Quantifying nasal deformities using a novel mathematical method to complement preoperative assessment in rhinoplasty...

Area of Science:

• Plastic Surgery
• Artificial Intelligence
• Medical Imaging

Background:

• Accurate quantification of nasal defects pre-rhinoplasty is challenging.
• Existing methods lack precision for optimal surgical planning.
• Enhancing facial symmetry and functionality through rhinoplasty requires reliable preoperative assessment.

Purpose of the Study:

• To introduce a novel AI-driven approach for quantifying nasal defects using 2D images.
• To provide a tool for improved preoperative planning in rhinoplasty.
• To enhance surgical outcomes and patient satisfaction through accurate defect assessment.

Main Methods:

• Utilized a pre-trained AI model for facial landmark detection on 250 patient images.
• Analyzed 36 distances between facial landmarks, normalized using min-max scaling.
• Calculated statistical parameters (mean, median, standard deviation) for defect quantification.

Main Results:

• Validated methodology across diverse ethnicities and regions.
• Achieved reliable quantification of nasal defects, averaging 76.2%.
• Demonstrated potential as a beneficial surgical aid for preoperative planning.

Conclusions:

• The AI method significantly improves rhinoplasty surgical planning and outcomes.
• Potential applications include other facial plastic surgeries and app-based software.
• This fusion of AI and plastic surgery enhances patient-doctor communication and satisfaction.