Related Experiment Video
Updated: Jun 30, 2026
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Delta Radiomics Based on MRI for Predicting Axillary Lymph Node Pathologic Complete Response After Neoadjuvant
Ning Mao1, Yuhan Bao2, Chuntong Dong3
1Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, P R China (N.M., J.L.); Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, P R China (N.M., H.M., H.X., F.L.); Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, P R China (N.M., H.M., H.X., F.L.); Shandong Provincial Key Medical and Health Laboratory of Intelligent Diagnosis and Treatment for Women's Diseases (Yantai Yuhuangding Hospital), Shandong, P R China (N.M., H.Z., H.M., Q.W., H.X., F.L.).
This study developed a radiomics nomogram using MRI to predict axillary complete response to chemotherapy in breast cancer patients. The nomogram accurately identifies patients likely to respond, reducing unnecessary surgeries.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Breast cancer patients with axillary lymph node metastases often receive neoadjuvant chemotherapy (NAC).
- Predicting pathologic complete response (pCR) in axillary lymph nodes (ALN) is crucial for treatment decisions.
- Accurate prediction can help avoid unnecessary axillary lymph node dissection (ALND).
Purpose of the Study:
- To develop and validate a radiomics nomogram for predicting axillary pathologic complete response (apCR) to NAC.
- To integrate magnetic resonance imaging (MRI) radiomics features with clinicopathological factors.
- To assess the nomogram's performance in predicting apCR in breast cancer patients with ALN metastases.
Main Methods:
- A total of 319 patients with ALN metastases received NAC and underwent MRI.
- Radiomics features were extracted from ALNs before and after NAC (pre-, post-, and delta-radiomics).
- A nomogram was built using logistic regression, incorporating selected radiomics features and clinicopathological factors (progesterone receptor status).
Main Results:
- The radiomics nomogram, combining post- and delta-radscores with progesterone receptor status, demonstrated high predictive performance (AUCs of 0.894 and 0.903 in internal and external sets).
- The nomogram showed favorable calibration and clinical utility, significantly reducing unnecessary ALND rates from 60.42% to 21.88%.
- Genetic analysis indicated that high apCR prediction scores correlated with upregulated immune-mediated genes and pathways.
Conclusions:
- The developed radiomics nomogram is a powerful tool for predicting apCR to NAC in breast cancer patients with ALN metastases.
- This nomogram can assist clinicians in identifying patients who will achieve apCR, thereby optimizing treatment strategies.
- The findings suggest potential for reducing overtreatment by avoiding unnecessary axillary lymph node dissection.
