Scholarlink

Objectives <p>To investigate the effect of CT slice thickness on radiomic features (RFs) in terms of reproducibility and discriminative power, and to assess whether a deep learning–based CT slice synthesis (DLS) algorithm can mitigate the adverse effects associated with thick-slice CT.</p> Materials and methods <p>This retrospective multicenter study included 506 patients with lung nodules (245 benign, 261 malignant) from two independent cohorts, which were divided into a training set, internal validation set (IVS), and external validation set (EVS). Chest CT reconstructed at 1-mm and 5-mm slice thicknesses was analyzed. A DLS algorithm was applied to convert 5-mm CT into synthetic 1-mm CT. RFs were extracted from all CT types to construct radiomics models. Reproducibility was assessed using the concordance correlation coefficient (CCC) and compared with the Wilcoxon signed-rank test. Discriminative power was evaluated by the area under the receiver operating characteristic curve (AUC) and compared with DeLong’s test.</p> Results <p>The CCCs of DLS 1-mm CT were 0.48 ± 0.37 and 0.49 ± 0.37 in Cohort 1 and Cohort 2, respectively, significantly higher than real 5-mm CT (all <i>p</i> &lt; 0.001). Most RFs from 5-mm CT lacked reproducibility (CCC ≥ 0.85; 0.9% in both Cohort 1 and Cohort 2), whereas DLS 1-mm CT showed marked improvement (Cohort 1, 27.6%; Cohort 2, 26.9%). The discriminative power of RFs from DLS 1-mm CT was superior to that of 5-mm CT and non-inferior to real 1-mm CT, both in model construction and evaluation.</p> Conclusion <p>CT slice thickness substantially influences the reproducibility and discriminative power of RFs, whereas the DLS algorithm effectively mitigates the limitations associated with thick-slice CT.</p> Critical relevance statement <p>Deep learning–based CT slice synthesis significantly reduces the slice thickness–related variability in radiomics feature reproducibility and discriminative power, providing a promising methodological approach to improve radiomics standardization and support its clinical translation.</p> Key Points <p><UnorderedList Mark="Bullet"> <ItemContent> <p>CT slice thickness variability substantially impairs radiomic feature reproducibility and discriminative performance, posing a major barrier to standardized radiomics analysis.</p> </ItemContent> <ItemContent> <p>Across two independent cohorts, deep learning–based slice synthesis mitigated the adverse effects of thick-slice CT on radiomic feature reproducibility and cross-thickness discriminative performance.</p> </ItemContent> </UnorderedList></p> Graphical Abstract <p></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 learning–based CT slice synthesis improves radiomic feature reproducibility and discriminative performance in lung nodule assessment

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月19日

查看全文
  • Hujun Yang,
  • Zhengping Zhang,
  • Lei Tian,
  • Pei Dang,
  • Long Wan,
  • Zhiyuan Zhou,
  • Jingjie Li,
  • Lei Cao,
  • Xiaoyan Yang,
  • Juan Chen

摘要

Objectives

To investigate the effect of CT slice thickness on radiomic features (RFs) in terms of reproducibility and discriminative power, and to assess whether a deep learning–based CT slice synthesis (DLS) algorithm can mitigate the adverse effects associated with thick-slice CT.

Materials and methods

This retrospective multicenter study included 506 patients with lung nodules (245 benign, 261 malignant) from two independent cohorts, which were divided into a training set, internal validation set (IVS), and external validation set (EVS). Chest CT reconstructed at 1-mm and 5-mm slice thicknesses was analyzed. A DLS algorithm was applied to convert 5-mm CT into synthetic 1-mm CT. RFs were extracted from all CT types to construct radiomics models. Reproducibility was assessed using the concordance correlation coefficient (CCC) and compared with the Wilcoxon signed-rank test. Discriminative power was evaluated by the area under the receiver operating characteristic curve (AUC) and compared with DeLong’s test.

Results

The CCCs of DLS 1-mm CT were 0.48 ± 0.37 and 0.49 ± 0.37 in Cohort 1 and Cohort 2, respectively, significantly higher than real 5-mm CT (all p < 0.001). Most RFs from 5-mm CT lacked reproducibility (CCC ≥ 0.85; 0.9% in both Cohort 1 and Cohort 2), whereas DLS 1-mm CT showed marked improvement (Cohort 1, 27.6%; Cohort 2, 26.9%). The discriminative power of RFs from DLS 1-mm CT was superior to that of 5-mm CT and non-inferior to real 1-mm CT, both in model construction and evaluation.

Conclusion

CT slice thickness substantially influences the reproducibility and discriminative power of RFs, whereas the DLS algorithm effectively mitigates the limitations associated with thick-slice CT.

Critical relevance statement

Deep learning–based CT slice synthesis significantly reduces the slice thickness–related variability in radiomics feature reproducibility and discriminative power, providing a promising methodological approach to improve radiomics standardization and support its clinical translation.

Key Points

CT slice thickness variability substantially impairs radiomic feature reproducibility and discriminative performance, posing a major barrier to standardized radiomics analysis.

Across two independent cohorts, deep learning–based slice synthesis mitigated the adverse effects of thick-slice CT on radiomic feature reproducibility and cross-thickness discriminative performance.

Graphical Abstract