A Coordinate Registration-Based Structured Magnetic Resonance Imaging Reporting Method for Nasopharyngeal Carcinoma: a Preliminary Study.
Quantitative imaging in medicine and surgery（2025）
School of Life & Environmental Science
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.
MoreTranslated text
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined