorts.
2. Controllable Mammography Synthesis: Leverages latent diffusion models for full-field synthesis and localized lesion inpainting, transferring knowledge to data-scarce CEM.
3. Efficient Video Synthesis: Combines 1D tokenization and masked transformers to reconstruct missing echocardiographic views (2-chamber from 4-chamber), enabling Ejection Fraction estimation on portable ultrasound devices.

The findings support the idea that synthetic data generated with physical and clinical rigor effectively overcomes clinical data constraints, enhancing diagnostic accuracy and decision support in clinical practice.

Photo: Illustration of the research developed in the doctoral thesis on generative modeling for medical data synthesis.

The post Doctoral Thesis: Advances in Generative Modeling for Medical Data: Applications in Imaging, Video, and Multimodal Synthesis. appeared first on Vicorob.

Thesis Overview

Brain pathology analysis through medical imaging is critical for clinical diagnosis, treatment planning, and patient outcome prediction. Computed tomography (CT) and magnetic resonance imaging (MRI) have become essential imaging modalities for assessing two major classes of brain pathologies: intracranial hemorrhage (ICH) and brain tumors. However, manual interpretation and analysis of these imaging studies are time-consuming, labor-intensive, and susceptible to intra- and interobserver variability. In recent years, artificial intelligence-based methods have shown great potential in automating the detection, segmentation, and quantification of brain lesions, thereby supporting clinical workflows and improving diagnostic accuracy. Nevertheless, these methods typically rely on large amounts of annotated data to achieve high performance. In medical imaging, obtaining such annotations is particularly challenging due to the need for expert knowledge, as well as the significant time and economic costs associated with manual labeling. As a result, while vast amounts of medical imaging data are routinely acquired in clinical practice, only a small fraction is accompanied by high-quality annotations. This imbalance highlights the need for approaches that can effectively leverage limited labeled data, motivating the development of learning strategies under limited supervision.

The main goal of this PhD thesis is to develop robust deep learning methodologies for neuroimaging analysis under limited supervision. To address annotation scarcity, we explore several complementary strategies. In the first stage, we propose a framework for hematoma expansion (HE) prediction in spontaneous intracerebral hemorrhage (ICH) using baseline CT scans. This approach combines a classification model with synthetic CT image generation to enhance robustness and alleviate data limitations. Our results show that integrating synthetic data with conventional augmentation improves both predictive performance and generalization. In the second stage, we develop semi-supervised deep learning frameworks that leverage both labeled and unlabeled data for binary brain lesion segmentation in brain tumors and spontaneous ICHs. We introduce a novel method that combines feature perturbation with mutual learning, achieving significant improvements in low-annotation settings (10–20% labeled data). In the third stage, we extend semi-supervised learning to multi-class hemorrhage segmentation, a more complex task requiring the differentiation of multiple hemorrhage subtypes. We conduct a comprehensive benchmark of established semi-supervised methods within a unified nnUNet framework, providing a systematic evaluation of different strategies for this setting.

All proposed methodologies are evaluated on both institutional datasets from collaborating hospitals and public international benchmarks, enabling objective comparison with state-of-the-art approaches. Notably, this work was carried out in close collaboration with the medical team at Hospital Dr. Josep Trueta, with clinical expertise integrated throughout the research process from problem formulation and data acquisition to result interpretation and validation. By combining deep learning techniques with clinical insight, this thesis aims to deliver practical tools that support clinical decision-making and ultimately improve patient care in brain tumors and ICHs. Emphasis is placed on reproducibility and clinical applicability, with all methods and experimental pipelines made publicly available to facilitate future research and the development of reliable automated decision-support systems.

The post Doctoral Thesis: Deep Learning Methods with Limited Supervision for Brain Pathology Analysis in Neuroimaging appeared first on Vicorob.

The delegation from the Medical Imaging Lab included Dr. Robert Martí, who served as a member of the workshop committee and chaired a scientific session, alongside PhD candidates Hadeel Awwad and Enric Sena. The workshop provided a valuable platform for the team to engage with international imaging peers, including newly onboarding researchers like Enric.

The work presented falls under the framework of the IMPACT project, which leverages deep learning to drive innovation in image analysis, optimize lesion detection, and advance treatment response prediction to promote personalized healthcare outcomes.

PhD candidate Hadeel Awwad presented a poster detailing preliminary results on predicting pathologic complete response (pCR) from Breast MRI using the multi-centre MAMA-MIA dataset. To find the configuration with the highest discriminative power, the study conducted a systematic evaluation of 78 different radiomics configurations spanning spatial regions—specifically comparing the primary tumour and a peritumoural ring—as well as temporal representations and mathematical transforms.

