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.

La sessió va apropar al públic alguns dels avenços més recents en l’estudi del cervell humà i el paper que hi juga actualment la intel·ligència artificial. Durant la conferència, Casamitjana va explicar com les noves eines computacionals permeten connectar diferents nivells d’estudi del cervell, des de l’escala microscòpica de les cèl·lules fins a l’anàlisi macroscòpica dels sistemes cerebrals i la seva interrelació.

La conferència també va presentar el projecte NextBrain, una iniciativa de recerca que utilitza tècniques d’intel·ligència artificial per oferir un mapa complet de l’arquitectura cel·lular del cervell sense precedents. Les tècniques desenvolupades permeten una anàlisi ràpida, precisa i accessible d’imatges cerebrals en individus vius. Aquest enfoc permet identificar patrons cerebrals complexos, facilitant l’estudi del desenvolupament i l’envelliment cerebral, així com en l’impacte de diverses malalties neurodegeneratives. Totes les eines del projecte NextBrain han estat publicades lliurement a la comunitat científica per a futurs estudis: https://github-pages.ucl.ac.uk/NextBrain

Veiem, doncs, com la intel·ligència artificial esdevé una tecnologia crucial en l’estudi del cervell, ja que permet examinar grans quantitats de dades amb patrons complexes. Obre les portes a estudis fins ara inimaginables, integrant dades de múltiples fonts que anticipin la detecció de malalties cerebrals. Ens permetrà, per exemple, poder dissenyar protocols i intervencions personalitzades i, fins i tot, crear bessons digitals que permetin simular la evolució dels pacients i l’impacte dels tractaments.

El cicle “Últimes fronteres. La ciència al segle XXI”, organitzat per la Casa de Cultura de Girona, té com a objectiu apropar la recerca científica i tecnològica més actual a la ciutadania. La sessió es va gravar en vídeo i estarà disponible al canal de Youtube de la Casa de Cultura de Girona.

The post La recerca en IA aplicada al cervell humà centra una conferència d’Adrià Casamitjana appeared first on Vicorob.

The applications presented span high-impact domains such as ecology (biodiversity estimation, tree species census, and biomass assessment) and cultural heritage preservation through the development of large-scale databases of historical documents.

The visit also included working meetings with the obstetrics team at Dr. Josep Trueta University Hospital, involving Dr. Anna Maroto and Dr. Clara Martínez, to explore ongoing research lines in fetal ultrasound imaging and identify new opportunities for clinical collaboration.

This activity is part of a long-standing collaboration between the two researchers, initiated in 2019 and consolidated through joint publications and competitive research proposals. In this context, it is also framed within the Ramón y Cajal programme awarded to Mariano Cabezas (RYC2023-042706-I), one of Spain’s flagship initiatives for the recruitment and consolidation of research talent, which supports his upcoming research stay in Japan and enables the expansion of these joint research lines. In parallel, Yago Díez’s involvement is linked to the J-PEAKS programme (2026 J-PEAKS Accelerated International Network Construction Support Program), aimed at fostering international research networks.

The post International collaboration in Computer Vision, Deep Learning and Medical Imaging appeared first on Vicorob.

During the conference, Vicorob presented the poster “Volumetric-Guided Brain Image Synthesis with Diffusion Models”, showcasing a novel approach to generating and transforming brain MRI images using artificial intelligence.

The work introduced a method that can generate brain MRI images and transform existing ones. It allows adjusting specific brain regions to explore “what if” scenarios, such as simulating changes related to aging or neurological conditions, and can predict how brain structure may evolve over time. These capabilities provide a flexible tool for studying brain changes and supporting research in neuroscience and medical imaging.

The conference program included keynote talks by leading researchers such as Ellen Van Obberghen-Schilling, who presented advances in AI-driven spatial imaging for personalized tumor treatments; Tom Vercauteren, who explored AI-powered hyperspectral imaging for real-time surgical support; and Katrien Verbert, who discussed interactive and conversational AI to improve the understanding of AI-based decisions.

