Deep learning–based automatic adenoid segmentation and a novel volume-based index for adenoid hypertrophy assessment

Key Points

• The aim is to develop an automated method for accurate segmentation and assessment of adenoid hypertrophy.
• Utilized deep learning techniques for automated adenoid segmentation.
• Proposed a 3D-AN method based on volumetric ratios.
• Focused on enabling early detection of airway obstruction related to adenoid issues.
• Demonstrated accurate adenoid segmentation through automated processing.
• Showed potential for the 3D-AN method to aid in enhancing clinical decision-making.
• Indicated that volumetric ratios could be beneficial for future adenoid assessments.