Ultrasound Radiogenomics-based Prediction Models for Gene Mutation Status in Breast Cancer

doi:10.37015/AUDT.2025.240010

Abstract

Abstract:

Ultrasound radiogenomics, an emerging field at the intersection of radiology and genomics, employs high-throughput methods to convert radiological images into high-dimensional data, which are then processed to extract and analyze radiomic features. These features, including shape, texture, and intensity variations, are correlated with specific genetic mutations such as TP53 and PIK3CA, critical for cancer progression and treatment response. By integrating clinical data with ultrasonic features, predictive models are developed using machine learning techniques, aiming to refine the capability to diagnose and personalize treatment plans for breast cancer patients. This approach reduces the need for invasive biopsies and medical costs for patients through a better understanding of the tumor’s biological behavior using ultrasound images. This review focuses on the application of ultrasound radiogenomics for predicting gene mutations in breast cancer, highlighting its transformative potential in clinical practice and discussing ongoing challenges and future directions in this field.

Key words: Ultrasound; Radiogenomics; Breast cancer; Gene mutation; Prediction models

Zhai Yue, Tan Dianhuan, Lin Xiaona, Lv Heng, Chen Yan, Li Yongbin, Luo Haiyu, Dan Qing, Zhao Chenyang, Xiang Hongjin, Zheng Tingting, Sun Desheng. Ultrasound Radiogenomics-based Prediction Models for Gene Mutation Status in Breast Cancer. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(1): 10-20.