Vicorob’s participation in IABM 2026 reinforces its commitment to advancing artificial intelligence technologies with a strong focus on real-world biomedical applications and societal impact.

The post Vicorob presents new AI-based approach for brain image simulation at IABM 2026 appeared first on Vicorob.

A new AI-assisted brain atlas that can help visualise the human brain in unprecedented detail in a major step forward for neuroscience and neuroimaging. The work is led by Dr. Juan Eugenio Iglesias (University College London and Harvard Medical School) and Adrià Casamitjana, a VICOROB (UdG) researcher, is the first-author

The human brain comprises hundreds of interconnected regions that drive our thoughts, emotions, and behaviours. Existing brain atlases can identify major structures in MRI scans – such as the hippocampus, which supports memory and learning – but their finer sub-regions remain hard to detect. These distinctions matter because sub-regions of the hippocampus, for example, are affected differently during Alzheimer’s disease progression.

Examining the brain at the cellular level is achievable using microscopy (histology), but cannot be done in living individuals, limiting its potential for understanding how the human brain changes during development, ageing and disease.

Published in Nature, the new study introduces NextBrain, an atlas of the entire adult human brain that can be used to analyse MRI scans of living patients in a matter of minutes and at a level of detail not possible until now.

The creators of the atlas, which is freely available, hope it will ultimately help to accelerate discovery in brain science and its translation into better diagnosis and treatment of conditions such as Alzheimer’s.

The post New brain atlas offers unprecedented detail in MRI scans appeared first on Vicorob.

Among the most remarkable results were those achieved in the MICCAI challenges, where ViCOROB teams once again demonstrated their expertise in image segmentation and AI-based analysis. In the Brain Tumor Segmentation challenge (BraTS), Valeriia Abramova obtained first place in the tumor segmentation task, while Agustin Cartaya achieved second place in the synthesis category. Micaela Rivas and Clara Lisazo also stood out by winning first place in the Eye Vessel Segmentation (GAVE) challenge, and Hasna R. Hamadache earned third place in the AIMS-TBI competition focused on traumatic brain injury segmentation. In the MAMA MIA challenge, dedicated to breast tumor segmentation, Hadeel Awwad achieved a third-place result, and Cansu Yalcin took part in the highly competitive MBH-Seg25 challenge on brain hemorrhage segmentation and classification. Each of these achievements highlights how ViCOROB researchers apply advanced AI techniques to a wide variety of medical imaging problems, from brain and to breast tumor detection.

The conference was also a platform to share ongoing research projects and promote scientific dialogue. Uma Lal-Trehan represented the group in the dynamic “Thesis Madness” session with a concise three-minute oral presentation summarising her latest findings, while Ricardo Montoya del Angel contributed to the Deep-Brea3th 2025 workshop with an oral presentation exploring deep learning techniques for respiratory imaging.

Recognition also came from the organizational side of the conference: Mariano Cabezas received the Outstanding Area Chair Award, which included a paid registration, for his contribution to the scientific review process. In addition, he was part of the Best Paper Awards Committee, a select group of seven experts responsible for evaluating the top 25 papers presented at MICCAI.

This year’s edition also showcased the strong academic presence of the MAIA Erasmus Mundus master’s programme, coordinated by ViCOROB, with 27 students presenting their research during the conference. Their participation reinforces the group’s commitment to high-level training and the transfer of knowledge to the next generation of scientists.

The post Strong ViCOROB presence at MICCAI 2025 appeared first on Vicorob.

From the moment I arrived, Berlin’s unique blend of history, creativity, and science left a lasting impression. Each day felt like a new layer unfolding, academically challenging, culturally rich, and personally empowering.

