AuthorsA. Storås, M. Riegler, T. B. Haugen, V. Thambawita, S. Hicks, H. L. Hammer, R. Kakulavarapu, P. Halvorsen, and M. H. Stensen
TitleAutomatic Unsupervised Clustering of Videos of the Intracytoplasmic Sperm Injection (ICSI) Procedure
AfilliationMachine Learning
Project(s)Department of Holistic Systems
StatusAccepted
Publication TypeProceedings, refereed
Year of Publication2022
Conference NameNAIS 2022
PublisherNAIS 2022
Keywordsclustering, Computer Vision and Pattern Recognition (cs.CV), human reproduction, medical videos, Unsupervised learning
Abstract

The in vitro fertilization procedure called intracytoplasmic sperm injection can be used to help fertilize an egg by injecting a single sperm cell directly into the cytoplasm of the egg. In order to evaluate, refine and improve the method in the fertility clinic, the procedure is usually observed at the clinic. Alternatively, a video of the procedure can be examined and labeled in a time-consuming process. To reduce the time required for the assessment, we propose an unsupervised method that automatically clusters video frames of the intracytoplasmic sperm injection procedure. Deep features are extracted from the video frames and form the basis for a clustering method. The method provides meaningful clusters representing different stages of the intracytoplasmic sperm injection procedure. The clusters can lead to more efficient examinations and possible new insights that can improve clinical practice. Further on, it may also contribute to improved clinical outcomes due to increased understanding about the technical aspects and better results of the procedure. Despite promising results, the proposed method can be further improved by increasing the amount of data and exploring other types of features.

Citation Key42538

Contact person