# Introduction
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.    

This work is co-funded by the European Union, under the Horizon Europe Innovation Action ThrombUS+ (Grant Agreement No. 101137227). Views and opinions expressed are however those of the authors only and do not necessarily reflect those of the European Union or HADEA as the granting authority. Neither the European Union nor the grant-ing authority HADEA can be held responsible for them.