Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Hussain Alasmawi, Leanne Bricker, Mohammad Yaqub

TL;DR

The FUSC method has the potential to reduce the manual labeling burden, making the process more efficient, and pave the way for advanced automated labeling solutions, contributing to the enhancement of clinical practices in fetal ultrasound imaging.

Abstract

Ultrasound is the primary imaging modality in clinical practice during pregnancy. More than 140M fetuses are born yearly, resulting in numerous scans. The availability of a large volume of fetal ultrasound scans presents the opportunity to train robust machine learning models. However, the abundance of scans also has its challenges, as manual labeling of each image is needed for supervised methods. Labeling is typically labor-intensive and requires expertise to annotate the images accurately. This study presents an unsupervised approach for automatically clustering ultrasound images into a large range of fetal views, reducing or eliminating the need for manual labeling. Our Fetal Ultrasound Semantic Clustering (FUSC) method is developed using a large dataset of 88,063 images and further evaluated on an additional unseen dataset of 8,187 images achieving over 92% clustering purity. The result of our investigation hold the potential to significantly impact the field of fetal ultrasound imaging and pave the way for more advanced automated labeling solutions. Finally, we make the code and the experimental setup publicly available to help advance the field.

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

TL;DR

The FUSC method has the potential to reduce the manual labeling burden, making the process more efficient, and pave the way for advanced automated labeling solutions, contributing to the enhancement of clinical practices in fetal ultrasound imaging.

Abstract

Ultrasound is the primary imaging modality in clinical practice during pregnancy. More than 140M fetuses are born yearly, resulting in numerous scans. The availability of a large volume of fetal ultrasound scans presents the opportunity to train robust machine learning models. However, the abundance of scans also has its challenges, as manual labeling of each image is needed for supervised methods. Labeling is typically labor-intensive and requires expertise to annotate the images accurately. This study presents an unsupervised approach for automatically clustering ultrasound images into a large range of fetal views, reducing or eliminating the need for manual labeling. Our Fetal Ultrasound Semantic Clustering (FUSC) method is developed using a large dataset of 88,063 images and further evaluated on an additional unseen dataset of 8,187 images achieving over 92% clustering purity. The result of our investigation hold the potential to significantly impact the field of fetal ultrasound imaging and pave the way for more advanced automated labeling solutions. Finally, we make the code and the experimental setup publicly available to help advance the field.
Paper Structure (22 sections, 4 equations, 4 figures, 4 tables)

This paper contains 22 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Experiments & Results
  4. Discussion & Conclusion
  5. Conflict of Interest Statement
  6. Data Availability Statement
  7. Declaration of Generative AI

Figures (4)

  • Figure 1: Samples of the views in the dataset, where n represents the number of samples.
  • Figure 2: This framework uses SSL to learn good representation. The nearest neighbors for each image in the embedding space are found. The SSL output trains a clustering model to categorize image embeddings. The blue and green vectors represent different image embedding, whereas we expect embedding with a similar color to represent images from the same class.
  • Figure 3: Samples of images in the best five clusters for the $FUSC^*_{simCLR}$ model.
  • Figure 4: Samples of clusters of $FUSC^*_{simCLR}$ model.