Research Progress on Ultrasound Radiomics in Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer

doi:10.26599/AUDT.2026.250066

Abstract

Abstract:

Axillary lymph node (ALN) metastasis is a critical factor influencing prognosis and treatment strategies in breast cancer patients. However, traditional methods—ranging from physical examination to ultrasound—often lack the precision required for clinical decision-making. In recent years, ultrasound radiomics and deep learning have emerged as promising solutions, leveraging high-throughput quantitative features from ultrasound images to enhance detection accuracy. This review explores the development and application of radiomics and deep learning across multiple ultrasound modalities (grayscale, elastography, and contrast-enhanced ultrasound), as well as in multimodal imaging approaches that integrate ultrasound with MRI and PET/CT, underscoring the benefits of incorporating clinicopathological variables to boost predictive performance. These studies provide a vital foundation for personalized treatment and precision medicine in breast cancer management.

Key words: Lymphatic metastasis; Radiomics; Deep learning; Ultrasonography

Gao Yuanjing, Niu Zihan, Luo Yanwen, Zhou Mengyuan, Xiao Mengsu, Jiang Yuxin, Zhu Qingli. Research Progress on Ultrasound Radiomics in Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(2): 79-89.

/ Recommend

Figures/Tables 2

Figure 1

Table 1

Summary of ultrasound radiomics studies in predicting axillary lymph node(ALN) status"

