EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Machine learning‐based integration of radiomics and dosiomics for early prediction of radiation‐induced temporal lobe injury in nasopharyngeal carcinoma: A multicenter study

Xiaoming Sun, Huijun Zhu, Jian Qiao, Yingying Liang, Zhipeng Zhu, Sixue Dong iD, Jiazhou Wang iD

Journal of Applied Clinical Medical Physics · 2026

DOI: 10.1002/acm2.70420 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Applied Clinical Medical Physics, 2026. Verfasst von Xiaoming Sun und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China. Hauptthemen laut MEDLINE: Machine Learning, Nasopharyngeal Carcinoma, Nasopharyngeal Neoplasms, Temporal Lobe. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Applied Research Programs of Health and Technology Commission Foundation of Guangxi, Foundation of the Second Affiliated Hospital of Guangxi Medical University, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study developed and validated a multimodal machine learning model integrating clinical, radiomics, and dosiomics characteristics to predict radiation‐induced temporal lobe injury (RTLI) in nasopharyngeal carcinoma patients.

Methods

This study utilized dual‐center retrospective cohorts comprising 213 patients. From pre‐treatment 3D computed tomography (CT) scans and radiation dose maps, we extracted 43 radiomics features and 43 dosiomics features. These quantitative imaging features underwent a rigorous three‐stage selection pipeline—including auto‐correlation analysis, significance testing ( t ‐tests), and least absolute shrinkage and selection operator‐regularized logistic regression (LASSO‐LR)—yielding 24 optimal image‐derived predictors (13 radiomics and 11 dosiomics features). In parallel, eight clinical features were preserved in all final models due to their established clinical relevance and prior biological significance. We systematically evaluated twelve predictive configurations by integrating three machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR)—with four feature modalities: clinical‐only, radiomics‐only, dosiomics‐only, and an integrated feature set.

Results

The SVM‐based integrated model demonstrated superior predictive performance, achieving an AUC of 0.819 during internal validation while maintaining robust generalizability in external testing (AUC = 0.714). The model exhibited excellent specificity (0.844) and remarkable cross‐cohort stability, as evidenced by low performance variability (standard deviation: ±0.077 in validation, ±0.056 in testing). These findings highlight the synergistic value of integrating clinically established parameters with quantitative characterization of anatomical heterogeneity (radiomics) and radiation dose distribution patterns (dosiomics) for accurate prediction of radiation‐induced temporal lobe injury.

Conclusion

This clinically applicable predictive framework enables early identification of high‐risk RTLI patients, facilitating timely interventions to mitigate neurotoxicity. The model's demonstrated multicenter validity, high specificity, and balanced performance across evaluation metrics address critical limitations of current prediction approaches, representing a significant advance in personalized radiation oncology for nasopharyngeal carcinoma patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningNasopharyngeal CarcinomaNasopharyngeal NeoplasmsTemporal LobeRadiation InjuriesRadiotherapy Planning, Computer-AssistedHumansRetrospective StudiesMaleFemaleMiddle AgedRadiotherapy DosageRadiotherapy, Intensity-ModulatedTomography, X-Ray ComputedAdultAlgorithmsAgedPrognosisSupport Vector MachineRadiomics

Stichwörter der Autor:innen

dosiomicsmachine learningpredictive modelingradiation‐induced temporal lobe injuryradiomicssupport vector machine

Autor:innen und Institutionen

  • Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
  • Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
  • Shanghai Clinical Research Center for Radiation Oncology, Shanghai, China.
  • Department of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, China.

ORCID-Profile: Sixue Dong, Jiazhou Wang

Förderung

  • Applied Research Programs of Health and Technology Commission Foundation of Guangxi
  • Foundation of the Second Affiliated Hospital of Guangxi Medical University
  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Shanghai Committee of Science and Technology Fund

Zitieren

APA

Sun, X., Zhu, H., Qiao, J., Liang, Y., Zhu, Z., Dong, S., & Wang, J. (2026). Machine learning‐based integration of radiomics and dosiomics for early prediction of radiation‐induced temporal lobe injury in nasopharyngeal carcinoma: A multicenter study. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70420

Vancouver

Sun X, Zhu H, Qiao J, Liang Y, Zhu Z, Dong S, et al. Machine learning‐based integration of radiomics and dosiomics for early prediction of radiation‐induced temporal lobe injury in nasopharyngeal carcinoma: A multicenter study. Journal of Applied Clinical Medical Physics. 2026. doi:10.1002/acm2.70420

BibTeX
@article{Sun2026,
  author = {Sun, Xiaoming and Zhu, Huijun and Qiao, Jian and Liang, Yingying and Zhu, Zhipeng and Dong, Sixue and Wang, Jiazhou},
  title = {Machine learning‐based integration of radiomics and dosiomics for early prediction of radiation‐induced temporal lobe injury in nasopharyngeal carcinoma: A multicenter study},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  doi = {10.1002/acm2.70420}
}
Kostenlos starten →