Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection
An improved machine learning approach is presented in this paper to guarantee the fast convergence of the Born Iterative Method, even in the presence of strong scatterers, by assuming a single operating frequency and a reduced number of antennas in the scattering setup. The initial estimation of the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/15/2308 |
| _version_ | 1797432904192622592 |
|---|---|
| author | Sandra Costanzo Alexandra Flores |
| author_facet | Sandra Costanzo Alexandra Flores |
| author_sort | Sandra Costanzo |
| collection | DOAJ |
| description | An improved machine learning approach is presented in this paper to guarantee the fast convergence of the Born Iterative Method, even in the presence of strong scatterers, by assuming a single operating frequency and a reduced number of antennas in the scattering setup. The initial estimation of the dielectric profile, provided by the Born Iterative Method, was processed by a specific convolutional neural network to improve the reconstruction using a fast machine learning approach. To ensure rapid convergence, a proper choice of the initial guess in terms of the minimum permittivity value over the entire domain was also made. Numerical validations on realistic breast phantoms were illustrated, demonstrating an average error of 2.4% and an accuracy greater than 96% for all considered tests, even when considering a single operating frequency and a reduced amount of training data. |
| first_indexed | 2024-03-09T10:09:21Z |
| format | Article |
| id | doaj.art-4c5e5703a7d44eb1b1429ab93b9d267e |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T10:09:21Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-4c5e5703a7d44eb1b1429ab93b9d267e2023-12-01T22:53:32ZengMDPI AGElectronics2079-92922022-07-011115230810.3390/electronics11152308Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer DetectionSandra Costanzo0Alexandra Flores1Dipartimento di Ingegneria Informatica, Modellistica, Elettronica e Sistemistica, Università della Calabria, 87036 Rende, ItalyDipartimento di Ingegneria Informatica, Modellistica, Elettronica e Sistemistica, Università della Calabria, 87036 Rende, ItalyAn improved machine learning approach is presented in this paper to guarantee the fast convergence of the Born Iterative Method, even in the presence of strong scatterers, by assuming a single operating frequency and a reduced number of antennas in the scattering setup. The initial estimation of the dielectric profile, provided by the Born Iterative Method, was processed by a specific convolutional neural network to improve the reconstruction using a fast machine learning approach. To ensure rapid convergence, a proper choice of the initial guess in terms of the minimum permittivity value over the entire domain was also made. Numerical validations on realistic breast phantoms were illustrated, demonstrating an average error of 2.4% and an accuracy greater than 96% for all considered tests, even when considering a single operating frequency and a reduced amount of training data.https://www.mdpi.com/2079-9292/11/15/2308microwave imaginginverse scatteringBorn Iterative Methodconvolutional neural networkbreast cancer |
| spellingShingle | Sandra Costanzo Alexandra Flores Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection Electronics microwave imaging inverse scattering Born Iterative Method convolutional neural network breast cancer |
| title | Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection |
| title_full | Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection |
| title_fullStr | Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection |
| title_full_unstemmed | Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection |
| title_short | Enhanced Machine Learning Approach for Accurate and Fast Resolution of Inverse Scattering Problem in Breast Cancer Detection |
| title_sort | enhanced machine learning approach for accurate and fast resolution of inverse scattering problem in breast cancer detection |
| topic | microwave imaging inverse scattering Born Iterative Method convolutional neural network breast cancer |
| url | https://www.mdpi.com/2079-9292/11/15/2308 |
| work_keys_str_mv | AT sandracostanzo enhancedmachinelearningapproachforaccurateandfastresolutionofinversescatteringprobleminbreastcancerdetection AT alexandraflores enhancedmachinelearningapproachforaccurateandfastresolutionofinversescatteringprobleminbreastcancerdetection |