Lymph node metastasis detection using artificial intelligence in T1 colorectal cancer: A comprehensive systematic...

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Accurate prediction of lymph node metastasis (LNM) is crucial for staging and treatment decisions in T1 colorectal cancer (CRC).
• Current methods for LNM assessment can be invasive and may lead to overtreatment.
• There is a growing need for non-invasive, accurate predictive tools in early-stage CRC management.

Approach:

• A systematic review was conducted to evaluate the application of artificial intelligence (AI) algorithms in predicting LNM in T1 CRC.
• Thirteen studies involving 8417 patients were analyzed to assess AI's performance.
• Key performance metrics including sensitivity, specificity, and Area Under the Curve (AUC) were extracted and synthesized.

Key Points:

• AI models demonstrated significant potential in predicting LNM in T1 CRC across the included studies.
• Reported sensitivity, specificity, and AUC values for AI in LNM prediction ranged from 0.561-1.0, 0.45-1.0, and 0.717-1.0, respectively.
• The application of AI in predicting LNM showed a potential reduction in unnecessary surgeries by approximately 70%.

Conclusions:

• AI holds considerable promise as a tool for predicting lymph node metastasis in T1 colorectal cancer.
• AI-driven prediction can aid in optimizing treatment strategies and potentially decreasing the rate of unnecessary surgical interventions.
• Further research and clinical validation are warranted to integrate AI into routine T1 CRC management protocols.