A coordinate registration-based structured magnetic resonance imaging reporting method for nasopharyngeal carcinoma: a preliminary study.

Abstract

Background: Current reporting methods for nasopharyngeal carcinoma (NPC) imaging are typically limited to binary descriptions of whether tumors invade specific anatomical structures. This approach is coarse and fails to capture precise invasion details necessary for improved clinical decision-making. Research on structured reporting methods for NPC that capture fine-grained invasion details is limited. In this study, we analyzed voxelwise invasion rate (VIR) based on the coordinate system registration and proposed a new preliminary method for automatic generation of structured reporting with quantitative information for NPC.

Methods: A dataset of magnetic resonance images from 778 patients, collected from a cancer center, was registered to a nasopharyngeal coordinate system constructed based on anatomical for further analysis. The VIR of the structures was calculated based on the overlapping voxels of nasopharyngeal tumor region of interest (ROI) and the ROI of typical anatomical structures to obtain a preliminary structured report of the magnetic resonance images of NPC. The binarized VIR results, thresholded by the receiver operating characteristic curve Youden index, were compared with the physician's manual fine-reading reports to verify their accuracy and to analyze the metric parameters of the patients' structured reports.

Results: The proposed structured reporting method for NPC achieved an average accuracy of 81.1% on 20 anatomical structures, and a specificity of 85.8% and an average area under the curve (AUC) of 0.791. Then, a preliminary structured reporting scheme for tumor invasion was designed to automatically generate clinical structured reports.

Conclusions: The VIR method provides a novel framework for structured magnetic resonance imaging (MRI) reporting of NPC, offering a more practical and quantitative approach to tumor invasion analysis. This advancement has significant potential for improving the automation and clinical utility of structured reporting in NPC diagnosis and management.