Related Experiment Video
Updated: Jan 3, 2026
Analysis of Lymph Node Volume by Ultra-High-Frequency Ultrasound Imaging in the Braf/Pten Genetically Engineered Mouse Model of Melanoma
Published on: September 8, 2021
Lymph Node Metastasis Prediction from Primary Breast Cancer US Images Using Deep Learning
Li-Qiang Zhou1, Xing-Long Wu1, Shu-Yan Huang1
1From the Sino-German Tongji-Caritas Research Center of Ultrasound in Medicine, Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, Hubei Province, China (L.Q.Z., G.G.W., Q.W., Y.B.D., X.W.C., C.F.D.); School of Mathematics and Computer Science, Wuhan Textile University, Wuhan, Hubei Province, China (X.L.W.); Department of Ultrasound, The First People's Hospital of Huaihua, University of South China, Huaihua, China (S.Y.H.); Department of Ultrasound, China Resources & Wisco General Hospital, Wuhan, Hubei Province, China (H.R.Y.); Department of Ultrasound, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China (L.Y.B.); Department of Thyroid and Breast Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, China (X.R.L.); and Medical Clinic 2, Caritas-Krankenhaus Bad Mergentheim, Academic Teaching Hospital of the University of Wuerzburg, Bad Mergentheim, Germany (C.F.D.).
Deep learning models accurately predict breast cancer lymph node metastasis using ultrasound images. This artificial intelligence approach offers a promising early diagnostic strategy for patients with clinically negative lymph nodes.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Medicine
- Oncology
Background:
- Deep learning (DL) demonstrates high performance in image recognition, offering potential for quantitative assessment of medical images.
- DL models can enhance diagnostic accuracy and efficiency in medical image analysis.
- Accurate assessment of axillary lymph node status is crucial for breast cancer management.
Purpose of the Study:
- To evaluate the feasibility of using deep learning (DL) to predict axillary lymph node metastasis in patients with primary breast cancer using ultrasound (US) images.
- To assess the diagnostic performance of DL models compared to human radiologists.
Main Methods:
- Collected US imaging data from 756 patients with primary breast cancer and clinically negative axillary lymph nodes.
- Trained and tested three convolutional neural network (CNN) architectures (Inception V3, Inception-ResNet V2, ResNet-101) on the dataset.
- Compared the performance of the best CNN model against five radiologists using metrics like accuracy, sensitivity, specificity, and AUC.
Main Results:
- The Inception V3 DL model achieved an Area Under the Curve (AUC) of 0.89 in predicting lymph node metastasis on an independent test set.
- The DL model demonstrated 85% sensitivity and 73% specificity, outperforming radiologists (73% sensitivity, 63% specificity).
- Heat maps indicated areas of interest for the DL model's predictions.
Conclusions:
- Deep learning models can effectively predict clinically negative axillary lymph node metastasis from US images in breast cancer patients.
- AI-powered analysis of US images presents a potential early diagnostic strategy for lymph node metastasis.
- This technology could aid in optimizing treatment decisions for breast cancer patients.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025