Applications of machine-learning algorithms for prediction of benign and malignant breast lesions using ultrasound radiomics signatures: A multi-center study

• Autorzy: Homayoun Hassan , Chan Wai Yee , Kuzan Taha Yusuf , Leong Wai Ling , Altintoprak Kübra Murzoglu , Mohammadi Afshin , Vijayananthan Anushya , Rahmat Kartini , Leong Sook Sam , Mirza-Aghazadeh-Attari Mohammad , Ejtehadifar Sajjad , Faeghi Fariborz , Acharya U. Rajendra , Ardakani Ali Abbasian

Identyfikatory

DOI

10.1016/j.bbe.2022.07.004

• Języki publikacji: EN

Abstrakty

EN

Artificial intelligence (AI) algorithms have an enormous potential to impact the field of radiology and diagnostic imaging, especially the field of cancer imaging. There have been efforts to use AI models to differentiate between benign and malignant breast lesions. However, most studies have been single-center studies without external validation. The present study examines the diagnostic efficacy of machine-learning algorithms in differentiating benign and malignant breast lesions using ultrasound images. Ultrasound images of 1259 solid non-cystic lesions from 3 different centers in 3 countries (Malaysia, Turkey, and Iran) were used for the machine-learning study. A total of 242 radiomics features were extracted from each breast lesion, and the robust features were considered for models’ development. Three machine-learning algorithms were used to carry out the classification task, namely, gradient boosting (XGBoost), random forest, and support vector machine. Sensitivity, specificity, accuracy, and area under the ROC curve (AUC) were determined to evaluate the models. Thirty-three robust features differed significantly between the two groups from all of the features. XGBoost, based on these robust features, showed the most favorable profile for all cohorts, as it achieved a sensitivity of 90.3%, specificity of 86.7%, the accuracy of 88.4%, and AUC of 0.890. The present study results show that incorporating selected robust radiomics features into well-curated machine-learning algorithms can generate high sensitivity, specificity, and accuracy in differentiating benign and malignant breast lesions. Furthermore, our results show that this optimal performance is preserved even in external validation datasets.

Słowa kluczowe

EN

artificial intelligence; breast cancer; computer assisted diagnosis; machine learning; radiomics

PL

sztuczna inteligencja; rak piersi; diagnoza wspomagana komputerowo; uczenie maszynowe; radiomika

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 3
• Strony: 921--933
• Opis fizyczny: Bibliogr. 47 poz., rys., tab., wykr.

Twórcy

autor

Homayoun Hassan

• Urology Research Center, Tehran University of Medical Sciences, Tehran, Iran

autor

Chan Wai Yee

• Gleneagles Hospital Kuala Lumpur, Department of Radiology, Jln Ampang, Kampung Berembang, Kuala Lumpur, Malaysia

autor

Kuzan Taha Yusuf

• Department of Radiology, Sancaktepe Sehit Prof. Dr. Ilhan Varank Training and Research Hospital, Istanbul, Turkey

autor

Leong Wai Ling

• Department of Biomedical Imaging, Universiti Malaya Research Imaging Centre, Faculty of Medicine, Universiti Malaya, Malaysia

autor

Altintoprak Kübra Murzoglu

• Department of Radiology, Sancaktepe Sehit Prof. Dr. Ilhan Varank Training and Research Hospital, Istanbul, Turkey

autor

Mohammadi Afshin

• Department of Radiology, Faculty of Medicine, Urmia University of Medical Science, Urmia, Iran

autor

Vijayananthan Anushya

• Department of Biomedical Imaging, Universiti Malaya Research Imaging Centre, Faculty of Medicine, Universiti Malaya, Malaysia

autor

Rahmat Kartini

• Department of Biomedical Imaging, Universiti Malaya Research Imaging Centre, Faculty of Medicine, Universiti Malaya, Malaysia

autor

Leong Sook Sam

• Centre of Medical Imaging, Faculty of Health Sciences, Universiti Teknologi MARA Selangor, Bandar Puncak Alam, Selangor, Malaysia

autor

Mirza-Aghazadeh-Attari Mohammad

• Medical Radiation Sciences Research Group, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran

autor

Ejtehadifar Sajjad

• Department of Radiology, Faculty of Medicine, Urmia University of Medical Science, Urmia, Iran

autor

Faeghi Fariborz

• Department of Radiology Technology, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran

autor

Acharya U. Rajendra

• Ngee Ann Polytechnic, Department of Electronics and Computer Engineering, Singapore
• Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore
• Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan

autor

Ardakani Ali Abbasian

• Department of Radiology Technology, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran

