| <!doctype html> |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <title>CellsiLAB: Cells and Image Analysis</title> |
| <style> |
| :root { color-scheme: light dark; } |
| body { |
| margin: 0; |
| font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif; |
| line-height: 1.6; |
| color: #e5e7eb; |
| background: transparent; |
| } |
| .wrap { max-width: 900px; margin: 0 auto; padding: 8px 4px 24px; } |
| h1 { font-size: 1.7rem; margin: 0 0 .2rem; color: #fff; } |
| h2 { |
| font-size: 1.1rem; margin: 1.6rem 0 .5rem; |
| border-bottom: 1px solid rgba(255,255,255,.12); padding-bottom: .3rem; |
| } |
| p { margin: .5rem 0; } |
| a { color: #c084fc; text-decoration: none; } |
| a:hover { text-decoration: underline; } |
| ul { margin: .4rem 0; padding-left: 1.2rem; } |
| li { margin: .25rem 0; } |
| .tagline { color: #9ca3af; font-size: .95rem; margin-bottom: 1rem; } |
| code { background: rgba(255,255,255,.08); padding: .1rem .35rem; border-radius: 4px; font-size: .85em; } |
| </style> |
| </head> |
| <body> |
| <div class="wrap"> |
| <h1>CellsiLAB: Cells and Image Analysis</h1> |
| <p class="tagline">Biomedical image analysis area of the <strong>Codalab</strong> research group at the Universitat Politècnica de Catalunya (UPC).</p> |
|
|
| <p>We work on <strong>applied artificial intelligence</strong>, focused mainly (though not exclusively) |
| on <strong>biomedical image analysis</strong>. We develop <strong>deep learning</strong> and |
| <strong>computer vision</strong> methods to support clinical decision-making, with a strong emphasis on |
| <strong>explainable</strong> and <strong>trustworthy AI</strong>: we care not only about <em>what</em> |
| a model predicts, but <em>why</em>.</p> |
|
|
| <h2>Research lines</h2> |
| <ul> |
| <li><strong>Explainable AI (xAI)</strong> for biomedical imaging: new methodologies, evaluation strategies and clinical applications.</li> |
| <li><strong>Computer vision for medical imaging</strong>: classification, segmentation and quality assessment.</li> |
| <li><strong>Generative and vision-language models</strong> applied to medical data.</li> |
| <li><strong>Federated learning</strong> for robust multi-center generalization.</li> |
| </ul> |
|
|
| <h2>Application domains</h2> |
| <ul> |
| <li><strong>Hematology</strong>: blood cell classification, myelodysplastic syndromes, leukemia and red cell morphology.</li> |
| <li><strong>Obstetrics</strong>: fetal ultrasound quality assessment (nuchal translucency).</li> |
| <li><strong>Pediatric ophthalmology</strong>: retinopathy of prematurity.</li> |
| </ul> |
|
|
| <h2>Research projects</h2> |
| <ul> |
| <li><strong>Explainable deep learning in medical image analysis</strong>: novel methods, evaluation strategies and clinical applications <em>(PID2023-146261OB-I00, 2024 to 2027)</em>.</li> |
| <li><strong>Computational system for the diagnosis of acute leukemia and lymphoma</strong> from peripheral blood images, including a proof of concept and technological valorization <em>(PDC2022-133514-I00, 2022 to 2024)</em>.</li> |
| <li><strong>CellsiMaticDeep</strong>, computational hematology: deep learning solutions for the diagnosis of hematological diseases from peripheral blood cell images <em>(PID2019-104087RB-I00, 2020 to 2023)</em>.</li> |
| <li><strong>Characterization and automatic classification of leukemic cells</strong> by means of digital image processing and pattern recognition for diagnosis support <em>(DPI2015-64493-R, 2016 to 2018)</em>.</li> |
| </ul> |
|
|
| <h2>Institutions and collaborations</h2> |
| <ul> |
| <li><strong>Universitat Politècnica de Catalunya (UPC)</strong></li> |
| <li><strong>Hospital Clínic de Barcelona</strong>, CORE Laboratory</li> |
| <li><strong>Hospital Sant Joan de Déu</strong>, Barcelona</li> |
| <li><strong>Centro de Diagnóstico Biomédico (CDB)</strong></li> |
| <li>International partners across Europe, Latin America and Asia</li> |
| </ul> |
|
|
| <h2>Team</h2> |
| <ul> |
| <li><strong>Dr. José Rodellar.</strong> Professor (Emeritus), UPC. Signal processing and machine learning for blood cell morphology. <a href="https://futur.upc.edu/178882" target="_blank">Profile</a></li> |
| <li><strong>Santiago Alférez.</strong> Assistant Professor, Dept. of Mathematics, UPC. Machine learning, statistics and explainable AI for medical image analysis. <a href="https://futur.upc.edu/EdwinSantiagoAlferezBaquero" target="_blank">Profile</a></li> |
| <li><strong>Kevin Barrera.</strong> Assistant Professor, UPC. Deep learning for cell morphology. <a href="https://futur.upc.edu/KevinIvanBarreraLlanga" target="_blank">Profile</a></li> |
| <li><strong>Dr. Anna Merino.</strong> Clinical lead, CORE Laboratory, Hospital Clínic de Barcelona. Hematology and cell morphology.</li> |
| </ul> |
|
|
| <h2>Datasets and Models</h2> |
| <p>Our public datasets and models will be published here soon. Stay tuned.</p> |
|
|
| <h2>Links</h2> |
| <ul> |
| <li>Website: <a href="https://cellsilab.com/" target="_blank">cellsilab.com</a></li> |
| </ul> |
|
|
| <p style="margin-top:1.5rem;color:#9ca3af;font-size:.9rem;"> |
| For collaborations or inquiries, please reach out through our |
| <a href="https://cellsilab.com/" target="_blank">website</a>. |
| </p> |
| </div> |
| </body> |
| </html> |
|
|