Back at VICOROB, within the iToBoS project, my research focused on developing machine learning models for the early diagnosis of skin cancer. Our aim was to create models that could eventually be used in clinical settings, supporting dermatologists with faster and more accurate decisions. But clinical deployment isn’t just about accuracy, it’s also about trust. Models need to be not only effective but also transparent and safe. This challenge led me to HHI, where I focused on building multi-modal vision-and-language models that could explain their predictions at a professional level, rather than just output a diagnosis.

The first step was to explore and benchmark existing models designed for similar tasks, understanding where they performed well and where they fell short. With those insights, I began adapting and improving them to better serve the needs of dermatological applications. Throughout this process, I had the privilege of collaborating closely with other PhD students and researchers at HHI. Their expertise in vision-language models and Explainable AI, as well as their openness to share knowledge, made a huge impact on the development of my work.

Beyond the technical growth, the experience of working in a new environment was refreshing and energizing. I noticed the differences, and appreciated the commonalities, between VICOROB and HHI, which helped me grow not only as a researcher but also as a team member in a broader scientific community. And there was something quietly magical about the routine itself: each morning on my way to the office in Charlottenburg, I passed the Brandenburg Gate. No matter how many times I walked by, it never failed to inspire me with its grandeur and historical presence.

Outside of work, Berlin offered so much more than I expected. The city’s energy, diversity, and openness created space for learning far beyond the lab. As a woman in tech, I found particular inspiration in the local community. Through the BLISS e.V. initiative, I joined career development events designed for women in machine learning and computer vision. There, I met a number of accomplished women whose stories of resilience and success deeply resonated with me.Another standout moment was attending “Redefine Possible,” an event hosted by Google Developers Berlin to celebrate International Women’s Day. Surrounded by driven young women from across Germany, we reflected on how far the field has come, and how much more we can do to foster equity and inclusion in science and tech. These experiences reminded me of the importance of community, visibility, and mentorship.

Overall, my stay in Berlin was an incredibly enriching experience, both academically and personally. Working at Fraunhofer HHI deepened my research and helped me grow as a scientist, while the diverse events and inspiring people I met along the way expanded my vision of what’s possible in my field. I returned home not only with valuable progress on my PhD, but also with renewed confidence, fresh ideas, and a stronger sense of belonging within the global research community. This stay has left a lasting impact on me, and I’m deeply grateful for the opportunity.

The post International Research: Sana Nazari at HHI Berlin appeared first on Vicorob.

The team stood out with an innovative proposal: an application capable of intelligently classifying scientific articles through recommendation systems and advanced AI algorithms. Developed using Python, TensorFlow, Scikit-Learn, and Google Collab, this tool combines technical robustness with an intuitive interface, facilitating the management and consultation of academic literature.

The presented solution was praised by the jury for its functionality and potential impact, earning the team a one-week research stay at the University of Craiova, as well as gift vouchers for each member. This experience allowed participants to apply their programming and problem-solving skills, strengthening the interdisciplinary and collaborative work that defines the Across Alliance.

The post First Place in the First Hackathon Across appeared first on Vicorob.

Aquest any, la doctoranda del programa en Tecnologia Uma Lal-Trehan serà l’encarregada de representar la Universitat de Girona (UdG) a la final interuniversitària de la 8a edició d’aquest concurs, impulsat per la Fundació Catalana per a la Recerca i la Innovació (FCRi). L’esdeveniment tindrà lloc el proper 3 de juliol a Girona. Lal-Trehan ha estat la candidata més ben valorada pel tribunal de la fase prèvia celebrada a Girona, organitzada per l’Escola de Doctorat.

A la final, Uma Lal-Trehan presentarà la seva tesi titulada “Intel·ligència Artificial i Imatge Cerebral: simplificant la complexitat”, on aborda l’aplicació de la Intel·ligència Artificial en el camp de la Medicina, amb un émfasi especial en la detecció d’ictus. “Explicar la teva tesi en quatre minuts pot semblar una tasca senzilla, ja que portem molts anys treballant en la nostra recerca, però la veritat és que comprimir tota aquesta informació i extreure’n les idees més importants per tal d’explicar-la a un públic no especialitzat porta molt de temps”, ha declarat Lal-Trehan.

