Scholarlink

Purpose <p>This study aims to develop a deep learning (DL) model based on conventional ultrasound images for differentiating pancreatic serous neoplasms (SCN) from mucinous cystic neoplasms (MCN). We seek to determine if such a model can surpass the diagnostic performance of routine sonographic evaluation and provide a valuable, cost-effective decision-support tool.</p> Methods <p>Data from 459 patients with histopathologically confirmed SCN and MCN from center 1 (<i>n</i> = 345) and center 2 (<i>n</i> = 114) were retrospectively collected. Five DL models (EfficientNet-B3, Resnet-101, Densenet-121, Se-resnext-50, Inception-v3) were constructed for differential diagnosis. Simultaneously compare the diagnostic performance of DL model with that of junior radiologists (JR) and senior radiologists (SR), and determine whether DL can assist radiologists in making better diagnoses.</p> Results <p>The EfficientNet-B3 model demonstrated the optimal predictive performance, with an area under the receiver operating curve (AUC) of 0.904 (95% CI:0.814–0.973) in the internal validation set and 0.866 (95% CI:0.783–0.936) in the external test set. In the external test set, the EfficientNet-B3 model demonstrated significantly superior diagnostic performance compared to both JR in both F1-score and specificity (all <i>P</i> &lt; 0.0125), while showing fully comparable performance to both SR in these precise metrics (all <i>P</i> &gt; 0.0125). With the EfficientNet-B3 model assistance, both JR showed statistically significant improvements in F1-score and specificity (all <i>P</i> &lt; 0.0125), whereas both SR exhibited no statistically significant changes in either performance metric (all <i>P</i> &gt; 0.0125).</p> Conclusions <p>The EfficientNet-B3 model demonstrated comparable diagnostic performance to SR while significantly enhancing the diagnostic accuracy of JR.</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 on ultrasound for differential diagnosis of pancreatic serous cystic neoplasm and mucinous cystic neoplasm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月29日

查看全文
  • Zhiqiang Yuan,
  • Yingyu Shi,
  • Shuang Chen,
  • Jiali Yang,
  • Juan Chen,
  • Jiawu Li,
  • Yang Pu,
  • Xiaojuan Ma,
  • Qianru Yang,
  • Xing Zhao,
  • Lichao Mou,
  • Yilei Shi,
  • Yan Luo

摘要

Purpose

This study aims to develop a deep learning (DL) model based on conventional ultrasound images for differentiating pancreatic serous neoplasms (SCN) from mucinous cystic neoplasms (MCN). We seek to determine if such a model can surpass the diagnostic performance of routine sonographic evaluation and provide a valuable, cost-effective decision-support tool.

Methods

Data from 459 patients with histopathologically confirmed SCN and MCN from center 1 (n = 345) and center 2 (n = 114) were retrospectively collected. Five DL models (EfficientNet-B3, Resnet-101, Densenet-121, Se-resnext-50, Inception-v3) were constructed for differential diagnosis. Simultaneously compare the diagnostic performance of DL model with that of junior radiologists (JR) and senior radiologists (SR), and determine whether DL can assist radiologists in making better diagnoses.

Results

The EfficientNet-B3 model demonstrated the optimal predictive performance, with an area under the receiver operating curve (AUC) of 0.904 (95% CI:0.814–0.973) in the internal validation set and 0.866 (95% CI:0.783–0.936) in the external test set. In the external test set, the EfficientNet-B3 model demonstrated significantly superior diagnostic performance compared to both JR in both F1-score and specificity (all P < 0.0125), while showing fully comparable performance to both SR in these precise metrics (all P > 0.0125). With the EfficientNet-B3 model assistance, both JR showed statistically significant improvements in F1-score and specificity (all P < 0.0125), whereas both SR exhibited no statistically significant changes in either performance metric (all P > 0.0125).

Conclusions

The EfficientNet-B3 model demonstrated comparable diagnostic performance to SR while significantly enhancing the diagnostic accuracy of JR.