MRI-based deep learning model predicts recurrent nasopharyngeal carcinoma in post-radiation nasopharyngeal necrosis

Key Points

• Recurrent nasopharyngeal carcinoma prediction may improve patient outcomes through early intervention.
• The model achieved an accuracy rate of 85% in identifying potential relapses within a defined timeframe.
• Assessment using MRI data and deep learning techniques provided insights into recurrence patterns based on post-radiation conditions.
• This approach indicates a promising shift towards utilizing advanced imaging technology for effective cancer management.