Aquest concurs representa una oportunitat única per donar visibilitat a la recerca que es realitza a les universitats catalanes i posar en valor la capacitat de comunicació dels doctorands. Des de Vicorob, ens sentim orgullosos de comptar amb talents com el de Lal-Trehan i li desitgem molta sort en aquesta final.

Participants i jurat del concurs “Presenta la Teva Tesi en 4 Minuts”. (UdG)

Podeu consultar més informació:

https://tesi4minuts.fundaciorecerca.cat/index.html 

https://www.udg.edu/ca/udg/detall-noticies/eventid/53244

The post Uma Lal-Trehan representarà la UdG a la final del concurs “Presenta la teva tesi en 4 minuts” appeared first on Vicorob.

The ViCOROB participation

Our students started to collect some important results from the beginning of the conference activities during the first Satellite events day, where several workshops and challenges results were announced. From the brain imaging research group, Valeria Abramova, 3rd year PhD student and 3 years in-a-row MICCAI attendee, participated in the International Brain Tumor Segmentation (BraTS) Challenge 2024 obtaining an outstanding 1st place in the meningioma radiotherapy segmentation task.

Clara Lisazo and Rachika E. Hamadache, 1st year PhD students, participated in the Topology-Aware Anatomical Segmentation of the Circle of Willis (TopCoW) challenge, for the second time, obtaining the 1st place in 3 tasks, bringing home once again 3 adorable Swiss toy cows directly from Zurich as awards. Rachika E. Hamadache also participated in the Fetal Tissue Annotation Challenge (FeTA) where she ranked 2nd place.

Ricardo Montoya Del Angel and Rachika E. Hamadache participated in Triphasic-aided Liver Lesion Segmentation challenge (TriALS) and they ranked 2nd in the Non-Contrast Lesion Segmentation task, winning a money award of 200$.

Cansu Yalçın, a second year PhD student obtained the 4th place in the MBH-Seg: Multi-class Brain Hemorrhage Segmentation in Non-contrast CT challenge winning a money award of 200$.

Ricardo Montoya Del Angel, a 2nd-year PhD student, had his paper accepted to the Deep-Breath: Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care. His article, ELK: Enhanced Learning through Cross-Modal Knowledge Transfer for Lesion Detection in Limited-Sample Contrast-Enhanced Mammography Datasets, was among the featured works. Similarly, Melika Pooyan, with her paper MRI Breast Tissue Segmentation Using nnUNet for Biomechanical Modelling, and Hadeel Awwad, a 1st-year PhD student, with her work Graph Neural Networks for Modelling Breast Biomechanical Compression, also had their papers accepted under the supervision of Robert Martí and Eloy García. Both Melike Pooyan’s and Hadeel Awwad’s studies were selected for oral presentations, which were delivered by Robert Martí and Eloy García during the workshop event.
Kaouther Mouheb, Ricardo Montoya Del Angel and Nohemi Sofia Leon Contreras, MAIA graduates, won the MICCAI Educational Challenge with their submission named Introduction to Diffusion Model, winning the money award of 300$.

The conference highlights: Fair and accessible AI

The MICCAI conferences have long been a global gathering for researchers to showcase the latest advancements in medical imaging, shaping the future of AI applications in healthcare and setting new trends. This year’s theme, “Fair and Accessible AI,” was especially prominent. For the first time in MICCAI history, the conference took place in Africa, underscoring the significance of ensuring AI benefits all populations worldwide. A special session, “From AFRICAI to MICCAI,” highlighted the growing importance of education and awareness in AI, particularly across the African continent. Reflecting this focus, many studies presented during the conference tackled challenges related to limited datasets, compact models, and fairness, aiming to create AI systems that better serve underrepresented populations.

The post ViCOROB at MICCAI: a positive outcome appeared first on Vicorob.