Scholarlink

Purpose <p>To develop a deep learning (DL) approach for automatic segmentation and accurate risk stratification in multiple myeloma <b>(</b>MM) using whole-body [<sup>18</sup>F]FDG PET/CT.</p> Methods <p>This retrospective study included MM patients who underwent [<sup>18</sup>F]FDG PET/CT between August 2013 and December 2023. To automatically segment focal lesions, an nnU-Net architecture was trained using dual-channel PET/CT inputs. For diffuse/mixed patterns, the tumor was automatically identified via bone segmentation using liver SUVmedian thresholds. Subsequently, DL and radiomics features were extracted using Pyradiomics and the STU-Net encoder. Then a deep learning radiomics nomogram (DLRN) was constructed using the Cox proportional hazards model and evaluated using the calibration curve, the receiver operating characteristic (ROC) curve, the Kaplan-Meier curve, and decision curve analysis.</p> Results <p>The study included 345 patients (median age, 59 years [IQR, 35–67 years], 198 male). The nnU-Net achieved a median DSC of 0.64–0.77 for focal lesions segmentation across cohorts. The DLRN was constructed by integrating deep learning radiomics score (DLRS), lactate dehydrogenase (LDH), and β2-microglobulin (β2-MG). The DLRN achieved an area under ROC curve (AUC) of 0.87 (95% confidence interval [CI]: 0.82–0.93), 0.84 (95% CI: 0.73–0.96), and 0.88 (95% CI: 0.76–0.99) for 3-year overall survival (OS) status prediction in the training, internal and external testing cohorts, which outperformed the International Staging System (ISS) (all <i>P</i> &lt; 0.05). Furthermore, the DLRN can effectively identify high-risk individuals (all <i>P</i> &lt; 0.05), demonstrated good agreement between predicted and observed survival probabilities, and provided clinical net benefit.</p> Conclusion <p>The pattern-specific DL approach achieved automated whole-body tumor segmentation in MM, and the established DLRN demonstrated improved risk stratification capability.</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

The deep learning radiomics nomogram for risk stratification in multiple myeloma using automatic whole-body [18F]FDG PET/CT segmentation approach

  • 期刊论文

  • 发表日期：

    2026年7月27日

查看全文
  • Meiling Xiao,
  • Yan Zhong,
  • Han Hao,
  • Xinhe Yu,
  • Daoyan Hu,
  • Jing Wang,
  • Chentao Jin,
  • Rui Zhou,
  • Rong Tian,
  • Lixiang Yang,
  • Congcong Yu,
  • Xiaofeng Dou,
  • Chunlei Han,
  • Riku Klén,
  • Xiaohui Zhang,
  • Mei Tian,
  • Hong Zhang

摘要

Purpose

To develop a deep learning (DL) approach for automatic segmentation and accurate risk stratification in multiple myeloma (MM) using whole-body [18F]FDG PET/CT.

Methods

This retrospective study included MM patients who underwent [18F]FDG PET/CT between August 2013 and December 2023. To automatically segment focal lesions, an nnU-Net architecture was trained using dual-channel PET/CT inputs. For diffuse/mixed patterns, the tumor was automatically identified via bone segmentation using liver SUVmedian thresholds. Subsequently, DL and radiomics features were extracted using Pyradiomics and the STU-Net encoder. Then a deep learning radiomics nomogram (DLRN) was constructed using the Cox proportional hazards model and evaluated using the calibration curve, the receiver operating characteristic (ROC) curve, the Kaplan-Meier curve, and decision curve analysis.

Results

The study included 345 patients (median age, 59 years [IQR, 35–67 years], 198 male). The nnU-Net achieved a median DSC of 0.64–0.77 for focal lesions segmentation across cohorts. The DLRN was constructed by integrating deep learning radiomics score (DLRS), lactate dehydrogenase (LDH), and β2-microglobulin (β2-MG). The DLRN achieved an area under ROC curve (AUC) of 0.87 (95% confidence interval [CI]: 0.82–0.93), 0.84 (95% CI: 0.73–0.96), and 0.88 (95% CI: 0.76–0.99) for 3-year overall survival (OS) status prediction in the training, internal and external testing cohorts, which outperformed the International Staging System (ISS) (all P < 0.05). Furthermore, the DLRN can effectively identify high-risk individuals (all P < 0.05), demonstrated good agreement between predicted and observed survival probabilities, and provided clinical net benefit.

Conclusion

The pattern-specific DL approach achieved automated whole-body tumor segmentation in MM, and the established DLRN demonstrated improved risk stratification capability.