Scholarlink

Background <p>Ultrasound-based deep learning (DL) models for the precise diagnosis of endometrial cancer are insufficient. Our aim is to develop and validate an automatic multi-modal ultrasound DL prediction model for the accurate identification of benign versus malignant endometrial diseases.</p> Methods <p>The retrospective dataset of patients with endometrial diseases from two hospitals was segregated into an internal set (<i>n</i> = 696) and an external set (<i>n</i> = 78). All patients underwent grayscale, color Doppler, and 3D reconstructed ultrasound scans. We established ResNet-18 DL models using individual sequences (DL<sub>gray</sub>, DL<sub>CDFI</sub>, DL<sub>3D</sub>) and multi-modal sequences (DL<sub>fusion</sub>), with comparative performance evaluation through area under the receiver operating characteristic curve (AUC) analysis. We compared the best-performing model with 12 radiologists and assessed the diagnostic performance of radiologists with model assistance.</p> Results <p>The DL<sub>fusion</sub> model exhibits precise discrimination capabilities for benign and malignant endometrial diseases, achieving an AUC of 0.92. This performance significantly surpasses that of DL<sub>gray</sub> (0.78, <i>p</i> &lt; 0.01), DL<sub>CDFI</sub> (0.79, <i>p</i> = 0.01), and assessments by radiologists (0.64, <i>p</i> &lt; 0.001). The DL<sub>fusion</sub> model is more accurate than radiologists (0.86 vs. 0.78, <i>p</i> &lt; 0.001) at detecting endometrial cancer. With the assistance of the DL<sub>fusion</sub> model, the average diagnostic accuracy of twelve radiologists significantly improves from 0.77 to 0.85 (<i>p</i> &lt; 0.001).</p> Conclusions <p>The DL<sub>fusion</sub> model based on multi-modal ultrasonic images exhibits a better capacity in diagnosing endometrial cancer compared with radiologists and DL models based on single modal, and significantly improves the diagnostic accuracy of radiologists, offering valuable support for clinical decision-making.</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 prediction model based on multi-modal transvaginal ultrasound scan images for endometrial cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月28日

查看全文
  • Xingzhe Liu,
  • Yuanjia Wen,
  • Jiahao Liu,
  • Wenzhi Lv,
  • Yuan Wu,
  • Yue Gao,
  • Shaoqing Zeng,
  • Guannan Li,
  • Yu Xia,
  • Shennan Shi,
  • Qiuyang Xu,
  • Xiaofei Jiao,
  • Wenjian Gong,
  • Ding Ma,
  • Guang-Nian Zhao,
  • Yong Fang,
  • Xiaodong Cheng,
  • Xiao-Yan Xu,
  • Dan Liu,
  • Qinglei Gao

摘要

Background

Ultrasound-based deep learning (DL) models for the precise diagnosis of endometrial cancer are insufficient. Our aim is to develop and validate an automatic multi-modal ultrasound DL prediction model for the accurate identification of benign versus malignant endometrial diseases.

Methods

The retrospective dataset of patients with endometrial diseases from two hospitals was segregated into an internal set (n = 696) and an external set (n = 78). All patients underwent grayscale, color Doppler, and 3D reconstructed ultrasound scans. We established ResNet-18 DL models using individual sequences (DLgray, DLCDFI, DL3D) and multi-modal sequences (DLfusion), with comparative performance evaluation through area under the receiver operating characteristic curve (AUC) analysis. We compared the best-performing model with 12 radiologists and assessed the diagnostic performance of radiologists with model assistance.

Results

The DLfusion model exhibits precise discrimination capabilities for benign and malignant endometrial diseases, achieving an AUC of 0.92. This performance significantly surpasses that of DLgray (0.78, p < 0.01), DLCDFI (0.79, p = 0.01), and assessments by radiologists (0.64, p < 0.001). The DLfusion model is more accurate than radiologists (0.86 vs. 0.78, p < 0.001) at detecting endometrial cancer. With the assistance of the DLfusion model, the average diagnostic accuracy of twelve radiologists significantly improves from 0.77 to 0.85 (p < 0.001).

Conclusions

The DLfusion model based on multi-modal ultrasonic images exhibits a better capacity in diagnosing endometrial cancer compared with radiologists and DL models based on single modal, and significantly improves the diagnostic accuracy of radiologists, offering valuable support for clinical decision-making.