Predicting ki-67 expression in breast cancer via transformer and multiple instance learning on DCE-MRI.
Authors
Affiliations (10)
Affiliations (10)
- Department of Medical Imaging, Guigang City People's Hospital, No. 1 Zhongshan Middle Road, Gangbei District, Guigang, Guangxi Zhuang Autonomous Region, 537100, China.
- Graduate School, Youjiang Medical University for Nationalities, No. 98, Chengxiang Road, Youjiang District, Baise, Guangxi Zhuang Autonomous Region, 533000, China.
- Department of Medical Imaging, Jinjiang Municipal Hospital, No. 16, Luoshan Section, Jinguang Road, Jinjiang, Quanzhou, Fujian Province, 362200, China.
- Department of Medical Imaging, The First People's Hospital of Qinzhou, No. 47 Qianjin Road, Qinnan District, Qinzhou, Guangxi Zhuang Autonomous Region, 535000, China.
- Department of Medical Imaging, The First People's Hospital of Qinzhou, No. 47 Qianjin Road, Qinnan District, Qinzhou, Guangxi Zhuang Autonomous Region, 535000, China. [email protected].
- Department of Medical Imaging, Affiliated Hospital of Youjiang Medical University for Nationalities, No.18, Zhongshan Er Road, Youjiang District, Baise, Guangxi Zhuang Autonomous Region, 533000, China. [email protected].
- Department of Medical Imaging, The People's Hospital of Chongzuo, No. 6 Longxiashan East Road, Jiangzhou District, Chongzuo, Guangxi Zhuang Autonomous Region, 532200, China.
- Department of Medical Imaging, Pingguo People's Hospital, No. 76 Jianmin Road, Matou Town, Pingguo, Baise, Guangxi Zhuang Autonomous Region, 531499, China.
- Department of Ultrasound, Baise People's Hospital, No. 8 Chengzhan Road, Youjiang District, Baise, Guangxi Zhuang Autonomous Region, 533000, China.
- Department of Medical Imaging, The People's Hospital of Guangxi Zhuang Autonomous Region, Guangxi Academy of Medical Sciences, No.6 Taoyuan Road, Nanning, Guangxi Zhuang Autonomous Region, 530021, China.
Abstract
Accurate assessment of Ki-67 expression levels in breast cancer is crucial for determining prognosis and making informed treatment decisions. Current immunohistochemical methods relying on needle biopsy introduce sampling errors due to tumor spatial heterogeneity, making the development of non-invasive, precise preoperative prediction methods of significant clinical importance. This study aims to explore and compare advanced deep learning models based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for noninvasive assessment of Ki-67 expression. This retrospective study analyzed preoperative DCE-MRI data from 308 patients with histologically confirmed breast cancer. Adjacent slices centered on the tumor's most significant cross-section were obtained to create a 2.5-dimensional (2·5D) dataset. We innovatively developed two deep learning models using the same dataset (1): a Multi-Instance Learning (MIL) model that combines slice-level predictive features with Predictive Likelihood Histogram (PLH) and Bag-of-Words (BoW) techniques (2); a Transformer-based fusion model that directly captures global contextual relationships between slices via self-attention mechanisms. The predictive performance of both models was systematically compared with traditional radiomics and clinical models. On an independent test set, the Transformer fusion model demonstrated optimal predictive performance with an area under the curve (AUC) of 0.875, achieving accuracy, sensitivity, and specificity of 0.839, 0.848, and 0.833, respectively. The MIL model ranked second (AUC = 0.825), with both models significantly outperforming traditional radiomics models (AUC = 0.698) and clinical models (AUC = 0.648). Deep learning models based on 2·5D DCE-MRI, especially Transformer models that achieve global feature fusion through self-attention mechanisms, can effectively and non-invasively predict Ki-67 expression status in breast cancer, surpassing traditional methods. This model shows potential as a reliable tool to help clinicians accurately assess tumor proliferation activity before surgery.