Colon Cancer Diagnosis Based on Machine Learning and Deep Learning: Modalities and Analysis Techniques

Area of Science:

• Oncology
• Medical Imaging
• Computational Biology

Background:

• Colon cancer poses significant global health and economic challenges due to high mortality rates.
• Accurate diagnosis relies on analyzing glandular structure from histopathology images.
• Early detection is crucial for effective treatment and improved survival rates.

Purpose of the Study:

• To provide a comprehensive survey of colon cancer diagnosis methods.
• To review current deep learning (DL) and machine learning (ML) techniques in colon cancer detection.
• To identify strengths, limitations, and future research directions in the field.

Main Methods:

• Literature review of studies on colon cancer diagnosis.
• Classification of techniques into deep learning (DL) and machine learning (ML).
• Discussion of imaging modalities (histopathology), datasets, and performance metrics.

Main Results:

• DL and ML techniques show promise for early colon cancer detection.
• These methods support the identification of pre-malignant polyps, aiding prevention.
• The review categorizes current studies, highlighting their respective advantages and disadvantages.

Conclusions:

• Advanced computational techniques are vital for enhancing colon cancer diagnosis and screening.
• Early detection through DL and ML can significantly lower mortality rates.
• Further research is needed to address existing challenges and refine diagnostic tools.