Semantic Video Segmentation for Intracytoplasmic Sperm Injection Procedures

TL;DR

This paper introduces a novel deep learning model for analyzing intracytoplasmic sperm injection procedures, achieving high accuracy in segmenting key objects and localizing the needle tip, with performance comparable to human experts.

Contribution

It is the first deep learning approach specifically designed for analyzing ICSI procedures, demonstrating high accuracy and real-time performance.

Findings

Mean IoU of 0.962 in segmentation

Mean pixel error of 3.793 pixels in needle localization

Model performance comparable to human annotators

Abstract

We present the first deep learning model for the analysis of intracytoplasmic sperm injection (ICSI) procedures. Using a dataset of ICSI procedure videos, we train a deep neural network to segment key objects in the videos achieving a mean IoU of 0.962, and to localize the needle tip achieving a mean pixel error of 3.793 pixels at 14 FPS on a single GPU. We further analyze the variation between the dataset's human annotators and find the model's performance to be comparable to human experts.