Radiological staging clinical decision support model for rectal cancer lymph node metastasis detection on MRI.

AI / informaticsBMC cancer· May 2026

Radiological staging clinical decision support model for rectal cancer lymph node metastasis detection on MRI.

Benjamin Keel, Aaron Quyn, David Jayne, Samuel D Relton

Read paper

Medical Imaging AIAI / informaticsDiagnosisQ2IF 4.0

Artificial intelligence model beat expert radiologists at staging rectal cancer lymph node metastasis on Magnetic Resonance Imaging

Radiological staging clinical decision support model for rectal cancer lymph node metastasis detection on MRI.

Benjamin Keel … Samuel D Relton

BMC cancer · May 2026

Background

Accurate staging of lymph node metastasis (lymph node metastasis) is crucial for personalising rectal cancer treatment.

Methods

Models were trained and evaluated on an in-house dataset provided by Leeds Teaching Hospitals NHS Trust (LTHT) including 458 patients with pre-operative Magnetic Resonance Imaging scans, patient clinical data, and post-operative pathological TNM staging.

n = 458 patients

Results

9%

higher F1 score

Artificial intelligence matched post-surgery pathology results more accurately than radiologists

n = 458 patients

More results

The results demonstrate state-of-the-art performance with cross-validated metrics of 0.828 AUC, 86.6% sensitivity, and 72.4% specificity.

“

Conclusion · 1 of 2

This study provides strong evidence that an end-to-end artificial intelligence model can significantly improve pre-operative staging of rectal cancer lymph node metastasis.

Conclusion · 2 of 2

The model outperformed expert radiologists and shows clear potential to enhance clinical decision making and improve patient outcomes.

Radiological staging clinical decision support model for rectal cancer lymph node metastasis detection on MRI.

Radiological staging clinical decision support model for rectal cancer lymph node metastasis detection on MRI.

Related papers