Özet
Microwave Imaging has emerged as a promising technique that can contribute to the breast lesion detection and classification. Using harmless electromagnetic waves, MWI is providing relevant diagnostic information without resorting to X-rays. Due to its harmless nature, frequent scanning is accessible for women of all age. In this chapter, we discuss about the clinical implementation of our novel MWI device, namely SAFE, which utilizes the variance in the electromagnetic properties of healthy and cancer affected breast tissue in order to provide information regarding women breast tissue health. As the device is not requiring physical compression, it can also detect the lesions that are near to the thoracic wall. SAFE detection and localization outcomes were evaluated based on the clinical reports provided by radiologists. A clinical study was conducted on 59 patients, including 32 with benign and 27 with malignant pathology outcomes. By using machine learning (ML) model, more specifically Stochastic Gradient Descent (SGD), SAFE correctly detected 81% of the lesions present in the breasts tissue, from which 83% of them were localized correctly. Results indicate that SAFE is capable of detecting and localizing high percentage of lesions present in the dataset, regardless of breast density, lesion size or participants age. In this chapter, we elaborate on our approach and achieved results and discuss SAFE ongoing and intended future work.
Orijinal dil | İngilizce |
---|---|
Ana bilgisayar yayını başlığı | Lecture Notes in Bioengineering |
Yayınlayan | Springer Science and Business Media Deutschland GmbH |
Sayfalar | 273-292 |
Sayfa sayısı | 20 |
DOI'lar | |
Yayın durumu | Yayınlandı - 2023 |
Yayın serisi
Adı | Lecture Notes in Bioengineering |
---|---|
Hacim | Part F809 |
ISSN (Basılı) | 2195-271X |
ISSN (Elektronik) | 2195-2728 |
Bibliyografik not
Publisher Copyright:© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Finansman
Acknowledgements This work was supported by the EMERALD project funded from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 764479, and by the Scientific and Technology Research Council of Turkey (TUBITAK) grant number 120N388.
Finansörler | Finansör numarası |
---|---|
Horizon 2020 Framework Programme | |
H2020 Marie Skłodowska-Curie Actions | 764479 |
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu | 120N388 |