The preliminary findings revealed that simple, dynamic, first-order peritumoural signals consistently achieved the highest classification accuracy, outperforming static or purely intratumoural features. These results justify integrating these localized temporal variables into future comprehensive models to improve treatment response prediction.

Beyond the scientific presentations, the workshop served as an excellent venue for strengthening ties within the international breast imaging community. The team took advantage of the event to establish new collaborations and lay the groundwork for future joint research initiatives with European and international partners.

This work has been funded by the IMPACT project from the Ministerio de Ciencia e Innovación y Universidades of Spain, and the PhD grant IFUdG2024 from the University of Girona.

The post Latest breast MRI research from ViCOROB featured at IWBI 2026 appeared first on Vicorob.

Thesis Overview

This PhD thesis focuses on the development of artificial intelligence methods based on deep learning for the analysis of brain images and, ultimately, to help improve the diagnosis and treatment of common neurological diseases such as stroke and meningioma.

Stroke is one of the leading causes of death and disability worldwide. It can be either ischemic or hemorrhagic, and in both cases the diagnosis relies on brain imaging examinations, most commonly computed tomography (CT). Meningioma, on the other hand, is the most common primary brain tumor. It is often detected and monitored through periodic magnetic resonance imaging (MRI) examinations, and when treatment is required, especially radiotherapy, treatment planning is based on these images to accurately define the area to be irradiated. Therefore, medical imaging is a key tool throughout all stages of the clinical management of these diseases.

In this context, this thesis explores how deep learning can make different steps of the clinical workflow more efficient and accurate. First, a method is proposed to predict the possible evolution of intracerebral hemorrhage in patients with hemorrhagic stroke using only the initial available CT scan. One of the main challenges is the limited availability of clinical data, and therefore a strategy is also proposed to generate synthetic examples simulating possible lesion evolutions. These synthetic images are used to train the model and improve its predictive capability, achieving competitive results compared with state-of-the-art methods.

Second, a system is developed to detect large vessel occlusions, one of the main causes of ischemic stroke, from CT angiography images, and to identify the affected vascular segment. The method focuses on a specific anatomical region, the Circle of Willis, which contains the most relevant vessels. This allows the analysis to be simplified, the process to be accelerated, and a high level of reliability to be maintained. The results have been validated using real hospital data and independent test sets, demonstrating good generalization capability.

Third, a method is presented for the segmentation of meningioma tumors in MRI images used for radiotherapy planning. The main contribution is a richer representation of the tumor, which considers not only the lesion itself but also its transition zone. This additional information improves segmentation accuracy and achieves better results, even in comparison with other recent approaches. The method was evaluated and validated in an international challenge, where it achieved first place.

Overall, this thesis demonstrates how artificial intelligence can contribute to making brain image analysis more automated, accurate, and efficient. An important part of the work was carried out in collaboration with the medical team at Hospital Dr. Josep Trueta, integrating real clinical knowledge throughout all stages of the project. The ultimate goal is to provide tools that can have a direct impact on clinical practice and contribute to improving the care of patients with stroke and brain tumors.

The post Doctoral Thesis: Deep Learning for Clinical Decision Support in Brain Tumors and Stroke appeared first on Vicorob.

Abstract:

This PhD thesis focuses on the development of deep learning methods to enhance medical image analysis, with a particular emphasis on improving focus, efficiency and fairness in acute ischemic stroke (AIS). AIS is a cerebrovascular disease that occurs when a cerebral artery becomes occluded, interrupting blood flow to part of the brain. Rapid diagnosis and treatment of AIS are essential to preserving salvageable tissue and minimizing long-term disability. However, not all patients benefit equally from current therapies despite similar clinical and procedural characteristics. Accurately identifying patients likely to benefit remains a major clinical challenge. In this context, neuroimaging, particularly brain Computed Tomography Angiography (CTA), plays a central role in patient triage during the acute stroke phase. The rich anatomical and vascular information present in CTA offers a valuable but complex input for automated image analysis, motivating the use of deep learning to support clinical decision-making.