Figures/Tables 4

Figure 1

Table 1

Table 2

Table 3

References 70

[1]	Agostinetto E, Losurdo A, Nader-Marta G, Santoro A, Punie K, Barroso R, et al. Progress and pitfalls in the use of immunotherapy for patients with triple negative breast cancer. Expert Opin Investig Drugs 2022;31:567-591.
[2]	Sha R, Dong X, Yan S, Dai H, Sun A, You L, et al. Cuproptosis-related genes predict prognosis and trastuzumab therapeutic response in HER2-positive breast cancer. Sci Rep 2024;14:2908.
[3]	Li P, Tan X, Dan Q, Hu A, Hu Z, Yang X, et al. MnO2/Ce6 microbubble-mediated hypoxia modulation for enhancing sono-photodynamic therapy against triple negative breast cancer. Biomater Sci 2024;12:1465-1476.
[4]	Bodalal Z, Trebeschi S, Nguyen-Kim TDL, Schats W, Beets-Tan R. Radiogenomics: bridging imaging and genomics. Abdom Radiol (NY) 2019;44:1960-1984.
[5]	Liu Z, Duan T, Zhang Y, Weng S, Xu H, Ren Y, et al. Radiogenomics: a key component of precision cancer medicine. Br J Cancer 2023;129:741-753.
[6]	ElBanan MG, Amer AM, Zinn PO, Colen RR. Imaging genomics of glioblastoma: state of the art bridge between genomics and neuroradiology. Neuroimaging Clin N Am 2015;25:141-153.
[7]	Pope WB. Genomics of brain tumor imaging. Neuroimaging Clin N Am 2015;25:105-119.
[8]	Grossmann P, Gutman DA, Dunn WD, Holder CA, Aerts HJWL. Imaging-genomics reveals driving pathways of MRI derived volumetric tumor phenotype features in Glioblastoma. BMC Cancer 2016;16:611.
[9]	Shui L, Ren H, Yang X, Li J, Chen Z, Yi C, et al. The era of radiogenomics in precision medicine: An emerging approach to support diagnosis, treatment decisions, and prognostication in oncology. Front Oncol 2020;10:570465.
[10]	Saxena S, Jena B, Gupta N, Das S, Sarmah D, Bhattacharya P, et al. Role of artificial intelligence in radiogenomics for cancers in the era of precision medicine. Cancers (Basel). 2022;14.
[11]	Liu Q, Jiang P, Jiang Y, Ge H, Li S, Jin H, et al. Prediction of aneurysm stability using a machine learning model based on PyRadiomics-derived morphological features. Stroke 2019;50:2314-2321.
[12]	Jiang X, Zhao H, Saldanha OL, Nebelung S, Kuhl C, Amygdalos I, et al. An MRI deep learning model predicts outcome in rectal cancer. Radiology 2023;307:e222223.
[13]	Menze B, Isensee F, Wiest R, Wiestler B, Maier-Hein K, Reyes M, et al. Analyzing magnetic resonance imaging data from glioma patients using deep learning. Comput Med Imaging Graph 2021;88:101828.
[14]	Zhuge Y, Ning H, Mathen P, Cheng JY, Krauze AV, Camphausen K, et al. Automated glioma grading on conventional MRI images using deep convolutional neural networks. Med Phys 2020;47:3044-3053.
[15]	Mzoughi H, Njeh I, Wali A, Slima MB, BenHamida A, Mhiri C, et al. Deep Multi-Scale 3D convolutional neural network (CNN) for MRI gliomas brain tumor classification. J Digit Imaging 2020;33:903-915.
[16]	Li P, Li Z, Wang Z, Li C, Wang M. mResU-Net: multi-scale residual U-Net-based brain tumor segmentation from multimodal MRI. Med Biol Eng Comput 2024;62:641-651.
[17]	Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017;14:749-762.
[18]	Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Machine Learning methods for quantitative radiomic biomarkers. Sci Rep 2015;5:13087.
[19]	Jiang L, You C, Xiao Y, Wang H, Su G-H, Xia B-Q, et al. Radiogenomic analysis reveals tumor heterogeneity of triple-negative breast cancer. Cell Rep Med 2022;3:100694.
[20]	Trivizakis E, Papadakis GZ, Souglakos I, Papanikolaou N, Koumakis L, Spandidos DA, et al. Artificial intelligence radiogenomics for advancing precision and effectiveness in oncologic care (review). Int J Oncol 2020;57:43-53.
[21]	Yin X-X, Hadjiloucas S, Zhang Y, Tian Z. MRI radiogenomics for intelligent diagnosis of breast tumors and accurate prediction of neoadjuvant chemotherapy responses-a review. Comput Methods Programs Biomed 2022;214:106510.
[22]	Zhang G, Ye H-R, Sun Y, Guo Z-Z. Ultrasound molecular imaging and its applications in cancer diagnosis and therapy. ACS Sens 2022;7:2857-2864.
[23]	Dan Q, Xu Z, Burrows H, Bissram J, Stringer JSA, Li Y. Diagnostic performance of deep learning in ultrasound diagnosis of breast cancer: a systematic review. NPJ Precis Oncol 2024;8:21.
[24]	Dan Q, Zheng T, Liu L, Sun D, Chen Y. Ultrasound for breast cancer screening in resource-limited settings: current practice and future directions. Cancers (Basel) 2023;15.
[25]	Dan Q, Jiang X, Wang R, Dai Z, Sun D. Biogenic imaging contrast agents. Adv Sci (Weinh) 2023;10:e2207090.
