Positron Emission Tomography-Derived Radiomics and Artificial Intelligence in Multiple Myeloma: State-of-the-Art

Area of Science:

• Oncology
• Medical Imaging
• Data Science

Background:

• Multiple myeloma (MM) is a common, heterogeneous blood cancer.
• Accurate patient stratification is crucial for effective treatment selection in MM.
• Current imaging methods like PET/CT have limitations in MM characterization.

Purpose of the Study:

• To review the current applications of radiomics and AI in multiple myeloma.
• To assess the potential of AI-driven image analysis for MM patient management.
• To summarize findings from systematic literature searches on radiomics and AI in MM.

Main Methods:

• Systematic literature search of PubMed, Web of Science, and Scopus.
• Inclusion of English-language articles on radiomics and AI analyses of PET/CT in MM.
• Review of studies focusing on machine learning (ML) and deep learning (DL) algorithms.

Main Results:

• Radiomics and AI extract valuable information from medical images beyond human visual perception.
• These techniques show potential for improved clinical stratification of MM patients.
• Initial results suggest enhanced clinical benefits for MM patients through AI-driven analysis.

Conclusions:

• Radiomics and AI hold significant promise for advancing multiple myeloma diagnostics and treatment.
• Further research and validation are necessary before widespread clinical implementation.
• These technologies can potentially optimize patient care and outcomes in MM.