In recent years, Artificial Intelligence (AI) has become one of the most prominent and versatile tools with applications that spread across multiple disciplines, including biomedical engineering. The introduction of AI has brought radical changes to the field, especially in the sector of pathology. Modern machine learning-based diagnosis methods are becoming increasingly popular and are being incorporated into the practical diagnosis to assist human pathologists.

Since we do not have any guaranteed cure for cancer at its advanced stages, early detection through periodic diagnosis is crucial in our fight against this disease. AI promises to be an effective weapon in this regard. AI-based methods are less costly and faster in detecting cancerous tumours and determining its type than most of the contemporary diagnosis methods. However, the accuracy and reliability of the decisions taken by computers are still questionable. Numerous researchers are working worldwide to make AI-based cancer diagnosis methods more robust and stable for practical use. So far, many novel approaches have been reported, and some have been practically tested as well. However, we are still some distance away from a point where we can reasonably trust machines solely to make such life-altering decisions as identifying cancer in patients. Therefore, more theoretical analysis and practical experiments are required in this field of research.

This Special Issue aims to promote research on machine learning (ML) and AI-based cancer diagnosis methods. Priorities will be given to the studies that focus on analyzing various types of cancer data such as histopathological images, Computer Tomography (CT) images, or tumour images (in the case of skin or colorectal cancer) using various Digital Image Processing and/or feature extraction methods. Researchers are encouraged to report their novel cancer classification, prediction, or segmentation methods. Review articles that focus on the trend of various ML-models being used in cancer diagnosis and comparative studies that explore the effectivity of previously reported methods are also welcome. New datasets containing images of a particular type or several types of cancer can be introduced through this Special Issue as well.

Potential topics include but are not limited to the following:

• Novel methods for cancer image classification and/or segmentation
• Machine learning-based models for cancer detection and/or prediction
• Various types of cancer image analysis
• Denoising and/or synthetic data generation of cancer diagnosis
• Mobile applications for cancer detection and/or prediction
• Review articles on machine learning-based cancer diagnosis
• New cancer image dataset introduction
• Comparative studies on cancer diagnosis