This thesis explores strategies to fully utilize CTA data using deep learning methods tailored for AIS. The first contribution proposes strategies to guide neural networks toward vascular structures extracted from CTA while retaining contextual parenchymal information. Several methods to combine vascular segmentations and CTA data are evaluated, including an attention-inspired mechanism designed to enhance the model’s focus on clinically relevant features for AIS due to large vessel occlusion (LVO) detection. The second contribution introduces Learnable 3D Pooling (L3P), a novel convolutional neural network-based module that compresses
3D medical images into 2D feature maps, enabling efficient, lightweight, and interpretable models. L3P-based architectures are validated across multiple tasks, including LVO detection in CTA, as well as brain age prediction from 3D T1-weighted MRI. In all cases, L3P maintains competitive performance compared to fully 3D networks, while significantly reducing computational demands and enhancing feature interpretability. The third contribution addresses the issue of hidden confounders in medical imaging pipelines. A controlled experimental framework is proposed to simulate and analyze the effects of confounding variables in clinically relevant classification tasks. Using large ensembles of bootstrapped models, measurable distributional patterns, such as inflated model performance, reduced performance variability and convergence of training and validation metrics, are identified as indicators of confounder-driven learning. This enables the development of a practical, unsupervised method to flag potential hidden biases, even when the nature of the confounder is unknown.

The proposed approaches are broadly applicable across medical imaging modalities and disease domains, with particular relevance to neuroimaging. Designed with generalizability in mind, these methods have demonstrated utility beyond stroke, highlighting their potential for diverse clinical contexts. Collectively, the contributions of this thesis advance the development of deep learning tools with efficiency, focus, and fairness.

The complete doctoral thesis can be consulted in the official PhD repository of the University of Girona (DUGi-doc):  https://dugi-doc.udg.edu

The post Doctoral Thesis: Deep Learning for Stroke Imaging: Enhancing Focus, Efficiency, and Fairness appeared first on Vicorob.

Abstract:

Skin cancer remains one of the most prevalent and deadly forms of cancer worldwide, with melanoma alone accounting for over 330,000 new cases and nearly 60,000 deaths in 2022. Early detection is critical, as survival rates drop dramatically from 99% to just 30% once the cancer has metastasized.

This thesis was conducted within the Computer Vision and Robotics (VICOROB) group and the European Union iToBoS project. It advances AI-driven tools for skin cancer diagnosis with a focus on clinical and dermoscopic image analysis to support a two-tiered screening workflow.

In the iToBoS diagnostic pipeline, first a full-body scan is performed to capture clinical images of all visible skin lesions. Then, dermoscopic images are acquired
for lesions identified as suspicious during the initial clinical assessment, allowing a more detailed examination.

The presented research contributes to the workflow and advances the field through four key contributions. First, we review clinical image-based diagnosis, identifying successful methods and unresolved challenges, then deploy a pre-trained model for clinical image classification. Second, we design compact deep learning models for real-time dermoscopic melanoma detection by integrating attention mechanisms to improve accuracy while reducing computational costs. Third, we expand the dermoscopic diagnosis to include other types of skin cancer and enhance performance through clinically structured labeling. The resulting ensemble model outperforms existing approaches while balancing sensitivity and specificity for realworld use. Finally, we integrate vision-language models to provide dermoscopiclevel explainability, ensuring transparent and interpretable diagnoses.

Together, these contributions enable accurate, scalable, and clinically viable skin cancer detection systems across two imaging modalities with the final objective of improving patient outcomes and reducing mortality rate.

The post Doctoral Thesis: Development of Intelligent Systems for Skin Cancer Diagnosis appeared first on Vicorob.

Abstract:

Locating an Autonomous Underwater Vehicle (AUV) is a complex problem since most of the common sensors applied in ground or aerial robotics experience a significant reduction in their capabilities underwater due to the strong attenuation of electromagnetic waves
within the water. Conventional underwater navigators use acoustic positioning systems that share information through water. However, the deployment of these systems is costly. A more inexpensive option is to fuse the AUV proprioceptive measurements with the measurements of the robot surroundings, solving the Simultaneous Localization and Mapping (SLAM) problem. Although during the last decades a great research effort has been made on this problem,
some fundamental questions concerning its formulation remain open. Aspects such as using Lie groups to model robot poses, applying a factor graph to model the joint probability distribution of the problem, developing an online solver algorithm, or reaching a tightly coupled
estimation have not found a consensus until recent years.

To enhance the surveying capabilities of an AUV, this thesis focuses on the development of a state-of-the-art AUV navigator, transferring recent findings from generalist robotics to the underwater field. Thus, a tightly coupled and graph-based underwater navigator is proposed that properly applies Lie algebra when necessary. The navigator is based on acoustic range sensors that provide point cloud measurements of the robot’s surroundings.

