FUSC: Fetal Ultrasound Semantic Clustering of Second Trimester Scans Using Deep Self-supervised Learning

The paper presents Fetal Ultrasound Semantic Clustering (FUSC), an unsupervised method that automates the clustering of ultrasound images into various fetal views. This approach eliminates the need for labor-intensive manual labeling. FUSC was developed on a dataset of 88,063 images and further tested on an additional unseen dataset of 8,187 images, achieving over 92% clustering purity. It holds potential to significantly impact the field of fetal ultrasound imaging and advance automated labeling solutions.

Publication date: 20 Oct 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2310.12600