Workshop
Workshop on ThrombUS+ Data Challenge: A Machine Learning Challenge for Automated DVT diagnosis based on Compression Ultrasound Videos. -
AI4DVT
2026
2 - 4 March, 2026 - Marbella, Spain
In conjunction with the 19th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSTEC 2026
CO-CHAIRS
|
Stylianos Didaskalou
Athena Research Center
Greece
|
|
|
|
Brief Bio
Dr. Stylianos Didaskalou graduated from the Department of Physics of the Aristotle University of Thessaloniki and later continued his studies at the Department of Molecular Biology and Genetics of the Democritus University of Thrace. He holds a master’s degree in Translational Research in Biomedicine and his doctoral thesis focused on cellular and molecular biology, with an emphasis on cell division. During his postgraduate studies, he specialized in microscopy, such as confocal microscopy and light sheet fluorescence microscopy, while also developing many methods for the analysis of multidimensional microscopy images. His research focuses on uncovering the molecular mechanisms underlying cancer tumor formation and evaluating potential therapeutic compounds. He employs advanced fluorescence microscopy techniques, data analysis and multidimensional image analysis, machine and deep learning, and molecular simulations. He has worked as a scientific collaborator on the BioImaging-GR and InTechThrace projects, contributing to many scientific articles published in international journals and presented at conferences. He is currently serving as technical project manager and coordinator of five (5) actions (Tasks) within the ThrombUS+ Horizon Europe project.
|
|
Harry (Hongqing) Yu
School of Computing, University of Derby
United Kingdom
|
|
|
|
Brief Bio
I am an Associate Professor and Programme Leader of three MSc Programmes in the School of Computing at the University of Derby. My teaching expertise is in Data Science and Machine Learning. I am a very active researcher as a member of the Data Science Research Centre at the University. Before joining the University of Derby, I worked as Senior Lecturer in Data Science and a Course Leader for MSc Sensor and Smart Cities. I have been involved in more than ten research projects that mostly were supported by Innovate UK and European Committee Research Frameworks and regional SME development frameworks. I obtained PhD award from the University of Leicester in 2009 and continued my research in the fields of Data/Text Mining, Semantic technologies, Deep Machine Learning and Natural Language Processing for healthcare, multimedia and learning systems.
|
SCOPE
Venous thromboembolism conditions, including deep vein thrombosis (DVT), are the third most common cause of vascular mortality worldwide after heart attack and stroke. Prompt diagnoses of DVT is essential to decrease the risk of fatal complications. Machine learning (ML) models have emerged as a valuable tool for assisting prompt diagnoses. These models, by performing pixel-wise segmentation in ultrasound videos, assess vein compressibility, an indicator of DVT or no-DVT. Training such models, requires an enormous amount of effort for creating the ground truth datasets. Thereby, this Data Challenge aims to foster development of AI models for DVT detection using ultrasound videos without the need for exhaustive pixel-wise annotations, reducing the burden of manual labeling, while also enabling robust and clinically relevant
predictions.
TOPICS OF INTEREST
Topics of interest include, but are not limited to:
- Biomedical Signal and Image Analysis
- Machine Learning and Pattern Recognition in Healthcare
- Clinical Decision Support Systems
- Health Informatics and Intelligent Systems
- AI-driven Diagnostic Support Systems
IMPORTANT DATES
Paper Submission:
December 17, 2025
Authors Notification:
January 14, 2026
Camera Ready and Registration:
January 22, 2026
WORKSHOP PROGRAM COMMITTEE
Available soon.
PAPER SUBMISSION
Prospective authors are invited to submit papers in any of the topics listed above.
Instructions for preparing the manuscript (in Word and Latex formats) are available at: Paper Templates
Please also check the Guidelines.
Papers must be submitted electronically via the web-based submission system using the appropriated button on this page.
PUBLICATIONS
The proceedings will be submitted for indexation by Thomson Reuters Conference Proceedings Citation Index (CPCI/ISI), DBLP, EI (Elsevier Engineering Village Index), Scopus, Semantic Scholar and Google Scholar.
After thorough reviewing by the workshop program committee, all accepted papers will be published in a special section of the conference proceedings book - under an ISBN reference and on digital support.
All papers presented at the conference venue will be available at the SCITEPRESS Digital Library (http://www.scitepress.org/DigitalLibrary/).
SCITEPRESS is a member of CrossRef (http://www.crossref.org/) and every paper is given a DOI (Digital Object Identifier).