Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Oncol.

Sec. Cancer Imaging and Image-directed Interventions

Volume 15 - 2025 | doi: 10.3389/fonc.2025.1587879

This article is part of the Research TopicAdvancing Cancer Imaging Technologies: Bridging the Gap from Research to Clinical PracticeView all 23 articles

Key Parameters in Intratumoral-Peritumoral Region Fusion Models: Optimizing Deep Learning Radiomics for Breast Cancer Diagnosis

Provisionally accepted
Jun-Tao  ShenJun-Tao Shen1,2Gong-Quan  ChenGong-Quan Chen3Hai-Mei  LunHai-Mei Lun2Hua-Fang  HuangHua-Fang Huang4Ling  ZhangLing Zhang5Ling-Ling  LiLing-Ling Li2Yun-Xia  DengYun-Xia Deng2Hui-Hua  WuHui-Hua Wu2,6Qiao  HuQiao Hu2*
  • 1Guangxi Medical University, Nanning, Guangxi Zhuang Region, China
  • 2Department of Ultrasound, People’s Hospital of Guangxi Zhuang Autonomous Region & Guangxi Academy of Medical Sciences, Nanning, China
  • 3Department of Ultrasound, Minda Hospital of Hubei Minzu University, Enshi, China
  • 4Department of Breast Surgery, Guilin Municipal Hospital of Traditional Chinese Medicine, Guilin, China
  • 5Department of Ultrasound, Fangchenggang First People’s Hospital, Fangchenggang, China
  • 6Guilin Medical University, Guilin, Guangxi Zhuang Region, China

The final, formatted version of the article will be published soon.

Background: Early diagnosis of breast cancer (BC) is crucial for improving patient outcomes. Features of the peritumoral region have been shown to significantly enhance the predictive performance of deep learning radiomics (DLR) models. This study aims to explore the impact of key parameter selection on improving the performance of the intratumoral-peritumoral region fusion model. The goal is to enhance the modal's noninvasive diagnostic capability for distinguishing benign and malignant breast tumors.This retrospective study included 411 female patients with breast lesions from four hospitals. DLR models were constructed using their contrastenhanced ultrasound (CEUS) images. The intratumoral region of interest (ROI) was gradually expanded to generate peritumoral regions of varying thicknesses. Six groups of fusion models were constructed using different key parameter combinations, including pseudo-color (PC) vs. grayscale (GRAY) images, original precise (OP) ROI vs. bounding box (BB) ROI, and direct extension (DE) strategy vs. feature-level fusion (FLF) strategy. Additionally, a reader study was conducted, comparing the diagnostic performance of the best fusion model with that of six radiologists. The performance of the models was evaluated using the area under the curve (AUC).Results: Incorporating the peritumoral region significantly enhanced the diagnostic performance of the DLR models. The PC-OP-DE-Peri (4mm) model achieved the highest performance in the testing cohort, with an AUC of 0.837. The performance surpassed both the intratumoral models and all radiologists. The effects of different key parameter selections on fusion model performance varied.This study suggests that the selection of PC images, OP ROIs, and the DE strategy effectively improves the performance of intratumoral-peritumoral region fusion models for predicting BC.

Keywords: Deep learning radiomics, multicenter, breast cancer, Peritumoral region, contrast-enhanced ultrasound

Received: 05 Mar 2025; Accepted: 21 Aug 2025.

Copyright: © 2025 Shen, Chen, Lun, Huang, Zhang, Li, Deng, Wu and Hu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Qiao Hu, Department of Ultrasound, People’s Hospital of Guangxi Zhuang Autonomous Region & Guangxi Academy of Medical Sciences, Nanning, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.