Bibliografia

• [1] Enzmann DR. Radiology’s value chain. Radiology 2012;263(1):243–52.
• [2] Martin-Carreras T, Chen P-H. From data to value: how artificial intelligence augments the radiology business to create value. Semin Musculosk Radiol 2020;24:65–73.
• [3] Dontchos BN, Yala A, Barzilay R, Xiang J, Lehman CD. External validation of a deep learning model for predicting mammographic breast density in routine clinical practice. Acad Radiol 2021;28:475–80.
• [4] Chiwome L, Okojie OM, Rahman A, Javed F, Hamid P. Artificial intelligence: is it Armageddon for breast radiologists? Cureus 2020;12:e8923.
• [5] Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer 2018;18:500–10.
• [6] Le EPV, Wang Y, Huang Y, Hickman S, Gilbert FJ. Artificial intelligence in breast imaging. Clin Radiol 2019;74:357–66.
• [7] Hickman SE, Baxter GC, Gilbert FJ. Adoption of artificial intelligence in breast imaging: evaluation, ethical constraints and limitations. Br J Cancer 2021;125:15–22.
• [8] Paravastu SS, Theng EH, Morris MA, Grayson P, Collins MT, Maass-Moreno R, et al. Artificial intelligence in vascular-PET: translational and clinical applications. PET Clin 2022;17:95–113.
• [9] Piri R, Edenbrandt L, Larsson M, Enqvist O, Skovrup S, Iversen KK, et al. ‘‘Global” cardiac atherosclerotic burden assessed by artificial intelligence-based versus manual segmentation in 18F-sodium fluoride PET/CT scans: Head-to-head comparison. J Nucl Cardiol. 2021:1-9.
• [10] Hansen JA, Naghavi-Behzad M, Gerke O, Baun C, Falch K, Duvnjak S, et al. Diagnosis of bone metastases in breast cancer: Lesion-based sensitivity of dual-time-point FDG-PET/CT compared to low-dose CTand bone scintigraphy. PloS One 2021;16:e0260066.
• [11] Wallis M, Tarvidon A, Helbich T, Schreer I. Guidelines from the European Society of Breast Imaging for diagnostic interventional breast procedures. Eur Radiol 2007;17:581–8.
• [12] Black E, Richmond R. Improving early detection of breast cancer in sub-Saharan Africa: why mammography may not be the way forward. Global Health 2019;15:3.
• [13] Hill DA, Haas JS, Wellman R, Hubbard RA, Lee CI, Alford-Teaster J, et al. Utilization of breast cancer screening with magnetic resonance imaging in community practice. J Gen Intern Med 2018;33:275–83.
• [14] Feig S. Cost-effectiveness of mammography, MRI, and ultrasonography for breast cancer screening. Radiol Clin North Am 2010;48:879–91.
• [15] Rebolj M, Assi V, Brentnall A, Parmar D, Duffy SW. Addition of ultrasound to mammography in the case of dense breast tissue: systematic review and meta-analysis. Br J Cancer 2018;118:1559–70.
• [16] Sood R, Rositch AF, Ambinder E, Pool K-L, Shakoor D, Pollack E, et al. Ultrasound for breast cancer detection in low-resource settings: systematic review and meta-analysis. Am Soc Clin Oncol 2018.
• [17] Hooley RJ, Scoutt LM, Philpotts LE. Breast ultrasonography: state of the art. Radiology 2013;268:642–59.
• [18] Pan H-B. The role of breast ultrasound in early cancer detection. J Med Ultrasound 2016;24:138–41.
• [19] Shen Y, Shamout FE, Oliver JR, Witowski J, Kannan K, Park J, et al. Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams. Nat Commun 2021;12:1–13.
• [20] Sechopoulos I, Mann RM. Stand-alone artificial intelligence - The future of breast cancer screening? Breast (Edinburgh, Scotland) 2020;49:254–60.
• [21] Avanzo M, Wei L, Stancanello J, Vallières M, Rao A, Morin O, et al. Machine and deep learning methods for radiomics. Med Phys 2020;47:e185–202.
• [22] Harding-Theobald E, Louissaint J, Maraj B, Cuaresma E, Townsend W, Mendiratta-Lala M, et al. Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma. Aliment Pharmacol Ther 2021;54:890–901.
• [23] Zou KH, Warfield SK, Bharatha A, Tempany CMC, Kaus MR, Haker SJ, et al. Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2004;11:178–89.
• [24] Abbasian Ardakani A, Bureau NJ, Ciaccio EJ, Acharya UR. Interpretation of radiomics features: a pictorial review. Comput Methods Programs Biomed 2022;215:106609.