Author	Year	Image type	Number of participants	Number of Centers	AUC (dataset)←model name	ALN status		Parameters	Region of interest segmentation	Feature selection method	Model construction method
Author	Year	Image type	Number of participants	Number of Centers	AUC (dataset)←model name	>0 vs=0	≥3 vs. 1-2	Parameters	Region of interest segmentation	Feature selection method	Model construction method
*means no seperated validation dataset. (final) means finally chosen method to construct the model. Training dataset: Used for model training; Validation dataset: A dataset randomly split from the same source as the training set, used for parameter tuning and model selection. In-test: internal dataset or independent dataset: Partitioned from the same-source data that was never involved in training. External dataset: dataset from other hospitals: Independently sourced data (e.g., collected from other hospitals/equipment). PL, Primary lesion; ALN, Axillary lymph node; val, Validation dataset; RAD, Radiomics; LR, Logistic regression; ICC, Intra-class correlation coefficient; LASSO, Least Absolute Shrinkage and Selection Operator; VIF, variance inflation factor; MRMR, Max-relevance and min-redundancy; ex-test, External dataset; LGOCV, leave group out cross-validation; PCA, principal component analysis; XGB/XGBoost, Extreme gradient boosting; SVM, support vector machine; DL, Deep learning; CNN, Convolutional Neural Network; RF, Random Forest; KNN, K-Nearest Neighbors; NB, naïve Bayesian; SWE, shear wave elastography; CEUS, Contrast enhanced ultrasound.
Only Grayscale US
Qiu [20]	2020	Primary Lesion (PL)	196	1	0.73 (validation dataset (val))← radiomics (radiomics(RAD)) 0.76 (val)←RAD + US-reported ALN	√		RAD, US-reported ALN status	Manual	Elastic net logistic regression; univariate analyses	Logistic regression (LR)
Yu [21]	2019	PL	426	1	0.71(val) ← RAD 0.81(val) ← combined model	√		RAD + size + US-reported ALN status	Manual	Intra-class correlation coefficient (ICC); Least Absolute Shrinkage and Selection Operator (LASSO); variance inflation factor (VIF)	Multivariable LR
Zhou [22]	2021	PL	192	2	0.65 (External dataset (ex-test))	√		RAD	Manual	Max-relevance and min-redundancy (MRMR); LASSO	LASSO; leave group out cross-validation (LGOCV)
Gao [23]	2021	PL	343	1	0.73 (val)		√	RAD，size, age	Manual	LASSO	LR
Wu [24]	2024	PL	215	2	0.66 (ex-test) ← clinical model 0.72 (ex-test) ← RAD model		√	RAD/clinicopathological features	Manual	ICC; Mann-Whitney U test; LASSO; principal component analysis (PCA) and Boruta (final)	Extreme gradient boosting (XGB/XGBoost)(final); LR; support vector machine (SVM)
Zhang [25]	2023	PL	176	1	0.81(val)← Deep learning (DL)-RAD model 0.82 (val)←DL-nomogram		√	RAD + ResNet-50; size, clinicopathological features	Manual	ICC, Independent sample T-test; random forest recursive elimination; LASSO	Univariate/multivariate LR analysis
Lee [26]	2021	PL + peritumoral area	153	1	0.81 (val)	√		DL features or handcrafted features (shape, textural)	Mask R- Convolutional Neural Network (CNN)	\；	DenseNet-121 (final)； LR；SVM；XGBoost
Wang [27]	2024	PL+ peritumoral area	321	1	0.78 (val)←clinical model 0.84 (val)←RAD model 0.91(val)←combined model	√		RAD + conventional ultrasound & immunohistochemical indicators	Manual	Correlation analysis; Univariate analysis; MRMR; LASSO	LR; Decision Tree; SVM; XGB (final); Random Forest(RF); K-Nearest Neighbors (KNN)
Zhang [28]	2024	PL+ peritumoral area	755	1	Combined model: 0.87(val) ←presence/absence 0.91(val)←high/low tumor burden	√	√	Conventional ultrasound & clinical indicators	Manual	MRMR; LASSO; Pearson’s coefficient and VIF	Multivariate LR;
Coronado [29]	2019	ALN	105	2	0.94(train+val-k-fold*)	√		Computed ROI features	Manual	A variation of Fisher Vector FV- CNN features Supervised machine learning
Sun [31]	2022	ALN	169	1	0.72 (test)	√		CNN features	Manual	Custom CNN
Ozaki [30]	2022	ALN	300	1	0.97(val)	√		DL features	Deep Analyzer	GoogleNet Xception; Supervised learning
Tang [32]	2023	ALN	147	2	0.92 (val)	√		RAD	Manual	ICC; Spearman correlation analysis; LASSO
Chen [33]	2023	ABUS	310	1	0.79(val)← ABUS RAD 0.74(val)← ABUS features 0.85(val)← RAD+retraction phenomenon+ US reported ALN status		√	RAD (ABUS) + ABUS imaging features +clinicopathologic features	Manual	Pearson correlation coefficient; Spearman’s rank correlation coefficient; LASSO	Univariate & Multivariate LR