The main contributions of this thesis are two, properly presented in the four articles that form this document. The first one is the development of a scan matching algorithm based on Gaussian Mixture Models (GMMs) to represent the sensor noise projected to the scan that
returns the uncertainty associated with the alignment result, an essential metric in SLAM problems. In addition, the Bayesian-GMM algorithm is first introduced to learn a GMM from a point cloud. The second main contribution of this thesis is the development of an algorithm to jointly preintegrate Inertial Measurement Unit (IMU) and Doppler Velocity Log (DVL) measurements to reach a tightly coupled estimation in an underwater Graph SLAM problem. Moreover, it allows compensating the preintegrated measurement from the Earth rotation
rate measured by high grade IMUs. Both algorithms are formulated considering Lie algebra to properly manipulate robot states and sensor measurements, introducing the SEN(3) group to jointly preintegrate IMU and DVL measurements.

Finally, this thesis also includes field experiments that prove the performance of the two proposed underwater navigators, one applying a Mechanical Profiling Sonar (MPS) and the other using a Mechanical Scanning MultiBeam EchoSounder (MS-MBES). The software architecture developed to implement both navigators is also presented, which provides a graphbased navigation framework to implement other navigators applying other sensor modalities.

The post Doctoral Thesis: Graph-based underwater localization techniques considering a rigorous on Lie group formulation appeared first on Vicorob.

Valerio presented the paper titled “Collision Avoidance with Adaptive Potential Fields for Underwater Vehicles Using Omnidirectional Vision”. The work, co-authored by Aurora Bottino (a Master student from Università degli Studi di Genova, Italy), and members of our research group Eduardo Ochoa, Rafael Garcia and Nuno Gracias, was accepted to the main technical session. It presents an algorithm designed to provide access to remotely operated underwater vehicles (ROVs) to any non-skilled human operator. Moving an underwater vehicle close to underwater structures to capture images is a challenging task that compromises the safety of the vehicle. For this reason, highly skilled human operators are chosen for this task. We developed a collision avoidance system that uses visual information of its surroundings from an omnidirectional camera to correct the robot’s direction of travel to maintain ROV/AUV safety while in proximity to obstacles, such that anybody can operate one without there being any collision risk.

Alaaeddine presented the paper titled “A Docking Station for the Girona I-AUV: Validation by Simulation”. The work, co-authored by Joan Esteba (former PhD at CIRS, now post-doctoral researcher at New York University Abu Dhabi, United Arab Emirates) and members of our research group Patryk Cieslak and Pere Ridao, was accepted to the main technical session. The paper showcases the development process of the docking station for the Girona I-AUV. It evaluated several docking station proposals to choose the most suitable design for the vehicle. The assessment of the proposed designs focused on three critical parameters: structural size, manufacturing cost and operational feasibility. The vertical docking design was ultimately chosen as it demonstrated an optimal balance between these requirements. It also includes several critical innovations: a dual-axis guidance system accommodating ±0.25m positional and ±25◦ yaw tolerances, a secure sliding lock mechanism for underwater station-keeping, and integrated data/power transfer capabilities.

The OCEANS conference was a nice opportunity to share the work we have been doing at Girona with the rest of the underwater robotics and marine science community, to learn what other researchers are doing, and to foster new collaborations with other research institutions.

The post Participation at OCEANS 2025 in Brest appeared first on Vicorob.

Abstract:

This thesis explores how advanced artificial intelligence techniques, specifically deep learning, can improve the analysis of brain scans (MRI) for people with multiple sclerosis (MS) in the clinical practice.

The study focuses on three key areas. First, it introduces a new AI tool designed to accurately and consistently isolate the brain from the surrounding tissues in MRI scans. This is crucial for many analyses and can improve the accuracy of brain volume measurements, which are important for tracking disease progression. Secondly, the research develops a method to generate synthetic brain scans from existing ones. This can help improve the detection of MS lesions (areas of brain damage) while potentially reducing the need for expensive and time-consuming MRI scans.

Finally, the study investigates the practical challenges of bringing these AI tools into real-world clinical use. This includes navigating regulations and ensuring the safety and effectiveness of these technologies for patients.

In summary, this research aims to improve the diagnosis and management of MS by developing and implementing innovative AI solutions for analyzing brain MRI scans.

The post Industrial Doctoral Thesis: Applications of deep learning techniques in Magnetic Resonance Imaging for Multiple Sclerosis: from research innovations to clinical implementation appeared first on Vicorob.