[26]	Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA, Schabath MB, et al. Radiomics: the process and the challenges. Magn Reson Imaging 2012;30:1234-1248.
[27]	Beichel RR, Smith BJ, Bauer C, Ulrich EJ, Ahmadvand P, Budzevich MM, et al. Multi-site quality and variability analysis of 3D FDG PET segmentations based on phantom and clinical image data. Med Phys 2017;44:479-496.
[28]	Dondi F, Gatta R, Albano D, Bellini P, Camoni L, Treglia G, et al. Role of radiomics features and machine learning for the histological classification of stage I and stage II NSCLC at [18F]FDG PET/CT: A comparison between two PET/CT scanners. J Clin Med. 2022;12.
[29]	Choi RY, Coyner AS, Kalpathy-Cramer J, Chiang MF, Campbell JP. Introduction to machine learning, neural networks, and deep learning. Transl Vis Sci Technol 2020;9:14.
[30]	Bini SA. Artificial Intelligence, Machine learning, deep Learning, and cognitive computing: What do these terms mean and how will they impact health care? J Arthroplasty 2018;33:2358-2361.
[31]	Sollini M, Cozzi L, Chiti A, Kirienko M. Texture analysis and machine learning to characterize suspected thyroid nodules and differentiated thyroid cancer: Where do we stand? Eur J Radiol 2018;99:1-8.
[32]	Yang Y, Zheng B, Li Y, Li Y, Ma X. Computer-aided diagnostic models to classify lymph node metastasis and lymphoma involvement in enlarged cervical lymph nodes using PET/CT. Med Phys 2023;50:152-162.
[33]	Rossi G, Barabino E, Fedeli A, Ficarra G, Coco S, Russo A, et al. Radiomic detection of EGFR mutations in NSCLC. Cancer Res 2021;81:724-731.
[34]	Barzaman K, Karami J, Zarei Z, Hosseinzadeh A, Kazemi MH, Moradi-Kalbolandi S, et al. Breast cancer: Biology, biomarkers, and treatments. Int Immunopharmacol 2020;84:106535.
[35]	Nolan E, Lindeman GJ, Visvader JE. Deciphering breast cancer: from biology to the clinic. Cell 2023;186:1708-1728.
[36]	Harbeck N, Gnant M. Breast cancer. Lancet. 2017;389:1134-1150.
[37]	Derakhshan F, Reis-Filho JS. Pathogenesis of triple-negative breast cancer. Annu Rev Pathol 2022;17:181-204.
[38]	Waks AG, Winer EP. Breast cancer treatment: A review. JAMA 2019;321:288-300.
[39]	Higuchi T, Nishimukai A, Ozawa H, Fujimoto Y, Yanai A, Miyagawa Y, et al. Prognostic significance of preoperative 18F-FDG PET/CT for breast cancer subtypes. Breast 2016; 30:5-12 doi: S0960-9776(16)30139-4 pmid: 27569020
[40]	Nishimukai A, Yagi T, Yanai A, Miyagawa Y, Enomoto Y, Murase K, et al. High Ki-67 expression and low progesterone receptor expression could independently lead to a worse prognosis for postmenopausal patients with estrogen receptor-positive and HER2-negative breast cancer. Clin Breast Cancer 2015;15:204-211.
[41]	Petrelli F, Viale G, Cabiddu M, Barni S. Prognostic value of different cut-off levels of Ki-67 in breast cancer: a systematic review and meta-analysis of 64,196 patients. Breast Cancer Res Treat 2015;153:477-491.
[42]	Sakamoto G, Inaji H, Akiyama F, Haga S, Hiraoka M, Inai K, et al. General rules for clinical and pathological recording of breast cancer 2005. Breast Cancer 2005; 12 Suppl:S1-27.
[43]	Zhou J, Jin A-Q, Zhou S-C, Li J-W, Zhi W-X, Huang Y-X, et al. Application of preoperative ultrasound features combined with clinical factors in predicting HER2-positive subtype (non-luminal) breast cancer. BMC Med Imaging 2021;21:184.
[44]	Zhang L, Li J, Xiao Y, Cui H, Du G, Wang Y, et al. Identifying ultrasound and clinical features of breast cancer molecular subtypes by ensemble decision. Sci Rep 2015;5:11085.
[45]	Wu T, Li J, Wang D, Leng X, Zhang L, Li Z, et al. Identification of a correlation between the sonographic appearance and molecular subtype of invasive breast cancer: A review of 311 cases. Clin Imaging 2019;53:179-185.
[46]	Rashmi S, Kamala S, Murthy SS, Kotha S, Rao YS, Chaudhary KV. Predicting the molecular subtype of breast cancer based on mammography and ultrasound findings. Indian J Radiol Imaging 2018;28:354-361.
[47]	Zheng F-Y, Lu Q, Huang B-J, Xia H-S, Yan L-X, Wang X, et al. Imaging features of automated breast volume scanner: Correlation with molecular subtypes of breast cancer. Eur J Radiol 2017;86:267-275.
[48]	Xu J, Li F, Chang F. Correlation of the ultrasound imaging of breast cancer and the expression of molecular biological indexes. Pak J Pharm Sci 2017;30:1425-1430.
[49]	Liu Y, Xiong W, Xu JM, Liu YX, Zhang J. Correlations between the expression of C-erB-2, CD34 and ER in breast cancer patients and the signs of conventional ultrasonography and ultrasound elastography. Eur Rev Med Pharmacol Sci 2018;22:5539-5545.
