Breast Cancer Detection using Machine Learning Approaches on Microwave-based Data

被引：10

作者：

Papini, Lorenzo ^{[1
]}

Badia, Mario ^{[1
]}

Sani, Lorenzo ^{[1
]}

Rana, Soumya Prakash ^{[1
,2
]}

Sanchez-Bayuela, Daniel Alvarez ^{[3
,4
]}

Vispa, Alessandro ^{[1
]}

Bigotti, Alessandra ^{[1
]}

Raspa, Giovanni ^{[1
]}

Ghavami, Navid ^{[1
]}

Castellano, Cristina Romero ^{[3
]}

Bernardi, Daniela ^{[5
]}

Tagliafico, Alberto ^{[6
,7
]}

Calabrese, Massimo ^{[7
]}

Ghavami, Mohammad ^{[2
]}

Tiberi, Gianluigi ^{[1
,2
]}

机构：

[1] UBT Umbria Bioengn Technol, Perugia, Italy

[2] London South Bank Univ, Sch Engn, London, England

[3] Univ Hosp Toledo, Serv Salud Castilla La Mancha, Toledo, Spain

[4] Univ Castilla La Mancha, Toledo, Spain

[5] Humanitas Res Hosp, Milan, Italy

[6] Univ Genoa, Genoa, Italy

[7] IRCCS Osped Policlin San Martino, Genoa, Italy

来源：

2023 17TH EUROPEAN CONFERENCE ON ANTENNAS AND PROPAGATION, EUCAP | 2023年

关键词：

Microwave breast imaging; Ultra wideband (UWB) imaging; Machine learning;

D O I：

10.23919/EuCAP57121.2023.10133340

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Microwave breast imaging is being investigated by research groups worldwide for its promising applications in early cancer detection, overcoming key limitations of conventional imaging systems. In this framework, artificial intelligence may play an important role to enhance the performances of new systems, based on this novel technology, for breast cancer detection. Research is being carried out to demonstrate the potential of implementing machine learning tools that have already been investigated for conventional mammography and MRI. This work presents the retrospective implementation of several supervised machine learning approaches on the microwave data obtained by MammoWave device in the framework of a clinical trial. Two different approaches are explored and explained in detail: the application of artificial intelligence directly on the MammoWave raw data and on dedicated features extracted from microwave images. Both approaches lead to promising results with high (>80%) and quite balanced specificity and sensitivity.

引用

页数：5

共 14 条

[1]

[Anonymous], US

[2] SMOTE: Synthetic minority over-sampling technique [J].