Li [34]	2023	ABUS	517	2	0.81(test)		√	RAD (ABUS) + size+ US-reported LN status +retraction phenomenon	Manual	ICC; LASSO	Univariate & Multivariate LR
Wang [35]	2023	ABUS	276	2	0.67(test)←RAD 0.83(test)←combined model	√		RAD (ABUS) + US-reported LN status + convergence + erythrocyte distribution width	Manual	ICC；LASSO	univariate LR
Li [36]	2023	US video	320	3	0.91(test)← video 0.86(test)← images	√		CNN features	Normalize the data	Video: CNN with R2+1D, TIN (final), ResNet-3D Static images: ResNet50, InceptionV3, VGG19
Zha [37]	2021	PL	452	1	0.77(val) ← RAD 0.83(val) ←combined model	√		RAD+ MSKKCC nomogram	Manual	mRMR; LASSO Cox regression	LR
Ouyang [38]	2024	PL	212	1	0.85 (val)	√		RAD + size, tumor type, age, Ki67	Manual	Pearson correlation Coefficients; LASSO	SVM, naïve Bayesian (NB), optimization method
Yao [39]	2024	PL	278	1	0.92(val)← RAD 0.93(val)← combined model		√	RAD + high tumor grade & positive LVI	Manual	The synthetic minority oversampling technique; PCA, recursive feature elimination	linear discriminant analysis; SVM, RF, decision tree;
Zhao [40]	2023	PL	199	1	0.68 (val) ← RAD 0.69 (val) ← RAD+conventional US + peripheral blood T cell 0.79 (val) ← combined model	√		RAD + peripheral blood T-cell subsets	Manual	LASSO	NB; LR (final), classification decision tree, SVM
Qian [41]	2024	PL	364	1	0.89(val) ← RAD 0.74(val) ← clinical model 0.91(val) ← combined model	√		DL (DenseNet-201) features + RAD + clinical features	Manual rectangle ROI	DL: Spearman correlation coefficient; RAD: LASSO; ICC; mRMR	Univariate analysis; Stepwise multivariable LR
Zhou [42]	2019	PL	834	2	0.90(in-test) 0.89 (ex-test)	√		DL features	/	Inception V3 (final); Inception-ResNet V2; ResNet-101
Wang [43]	2024	PL	266	1	0.80 (in-test)	√		DL features	DeepLabV3 + ResNet-101	CNN
Liu [44]	2024	PL	883	4	0.91(ex-test1); 0.93 (ex-test2); 0.95 (ex-test3)	√		DL features (ResNet50) + RAD+ clinical parameters	Manual	ResNet50; ICC； LASSO	Univariate & multivariate LR
You [45]	2024	PL	792	3	Combined model: 0.83 (ex-test1); 0.83(ex-test2)	√(received NAC)		DL features; Clinicopathologic data	You Only Look Once Version 5	Progressive multi-granularity (PMG) classification network; Multivariable logistic regression; image super-resolution via iterative refinement (SR3)
Guo [46]	2020	PL	937	2	0.84(ex-test) ← SLN 0.81(ex-test) ←non-SLN	√	Non-SLN metastasis	DL features + US-reported ALN status	Manual	DenseNet
Multimodal US (Combined with Grayscale US)
Zheng [47]	2020	PL (shear wave elastography (SWE) & grayscale)	584	1	Combined model: 0.902(in-test) ←presence/absence 0.91(in-test) ←high/low tumor burden	√	√	DL features of (grayscale & SWE) + clinicopathological parameters	Manual rectangle ROI	ResNet50 (final), ResNet101, Inception V3, and VGG19
Jiang [48]	2022	PL (SWE)	433	2	C-index: 0.82(ex-test) ← presence/absence 0.81(ex-test) ← high/low tumor burden	√	√	RAD (grayscale/SWE) + molecular subtype + US-reported ALN status	Manual	Spearman’s correlation; LASSO; MRMR	Proportional odds ordinal LR
Wang [49]	2023	PL (strain elastography)	359	2	0.79(ex-test) ←PL (grayscale) 0.73 (ex-test) ←PL(color Doppler flow imaging (CDFI)); 0.88(ex-test) ←PL (elastography)	√		DL (grayscale/CDFI/strain elastography)	Manual	ResNet-18
Gong [50]	2025	ALN (grayscale+ SWE)	519	1	0.86 (in-test) ← ALN (grayscale) 0.83 (in-test) ←ALN (SWE); 0.93 (ex-test) ←ALN (SWE + grayscale)	√		DAMF-former(grayscale/SWE)	Manual rectangle ROI	DAMF-former (core module: dual-modal adaptive fusion module)
Sun [51]	2024	PL (grayscale, Contrast enhanced ultrasound (CEUS))	111	1	0.82 (val)← US-reported ALN 0.89 (val)← US-reported ALN+RAD (grayscale) 0.90 (val)← US-reported ALN+RAD (grayscale+CEUS)	√		RAD (grayscale/CEUS), US-reported ALN status	Manual (grayscale); computer vision algorithm (CEUS)	VIF; MRMR; LASSO	LR
Yan [52]	2025	PL (grayscale, CEUS)	282	2	0.81 (ex-test)	√		RAD (grayscale)，histologic type (only for nomogram)	Manual	RF, LASSO	Univariate & multivariate LR, NB, SVM; KNN; XGBoost (final); nomogram
Other multimodal imaging (combined with grayscale US)
Tang [53]	2025	PL (MRI + US)	588	2	0.81(ex-test) ← DL (MRI + US + clinical parameters)	√		DL features (MRI/US), age, MRI-derived tumor size, MRI-derived ALN status	Manual rectangle ROI	ConvNeXt (final), ResNet18, VGG16 → US 3D-ResNet (final), C3D, R (2+1)D → MRI; multivariable LR
Li [54]	2023	(18F-FDG) PET/CT	124	1	0.87(val)← T-stage+ US/PET reported ALN status+ RAD(PET)	√		RAD (PET), T-stage, US/PET reported ALN status	Manual	LASSO	Univariate & multivariate LR

