A Survey on Machine Learning Based Medical Assistive Systems in Current Oncological Sciences

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Cancer is a global health challenge, often detected late due to subtle early symptoms.
• Automated detection systems aim to improve early cancer identification and reduce false positives.

Purpose of the Study:

• To review current machine learning techniques for cancer detection across various human organs.
• To detail imaging operations relevant to each cancer type discussed.

Main Methods:

• Review of state-of-the-art machine learning models for cancer identification.
• Elaboration of imaging analysis techniques supporting these models.

Main Results:

• Machine learning algorithms show promise in supporting healthcare practitioners for disease detection and growth prediction.
• These algorithms assist in risk assessment, potentially lowering cancer-related mortality.

Conclusions:

• Machine learning models provide valuable tools for preliminary investigations and tumor cell nature determination.
• Computer-Aided Detection (CAD) tools assist diagnostic radiologists in cancer assessment.