Advancements in Research on the Classification of Benign and Malignant Breast Tumors Utilizing Ultrasound Radiomics and Deep Learning

Qinyu Xiao; Qiuhui Hu; Yiwei Wang

doi:10.54097/gp6mcj41

Authors

Qinyu Xiao
Qiuhui Hu
Yiwei Wang

DOI:

https://doi.org/10.54097/gp6mcj41

Keywords:

Breast Ultrasound Imaging, Conventional Machine Learning, Deep Learning, Multimodal Diagnosis

Abstract

This paper examines the applications of traditional machine learning and deep learning in the analysis of breast ultrasound images for tumor diagnosis and explores recent developments in multimodal imaging. Traditional machine learning efficiently classifies breast ultrasound images through preprocessing, feature extraction, and selection, utilizing classifiers such as support vector machines. However, the design of features is highly dependent and its application scope is limited. Deep learning methods, particularly convolutional neural networks, autonomously extract sophisticated features, demonstrating enhanced classification performance and generalization capabilities. For instance, they achieve diagnostic accuracies exceeding 90% in large-scale datasets, with some studies outperforming clinicians. Moreover, this study highlights that the multimodal analysis strategy, integrating breast ultrasound with shear wave elastography, compensates for the limitations of unimodal images and enhances diagnostic accuracy and reliability, signifying a significant advancement in the technology for early breast cancer diagnosis.

Downloads

Download data is not yet available.

References

[1] COUGHLIN S S. Epidemiology of Breast Cancer in Women [J]. Advances in experimental medicine and biology, 2019, 1152: 9-29.

[2] BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA: a cancer journal for clinicians, 2018, 68(6): 394-424.

[3] ZHANG Y N, XIA K R, LI C Y, et al. Review of Breast Cancer Pathologigcal Image Processing [J]. BioMed research international, 2021, 2021: 1994764.

[4] HARBECK N, GNANT M. Breast cancer [J]. Lancet (London, England), 2017, 389(10074): 1134-50.

[5] BARZAMAN K, KARAMI J, ZAREI Z, et al. Breast cancer: Biology, biomarkers, and treatments [J]. International immunopharmacology, 2020, 84: 106535.

[6] CHAPMAN C, MURRAY A, CHAKRABARTI J, et al. Autoantibodies in breast cancer: their use as an aid to early diagnosis [J]. Annals of oncology: official journal of the European Society for Medical Oncology, 2007, 18(5): 868-73.

[7] FAN L, STRASSER-WEIPPL K, LI J J, et al. Breast cancer in China [J]. The Lancet Oncology, 2014, 15(7): e279-89.

[8] OREL S G, SCHNALL M D. MR imaging of the breast for the detection, diagnosis, and staging of breast cancer [J]. Radiology, 2001, 220(1): 13-30.

[9] YU Y, HE Z, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: A machine learning, multicenter study [J]. EBioMedicine, 2021, 69: 103460.

[10] COSTANTINI M, BELLI P, IERARDI C, et al. Solid breast mass characterisation: use of the sonographic BI-RADS classification [J]. La Radiologia medica, 2007, 112(6): 877-94.

[11] DORLING L, CARVALHO S, ALLEN J, et al. Breast Cancer Risk Genes - Association Analysis in More than 113,000 Women [J]. The New England journal of medicine, 2021, 384(5): 428-39.

[12] CONTI A, DUGGENTO A, INDOVINA I, et al. Radiomics in breast cancer classification and prediction [J]. Seminars in cancer biology, 2021, 72: 238-50.

[13] HECK L, HERZEN J. Recent advances in X-ray imaging of breast tissue: From two- to three-dimensional imaging [J]. Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB), 2020, 79: 69-79.

[14] BIRD R E, WALLACE T W, YANKASKAS B C. Analysis of cancers missed at screening mammography [J]. Radiology, 1992, 184(3): 613-7.

[15] DI MARIA S, VEDANTHAM S, VAZ P. X-ray dosimetry in breast cancer screening: 2D and 3D mammography [J]. European journal of radiology, 2022, 151: 110278.