[50]	Sturesdotter L, Sandsveden M, Johnson K, Larsson A-M, Zackrisson S, Sartor H. Mammographic tumour appearance is related to clinicopathological factors and surrogate molecular breast cancer subtype. Sci Rep 2020;10:20814.
[51]	Wang D, Zhu K, Tian J, Li Z, Du G, Guo Q, et al. Clinicopathological and ultrasonic features of triple-negative breast cancers: a comparison with hormone receptor-positive/human epidermal growth factor receptor-2-negative breast cancers. Ultrasound Med Biol 2018;44:1124-1132.
[52]	Huang Y, Guo Y, Xiao Q, Liang S, Yu Q, Qian L, et al. Unraveling the pivotal network of ultrasound and somatic mutations in triple-negative and non-triple-negative breast cancer. Breast Cancer (Dove Med Press) 2023;15:461-472.
[53]	Yi M, Lin Y, Lin Z, Xu Z, Li L, Huang R, et al. Biopsy or follow-up: AI improves the clinical strategy of US BI-RADS 4A breast nodules using a convolutional neural network. Clin Breast Cancer 2024;24:e319-e332.e2.
[54]	Gao Y, Wang W, Yang Y, Xu Z, Lin Y, Lang T, et al. An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer. BMC Cancer 2024;24:69.
[55]	Wang H, Chen W, Jiang S, Li T, Chen F, Lei J, et al. Intra- and peritumoral radiomics features based on multicenter automatic breast volume scanner for noninvasive and preoperative prediction of HER2 status in breast cancer: a model ensemble research. Sci Rep 2024;14:5020.
[56]	Huang Y, Qiang Y, Jian L, Jin Z, Lang Q, Sheng C, et al. Ultrasonic features and molecular subtype predict somatic mutations in TP53 and PIK3CA genes in breast cancer. Acad Radiol 2022;29:e261-e270.
[57]	Quan M-Y, Huang Y-X, Wang C-Y, Zhang Q, Chang C, Zhou S-C. Deep learning radiomics model based on breast ultrasound video to predict HER2 expression status. Front Endocrinol (Lausanne) 2023;14:1144812.
[58]	Liang S, Xu S, Zhou S, Chang C, Shao Z, Wang Y, et al. IMAGGS: a radiogenomic framework for identifying multi-way associations in breast cancer subtypes. J Genet Genomics 2024;51:443-453.
[59]	Yan M, Yao J, Zhang X, Xu D, Yang C. Machine learning-based model constructed from ultrasound radiomics and clinical features for predicting HER2 status in breast cancer patients with indeterminate (2+) immunohistochemical results. Cancer Med 2024;13:e6946.
[60]	Yu F-H, Miao S-M, Li C-Y, Hang J, Deng J, Ye X-H, et al. Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer. Eur Radiol 2023;33:5634-5644.
[61]	Gu J, Tong T, Xu D, Cheng F, Fang C, He C, et al. Deep learning radiomics of ultrasonography for comprehensively predicting tumor and axillary lymph node status after neoadjuvant chemotherapy in breast cancer patients: A multicenter study. Cancer 2023;129:356-366.
[62]	Moon WK, Chen H-H, Shin SU, Han W, Chang R-F. Evaluation of TP53/PIK3CA mutations using texture and morphology analysis on breast MRI. Magn Reson Imaging 2019;63:60-69.
[63]	Tan Y, Liu R, Xue J-W, Feng Z. Construction and validation of artificial intelligence pathomics models for predicting pathological staging in colorectal cancer: Using multimodal data and clinical variables. Cancer Med 2024;13:e6947.
[64]	Zhang Y-F, Zhou C, Guo S, Wang C, Yang J, Yang Z-J, et al. Deep learning algorithm-based multimodal MRI radiomics and pathomics data improve prediction of bone metastases in primary prostate cancer. J Cancer Res Clin Oncol 2024;150:78.
[65]	Boehm KM, Aherne EA, Ellenson L, Nikolovski I, Alghamdi M, Vázquez-García I, et al. Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer. Nat Cancer 2022;3:723-733.
[66]	Zhou C, Zhang Y-F, Guo S, Huang Y-Q, Qiao X-N, Wang R, et al. Multimodal data integration for predicting progression risk in castration-resistant prostate cancer using deep learning: a multicenter retrospective study. Front Oncol 2024;14:1287995.
[67]	Liu L, Yi X, Lu C, Pang Y, Zu X, Chen M, et al. Background, applications and challenges of radiogenomics in genitourinary tumor. Am J Cancer Res 2021;11:1936-1945.
[68]	Pinker K, Shitano F, Sala E, Do RK, Young RJ, Wibmer AG, et al. Background, current role, and potential applications of radiogenomics. J Magn Reson Imaging 2018;47:604-620.
[69]	Xu X, Zhang M, Xu F, Jiang S. Wnt signaling in breast cancer: biological mechanisms, challenges and opportunities. Mol Cancer 2020;19:165.
[70]	Soysal SD, Tzankov A, Muenst SE. Role of the tumor microenvironment in breast cancer. Pathobiology 2015;82:142-152.

