What question did this study set out to answer?

The study aims to evaluate the clinical relevance of retropharyngeal edema volume and develop a deep learning algorithm for segmentation and classification.

February 25, 2026European Radiology Experimental1 citationsOpen Access

Acute deep neck infection MRI: deep learning segmentation and clinical relevance of retropharyngeal edema volume

VVVille Sakari ViertonenUniversity of Turku ASAapo SirénUniversity of Turku MNMikko NymanUniversity of Turku

Key Points

The study aims to evaluate the clinical relevance of retropharyngeal edema volume and develop a deep learning algorithm for segmentation and classification.
Developed a deep learning-based algorithm for slice-wise classification and automatic segmentation of retropharyngeal edema.
Achieved classification performance and assessed segmentation using Dice similarity coefficients.
Compared volume of retropharyngeal edema with markers of severe illness.
Retropharyngeal edema volume correlated with markers of severe illness.
Classification model showed excellent performance in detecting edema.
Segmentation produced modest Dice similarity coefficients, aligning with existing tumor segmentation algorithms.

Abstract

RPE volume correlated with markers of severe illness and outperformed binary RPE classification. We developed a DL-based algorithm for slice-wise classification and automatic segmentation of RPE. The classification model achieved excellent performance, while segmentation yielded modest Dice similarity coefficients consistent with prior imaging-based tumor segmentation algorithms.

KI fragen

Bookmark

View Full Paper