Neck Imaging Reporting and Data System
NI-RADS is the ACR's system for surveillance imaging after treatment for head and neck cancer — the setting where post-surgical and post-radiation change constantly mimics recurrence. It pairs a standardized lexicon with numeric levels of suspicion, each tied to a management recommendation, so the “worrying-looking but treated” neck gets read consistently instead of case by case. The original 2018 paradigm covered CT and FDG-PET/CT; the 2025 update adds descriptors and management guidance specific to MRI, for the cancers best followed with that modality. Its aim is to catch submucosal recurrence early enough for salvage surgery while damping down false alarms.
Adds descriptors and management guidance specific to MRI, extending standardized post-treatment surveillance to the head-and-neck cancers best followed with that modality.
The original paradigm: a standardized surveillance lexicon with numeric levels of suspicion tied to management, for CT and FDG-PET/CT after treatment of head and neck cancer.
An LLM (GPT-5) extracted pNI-RADS and nNI-RADS scores from OPC surveillance reports with 93.3% and 90.3% agreement for NI-RADS 1 (no disease). For NI-RADS ≥2, exact category agreement was 73.1% (pNI-RADS) and 64.3% (nNI-RADS). Disease-status specificity was 0.95–0.99. Retrospect…
RadPigeon is an independent radiology news digest and is not affiliated with or endorsed by American College of Radiology (ACR). “NI-RADS” is a trademark of its owner and is named here only to refer to the system. Always consult the official source for the exact, current criteria.