Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study

Liao, Jianwei; Gui, Yu; Li, Z.-Q.; Deng, Zijian; Han, Xuefei; Huang, Tian; Li, Cai; Liu, Xingyu; Tang, Chengyong; Jia, Lei; Ya, Wei; Huang, Lan; Niu, Fengling; Liu, Jing; Yang, Xi; Li, Shichao; Cui, Xiang; Wu, Xin; Chen, Qingqiu; Wan, Andi; Jiang, Jun; Zhang, Yi; Luo, Xiangdong; Wang, Peng; Cai, Zhenhua; Chen, Li

doi:10.1016/j.eclinm.2023.102001

Cited by 6 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have explored the efficacy of different AI models in the diagnosis of breast nodules. [20][21][22][23][24][25][26] Most of these studies have focused on two-dimensional grayscale ultrasound images, ultrasound elastography, and other multimodal images. However, there is a relatively limited number of studies that have specifically utilized super-resolution ultrasound images.…”

Section: Performance Of Nomogrammentioning

confidence: 99%

Nomogram Based on Super-Resolution Ultrasound Images Outperforms in Predicting Benign and Malignant Breast Lesions

Yang,

2023

BCTT

View full text Add to dashboard Cite

To establish a good predictive model using a deep-learning (DL)-based three-dimensional (3D) super-resolution ultrasound images for the diagnosis of benign and malignant breast lesions. Methods: This retrospective study included 333 patients with histopathologically confirmed breast lesions, randomly split into training (N=266) and testing (N=67) datasets. Eight models, including four deep learning models (ORResNet101, ORMobileNet_v2, SRResNet101, SRMobileNet_v2) and four machine learning models (OR_LR, OR_SVM, SR_LR, SR_SVM), were developed based on original and super-resolution images. The best performing model was SRMobileNet_v2, which was used to construct a nomogram integrating clinical factors. The performance of nomogram was evaluated using receiver operating characteristic (ROC) analysis, decision curve analysis (DCA), and calibration curves. Results: SRMobileNet_v2, MobileNet_V2 based on super-resolution ultrasound images, had the best predictive performance in four traditional machine learning models and four deep learning models, with AUC improvements of 0.089 and 0.031 in the training and testing sets, relative to the ORMobileNet_v2 model based on original ultrasound images. The deep-learning nomogram was constructed using the SRMobileNet_v2 model score, tumor size, and patient age, resulting in superior predictive efficacy compared to the nomogram without the SRMobileNet_v2 model score. Furthermore, it demonstrated favorable calibration, discrimination, and clinical utility in both cohorts. Conclusion:The diagnostic prediction model utilizing super-resolution reconstructed ultrasound images outperforms the model based on original images in distinguishing between benign and malignant breast lesions. The nomogram based on super-resolution ultrasound images has the potential to serve as a reliable auxiliary diagnostic tool for clinicians, exhibiting superior predictive performance in distinguishing between benign and malignant breast lesions.

show abstract

Section: Performance Of Nomogrammentioning

confidence: 99%

Nomogram Based on Super-Resolution Ultrasound Images Outperforms in Predicting Benign and Malignant Breast Lesions

Yang,

2023

BCTT

View full text Add to dashboard Cite

show abstract

Sonogenetics in the Treatment of Chronic Diseases: A New Method for Cell Regulation

Zhu,

Fang,

Sun

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Sonogenetics is an innovative technology that integrates ultrasound with genetic editing to precisely modulate cellular activities in a non‐invasive manner. This method entails introducing and activating mechanosensitive channels on the cell membrane of specific cells using gene delivery vectors. When exposed to ultrasound, these channels can be manipulated to open or close, thereby impacting cellular functions. Sonogenetics is currently being used extensively in the treatment of various chronic diseases, including Parkinson's disease, vision restoration, and cancer therapy. This paper provides a comprehensive review of key components of sonogenetics and focuses on evaluating its prospects and potential challenges in the treatment of chronic disease.

show abstract

IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images

Chen,

Li,

Zhang

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study

Cited by 6 publications

References 37 publications

Nomogram Based on Super-Resolution Ultrasound Images Outperforms in Predicting Benign and Malignant Breast Lesions

Nomogram Based on Super-Resolution Ultrasound Images Outperforms in Predicting Benign and Malignant Breast Lesions

Sonogenetics in the Treatment of Chronic Diseases: A New Method for Cell Regulation

IRUM: An Image Representation and Unified Learning Method for Breast Cancer Diagnosis from Multi-View Ultrasound Images

Contact Info

Product

Resources

About