Prediction of Axillary Lymph Node Metastatic Load of Breast Cancer Based on Ultrasound Deep Learning Radiomics Nomogram

Zhang, Heng; Zhao, Tong; Zhang, Sai; Sun, Jun; Zhang, Fan; Li, Xiaoqin; Ni, Xinye

doi:10.1177/15330338231166218

Cited by 8 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting proteomic-and lipidomic-based models demonstrate the high potential for diagnosing regional metastasis with 91% sensitivity and 89% specificity (AUC = 0.92) for the protein model. The performance of the proteomic-based model was significantly better compared to machine learning models using ultrasound and MRI data [82,83], dynamiccontrast-enhanced MRI [84], MRI with genomic data [85] and ultrasound [86]. A radiomics machine learning model based on computed tomography exhibited comparable sensitivity and specificity [87].…”

Section: Discussionmentioning

confidence: 99%

Integrating Proteomics and Lipidomics for Evaluating the Risk of Breast Cancer Progression: A Pilot Study

et al. 2023

View full text Add to dashboard Cite

Metastasis is a serious and often life-threatening condition, representing the leading cause of death among women with breast cancer (BC). Although the current clinical classification of BC is well-established, the addition of minimally invasive laboratory tests based on peripheral blood biomarkers that reflect pathological changes in the body is of utmost importance. In the current study, the serum proteome and lipidome profiles for 50 BC patients with (25) and without (25) metastasis were studied. Targeted proteomic analysis for concertation measurements of 125 proteins in the serum was performed via liquid chromatography–multiple reaction monitoring mass spectrometry (LC–MRM MS) using the BAK 125 kit (MRM Proteomics Inc., Victoria, BC, Canada). Untargeted label-free lipidomic analysis was performed using liquid chromatography coupled to tandem mass-spectrometry (LC–MS/MS), in both positive and negative ion modes. Finally, 87 serum proteins and 295 lipids were quantified and showed a moderate correlation with tumor grade, histological and biological subtypes, and the number of lymph node metastases. Two highly accurate classifiers that enabled distinguishing between metastatic and non-metastatic BC were developed based on proteomic (accuracy 90%) and lipidomic (accuracy 80%) features. The best classifier (91% sensitivity, 89% specificity, AUC = 0.92) for BC metastasis diagnostics was based on logistic regression and the serum levels of 11 proteins: alpha-2-macroglobulin, coagulation factor XII, adiponectin, leucine-rich alpha-2-glycoprotein, alpha-2-HS-glycoprotein, Ig mu chain C region, apolipoprotein C-IV, carbonic anhydrase 1, apolipoprotein A-II, apolipoprotein C-II and alpha-1-acid glycoprotein 1.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrating Proteomics and Lipidomics for Evaluating the Risk of Breast Cancer Progression: A Pilot Study

et al. 2023

View full text Add to dashboard Cite

show abstract

Ultrasound‐based radiomics for the differential diagnosis of breast masses: A systematic review and meta‐analysis

Li,

Zhang,

Ding

2024

J of Clinical Ultrasound

View full text Add to dashboard Cite

ObjectivesUltrasound‐based radiomics has demonstrated excellent diagnostic performance in differentiating benign and malignant breast masses. Given a few clinical studies on their diagnostic role, we conducted a meta‐analysis of the potential effects of ultrasound‐based radiomics for the differential diagnosis of breast masses, aiming to provide evidence‐based medical basis for clinical research.Materials and MethodsWe searched Embase, Web of Science, Cochrane Library, and PubMed databases from inception through to February 2023. The methodological quality assessment of the included studies was performed according to Quality Assessment of Diagnostic Accuracy Studies checklist. A diagnostic test accuracy systematic review and meta‐analysis was performed in accordance with PRISMA guidelines. Sensitivity, specificity, and area under curve delineating benign and malignant lesions were recorded. We also used sensitivity analysis and subgroup analysis to explore potential sources of heterogeneity. Deeks' funnel plots was used to examine the publication bias.ResultsA total of 11 studies were included in this meta‐analysis. For the diagnosis of malignant breast masses worldwide, the overall mean rates of sensitivity and specificity of ultrasound‐based radiomics were 0.90 (95% confidence interval [CI], 0.83–0.95) and 0.89 (95% CI, 0.82–0.94), respectively. The summary diagnostic odds ratio was 76 (95% CI, 26–219), and the area under the curve for the summary receiver operating characteristic curve was 0.95 (95% CI, 0.93–0.97).ConclusionUltrasound‐based radiomics has the potential to improve diagnostic accuracy to discriminate between benign and malignant breast masses, and could reduce unnecessary biopsies.

show abstract

Application of artificial intelligence in ultrasound imaging for predicting lymph node metastasis in breast cancer: A meta-analysis

Wang,

Liu,

2024

Clinical Imaging

View full text Add to dashboard Cite

Prediction of Axillary Lymph Node Metastatic Load of Breast Cancer Based on Ultrasound Deep Learning Radiomics Nomogram

Cited by 8 publications

References 29 publications

Integrating Proteomics and Lipidomics for Evaluating the Risk of Breast Cancer Progression: A Pilot Study

Integrating Proteomics and Lipidomics for Evaluating the Risk of Breast Cancer Progression: A Pilot Study

Ultrasound‐based radiomics for the differential diagnosis of breast masses: A systematic review and meta‐analysis

Application of artificial intelligence in ultrasound imaging for predicting lymph node metastasis in breast cancer: A meta-analysis

Contact Info

Product

Resources

About