BCLC classification and AI-based image quantification: What is meant to be will come together - but how and when?

Area of Science:

• Hepatocellular Carcinoma Research
• Medical Imaging Analysis
• Artificial Intelligence in Oncology

Background:

• The Barcelona Clinic Liver Cancer (BCLC) classification is a standard for hepatocellular carcinoma (HCC) prognosis and treatment selection.
• Current BCLC relies on basic clinical and imaging data, potentially underutilizing information from radiology.
• Advancements in Artificial Intelligence (AI) offer new methods for detailed, automated analysis of medical images.

Purpose of the Study:

• To evaluate AI-quantified imaging parameters for their potential synergy with the BCLC classification.
• To explore how AI can bridge the gap between quantitative imaging and clinical decision-making in HCC management.

Main Methods:

• Review of current AI applications in radiology for HCC, including automated tumor volumetry and radiomics.
• Assessment of AI's capability to extract quantitative features from routine radiology imaging.
• Analysis of the potential integration of AI-derived data with the established BCLC classification framework.

Main Results:

• AI methods can automatically extract detailed digital imaging features with high precision, going beyond BCLC's current scope.
• Despite AI advancements, a translational gap exists due to technical, administrative, and implementation challenges.
• AI holds potential to supplement the BCLC classification by providing richer imaging insights.

Conclusions:

• AI-powered quantitative imaging offers a promising avenue to augment the established BCLC classification for HCC.
• Overcoming implementation barriers is crucial for realizing the full clinical potential of AI in HCC management.
• Synergistic use of AI and BCLC classification could lead to more precise prognostic assessment and treatment selection in HCC.