Purpose: Breast cancer is one of the predominant types of cancer in the world. Early diagnosis of the diseased condition is helpful to physicians to plan the treatment and able to achieve speedy recovery of the individual. Aim: The objective of the proposed work is to develop an expert system using principles of artificial intelligence to aid oncologists and clinicians in the diagnosis and follow-up analysis for breast cancer. The proposed system comprises of three sections, namely, knowledge database, diagnostic toolkit, and follow-up analysis. Method: The knowledge database comprises of information related to breast cancer for quick reference of the clinician. The diagnostic toolkit comprises of survey forms and feature based rule tests for pre-diagnosis. Subsequent section includes machine learning guided biochemical tests and deep learning aided medical imaging tests for diagnosis, leads to confirmation and staging of breast cancer. The follow-up analysis aids in the assessment of the prognosis of patients. Conclusion: The proposed expert system could be a comprehensive set-up for the clinicians in their medical diagnosis and analysis and it provides a better service for breast cancer patients.

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

Expert System for Breast Cancer Identification

  • S. Rajkumar,
  • V. A. Sairam,
  • Samyuktha Kapoor,
  • Ahmad Abdelhafiz Ali Samhan,
  • J. Nithila,
  • Jayant Giri

摘要

Purpose: Breast cancer is one of the predominant types of cancer in the world. Early diagnosis of the diseased condition is helpful to physicians to plan the treatment and able to achieve speedy recovery of the individual. Aim: The objective of the proposed work is to develop an expert system using principles of artificial intelligence to aid oncologists and clinicians in the diagnosis and follow-up analysis for breast cancer. The proposed system comprises of three sections, namely, knowledge database, diagnostic toolkit, and follow-up analysis. Method: The knowledge database comprises of information related to breast cancer for quick reference of the clinician. The diagnostic toolkit comprises of survey forms and feature based rule tests for pre-diagnosis. Subsequent section includes machine learning guided biochemical tests and deep learning aided medical imaging tests for diagnosis, leads to confirmation and staging of breast cancer. The follow-up analysis aids in the assessment of the prognosis of patients. Conclusion: The proposed expert system could be a comprehensive set-up for the clinicians in their medical diagnosis and analysis and it provides a better service for breast cancer patients.