Deep Learning-Based Three-dimensional Transvaginal Ultrasound in Diagnosis of Intrauterine Adhesion

Ji Li,Xiaofeng Qing,Dan Liu,Huizhen Xiang,Lanlan Yu,M Pallikonda Rajasekaran

doi:10.1155/2021/2947021

Abstract

This study was aimed to enhance and detect the characteristics of three-dimensional transvaginal ultrasound images based on the partial differential algorithm and HSegNet algorithm under deep learning. Thereby, the effect of quantitative parameter values of optimized three-dimensional ultrasound image was analyzed on the diagnosis and evaluation of intrauterine adhesions. Specifically, 75 patients with suspected intrauterine adhesion in hospital who underwent the hysteroscopic diagnosis were selected as the research subjects. The three-dimensional transvaginal ultrasound image was enhanced and optimized by the partial differential equation algorithm and processed by the deep learning algorithm. Subsequently, three-dimensional transvaginal ultrasound examinations were performed on the study subjects that met the standards. The March classification method was used to classify the patients with intrauterine adhesion. Finally, the results by the three-dimensional transvaginal ultrasound were compared with the diagnosis results in hysteroscope surgery. The results showed that the HSegNet algorithm model realized the automatic labeling of intrauterine adhesion in the transvaginal ultrasound image and the final accuracy coefficient was 97.3%. It suggested that the three-dimensional transvaginal ultrasound diagnosis based on deep learning was efficient and accurate. The accuracy of the three-dimensional transvaginal ultrasound was 97.14%, the sensitivity was 96.6%, and the specificity was 72%. In conclusion, the three-dimensional transvaginal examination can effectively improve the diagnostic efficiency of intrauterine adhesion, providing theoretical support for the subsequent diagnosis and grading of intrauterine adhesion.

Highlights

Intrauterine adhesion is a common gynecological disease, known as Asherman syndrome in clinical practice
Its symptoms were first described by Fritsch in 1894 and were not reported in detail by Asherman for the first time until 1948 [1,2,3,4]. e main reason for intrauterine adhesion is the trauma of the pregnant or nonpregnant uterus, resulting in damage to the base of the endometrium and partial occlusion of the uterine cavity. e intrauterine adhesions caused by nonpregnancy only accounted for 9% of the total [5]
Intrauterine adhesion in different parts and of different degrees differs in clinical manifestations, but the essence of intrauterine adhesion is the fibrosis of the endometrium

Summary

Introduction

Intrauterine adhesion is a common gynecological disease, known as Asherman syndrome in clinical practice. Hysteroscopy has been clinically determined to be the gold standard for the diagnosis and treatment of such diseases [11] It has high specificity and enables the doctor to observe the characteristics of the uterine cavity under direct vision so that the location and range of intrauterine adhesion can be accurately and effectively evaluated, which is an important basis for the prognosis of subsequent treatment. E traditional image denoising algorithm cannot balance the contradiction, but the partial image denoising algorithm under deep learning could achieve the selective smooth to balance the contradiction As a result, it can directly reflect the degree of cervical adhesion and provide important parameters such as the volume of the endometrium in the uterine cavity. As the diagnosis of intrauterine adhesions was done based on it, its application effects were evaluated, which provided reference for the improvement of the clinical diagnosis of intrauterine adhesions

Materials and Methods

Results

Findings

Discussion