Breast cancer is the most common cancer among women in the world. It is one of the leading causes of cancer related death in most of the countries including Malaysia. Conventional method to diagnose breast cancer requires pathologist to examine the breast tissue under a microscope. This task is time consuming, tedious, and complex. Fortunately, computer methods such as image processing could be used to assist breast tissue examination and speed up the process. This study proposes contrast enhancement using partial contrast technique to enhance quality and contrast of the breast cancer histopathology images. Intensity ranges of the selected areas on breast cancer histopathology images such as nucleus, cytoplasm and mitotic cells were determined. Using the proposed technique, the determined intensity ranges were stretched, and the others were compressed. PSNR and RMSE metrics were used to analyse the results. The average PSNR of the enhanced image (26.632 dB) is higher than the original images (24.425 dB). For RMSE, the enhanced image has a lower value (7.303) than the original image (7.976). This shows the proposed partial contrast technique could provide better contrast of breast cancer images.

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

Contrast Enhancement Method Using Partial Contrast Technique on Breast Cancer Histopathology Images

  • Nazahah Mustafa,
  • Nur Syawanis Mohamad Sahidi,
  • Haniza Yazid,
  • Khairul Shakir Ab Rahman,
  • Suhardy Daud

摘要

Breast cancer is the most common cancer among women in the world. It is one of the leading causes of cancer related death in most of the countries including Malaysia. Conventional method to diagnose breast cancer requires pathologist to examine the breast tissue under a microscope. This task is time consuming, tedious, and complex. Fortunately, computer methods such as image processing could be used to assist breast tissue examination and speed up the process. This study proposes contrast enhancement using partial contrast technique to enhance quality and contrast of the breast cancer histopathology images. Intensity ranges of the selected areas on breast cancer histopathology images such as nucleus, cytoplasm and mitotic cells were determined. Using the proposed technique, the determined intensity ranges were stretched, and the others were compressed. PSNR and RMSE metrics were used to analyse the results. The average PSNR of the enhanced image (26.632 dB) is higher than the original images (24.425 dB). For RMSE, the enhanced image has a lower value (7.303) than the original image (7.976). This shows the proposed partial contrast technique could provide better contrast of breast cancer images.