• [25] Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures. They are data. Radiology 2016;278:563–77.
• [26] Singh D, Singh B. Investigating the impact of data normalization on classification performance. Appl Soft Comput 2020;97:105524.
• [27] Noble WS. What is a support vector machine? Nat Biotechnol 2006;24:1565–7.
• [28] Meyer D, Leisch F, Hornik K. The support vector machine under test. Neurocomputing 2003;55:169–86.
• [29] Pal M. Random forest classifier for remote sensing classification. Int J Remote Sens 2005;26:217–22.
• [30] Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front Neurorob 2013;7:21.
• [31] Arefan D, Hausler RM, Sumkin JH, Sun M, Wu S. Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes. BMC Cancer 2021;21:370.
• [32] Jiang M, Li C-L, Chen R-X, Tang S-C, Lv W-Z, Luo X-M, et al. Management of breast lesions seen on US images: dual-model radiomics including shear-wave elastography may match performance of expert radiologists. Eur J Radiol 2021;141:109781.
• [33] Mao N, Yin P, Zhang H, Zhang K, Song X, Xing D, et al. Mammography-based radiomics for predicting the risk of breast cancer recurrence: a multicenter study. Br J Radiol 2021;94:20210348.
• [34] Romeo V, Cuocolo R, Apolito R, Stanzione A, Ventimiglia A, Vitale A, et al. Clinical value of radiomics and machine learning in breast ultrasound: a multicenter study for differential diagnosis of benign and malignant lesions. Eur Radiol 2021;31:9511–9.
• [35] Huo L, Tan Y, Wang S, Geng C, Li Y, Ma X, et al. Machine learning models to improve the differentiation between benign and malignant breast lesions on ultrasound: A multicenter external validation study. Cancer Manage Res 2021;13:3367–79.
• [36] Zhang X, Li H, Wang C, Cheng W, Zhu Y, Li D, et al. Evaluating the accuracy of breast cancer and molecular subtype diagnosis by ultrasound image deep learning model. Front Oncol 2021;11:623506.
• [37] Cheng PM, Montagnon E, Yamashita R, Pan I, Cadrin-Chênevert A, Perdigón Romero F, et al. Deep learning: an update for radiologists. Radiographics 2021;41:1427–45.
• [38] Kim C, Kim WH, Kim HJ, Kim J. A multi-scale capsule network for improving diagnostic generalizability in breast cancer diagnosis using ultrasonography. In: International Workshop on PRedictive Intelligence in MEdicine. Springer; 2021. p. 181–91.
• [39] Kim J, Kim HJ, Kim C, Lee JH, Kim KW, Park YM, et al. Deep learning-based breast cancer diagnosis at ultrasound: initial application of weakly-supervised algorithm without image annotation original research. 2021.
• [40] Moore JX, Han Y, Appleton C, Colditz G, Toriola AT. Determinants of mammographic breast density by race among a large screening population. JNCI Cancer Spectrum 2020;4:pkaa010.
• [41] Galukande M, Kiguli-Malwadde E. Mammographic breast density patterns among a group of women in sub Saharan Africa. Afr Health Sci 2012;12:422–5.
• [42] Ellison-Loschmann L, McKenzie F, Highnam R, Cave A, Walker J, Jeffreys M, et al. Age and ethnic differences in volumetric breast density in New Zealand women: a cross-sectional study. PloS One 2013;8:e70217.
• [43] El-Bastawissi AY, White E, Mandelson MT, Taplin S. Variation in mammographic breast density by race. Ann Epidemiol 2001;11:257–63.
• [44] van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. Radiomics in medical imaging-‘‘how-to” guide and critical reflection. Insights Imag 2020;11:91.
• [45] Ramspek CL, Jager KJ, Dekker FW, Zoccali C, van Diepen M. External validation of prognostic models: what, why, how, when and where? Clin Kidney J 2021;14:49–58.
• [46] Snell KIE, Archer L, Ensor J, Bonnett LJ, Debray TPA, Phillips B, et al. External validation of clinical prediction models: simulation-based sample size calculations were more reliable than rules-of-thumb. J Clin Epidemiol 2021;135:79–89.
• [47] 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;14:749–62.