Pre-treatment prediction of response to neoadjuvant chemotherapy in breast cancer patients using a nomogram based on findings from cone-beam breast computed tomography.
4 affiliations
- 1Department of Breast Surgery, Guangxi Medical University Cancer Hospital, Nanning, China.
- 2Department of Radiology, Guangxi Medical University Cancer Hospital, Nanning, China.
- 3Department of Radiology, Guangxi Medical University Cancer Hospital, Nanning, China. [email protected].
- 4Department of Breast Surgery, Guangxi Medical University Cancer Hospital, Nanning, China. [email protected].
Abstract
Background
Cone-beam breast computed tomography (CBBCT) can provide detailed information about breast tissue, but whether such information can help predict treatment response is unclear.Purpose
To develop a nomogram based on findings from CBBCT as well as conventional clinical variables to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in patients with breast cancer.Materials and methods
Medical data were retrospectively analyzed for a consecutive series of women with breast cancer who underwent NAC followed within three months by resection surgery at our hospital between September 2019 and March 2022. Patients were randomized into a development cohort and validation cohort. A nomogram to predict pCR after chemotherapy was formulated based on univariable and multivariable logistic regression of pre-treatment data from the development cohort, and it was tested against data from the validation cohort. The performance of the nomogram was evaluated in terms of the area under receiver operating characteristic curves (AUC), calibration plots and decision curve analysis.Results
Of the 215 breast cancer patients in this study, 69 (32.1%) achieved pCR after NAC. Multivariable logistic regression of the development cohort linked such response independently to absence of estrogen receptor (ER) expression, expression of human epidermal growth factor receptor 2 (HER-2), small tumor diameter and non-mass enhancement (NME) on CBBCT. The resulting nomogram predicted response with AUCs of 0.841 (95% CI: 0.78-0.90) in the development cohort (n = 150) and 0.836 (95% CI: 0.74-0.94) in the validation cohort (n = 65), and it was efficient against data from both cohorts based on calibration curves. Decision curve analysis suggested that the nomogram is clinically useful.Conclusion
A nomogram incorporating molecular biomarkers and findings from CBBCT may help predict breast cancer patients more likely to respond to NAC.
Related
- Fusion of Deep Learning Radiomics and Clinical Features for Individualized Prediction of Neoadjuvant Chemotherapy Response in Osteosarcoma
- Multimodal prediction of neoadjuvant chemotherapy response in locally advanced gastric cancer: a multicenter cohort study
- Impact of neoadjuvant chemotherapy on local breast microbiota and macrophages in ER-positive breast cancer with links to treatment response
- Machine learning model for the prediction of pathological complete response after neoadjuvant chemotherapy in breast cancer.
- Multimodal lifestyle intervention during neoadjuvant chemotherapy in patients with early breast cancer as a strategy to improve treatment response: Protocol of the DIANA randomized clinical trial
BibTeX
@article{zhang2026pretreatment,
title = {{Pre-treatment prediction of response to neoadjuvant chemotherapy in breast cancer patients using a nomogram based on findings from cone-beam breast computed tomography.}},
author = {Yu-Jiao Zhang and Zhu-Ming Liang and Xiang-Yang Huang and Yan-Jing Yu and Ya-Nan Mo and Ning-Bin Luo and Yi-Nan Ji},
journal = {BMC cancer},
year = {2026},
month = aug,
doi = {10.1186/s12885-026-16486-1},
url = {https://europepmc.org/article/MED/42958155},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Pre-treatment prediction of response to neoadjuvant chemotherapy in breast cancer patients using a nomogram based on findings from cone-beam breast computed tomography.
AU - Yu-Jiao Zhang
AU - Zhu-Ming Liang
AU - Xiang-Yang Huang
AU - Yan-Jing Yu
AU - Ya-Nan Mo
AU - Ning-Bin Luo
AU - Yi-Nan Ji
PY - 2026
DA - 2026/08/01
JO - BMC cancer
DO - 10.1186/s12885-026-16486-1
UR - https://europepmc.org/article/MED/42958155
AB - Background Cone-beam breast computed tomography (CBBCT) can provide detailed information about breast tissue, but whether such information can help predict treatment response is unclear.Purpose To develop a nomogram based on findings from CBBCT as well as conventional clinical variables to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in patients with breast cancer.Materials and methods Medical data were retrospectively analyzed for a consecutive series of women with breast cancer who underwent NAC followed within three months by resection surgery at our hospital between September 2019 and March 2022. Patients were randomized into a development cohort and validation cohort. A nomogram to predict pCR after chemotherapy was formulated based on univariable and multivariable logistic regression of pre-treatment data from the development cohort, and it was tested against data from the validation cohort. The performance of the nomogram was evaluated in terms of the area under receiver operating characteristic curves (AUC), calibration plots and decision curve analysis.Results Of the 215 breast cancer patients in this study, 69 (32.1%) achieved pCR after NAC. Multivariable logistic regression of the development cohort linked such response independently to absence of estrogen receptor (ER) expression, expression of human epidermal growth factor receptor 2 (HER-2), small tumor diameter and non-mass enhancement (NME) on CBBCT. The resulting nomogram predicted response with AUCs of 0.841 (95% CI: 0.78-0.90) in the development cohort (n = 150) and 0.836 (95% CI: 0.74-0.94) in the validation cohort (n = 65), and it was efficient against data from both cohorts based on calibration curves. Decision curve analysis suggested that the nomogram is clinically useful.Conclusion A nomogram incorporating molecular biomarkers and findings from CBBCT may help predict breast cancer patients more likely to respond to NAC.
SN - 1471-2407
ER -