[16] YU Y, TAN Y, XIE C, et al. Development and Validation of a Preoperative Magnetic Resonance Imaging Radiomics-Based Signature to Predict Axillary Lymph Node Metastasis and Disease-Free Survival in Patients With Early-Stage Breast Cancer [J]. JAMA network open, 2020, 3(12): e2028086.

[17] ALONSO ROCA S, DELGADO LAGUNA A B, ARANTZETA LEXARRETA J, et al. Screening in patients with increased risk of breast cancer (part 1): pros and cons of MRI screening [J]. Radiologia, 2020, 62(4): 252-65.

[18] SOOD R, ROSITCH A F, SHAKOOR D, et al. Ultrasound for Breast Cancer Detection Globally: A Systematic Review and Meta-Analysis [J]. Journal of global oncology, 2019, 5: 1-17.

[19] BITENCOURT A, DAIMIEL NARANJO I, LO GULLO R, et al. AI-enhanced breast imaging: Where are we and where are we heading? [J]. European journal of radiology, 2021, 142: 109882.

[20] KRATKIEWICZ K, PATTYN A, ALIJABBARI N, et al. Ultrasound and Photoacoustic Imaging of Breast Cancer: Clinical Systems, Challenges, and Future Outlook [J]. Journal of clinical medicine, 2022, 11(5).

[21] LE E P V, WANG Y, HUANG Y, et al. Artificial intelligence in breast imaging [J]. Clinical radiology, 2019, 74(5): 357-66.

[22] LANE N, LAHHAM S, JOSEPH L, et al. Ultrasound in medical education: listening to the echoes of the past to shape a vision for the future [J]. European journal of trauma and emergency surgery : official publication of the European Trauma Society, 2015, 41(5): 461-7.

[23] RAHMAN W T, HELVIE M A. Breast cancer screening in average and high-risk women [J]. Best practice & research Clinical obstetrics & gynaecology, 2022, 83: 3-14.

[24] XUE S, ZHAO Q, TAI M, et al. Correlation between Breast Ultrasound Microcalcification and the Prognosis of Breast Cancer [J]. Journal of healthcare engineering, 2021, 2021: 6835963.

[25] YAO Z, LUO T, DONG Y, et al. Virtual elastography ultrasound via generative adversarial network for breast cancer diagnosis [J]. Nature communications, 2023, 14(1): 788.

[26] YOON W B, OH J E, CHAE E Y, et al. Automatic Detection of Pectoral Muscle Region for Computer-Aided Diagnosis Using MIAS Mammograms [J]. BioMed research international, 2016, 2016: 5967580.

[27] CAHAN A, CIMINO J J. A Learning Health Care System Using Computer-Aided Diagnosis [J]. Journal of medical Internet research, 2017, 19(3): e54.

[28] SHIN H C, ROTH H R, GAO M, et al. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning [J]. IEEE transactions on medical imaging, 2016, 35(5): 1285-98.

[29] HUANG S, CAI N, PACHECO P P, et al. Applications of Support Vector Machine (SVM) Learning in Cancer Genomics [J]. Cancer genomics & proteomics, 2018, 15(1): 41-51.

[30] ABDEL-NASSER M, MELENDEZ J, MORENO A, et al. Breast tumor classification in ultrasound images using texture analysis and super-resolution methods [J]. Engineering Applications of Artificial Intelligence, 2017, 59: 84-92.

[31] LIU Y, REN L, CAO X, et al. Breast tumors recognition based on edge feature extraction using support vector machine [J]. Biomedical Signal Processing and Control, 2020, 58.

[32] KRITI, VIRMANI J, AGARWAL R. Effect of despeckle filtering on classification of breast tumors using ultrasound images [J]. Biocybernetics and Biomedical Engineering, 2019, 39(2): 536-60.

[33] LIU X, LIU J, XU X, et al. A robust detail preserving anisotropic diffusion for speckle reduction in ultrasound images [J]. BMC genomics, 2011, 12 Suppl 5(Suppl 5): S14.

