Skip to main content

ORIGINAL RESEARCH article

Front. Oncol.
Sec. Cancer Imaging and Image-directed Interventions
Volume 14 - 2024 | doi: 10.3389/fonc.2024.1440881
This article is part of the Research Topic Deep Learning for Medical Imaging Applications View all 5 articles

Achieving Enhanced Diagnostic Precision in Endometrial Lesion Analysis through a Data Enhancement Framework

Provisionally accepted
Yi Luo Yi Luo 1,2Meiyi Yang Meiyi Yang 3Xiaoying Liu Xiaoying Liu 2*Liufeng Qin Liufeng Qin 2*Zhengjun Yu Zhengjun Yu 4*Yunxia Gao Yunxia Gao 5*Xia Xu Xia Xu 6*Guofen Cha Guofen Cha 7*Xuehua Zhu Xuehua Zhu 8*Gang Chen Gang Chen 4*Xue Wang Xue Wang 2*Lulu Cao Lulu Cao 2*Yuwang Zhou Yuwang Zhou 2*Yun Fang Yun Fang 2*
  • 1 Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Qu zhou, China
  • 2 The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
  • 3 University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
  • 4 Kaihua County People's Hospital, Quzhou, China
  • 5 The Second People's Hospital of Quzhou, Quzhou, Zhejiang Province, China
  • 6 Changshan County People's Hospital, Quzhou, China
  • 7 Quzhou Kecheng People's Hospital, Quzhou, China
  • 8 Quzhou Maternity and Child Health Care Hospital, Quzhou, Zhejiang, China

The final, formatted version of the article will be published soon.

    The aim of this study was to enhance the precision of categorization of endometrial lesions in ultrasound images via a data enhancement framework based on deep learning (DL), through addressing diagnostic accuracy challenges, contributing to future research.Ultrasound image datasets from 734 patients across six hospitals were collected. A data enhancement framework, including image features cleaning and soften label, was devised and validated across multiple DL models, including ResNet50, DenseNet169, DenseNet201, and ViT-B. A hybrid model, integrating convolutional neural network and transformer architectures for optimal performance, to predict lesion types was developed.Results: Implementation of our novel strategies resulted in a substantial enhancement in model accuracy. The ensemble model achieved accuracy and macro-area under the receiver operating characteristic curve values of 0.809 of 0.911, respectively, underscoring the potential for use of DL in endometrial lesion ultrasound image classification.We successfully developed a data enhancement framework to accurately classify endometrial lesions in ultrasound images. Integration of anomaly detection, data cleaning, and soften label strategies enhanced the comprehension of lesion image features by the model, thereby boosting its classification capacity. Our research offers valuable insights for future studies and lays the foundation for creation of more precise diagnostic tools.

    Keywords: deep learning, Data Enhancement Framework, endometrial cancer, Ultrasonography, diagnosis

    Received: 05 Jun 2024; Accepted: 23 Sep 2024.

    Copyright: © 2024 Luo, Yang, Liu, Qin, Yu, Gao, Xu, Cha, Zhu, Chen, Wang, Cao, Zhou and Fang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Xiaoying Liu, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
    Liufeng Qin, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
    Zhengjun Yu, Kaihua County People's Hospital, Quzhou, China
    Yunxia Gao, The Second People's Hospital of Quzhou, Quzhou, Zhejiang Province, China
    Xia Xu, Changshan County People's Hospital, Quzhou, China
    Guofen Cha, Quzhou Kecheng People's Hospital, Quzhou, China
    Xuehua Zhu, Quzhou Maternity and Child Health Care Hospital, Quzhou, Zhejiang, China
    Gang Chen, Kaihua County People's Hospital, Quzhou, China
    Xue Wang, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
    Lulu Cao, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
    Yuwang Zhou, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China
    Yun Fang, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s Hospital, Quzhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.