Scholarlink

Background <p>This study aimed to develop an ultrasound (US)-based deep learning (DL) model to evaluate the presence of crescents in patients with immunoglobulin A nephropathy (IgAN).</p> Methods <p>We created a training set consisting of 2,682 US images obtained from 931 patients with IgAN at the First Affiliated Hospital of Anhui Medical University. The external testing set included 198 patients from Nanchong Central Hospital based on the same criteria. Five DL models were trained in the training set and tested in the testing set. The performance of each model was evaluated for the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value and negative predictive value.</p> Results <p>The DenseNet121 model achieved an accuracy of 0.773 in the external testing set for predicting the presence of crescents, with a sensitivity of 57.6% and specificity of 87.9%.</p> Conclusion <p>Using renal ultrasound imaging data, DL may be able to predict crescent status in IgAN, providing clinicians with a potentially non-invasive means to better understand crescent status in patients with IgAN.</p> Clinical trial number <p>Not applicable.</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

Presence of crescents in IgA nephropathy–prediction from ultrasound images using deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月14日

查看全文
  • Xiaomin Hu,
  • Weihan Xiao,
  • Di Wang,
  • Jiao Yao,
  • Xiaoling Liu,
  • Huaming Xian,
  • Xisheng Xie,
  • Chaoxue Zhang,
  • Xiachuan Qin

摘要

Background

This study aimed to develop an ultrasound (US)-based deep learning (DL) model to evaluate the presence of crescents in patients with immunoglobulin A nephropathy (IgAN).

Methods

We created a training set consisting of 2,682 US images obtained from 931 patients with IgAN at the First Affiliated Hospital of Anhui Medical University. The external testing set included 198 patients from Nanchong Central Hospital based on the same criteria. Five DL models were trained in the training set and tested in the testing set. The performance of each model was evaluated for the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value and negative predictive value.

Results

The DenseNet121 model achieved an accuracy of 0.773 in the external testing set for predicting the presence of crescents, with a sensitivity of 57.6% and specificity of 87.9%.

Conclusion

Using renal ultrasound imaging data, DL may be able to predict crescent status in IgAN, providing clinicians with a potentially non-invasive means to better understand crescent status in patients with IgAN.

Clinical trial number

Not applicable.