Table 1

References 56

[1]	Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin 2022; 72: 7-33.
[2]	Chen W, Zheng R, Baade PD, Zhang S, Zeng H, Bray F, et al. Cancer statistics in China, 2015. CA Cancer J Clin 2016; 66: 115-132.
[3]	Sechopoulos I, Teuwen J, Mann R. Artificial intelligence for breast cancer detection in mammography and digital breast tomosynthesis: state of the art. Semin Cancer Biol 2021; 72: 214-225. doi: 10.1016/j.semcancer.2020.06.002
[4]	Giuliano AE, Ballman KV, McCall L, Beitsch PD, Brennan MB, Kelemen PR, et al. Effect of axillary dissection vs no axillary dissection on 10-year overall survival among women with invasive breast cancer and sentinel node metastasis: the ACOSOG Z0011 (alliance) randomized clinical trial. JAMA 2017; 318: 918-926. doi: 10.1001/jama.2017.11470
[5]	de Boniface J, Filtenborg Tvedskov T, Rydén L, Szulkin R, Reimer T, Kühn T, et al. Omitting axillary dissection in breast cancer with sentinel-node metastases. N Engl J Med 2024; 390: 1163-1175. doi: 10.1056/NEJMoa2313487
[6]	Lyman GH, Somerfield MR, Bosserman LD, Perkins CL, Weaver DL, Giuliano AE. Sentinel lymph node biopsy for patients with early-stage breast cancer: American society of clinical oncology clinical practice guideline update. J Clin Oncol 2017; 35: 561-564.
[7]	Gentilini OD, Botteri E, Sangalli C, Galimberti V, Porpiglia M, Agresti R, et al. Sentinel lymph node biopsy vs no axillary surgery in patients with small breast cancer and negative results on ultrasonography of axillary lymph nodes: the sound randomized clinical trial. JAMA Oncol 2023; 9: 1557-1564. doi: 10.1001/jamaoncol.2023.3759
[8]	Valente SA, Levine GM, Silverstein MJ, Rayhanabad JA, Weng-Grumley JG, Ji L, et al. Accuracy of predicting axillary lymph node positivity by physical examination, mammography, ultrasonography, and magnetic resonance imaging. Ann Surg Oncol 2012; 19: 1825-1830. doi: 10.1245/s10434-011-2200-7
[9]	Alvarez S, Añorbe E, Alcorta P, López F, Alonso I, Cortés J. Role of sonography in the diagnosis of axillary lymph node metastases in breast cancer: a systematic review. AJR Am J Roentgenol 2006; 186: 1342-1348. doi: 10.2214/AJR.05.0936
[10]	Cools-Lartigue J, Meterissian S. Accuracy of axillary ultrasound in the diagnosis of nodal metastasis in invasive breast cancer: a review. World J Surg 2012; 36: 46-54. doi: 10.1007/s00268-011-1319-9
[11]	Chen X, He Y, Wang J, Huo L, Fan Z, Li J, et al. Feasibility of using negative ultrasonography results of axillary lymph nodes to predict sentinel lymph node metastasis in breast cancer patients. Cancer Med 2018; 7: 3066-3072. doi: 10.1002/cam4.1606
[12]	Zhu Y, Zhou W, Jia XH, Huang O, Zhan WW. Preoperative axillary ultrasound in the selection of patients with a heavy axillary tumor burden in early-stage breast cancer: what leads to false-positive results?. J Ultrasound Med 2018; 37: 1357-1365.
[13]	Ahmed M, Jozsa F, Baker R, Rubio IT, Benson J, Douek M. Meta-analysis of tumour burden in pre-operative axillary ultrasound positive and negative breast cancer patients. Breast Cancer Res Treat 2017; 166: 329-336. doi: 10.1007/s10549-017-4405-3
[14]	van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017; 77: e104-e107. doi: 10.1158/0008-5472.CAN-17-0339
[15]	Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology 2016; 278: 563-577. doi: 10.1148/radiol.2015151169
[16]	Bevilacqua JL, Kattan MW, Fey JV, Cody HS, 3rd PI, Borgen Zee KJ. Doctor, what are my chances of having a positive sentinel node? A validated nomogram for risk estimation. J Clin Oncol 2007; 25: 3670-3679. doi: 10.1200/JCO.2006.08.8013
