EUVIMEDEUVIMED entdecken
Multizentrische Studie

Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study

Qiao Zeng, Lan Liu, Chongwu He, Xiaoqiang Zeng, Pengfei Wei, Dong Xu, Ning Mao, Tenghua Yu

Academic Radiology · 2025

DOI: 10.1016/j.acra.2024.10.033 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Academic Radiology, 2025. Verfasst von Qiao Zeng und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Jiangxi Cancer Hospital&Institute,Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang …. Hauptthemen laut MEDLINE: Breast Neoplasms, Neoadjuvant Therapy, Deep Learning, Magnetic Resonance Imaging. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 41 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: The early prediction of response to neoadjuvant chemotherapy (NAC) will aid in the development of personalized treatments for patients with breast cancer. This study investigated the value of longitudinal multimodal deep learning (DL) based on breast MR and ultrasound (US) in predicting pathological complete response (pCR) after NAC. MATERIALS AND METHODS: We retrospectively reviewed the pre-NAC and post-2nd-NAC MR and/or US images of 448 patients enrolled from three centers and extracted DL features from the largest section of the breast tumour using ResNet50. T test, Pearson correlation analysis and least absolute shrinkage and selection operator regression were used to select the most significant DL features for the pre-NAC and post-2nd-NAC MR and US DL models. The stacking model integrates different single-modality DL models and meaningful clinical data. The diagnostic performance of the models was evaluated. RESULTS: In all the patients, the pCR rate was 36.65%. There was no significant difference in diagnostic performance between the different single-modality DL models (DeLong test, p > 0.05). The stacking model integrating the above four DL models with HER2 status yielded areas under the curves of 0.951-0.979, accuracies of 91.55%-92.65%, sensitivities of 90.63%-93.94%, and specificities of 89.47%-94.44% in the cohorts. CONCLUSION: Longitudinal multimodal DL can be useful in predicting pCR. The stacking model can be used as a new tool for the early noninvasive prediction of the response to NAC, as evidenced by its excellent performance, and therefore aid the development of personalized treatment strategies for patients with breast cancer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsNeoadjuvant TherapyDeep LearningMagnetic Resonance ImagingUltrasonography, MammaryHumansFemaleMiddle AgedRetrospective StudiesAdultTreatment OutcomeAgedBreastPredictive Value of Tests

Stichwörter der Autor:innen

Breast cancerDeep learningMagnetic resonance imagingNeoadjuvant chemotherapyUltrasonography

Autor:innen und Institutionen

  • Department of Radiology, Jiangxi Cancer Hospital&Institute,Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College, Nanchang 330029, Jiangxi Province, China (Q.Z., L.L., P…
  • Department of Breast Surgery, Jiangxi Cancer Hospital&Institute,Jiangxi Clinical Research Center for Cancer, The Second Affiliated Hospital of Nanchang Medical College, Nanchang 330029, Jiangxi Province, China (C.H., X.…
  • Department of Ultrasound, Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Cancer and Basic Medicine (IBMC), Chinese Academy of Sciences, Hangzhou 310022, China (…
  • Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, China (N.M.).

Zitieren

APA

Zeng, Q., Liu, L., He, C., Zeng, X., Wei, P., Xu, D., Mao, N., & Yu, T. (2025). Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study. Academic Radiology. https://doi.org/10.1016/j.acra.2024.10.033

Vancouver

Zeng Q, Liu L, He C, Zeng X, Wei P, Xu D, et al. Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study. Academic Radiology. 2025. doi:10.1016/j.acra.2024.10.033

BibTeX
@article{Zeng2025,
  author = {Zeng, Qiao and Liu, Lan and He, Chongwu and Zeng, Xiaoqiang and Wei, Pengfei and Xu, Dong and Mao, Ning and Yu, Tenghua},
  title = {Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study},
  journal = {Academic Radiology},
  year = {2025},
  doi = {10.1016/j.acra.2024.10.033}
}
Kostenlos starten →