Scholarlink

Purpose <p> The utility of <sup>18</sup>F-fluorodeoxyglucose positron emission tomography with low-dose computed tomography (<sup>18</sup>F-FDG PET/CT) to diagnose patients with atypical features but clinically confirmed PMR is unknown. This study explored <sup>18</sup>F-FDG PET/CT findings among atypical PMR cases and contrasted results with a typical PMR population. The performance of an AI model for PMR diagnosis was also tested.</p> Methods <p> Natural language processing searched the electronic data warehouse at our institution for <sup>18</sup>F-FDG PET/CT reports with PMR findings. Medical record review confirmed the clinical diagnosis for potential cases. Required entry Criteria of the 2012 EULAR/ACR Classification for PMR (age ≥50 years, bilateral shoulder aching and abnormal CRP and/or ESR) stratified patients as “typical” or“atypical”. Qualitative and semi-quantitative (SUV<sub>max</sub>) scoring of <sup>18</sup>F-FDG uptake at characteristic musculoskeletal sites was undertaken for steroid-naïve, atypical PMR patients and compared with results for steroid-naïve, typical cases from an earlier study. A ResNet50 AI model was tested on the atypical cohort’s images, with GradCam maps generated and cross-checked by an experienced clinician. </p> Results <p> 225 <sup>18</sup>F-FDG PET/CT reports were retrieved from &gt;38,000 scans; 121 patients had a clinical PMR diagnosis. Seventeen steroid-naïve, atypical cases were compared with 35 steroid-naïve, typical patients. The frequency of abnormalities at key musculoskeletal sites was similar between groups, however mean SUV<sub>max</sub>was significantly higher in the typical cohort. The AI model identified a PMR diagnosis in 16/17 (94.1%) atypical patients.</p> Conclusion <p> Characteristic findings of PMR are appreciated on <sup>18</sup>F-FDG PET/CT among atypical patients, but avidity is reduced. AI technology can reliably detect this imaging pattern. Words: 249 <sub>(max. 250)</sub>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Polymyalgia rheumatica patients presenting with atypical clinical features still exhibit characteristic 18F-FDG PET/CT findings

  • 期刊论文

  • 发表日期：

    2025年12月6日

查看全文
  • Emily Martin,
  • Christopher R. McMaster,
  • Aurora MT Poon,
  • Saskia J. Rowson,
  • Bonnia Liu,
  • Jessica L. Leung,
  • David FL Liew,
  • Andrew M. Scott,
  • Claire E. Owen

摘要

Purpose

The utility of 18F-fluorodeoxyglucose positron emission tomography with low-dose computed tomography (18F-FDG PET/CT) to diagnose patients with atypical features but clinically confirmed PMR is unknown. This study explored 18F-FDG PET/CT findings among atypical PMR cases and contrasted results with a typical PMR population. The performance of an AI model for PMR diagnosis was also tested.

Methods

Natural language processing searched the electronic data warehouse at our institution for 18F-FDG PET/CT reports with PMR findings. Medical record review confirmed the clinical diagnosis for potential cases. Required entry Criteria of the 2012 EULAR/ACR Classification for PMR (age ≥50 years, bilateral shoulder aching and abnormal CRP and/or ESR) stratified patients as “typical” or“atypical”. Qualitative and semi-quantitative (SUVmax) scoring of 18F-FDG uptake at characteristic musculoskeletal sites was undertaken for steroid-naïve, atypical PMR patients and compared with results for steroid-naïve, typical cases from an earlier study. A ResNet50 AI model was tested on the atypical cohort’s images, with GradCam maps generated and cross-checked by an experienced clinician.

Results

225 18F-FDG PET/CT reports were retrieved from >38,000 scans; 121 patients had a clinical PMR diagnosis. Seventeen steroid-naïve, atypical cases were compared with 35 steroid-naïve, typical patients. The frequency of abnormalities at key musculoskeletal sites was similar between groups, however mean SUVmaxwas significantly higher in the typical cohort. The AI model identified a PMR diagnosis in 16/17 (94.1%) atypical patients.

Conclusion

Characteristic findings of PMR are appreciated on 18F-FDG PET/CT among atypical patients, but avidity is reduced. AI technology can reliably detect this imaging pattern. Words: 249 (max. 250).