A Vaginitis Classification Method Based on Multi-Spectral Image Feature Fusion.

Guitao Li,Youzheng Wang,Peng Gao,Sunxiangyu Liu,Kongya Zhao,Ying Wang

doi:10.3390/s22031132

Abstract

Vaginitis is one of the commonly encountered diseases of female reproductive tract infections. The clinical diagnosis mainly relies on manual observation under a microscope. There has been some investigation on the classification of vaginitis diseases based on computer-aided diagnosis to reduce the workload of clinical laboratory staff. However, the studies only using RGB images limit the development of vaginitis diagnosis. Through multi-spectral technology, we propose a vaginitis classification algorithm based on multi-spectral image feature layer fusion. Compared with the traditional RGB image, our approach improves the classification accuracy by 11.39%, precision by 15.82%, and recall by 27.25%. Meanwhile, we prove that the level of influence of each spectrum on the disease is distinctive, and the subdivided spectral image is more conducive to the image analysis of vaginitis disease.

Highlights

Vaginitis is the most common disease of female reproductive tract infections
Vaginitis is a general name of various inflammatory diseases of vaginal mucosa caused by different reasons, mainly including aerobic vaginitis (AV), bacterial vaginosis (BV), vulvovaginal candidiasis (VVC), and trichomonas vaginitis (TV)
convolutional neural network (CNN) (Convolutional Neural Networks) is the most popular deep learning framework, and it has been widely adopted in the task of image classification, recognition, segmentation, and super-resolution reconstruction

Summary

Introduction

Vaginitis is the most common disease of female reproductive tract infections. It is reported [1] that in 2019, about 14.7 million female patients among 20–64 years old have vaginitis in China. A common disease does not mean it is harmless. On the contrary, it is the cause of serious consequences, such as HPV infection leading to cervical cancer [2,3], miscarriage, premature rupture of membranes, and premature delivery for pregnancy [4]. CNN (Convolutional Neural Networks) is the most popular deep learning framework, and it has been widely adopted in the task of image classification, recognition, segmentation, and super-resolution reconstruction.

Methods

Results

Conclusion