Scholarlink

Polycystic Ovary Syndrome (PCOS) is a prevalent hormonal disorder among women of childbearing age, marked by an imbalance in hormones, inconsistent menstrual periods, and polycystic ovaries. Prompt and precise detection of PCOS is vital for effective management and therapy. Conventional diagnostic methods include clinical assessments, blood tests, and ultrasound scans. Nevertheless, these techniques may be subjective, lengthy, and vary between observers. Lately, deep learning methods have demonstrated significant potential in automating the analysis of medical images, including PCOS diagnosis. This paper reviews the latest deep learning strategies for the automated detection of PCOS using various medical imaging tools, such as ultrasound, MRI, and infrared thermography. It examines the hurdles, data sources, evaluation criteria, and the efficacy of different deep learning models in this domain. Furthermore, it sheds light on the possible clinical uses, constraints, and prospective areas of research within this specialty.

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

Deep Learning Approaches for Automated Diagnosis of Polycystic Ovary Syndrome Using Medical Imaging: A Comprehensive Survey

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Chiranjib Dutta,
  • Sabyasachi Mazumder,
  • Sayan Neogy,
  • Sandip Roy

摘要

Polycystic Ovary Syndrome (PCOS) is a prevalent hormonal disorder among women of childbearing age, marked by an imbalance in hormones, inconsistent menstrual periods, and polycystic ovaries. Prompt and precise detection of PCOS is vital for effective management and therapy. Conventional diagnostic methods include clinical assessments, blood tests, and ultrasound scans. Nevertheless, these techniques may be subjective, lengthy, and vary between observers. Lately, deep learning methods have demonstrated significant potential in automating the analysis of medical images, including PCOS diagnosis. This paper reviews the latest deep learning strategies for the automated detection of PCOS using various medical imaging tools, such as ultrasound, MRI, and infrared thermography. It examines the hurdles, data sources, evaluation criteria, and the efficacy of different deep learning models in this domain. Furthermore, it sheds light on the possible clinical uses, constraints, and prospective areas of research within this specialty.