[17]	Chue KM, Yong WS, Thike AA, Ahmed SS, Li HH, Wong CY, et al. Predicting the likelihood of additional lymph node metastasis in sentinel lymph node positive breast cancer: validation of the Memorial Sloan-Kettering Cancer Centre (MSKCC) nomogram. J Clin Pathol 2014; 67: 112-119. doi: 10.1136/jclinpath-2013-201524
[18]	Rouzier R, Uzan C, Rousseau A, Guillot E, Zilberman S, Meyer C, et al. Multicenter prospective evaluation of the reliability of the combined use of two models to predict non-sentinel lymph node status in breast cancer patients with metastatic sentinel lymph nodes: the MSKCC nomogram and the Tenon score. Results of the NOTEGS study. Br J Cancer 2017; 116: 1135-1140.
[19]	Barranger E, Coutant C, Flahault A, Delpech Y, Darai E, Uzan S. An axilla scoring system to predict non-sentinel lymph node status in breast cancer patients with sentinel lymph node involvement. Breast Cancer Res Treat 2005; 91: 113-119. doi: 10.1007/s10549-004-5781-z
[20]	Qiu X, Jiang Y, Zhao Q, Yan C, Huang M, Jiang T. Could ultrasound-based radiomics noninvasively predict axillary lymph node metastasis in breast cancer?. J Ultrasound Med 2020; 39: 1897-1905.
[21]	Yu FH, Wang JX, Ye XH, Deng J, Hang J, Yang B. Ultrasound-based radiomics nomogram: A potential biomarker to predict axillary lymph node metastasis in early-stage invasive breast cancer. Eur J Radiol 2019; 119: 108658 doi: 10.1016/j.ejrad.2019.108658
[22]	Zhou WJ, Zhang YD, Kong WT, Zhang CX, Zhang B. Preoperative prediction of axillary lymph node metastasis in patients with breast cancer based on radiomics of gray-scale ultrasonography. Gland Surg 2021; 10: 1989-2001. doi: 10.21037/gs-21-315
[23]	Gao Y, Luo Y, Zhao C, Xiao M, Ma L, Li W, et al. Nomogram based on radiomics analysis of primary breast cancer ultrasound images: prediction of axillary lymph node tumor burden in patients. Eur Radiol 2021; 31: 928-937. doi: 10.1007/s00330-020-07181-1
[24]	Wu J, Ge L, Guo Y, Xu D, Wang Z. Utilizing multiclassifier radiomics analysis of ultrasound to predict high axillary lymph node tumour burden in node-positive breast cancer patients: a multicentre study. Ann Med 2024; 56: 395061
[25]	Zhang H, Zhao T, Zhang S, Sun J, Zhang F, Li X, et al. Prediction of axillary lymph node metastatic load of breast cancer based on ultrasound deep learning radiomics nomogram. Technol Cancer Res Treat 2023; 22: 15330338231166218
[26]	Lee YW, Huang CS, Shih CC, Chang RF. Axillary lymph node metastasis status prediction of early-stage breast cancer using convolutional neural networks. Comput Biol Med 2021; 130: 104206 doi: 10.1016/j.compbiomed.2020.104206
[27]	Wang SR, Cao CL, Du TT, Wang JL, Li J, Li WX, et al. Machine learning model for predicting axillary lymph node metastasis in clinically node positive breast cancer based on peritumoral ultrasound radiomics and shap feature analysis. J Ultrasound Med 2024; 43: 1611-1625. doi: 10.1002/jum.16483
[28]	Zhang W, Wang S, Wang Y, Sun J, Wei H, Xue W, et al. Ultrasound-based radiomics nomogram for predicting axillary lymph node metastasis in early-stage breast cancer. Radiol Med 2024; 129: 211-221. doi: 10.1007/s11547-024-01768-0
[29]	Coronado-Gutiérrez D, Santamaría G, Ganau S, Bargalló X, Orlando S, Oliva-Brañas ME, et al. Quantitative ultrasound image analysis of axillary lymph nodes to diagnose metastatic involvement in breast cancer. Ultrasound Med Biol 2019; 45: 2932-2941. doi: 10.1016/j.ultrasmedbio.2019.07.413
