Computational Intelligence in Cancer Diagnostics: A Contemporary Review of Smart Phone Apps, Current Problems, and...

Area of Science:

• Oncology
• Artificial Intelligence
• Medical Imaging

Background:

• Cancer is a leading cause of mortality, often difficult to detect early.
• Accurate and timely cancer diagnosis is crucial for effective treatment and prognosis.
• Traditional diagnostic methods rely on imaging techniques like X-rays, CT, MRI, and PET scans.

Purpose of the Study:

• To evaluate computational intelligence approaches for cancer diagnosis.
• To highlight the role of machine learning and deep learning models in cancer detection.
• To review the advantages and disadvantages of various AI models in cancer diagnosis.

Main Methods:

• Systematic review of 114 studies using the PRISMA-ScR methodology.
• Evaluation of machine learning models including K Nearest Neighbour (KNN), Support Vector Machine (SVM), Naïve Bayes, and Decision Tree.
• Assessment of deep learning models such as Deep Neural Networks and Deep Boltzmann Machines.

Main Results:

• Artificial intelligence models demonstrate significant potential in enhancing cancer imaging analysis.
• Various machine learning and deep learning techniques offer distinct advantages for cancer diagnosis.
• The review outlines the application of these AI models across different cancer types.

Conclusions:

• AI, particularly machine learning and deep learning, holds substantial promise for advancing cancer diagnosis.
• Further research is needed to address clinical challenges and fully integrate AI into diagnostic workflows.
• AI can significantly improve the accuracy and efficiency of cancer detection and imaging interpretation.