DL methods	Breast cancer related	Radiogenomics related	US related
AI	Mammogram	Therapy response	Sonography
CNN	Triple-negative	Treatment response	Doppler
Transformer	MRI	Molecular signatures	Transducer
		Imaging genomics	Ultrasonic

References	Subtype	US features
Zhang et al. [44]	Luminal-A	Presence of echogenic halo and post-acoustic shadowing
	Luminal-B	Absence of an echogenic halo and the presence of vascularity
	HER2-amplified	Post-acoustic enhancement, calcification, vascularity, and advanced age
	Triple-negative	(1) Irregular shape, lobulate margin, absence of calcification
		(2) Oval shape, hypovascularity, and micro-lobulate margin
Wu et al. [45]	Luminal-A	low histologic grade, spiculated margins, an echogenic rim and posterior acoustic attenuation
	Luminal-B	Indistinct margin and relative vascularity
	HER2-amplified	Spiculated margins, enhanced posterior acoustics, calcifications, and vascularity
	Triple-negative	High tumor grade, circumscribed and microlobulated margins, and the absence of an echogenic rim and calcifications; to be markedly hypoechoic; and to have posterior acoustic enhancement and hypovascularity
Xu et al. [48]	ER+ and PR+	The ratio of the longest/ shortest dimension (>1), spiculate margin and halo
Rashmi et al. [46]	Luminal-A	Non-circumscribed margins and posterior acoustic shadowing
	Luminal-B	Non-circumscribed margins, posterior acoustic shadowing, and high vascularity
	HER2-amplified	Microcalcification and posterior mixed acoustic pattern
	Triple-negative	Circumscribed margins and posterior acoustic enhancement
Liu et al. [49]	HER2+	Tumor blood supply and microcalcification
Sturesdotter et al. [50]	ER+ and PR+	Spiculated tumours and lower histological grade
	Luminal-A	Spiculated tumours
Wang et al. [51]	Triple-negative	Microlobulated, markedly hypo-echoic masses with an abrupt interface boundary, posterior acoustic enhancement, absence of calcifications and more characteristics of surrounding tissue

References	Method	Subtype	US features
Zhou et al. [43]	LR	ER+ vs ER−	Shape, orientation, margins
	LR	PR+ vs PR−	Boundary, echo pattern
	LR	HER2+ vs HER2−	Calcification, and posterior acoustic features
Huang et al. [56]	LR	TP53 and PIK3CA mutations	Mass-like, calcification, shape (regular or irregular)
Quan et al. [57]	ML	HER2+ vs HER2−	Extracted static and dynamic radiomics feature from video
Liang et al. [58]	ML	Luminal, HER2-amplified and Triple-negative	Shape, sphericity, texture, calcifications
Yan et al. [59]	ML	HER2+ vs HER2−	19 US radiomics features