[30]	Ozaki J, Fujioka T, Yamaga E, Hayashi A, Kujiraoka Y, Imokawa T, et al. Deep learning method with a convolutional neural network for image classification of normal and metastatic axillary lymph nodes on breast ultrasonography. Jpn J Radiol 2022; 40: 814-822. doi: 10.1007/s11604-022-01261-6
[31]	Sun S, Mutasa S, Liu MZ, Nemer J, Sun M, Siddique M, et al. Deep learning prediction of axillary lymph node status using ultrasound images. Comput Biol Med 2022; 143: 105250 doi: 10.1016/j.compbiomed.2022.105250
[32]	Tang YL, Wang B, Ou-Yang T, Lv WZ, Tang SC, Wei A, et al. Ultrasound radiomics based on axillary lymph nodes images for predicting lymph node metastasis in breast cancer. Front Oncol 2023; 13: 1217309 doi: 10.3389/fonc.2023.1217309
[33]	Chen Y, Xie Y, Li B, Shao H, Na Z, Wang Q, et al. Automated breast ultrasound (ABUS)-based radiomics nomogram: an individualized tool for predicting axillary lymph node tumor burden in patients with early breast cancer. BMC Cancer 2023; 23: 340 doi: 10.1186/s12885-023-10743-3
[34]	Li N, Song C, Huang X, Zhang H, Su J, Yang L, et al. Optimized radiomics nomogram based on automated breast ultrasound system: a potential tool for preoperative prediction of metastatic lymph node burden in breast cancer. Breast Cancer (Dove Med Press) 2023; 15: 121-132.
[35]	Wang H, Yang XW, Chen F, Qin YY, Li XB, Ma SM, et al. Non-invasive assessment of axillary lymph node metastasis risk in early invasive breast cancer adopting automated breast volume scanning-based radiomics nomogram: a multicenter study. Ultrasound Med Biol 2023; 49: 1202-1211. doi: 10.1016/j.ultrasmedbio.2023.01.006
[36]	Li WB, Du ZC, Liu YJ, Gao JX, Wang JG, Dai Q, et al. Prediction of axillary lymph node metastasis in early breast cancer patients with ultrasonic videos based deep learning. Front Oncol 2023; 13: 1219838 doi: 10.3389/fonc.2023.1219838
[37]	Zha HL, Zong M, Liu XP, Pan JZ, Wang H, Gong HY, et al. Preoperative ultrasound-based radiomics score can improve the accuracy of the Memorial Sloan Kettering Cancer Center nomogram for predicting sentinel lymph node metastasis in breast cancer. Eur J Radiol 2021; 135: 109512 doi: 10.1016/j.ejrad.2020.109512
[38]	Ouyang Q, Chen Q, Zhang L, Lin Q, Yan J, Sun H, et al. Construction of a risk prediction model for axillary lymph node metastasis in breast cancer based on gray-scale ultrasound and clinical pathological features. Front Oncol 2024; 14: 1415584 doi: 10.3389/fonc.2024.1415584
[39]	Yao J, Zhou W, Xu S, Jia X, Zhou J, Chen X, et al. Machine learning-based breast tumor ultrasound radiomics for pre-operative prediction of axillary sentinel lymph node metastasis burden in early-stage invasive breast cancer. Ultrasound Med Biol 2024; 50: 229-236. doi: 10.1016/j.ultrasmedbio.2023.10.004
[40]	Zhao M, Zheng Y, Chu J, Liu Z, Dong F. Ultrasound-based radiomics combined with immune status to predict sentinel lymph node metastasis in primary breast cancer. Sci Rep 2023; 13: 16918 doi: 10.1038/s41598-023-44156-w
[41]	Qian L, Liu X, Zhou S, Zhi W, Zhang K, Li H, et al. A cutting-edge deep learning-and-radiomics-based ultrasound nomogram for precise prediction of axillary lymph node metastasis in breast cancer patients ≥ 75 years. Front Endocrinol (Lausanne) 2024; 15: 1323452 doi: 10.3389/fendo.2024.1323452
[42]	Zhou LQ, Wu XL, Huang SY, Wu GG, Ye HR, Wei Q, et al. Lymph node metastasis prediction from primary breast cancer us images using deep learning. Radiology 2020; 294: 19-28. doi: 10.1148/radiol.2019190372
