loading page

Frozen Large-scale Pretrained Vision-Language Models are an Effective Foundational Backbone for Enhancing Multimodal Breast Cancer Risk Assessment
  • +4
  • Hung Q. Vo,
  • Lin Wang,
  • Kelvin K Wong,
  • Chika F Ezeana,
  • Xiaohui Yu,
  • Hien V Nguyen,
  • Stephen T C Wong
Hung Q. Vo

Corresponding Author:[email protected]

Author Profile
Lin Wang
Kelvin K Wong
Chika F Ezeana
Xiaohui Yu
Hien V Nguyen
Stephen T C Wong


Breast cancer is a pervasive global health concern among women. Leveraging multimodal data from enterprise patient databases-including Picture Archiving and Communication Systems (PACS) and Electronic Health Records (EHRs)-holds promise for improving risk assessment. This study introduces a multimodal deep-learning model leveraging mammogram datasets to evaluate breast cancer risk. Our approach integrates frozen large-scale pretrained vision-language models, showcasing superior performance and stability compared to traditional imagetabular models across two public breast cancer datasets. The model consistently outperforms conventional full finetuning methods by using frozen pretrained vision-language models alongside a lightweight trainable classifier. The observed improvements are significant. In the CBIS-DDSM dataset, the Area Under the Curve (AUC) increases from 0.867 to 0.902 during validation and from 0.803 to 0.830 for the official test set. Within the EMBED dataset, AUC improves from 0.780 to 0.805 during validation. In scenarios with limited data, using Breast Imaging-Reporting and Data System category three (BI-RADS 3) cases, AUC improves from 0.91 to 0.96 on the official CBIS-DDSM test set and from 0.79 to 0.83 on a challenging validation set. This study underscores the benefits of vision-language models in jointly training diverse image-clinical datasets from multiple healthcare institutions, effectively addressing challenges related to non-aligned tabular features. Combining training data enhances breast cancer prediction on the EMBED dataset, outperforming all other experiments. In summary, our research emphasizes the efficacy of frozen large-scale pretrained vision-language models in multimodal breast cancer prediction, offering superior performance and stability over conventional methods, reinforcing their potential for breast cancer risk assessment.
12 Jan 2024Submitted to TechRxiv
22 Jan 2024Published in TechRxiv