Scholarlink

Advances in computer vision, especially with convolutional neural networks and transformer models, have improved the accuracy and efficiency of medical image analysis, facilitating more accessible and accurate diagnoses in the biomedical field. Early detection of cervical cancer (CaCu) precursor lesions is key to preventing the development of this neoplasm, but achieving an accurate diagnosis requires great expertise due to the morphological complexity of the cells involved. In this project, we implemented the development of a deep learning computer vision tool to identify and classify squamous intraepithelial lesions of the cervix using a Papanicolaou cytology database, observing 83% accuracy and a macro F1-score index of 0.83 using an artificial convolutional neural network.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Classification of Low-Grade Squamous Intraepithelial Lesions of the Cervix Using Deep Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jesús Alberto Palma-García,
  • Berenice Illades-Aguiar,
  • Mónica Espinoza-Rojo,
  • Mónica Ramírez-Ruano,
  • Alberto Ochoa-Zezzati ,
  • Iván Gallardo-Bernal,
  • Fredy Omar Beltrán-Anaya

摘要

Advances in computer vision, especially with convolutional neural networks and transformer models, have improved the accuracy and efficiency of medical image analysis, facilitating more accessible and accurate diagnoses in the biomedical field. Early detection of cervical cancer (CaCu) precursor lesions is key to preventing the development of this neoplasm, but achieving an accurate diagnosis requires great expertise due to the morphological complexity of the cells involved. In this project, we implemented the development of a deep learning computer vision tool to identify and classify squamous intraepithelial lesions of the cervix using a Papanicolaou cytology database, observing 83% accuracy and a macro F1-score index of 0.83 using an artificial convolutional neural network.