[43]	Wang X, Nie L, Zhu Q, Zuo Z, Liu G, Sun Q, et al. Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer. BMC Cancer 2024; 24: 910 doi: 10.1186/s12885-024-12619-6
[44]	Liu H, Zou L, Xu N, Shen H, Zhang Y, Wan P, et al. Deep learning radiomics based prediction of axillary lymph node metastasis in breast cancer. NPJ Breast Cancer 2024; 10: 22 doi: 10.1038/s41523-024-00628-4
[45]	You J, Huang Y, Ouyang L, Zhang X, Chen P, Wu X, et al. Automated and reusable deep learning (AutoRDL) framework for predicting response to neoadjuvant chemotherapy and axillary lymph node metastasis in breast cancer using ultrasound images: a retrospective, multicentre study. EClinicalMedicine 2024; 69: 102499 doi: 10.1016/j.eclinm.2024.102499
[46]	Guo X, Liu Z, Sun C, Zhang L, Wang Y, Li Z, et al. Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer. EBioMedicine 2020; 60: 103018 doi: 10.1016/j.ebiom.2020.103018
[47]	Zheng X, Yao Z, Huang Y, Yu Y, Wang Y, Liu Y, et al. Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer. Nat Commun 2020; 11: 1236 doi: 10.1038/s41467-020-15027-z
[48]	Jiang M, Li CL, Luo XM, Chuan ZR, Chen RX, Tang SC, et al. Radiomics model based on shear-wave elastography in the assessment of axillary lymph node status in early-stage breast cancer. Eur Radiol 2022; 32: 2313-2325. doi: 10.1007/s00330-021-08330-w
[49]	Wang C, Zhao Y, Wan M, Huang L, Liao L, Guo L, et al. Prediction of sentinel lymph node metastasis in breast cancer by using deep learning radiomics based on ultrasound images. Medicine (Baltimore) 2023; 102: e35868 doi: 10.1097/MD.0000000000035868
[50]	Gong C, Wu Y, Zhang G, Liu X, Zhu X, Cai N, et al. Computer-assisted diagnosis for axillary lymph node metastasis of early breast cancer based on transformer with dual-modal adaptive mid-term fusion using ultrasound elastography. Comput Med Imaging Graph 2025; 119: 102472 doi: 10.1016/j.compmedimag.2024.102472
[51]	Sun C, Gong X, Hou L, Yang D, Li Q, Li L, et al. A nomogram based on conventional and contrast-enhanced ultrasound radiomics for the noninvasively prediction of axillary lymph node metastasis in breast cancer patients. Front Oncol 2024; 14: 1400872 doi: 10.3389/fonc.2024.1400872
[52]	Yan M, He D, Sun Y, Huang L, Cai L, Wang C, et al. Comparative analysis of nomogram and machine learning models for predicting axillary lymph node metastasis in early-stage breast cancer: a study on clinically and ultrasound-negative axillary cases across two centers. Ultrasound Med Biol 2025; 51: 463-474. doi: 10.1016/j.ultrasmedbio.2024.11.003
[53]	Tang X, Zhang H, Mao R, Zhang Y, Jiang X, Lin M, et al. Preoperative prediction of axillary lymph node metastasis in patients with breast cancer through multimodal deep learning based on ultrasound and magnetic resonance imaging images. Acad Radiol 2025; 32: 1-11. doi: 10.1016/j.acra.2024.07.029
[54]	Li Y, Han D, Shen C, Duan X. Construction of a comprehensive predictive model for axillary lymph node metastasis in breast cancer: a retrospective study. BMC Cancer 2023; 23: 1028 doi: 10.1186/s12885-023-11498-7
[55]	Guo F, Sun S, Deng X, Wang Y, Yao W, Yue P, et al. Predicting axillary lymph node metastasis in breast cancer using a multimodal radiomics and deep learning model. Front Immunol 2024; 15: 1482020 doi: 10.3389/fimmu.2024.1482020
[56]	Wang Q, Lin Y, Ding C, Guan W, Zhang X, Jia J, et al. Multi-modality radiomics model predicts axillary lymph node metastasis of breast cancer using MRI and mammography. Eur Radiol 2024; 34: 6121-6131. doi: 10.1007/s00330-024-10638-2