A deep learning tool, DeepENE, exceeded radiologist performance in identifying lymph node extranodal extension in head and neck cancers using preoperative CT scans.
Key Details
- 1DeepENE algorithm developed for detecting extranodal extension (ENE) on preoperative CT in laryngeal and hypopharyngeal squamous cell carcinoma (LHSCC) patients.
- 2Study included 289 LHSCC patients and 1,954 pathologically confirmed lymph nodes from 2011 to 2022.
- 3DeepENE was validated across three external test sets, showing AUCs of 0.96, 0.87, and 0.90, compared to radiologist AUCs of 0.85, 0.66, and 0.71 respectively.
- 4AI showed higher sensitivity (e.g. 97%, 78%, 87%) than radiologists (77%, 36%, 46%) across external test sets.
- 5Specificity and accuracy of DeepENE were comparable to radiologists, while sensitivity and AUC were consistently higher.
- 6Researchers plan prospective trials to use DeepENE as a decision-support tool in clinical workflows.
Why It Matters
This development highlights AI's ability to boost detection accuracy for challenging radiological findings, which can lead to more reliable pretreatment planning and outcomes for head and neck cancer patients. Adoption of such tools could enhance radiologist performance, reduce diagnostic variability, and support precision oncology.
Source
AuntMinnie
Related News
•Radiology Business
AI-Powered Tool Streamlines CT Scan Prioritization in Emergency Departments
An AI-based CT queue system significantly reduces wait times for ED patients by prioritizing scans likely to reveal critical findings.
•Radiology Business
AI Workflow Enables General Radiologists to Match Breast Specialists in Screening
AI-powered workflow helps generalist radiologists detect breast cancer at rates comparable to specialists.
•Radiology Business
LLMs Automate Radiology Report Quality Control, Study Finds
LLM-based systems can rapidly automate radiology report quality control, saving significant manual review time.