The paper “Cross-task Data Augmentation by Pseudo-label Generation for Region-based Coronary Artery Instance Segmentation” by Pokhrel, S., Bhandari, S., Vasquez, E., Shrestha, YR, Bhattarai, B. has be accepted at Data Engineering in Medical Imaging, MICCAI 2024.
This paper introduces the use of pseudo-labels to address the issue of limited data in the angiographic dataset to enhance the performance of the baseline YOLO model. Unlike existing data augmentation techniques that improve the model constrained to a fixed dataset, this paper introduces the use of pseudo-labels generated on a dataset of separate related task to diversify and improve model performance.
🔗Preprint: https://arxiv.org/abs/2310.05990
