Can I read ScribSD: Scribble-Supervised Fetal MRI Segmentation Based on Simultaneous Feature and Prediction Self-distillation on EtoBox?

ScribSD: Scribble-Supervised Fetal MRI Segmentation Based on Simultaneous Feature and Prediction Self-distillation by Yijie Qu; Qianfei Zhao; Linda Wei; Tao Lu; Shaoting Zhang; Guotai Wang is a book available to read on EtoBox.

What is ScribSD: Scribble-Supervised Fetal MRI Segmentation Based on Simultaneous Feature and Prediction Self-distillation about?

## Automatic segmentation of different organs in fetal Magnetic Resonance Imaging (MRI) plays an important role in measuring the development of the fetus. However, obtaining a large amount of highquality manually annotated fetal MRI is time-consuming and requires specialized knowledge, which hinders the widespread application that relies on such data to train a model with good segmentation performance. Using weak annotations such as scribbles can substantially reduce the annotation cost, but often leads to poor segmentation performance due to insufficient supervision. In this work, we propose a Scribble-supervised Self-Distillation (ScribSD) method to alleviate this problem. For a student network supervised by scribbles and a teacher based on Exponential Moving Average (EMA), we first introduce prediction-level Knowledge Distillation (KD) that leverages soft predictions of the teacher network to supervise the student, and then propose feature-level KD that encourages the similarity of features between the teacher and student at multiple scales, which efficiently improves the segmentation performance of the student network. Experimental results demonstrate that our KD modules substa

Author

Yijie Qu; Qianfei Zhao; Linda Wei; Tao Lu; Shaoting Zhang; Guotai Wang

Publisher

Springer International Publishing

Published

2023

Language

EN

ISBN

9783031449178

Subjects

Computer Science, Technology, Engineering