Deep Learning Models to Detect Anterior Cruciate Ligament Injury on MRI: A Comprehensive Review

Area of Science:

• Orthopedics
• Radiology
• Artificial Intelligence

Background:

• Magnetic resonance imaging (MRI) is standard for diagnosing anterior cruciate ligament (ACL) injuries.
• Artificial intelligence (AI) and deep learning (DL) are increasingly explored in medical imaging.
• DL applications in musculoskeletal imaging, particularly for ACL tears, are a growing research area.

Purpose of the Study:

• To review current applications of DL models for detecting ACL injuries on MRI.
• To synthesize existing literature on DL for ACL tear detection.
• To identify trends and challenges in this field.

Main Methods:

• Systematic review of 23 relevant articles.
• Analysis of DL concepts and applications in ACL injury detection.
• Synthesis of findings on DL model performance and clinical impact.

Main Results:

• DL models demonstrate high accuracy in identifying ACL injuries on MRI.
• These models can assist clinicians, particularly those with less experience.
• Significant time efficiency was observed with DL applications.
• Research originated from 10 countries, led by China and the USA.

Conclusions:

• DL models are a promising tool for MRI-based ACL injury detection.
• These AI-driven approaches can enhance clinical practice and patient care.
• Further technological advancements are needed for routine clinical implementation.