Scholarlink

Purpose <p>To develop and validate a multimodal deep learning framework that integrates clinical metadata with [<sup>18</sup>F]FDG PET/CT imaging to resolve overlapping metabolic phenotypes. The primary objective is the histological subtyping of non-small cell lung cancer (NSCLC), utilizing binary clinical staging (early vs. advanced) strategically as an auxiliary regularization task.</p> Methods <p>A multi-center surgical NSCLC cohort (<i>n</i> = 780) was partitioned into a development set (<i>n</i> = 675) and an independent external test set (<i>n</i> = 105). The framework first utilized a 3D Transformer for bounding-box-based tumor localization. Subsequently, a multi-task network employed Feature-wise Linear Modulation (FiLM) to dynamically inject clinical metadata into the visual backbone.</p> Results <p>For histological subtyping of adenocarcinoma versus squamous cell carcinoma, in the validation cohort, the proposed multimodal framework achieved the highest area under the receiver operating characteristic curve (AUC) of 0.894 (95% CI: 0.813–0.959), significantly outperforming the conventional radiomics baseline (AUC = 0.796, DeLong test <i>P</i> = 0.017) and the clinical-only baseline (AUC = 0.759, <i>P</i> = 0.004). On the internal test set, the multimodal model maintained an AUC of 0.832 (95% CI: 0.744–0.906), outperforming competing models numerically, though differences did not reach statistical significance (all <i>P</i> &gt; 0.11). On the independent external test cohort, the multimodal framework demonstrated superior cross-center stability, maintaining an AUC of 0.787 (95% CI: 0.687–0.876). On the external cohort, the between-model AUC differences did not reach statistical significance against the clinical-only model (AUC of 0.740, <i>P</i> = 0.480) or the image-only model (AUC of 0.685, <i>P</i> = 0.082). Nevertheless, the multimodal framework achieved the highest F1-score and yielded the most optimal net clinical benefit across a wide range of threshold probabilities in decision curve analysis. For the intrinsically challenging auxiliary staging task, the unguided image-only network exhibited severe vulnerability, however, the FiLM-based multimodal mechanism effectively enhanced diagnostic capacity by employing systemic clinical priors, improving the AUC to 0.656.</p> Conclusion <p>Combining 3D detection with an early clinico-biological fusion strategy effectively enhances NSCLC characterization on [<sup>18</sup>F]FDG PET/CT, which has the potential to mitigate the limitations of single-modality imaging in resolving diagnostically ambiguous cases characterized by overlapping [<sup>18</sup>F]FDG uptake phenotypes, thereby providing a non-invasive decision-support tool in the precision management of NSCLC.</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

Deep integration of clinical metadata with [18F]FDG PET/CT imaging for histological subtyping in non-small cell lung cancer: a multi-center study

  • 期刊论文

  • 发表日期：

    2026年6月18日

查看全文
  • Jucheng Zhang,
  • Xiaohui Zhang,
  • Jing Wang,
  • Han Hao,
  • Daoyan Hu,
  • Kangjun Hu,
  • Xuena Li,
  • Yaming Li,
  • Guanghui Liu,
  • Rong Tian,
  • Weiming Wu,
  • Xiaofen Ma,
  • Yile Huang,
  • Chentao Jin,
  • Yan Zhong,
  • Mei Tian,
  • Hong Zhang

摘要

Purpose

To develop and validate a multimodal deep learning framework that integrates clinical metadata with [18F]FDG PET/CT imaging to resolve overlapping metabolic phenotypes. The primary objective is the histological subtyping of non-small cell lung cancer (NSCLC), utilizing binary clinical staging (early vs. advanced) strategically as an auxiliary regularization task.

Methods

A multi-center surgical NSCLC cohort (n = 780) was partitioned into a development set (n = 675) and an independent external test set (n = 105). The framework first utilized a 3D Transformer for bounding-box-based tumor localization. Subsequently, a multi-task network employed Feature-wise Linear Modulation (FiLM) to dynamically inject clinical metadata into the visual backbone.

Results

For histological subtyping of adenocarcinoma versus squamous cell carcinoma, in the validation cohort, the proposed multimodal framework achieved the highest area under the receiver operating characteristic curve (AUC) of 0.894 (95% CI: 0.813–0.959), significantly outperforming the conventional radiomics baseline (AUC = 0.796, DeLong test P = 0.017) and the clinical-only baseline (AUC = 0.759, P = 0.004). On the internal test set, the multimodal model maintained an AUC of 0.832 (95% CI: 0.744–0.906), outperforming competing models numerically, though differences did not reach statistical significance (all P > 0.11). On the independent external test cohort, the multimodal framework demonstrated superior cross-center stability, maintaining an AUC of 0.787 (95% CI: 0.687–0.876). On the external cohort, the between-model AUC differences did not reach statistical significance against the clinical-only model (AUC of 0.740, P = 0.480) or the image-only model (AUC of 0.685, P = 0.082). Nevertheless, the multimodal framework achieved the highest F1-score and yielded the most optimal net clinical benefit across a wide range of threshold probabilities in decision curve analysis. For the intrinsically challenging auxiliary staging task, the unguided image-only network exhibited severe vulnerability, however, the FiLM-based multimodal mechanism effectively enhanced diagnostic capacity by employing systemic clinical priors, improving the AUC to 0.656.

Conclusion

Combining 3D detection with an early clinico-biological fusion strategy effectively enhances NSCLC characterization on [18F]FDG PET/CT, which has the potential to mitigate the limitations of single-modality imaging in resolving diagnostically ambiguous cases characterized by overlapping [18F]FDG uptake phenotypes, thereby providing a non-invasive decision-support tool in the precision management of NSCLC.