Scholarlink

Background <p>Fever of unknown origin (FUO) remains diagnostically challenging because of heterogeneous causes, non-specific clinical manifestations, and overlapping imaging findings. We developed and validated FUO-PETMamba, a PET maximum-intensity-projection (MIP)-based artificial intelligence framework for AI-assisted aetiological classification of FUO.</p> Methods <p>This retrospective multicentre study included 681 patients with FUO who underwent baseline [18&#xa0;F]FDG PET/CT, comprising one development cohort (<i>n</i> = 355) and two independent external validation cohorts (<i>n</i> = 195 and <i>n</i> = 131). FUO-PETMamba is a weakly supervised framework analysing PET MIP images generated from PET data. Model performance was assessed by discrimination, calibration, decision curve analysis (DCA). Attention-based visual explanations were generated using attention mechanisms and gradient-based activation mapping. A reader study assessed the potential assistive effect of model-predicted probabilities on physicians with different PET/CT experience.</p> Results <p>In the development cohort, FUO-PETMamba achieved AUCs of 0.838 for malignancy, 0.851 for infection, 0.914 for autoimmune disease, and 0.788 for miscellaneous causes. Corresponding AUCs were 0.809, 0.815, 0.805, and 0.849 in external validation cohort 1, and 0.808, 0.772, 0.701, and 0.927 in external validation cohort 2, respectively. Calibration and decision curve analysis suggested potential clinical benefit for the major aetiological categories, although performance varied across cohorts and classes. The miscellaneous category should be interpreted cautiously because of limited case numbers and low positive predictive value and F1 scores. In the reader study, AI assistance improved diagnostic accuracy for junior and intermediate physicians, whereas changes in senior-physician performance were variable. Post hoc attention-based visualisations highlighted clinically plausible hypermetabolic patterns and served as qualitative explanatory aids.</p> Conclusions <p>FUO-PETMamba provides a PET MIP-based AI-assisted diagnostic support framework for aetiological classification of FUO across multicentre cohorts and may help reduce experience-dependent diagnostic variability after prospective validation.</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

FUO-PETMamba: a pet maximum-intensity-projection-based artificial intelligence framework for aetiological classification of fever of unknown origin with multicentre validation

  • 期刊论文

  • 发表日期：

    2026年7月11日

查看全文
  • Chong Jiang,
  • Zekun Jiang,
  • Yue Teng,
  • Ruihe Lai,
  • Yi Zhou,
  • Zitong Zhang,
  • Hexiao Huang,
  • Yunyi Liu,
  • Zhichao Xie,
  • Ming Jiang,
  • Jingyan Xu,
  • Chongyang Ding,
  • Linhao Qu,
  • Rong Tian

摘要

Background

Fever of unknown origin (FUO) remains diagnostically challenging because of heterogeneous causes, non-specific clinical manifestations, and overlapping imaging findings. We developed and validated FUO-PETMamba, a PET maximum-intensity-projection (MIP)-based artificial intelligence framework for AI-assisted aetiological classification of FUO.

Methods

This retrospective multicentre study included 681 patients with FUO who underwent baseline [18 F]FDG PET/CT, comprising one development cohort (n = 355) and two independent external validation cohorts (n = 195 and n = 131). FUO-PETMamba is a weakly supervised framework analysing PET MIP images generated from PET data. Model performance was assessed by discrimination, calibration, decision curve analysis (DCA). Attention-based visual explanations were generated using attention mechanisms and gradient-based activation mapping. A reader study assessed the potential assistive effect of model-predicted probabilities on physicians with different PET/CT experience.

Results

In the development cohort, FUO-PETMamba achieved AUCs of 0.838 for malignancy, 0.851 for infection, 0.914 for autoimmune disease, and 0.788 for miscellaneous causes. Corresponding AUCs were 0.809, 0.815, 0.805, and 0.849 in external validation cohort 1, and 0.808, 0.772, 0.701, and 0.927 in external validation cohort 2, respectively. Calibration and decision curve analysis suggested potential clinical benefit for the major aetiological categories, although performance varied across cohorts and classes. The miscellaneous category should be interpreted cautiously because of limited case numbers and low positive predictive value and F1 scores. In the reader study, AI assistance improved diagnostic accuracy for junior and intermediate physicians, whereas changes in senior-physician performance were variable. Post hoc attention-based visualisations highlighted clinically plausible hypermetabolic patterns and served as qualitative explanatory aids.

Conclusions

FUO-PETMamba provides a PET MIP-based AI-assisted diagnostic support framework for aetiological classification of FUO across multicentre cohorts and may help reduce experience-dependent diagnostic variability after prospective validation.