Scholarlink

Purpose <p>The aim of this study is to develop a deep learning model using preoperative multimodal MR data to predict the Ki-67 expression level of glioma and externally validate the predictive performance of the model.</p> Methods <p>This study retrospectively collected the clinical and imaging data from 421 patients with grade 2–4 gliomas who underwent surgical resection or biopsy and were pathologically diagnosed in two hospitals between January 2020 and December 2024. The 421 patients were divided into a training set (<i>N</i> = 217), an internal validation set (<i>N</i> = 94), and an external validation set (<i>N</i> = 110). Then, the tumor margins were delineated on contrast-enhanced T1- weighted imaging (CE-T1WI) and contrast-enhanced T2-fluid-attenuated inversion recovery (CE-T2FLAIR) to obtain the three-dimensional region of interest (3D ROI) of the tumor. Three vision transformer (ViT) models based on CE-T1WI, CE-T2FLAIR, and CE-T1WI + CE-T2FLAIR (CE-T1WI_ViT, CE-T2FLAIR_ViT and Combined_ViT) were constructed respectively. The predictive performance of the models was evaluated by the area under the receiver operating characteristic curve (AUC). Finally, to further assess the predictive performance of our transformer model, we trained and tested three convolutional neural network (CNN) models (ShuffleNet, ResNet50, and DenseNet121) on the same dataset and compared our trained Combined_ViT model with these three CNN models.</p> Results <p>The three models, including CE-T1WI_ViT, CE-T2FLAIR_ViT, and Combined_ViT, demonstrated high predictive accuracy for Ki-67 level in grade 2–4 gliomas, with AUC values of 0.859 (95% confidence interval [CI], 0.792–0.926), 0.825 (95%CI, 0.745–0.906), and 0.922 (95%CI, 0.868–0.976), respectively. Among the three models, the Combined_ViT model achieved the highest predictive accuracy. Furthermore, the predictive performance of the Combined_ViT model exceeded that of the three CNN models (ShuffleNet, ResNet50, and DenseNet121), with AUC values of 0.897 (95%CI, 0.839–0.954), 0.905 (95%CI, 0.843–0.966), and 0.913 (95%CI, 0.861–0.965) respectively.</p> Conclusions <p>The deep learning models based on ViT can effectively predict the Ki-67 expression level of glioma, and are a feasible alternative to CNN models.</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

A transformer-based multimodal deep learning model for preoperative prediction of Ki-67 expression level in glioma

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月17日

查看全文
  • Liu Liu,
  • Fangfang Hu,
  • Minquan Lai,
  • Xianjing Zhao,
  • Pinggui Lei,
  • Zhenwei Yao,
  • Bing Fan

摘要

Purpose

The aim of this study is to develop a deep learning model using preoperative multimodal MR data to predict the Ki-67 expression level of glioma and externally validate the predictive performance of the model.

Methods

This study retrospectively collected the clinical and imaging data from 421 patients with grade 2–4 gliomas who underwent surgical resection or biopsy and were pathologically diagnosed in two hospitals between January 2020 and December 2024. The 421 patients were divided into a training set (N = 217), an internal validation set (N = 94), and an external validation set (N = 110). Then, the tumor margins were delineated on contrast-enhanced T1- weighted imaging (CE-T1WI) and contrast-enhanced T2-fluid-attenuated inversion recovery (CE-T2FLAIR) to obtain the three-dimensional region of interest (3D ROI) of the tumor. Three vision transformer (ViT) models based on CE-T1WI, CE-T2FLAIR, and CE-T1WI + CE-T2FLAIR (CE-T1WI_ViT, CE-T2FLAIR_ViT and Combined_ViT) were constructed respectively. The predictive performance of the models was evaluated by the area under the receiver operating characteristic curve (AUC). Finally, to further assess the predictive performance of our transformer model, we trained and tested three convolutional neural network (CNN) models (ShuffleNet, ResNet50, and DenseNet121) on the same dataset and compared our trained Combined_ViT model with these three CNN models.

Results

The three models, including CE-T1WI_ViT, CE-T2FLAIR_ViT, and Combined_ViT, demonstrated high predictive accuracy for Ki-67 level in grade 2–4 gliomas, with AUC values of 0.859 (95% confidence interval [CI], 0.792–0.926), 0.825 (95%CI, 0.745–0.906), and 0.922 (95%CI, 0.868–0.976), respectively. Among the three models, the Combined_ViT model achieved the highest predictive accuracy. Furthermore, the predictive performance of the Combined_ViT model exceeded that of the three CNN models (ShuffleNet, ResNet50, and DenseNet121), with AUC values of 0.897 (95%CI, 0.839–0.954), 0.905 (95%CI, 0.843–0.966), and 0.913 (95%CI, 0.861–0.965) respectively.

Conclusions

The deep learning models based on ViT can effectively predict the Ki-67 expression level of glioma, and are a feasible alternative to CNN models.

Clinical trial number

Not applicable.