[34] XU H H, GONG Y C, XIA X Y, et al. Gabor-based anisotropic diffusion with lattice Boltzmann method for medical ultrasound despeckling [J]. Mathematical biosciences and engineering : MBE, 2019, 16(6): 7546-61.

[35] ZHANG Q, HAN H, JI C, et al. Gabor-based anisotropic diffusion for speckle noise reduction in medical ultrasonography [J]. Journal of the Optical Society of America A, Optics, image science, and vision, 2014, 31(6): 1273-83.

[36] LEY C, MARTIN R K, PAREEK A, et al. Machine learning and conventional statistics: making sense of the differences [J]. Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA, 2022, 30(3): 753-7.

[37] JIANG T, GRADUS J L, ROSELLINI A J. Supervised Machine Learning: A Brief Primer [J]. Behavior therapy, 2020, 51(5): 675-87.

[38] CARNAHAN B, MEYER G, KUNTZ L A. Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research [J]. Human factors, 2003, 45(3): 408-23.

[39] DIN N M U, DAR R A, RASOOL M, et al. Breast cancer detection using deep learning: Datasets, methods, and challenges ahead [J]. Computers in biology and medicine, 2022, 149: 106073.

[40] KALAFI E Y, NOR N A M, TAIB N A, et al. Machine Learning and Deep Learning Approaches in Breast Cancer Survival Prediction Using Clinical Data [J]. Folia biologica, 2019, 65(5-6): 212-20.

[41] BALKENENDE L, TEUWEN J, MANN R M. Application of Deep Learning in Breast Cancer Imaging [J]. Seminars in nuclear medicine, 2022, 52(5): 584-96.

[42] ANTROPOVA N, HUYNH B Q, GIGER M L. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets [J]. Medical physics, 2017, 44(10): 5162-71.

[43] HAN S, KANG H K, JEONG J Y, et al. A deep learning framework for supporting the classification of breast lesions in ultrasound images [J]. Physics in medicine and biology, 2017, 62(19): 7714-28.

[44] FUJIOKA T, KATSUTA L, KUBOTA K, et al. Classification of Breast Masses on Ultrasound Shear Wave Elastography using Convolutional Neural Networks [J]. Ultrasonic imaging, 2020, 42(4-5): 213-20.

[45] ITOH A, UENO E, TOHNO E, et al. Breast disease: clinical application of US elastography for diagnosis [J]. Radiology, 2006, 239(2): 341-50.

[46] ZHOU B Y, WANG L F, YIN H H, et al. Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study [J]. EBioMedicine, 2021, 74: 103684.

[47] LI J, SUN B, LI Y, et al. Correlation analysis between shear-wave elastography and pathological profiles in breast cancer [J]. Breast cancer research and treatment, 2023, 197(2): 269-76.

[48] SONG E J, SOHN Y M, SEO M. Tumor stiffness measured by quantitative and qualitative shear wave elastography of breast cancer [J]. The British journal of radiology, 2018, 91(1086): 20170830.

[49] JIANG M, LI C L, LUO X M, et al. Radiomics model based on shear-wave elastography in the assessment of axillary lymph node status in early-stage breast cancer [J]. European radiology, 2022, 32(4): 2313-25.

[50] HUANG J X, LIN S Y, OU Y, et al. Combining conventional ultrasound and sonoelastography to predict axillary status after neoadjuvant chemotherapy for breast cancer [J]. European radiology, 2022, 32(9): 5986-96.

[51] FORTE A J, HUAYLLANI M T, BOCZAR D, et al. The basics of ultrasound elastography for diagnosis, assessment, and staging breast cancer-related lymphedema: a systematic review of the literature [J]. Gland surgery, 2020, 9(2): 589-95.

[52] QIAN X, PEI J, ZHENG H, et al. Prospective assessment of breast cancer risk from multimodal multiview ultrasound images via clinically applicable deep learning [J]. Nature biomedical engineering, 2021, 5(6): 522-32.