AUTHOR=Liu Yiyang , Zhou Qin , Peng Boyuan , Jiang Jingjing , Fang Li , Weng Weihao , Wang Wenwen , Wang Shixuan , Zhu Xin 

TITLE=Automatic Measurement of Endometrial Thickness From Transvaginal Ultrasound Images

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.853845

DOI=10.3389/fbioe.2022.853845

ISSN=2296-4185

ABSTRACT=Purpose: Endometrial thickness is one of the most important indicators in endometrial disease screening. Herein, we propose a method for automated measurement of endometrial thickness from transvaginal ultrasound images.
 Methods: Accurate automated measurement of endometrial thickness relies on endometrium segmentation from transvaginal ultrasound images that usually have ambiguous boundaries and heterogeneous textures. Therefore, a two-step method was proposed for automated measurement of endometrial thickness. First, a semantic segmentation method was developed based on deep learning, to segment the endometrium from 2D transvaginal ultrasound images. Then, we estimated endometrium thickness from the segmented results, using a largest inscribed circle searching method. Overall 8,119 images (size: 852x1136 pixels) from 467 subjects were used to train and validate the proposed method. 
 Result: We achieved an average Dice coefficient of 0.82 for endometrial segmentation using a validation dataset of 1,059 images from 71 subjects. With validation using 3,210 images from 214 subjects, 89.3% of endometrial thickness errors were within the clinically accepted range of ± 2 mm.
 Conclusion: Endometrial thickness can be automatically and accurately estimated from transvaginal ultrasound images for clinical diagnosis.