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.2025.1609421

This article is part of the Research TopicAdvances in Intelligence or Nanomedicine-based Theranostics for CancersView all articles

Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics

Provisionally accepted
Wen  XiaoboWen Xiaobo1*Yutao  ZhaoYutao Zhao1Wen  DongWen Dong2Congbo  YangCongbo Yang2Jinzhi  LiJinzhi Li2Li  SunLi Sun1Yutao  XiuYutao Xiu1Change  GaoChange Gao3*Ming  ZhangMing Zhang2*
  • 1Qingdao Cancer Institute, Qingdao University, Qingdao, China
  • 2Yunnan Cancer Hospital, Kunming, Yunnan Province, China
  • 3The First Affiliated Hospital of Kunming Medical University, Kunming, Yunnan Province, China

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

Abstract Objective: This study aimed to identify CT‐based radiomic alterations associated with radiation pneumonitis (RP) and to evaluate the feasibility of machine‐learning classifiers for personalized RP diagnosis in breast cancer patients using these radiomic signatures.Methods: We retrospectively analyzed 146 planning CT scans (pre- and post-radiotherapy) from 73 breast cancer patients with confirmed RP. The entire lung was delineated as the region of interest(ROI), and 1,834 radiomics features were extracted using PyRadiomics. Feature selection was performed sequentially by Mann–Whitney U-test (p < 0.05), Spearman’s rank correlation (|ρ| < 0.9), and least absolute shrinkage and selection operator (LASSO). Eight classifiers (logistic regression [LR], support vector machine [SVM], k-nearest neighbors [KNN], random forest [RF], extra trees [ET], XGBoost, LightGBM, and multilayer perceptron [MLP]) were trained and evaluated using accuracy, area under the receiver operating characteristic curve (AUC) with 95% confidence intervals, sensitivity, and specificity.Results:In the independent test cohort, LR achieved the highest performance (accuracy 0.897; AUC 0.929 [95% CI, 0.838–1.000]; sensitivity 0.786; specificity 1.000). LightGBM and MLP also exhibited robust discrimination with AUCs of 0.855 (95% CI, 0.719–0.990) and 0.848 (95% CI, 0.705–0.991), respectively. Five texture and four first-order features were retained, underscoring the importance of texture-focused extractors (wavelet, lbp).Conclusion: CT-derived radiomics signatures combined with machine learning classifiers enable accurate detection of RP in breast cancer patients. Texture-oriented feature selection enhances model discrimination, providing potential for personalized diagnosis of RP in breast cancer patients and adaptive treatment planning.

Keywords: breast cancer, Radiomics, Radiation Pneumonitis, machine learning, Artificial intelligence Laplacian of Gaussian LR: logistic regression MLP: Multilayer Perceptron ROC: receiver operating characteristic curve ROI: region of interest RP: radiation pneumonitis SVM: support vector machine

Received: 10 Apr 2025; Accepted: 30 Jun 2025.

Copyright: © 2025 Xiaobo, Zhao, Dong, Yang, Li, Sun, Xiu, Gao and Zhang. 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:
Wen Xiaobo, Qingdao Cancer Institute, Qingdao University, Qingdao, China
Change Gao, The First Affiliated Hospital of Kunming Medical University, Kunming, 650032, Yunnan Province, China
Ming Zhang, Yunnan Cancer Hospital, Kunming, Yunnan Province, 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.