Deep learning radiopathomics based on preoperative US images and biopsy whole slide images can distinguish between luminal and non-luminal tumors in early-stage breast cancers

Q: What clinical problem does the DLRP model address?

It aims to preoperatively distinguish luminal from non-luminal early-stage breast cancers to support neoadjuvant treatment decisions.

Q: Which image types are used for prediction?

The model uses preoperative ultrasound (US) images and H&E-stained biopsy whole slide images (WSIs).

Q: How does the DLRP model perform compared with other approaches?

In the external test cohort, DLRP outperformed deep learning radiomics using US images only and deep learning pathomics using WSIs only, with higher AUC values.

Sep 24, 2026

Uploaded by Riley West

A multicentre deep learning radiopathomics (DLRP) framework distinguishes luminal from non-luminal early-stage breast cancers preoperatively using two data sources: preoperative ultrasound (US) images and hematoxylin and eosin (H&E)-stained biopsy whole slide images (WSIs). The model employs ResNet18 for US and a multi-instance attention network for WSIs, with a US-guided co-attention module for feature fusion. Across internal and external cohorts, DLRP achieved higher discrimination than US-only radiomics and WSI-only pathomics baselines, supporting more reliable treatment planning.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Summary

Background

Methods

Findings

Interpretation

Funding

Research in context

Evidence before this study

Articles Deep learning radiopathomics based on preoperative US images and biopsywhole slide images can distinguish between luminal and non-luminal tumors in early-stage breast cancers Yini Huang,a,f Zhao Yao,b,f Lingling Li,a,f Rushuang Mao,a,f Weijun Huang,c Zhengming Hu,d Yixin Hu,a Yun Wang,a RuohanGuo,a Xiaofeng Tang,a Liang Yang,a Yuanyuan Wang,b Rongzhen Luo,e,∗ Jinhua Yu,b,∗∗ and Jianhua Zhoua,∗∗∗ aDepartment of Ultrasound, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China bSchool of Information Science and Technology, Fudan University, Shanghai, China cDivision of Interventional Ultrasound, Department of Medical Ultrasonics, Foshan First People’s Hospital, Foshan, Guangdong, China dDepartment of Ultrasound, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China eDepartment of Pathology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China Summary Background For patients with early-stage breast cancers, neoadjuvant treatment is recommended for non-luminal tumors instead of luminal tumors. Preoperative distinguish between luminal and non-luminal cancers at early stages will facilitate treatment decisions making. However, the molecular immunohistochemical subtypes based on biopsy specimens are not always consistent with ﬁnal results based on surgical specimens due to the high intra-tumoral heterogeneity. Given that, we aimed to develop and validate a deep learning radiopathomics (DLRP) model to preoperatively distinguish between luminal and non-luminal breast cancers at early stages based on preoperative ultrasound (US) images, and hematoxylin and eosin (H&E)-stained biopsy slides. Methods This multicentre study included three cohorts from a prospective study conducted by our team and registered on the Chinese Clinical Trial Registry (ChiCTR1900027497) . Between January 2019 and August 2021, 1809 US images and 603 H&E-stained whole slide images (WSIs) from 603 patients with early-stage breast cancers were obtained. A Resnet18 model pre-trained on ImageNet and a multi-instance learning based attention model were used to extract the features of US and WSIs, respectively. An US-guided Co-Attention module (UCA) was designed for feature fusion of US and WSIs. The DLRP model was constructed based on these three feature sets including deep learning US feature, deep learning WSIs feature and UCA-fused feature from a training cohort (1467 US images and 489 WSIs from 489 patients) . The DLRP model’s diagnostic performance was validated in an internal validation cohort (342 US images and 114 WSIs from 114 patients) and an external test cohort (279 US images and 90 WSIs from 90 patients) . We also compared diagnostic efﬁcacy of the DLRP model with that of deep learning radiomics model and deep learning pathomics model in the external test cohort. Findings The DLRP yielded high performance with area under the curve (AUC) values of 0.929 (95% CI 0.865–0.968) in the internal validation cohort, and 0.900 (95% CI 0.816–0.953) in the external test cohort. The DLRP also outperformed deep learning radiomics model based on US images only (AUC 0.815 [0.719–0.889], p < 0.027) and deep learning pathomics model based on WSIs only (AUC 0.802 [0.704–0.878], p < 0.013) in the external test cohort. Interpretation The DLRP can effectively distinguish between luminal and non-luminal breast cancers at early stages before surgery based on pretherapeutic US images and biopsy H&E-stained WSIs, providing a tool to facilitate treatment decision making in early-stage breast cancers. Funding Natural Science Foundation of Guangdong Province (No. 2023A1515011564), and National Natural Science Foundation of China (No. 91959127; No. 81971631) . *Corresponding author. Department of Pathology, Sun Yat-Sen University Cancer

FAQs

What clinical problem does the DLRP model address?

It aims to preoperatively distinguish luminal from non-luminal early-stage breast cancers to support neoadjuvant treatment decisions.

Which image types are used for prediction?

The model uses preoperative ultrasound (US) images and H&E-stained biopsy whole slide images (WSIs).

How does the DLRP model perform compared with other approaches?

In the external test cohort, DLRP outperformed deep learning radiomics using US images only and deep learning pathomics using WSIs only, with higher AUC values.

Sep 24, 2026

Uploaded by Riley West