In microwave breast cancer detection, it is often beneficial to arrange sensors in close proximity to the breast. The resultant coupling generally changes the antenna response. As an a priori characterization of the radio frequency system becomes difficult, this can lead to severe degradation of the detection efficacy. The purpose of this paper is to demonstrate the advantages of ... [Show full abstract] adopting an interferometric multiple signal classification (I-MUSIC) approach due to its limited dependence from a priori information on the antenna. The performance of I-MUSIC detection was measured in terms of signal-to-clutter ratio (SCR), signal-to-mean ratio (SMR), and spatial displacement (SD) and compared to other common linear noncoherent imaging methods, such as migration and the standard wideband MUSIC (WB-MUSIC) which also works when the antenna is not accounted for.
The data were acquired by scanning a synthetic oil-in-gelatin phantom that mimics the dielectric properties of breast tissues across the spectrum 1-3 GHz using a proprietary breast microwave multi-monostatic radar system. The phantom is a multilayer structure that includes skin, adipose, fibroconnective, fibroglandular, and tumor tissue with an adipose component accounting for 60% of the whole structure. The detected tumor has a diameter of 5 mm and is inserted inside a fibroglandular region with a permittivity contrast εr-tumor/εr-fibroglandular < 1.5 over the operating band. Three datasets were recorded corresponding to three antennas with different coupling mechanisms. This was done to assess the independence of the I-MUSIC method from antenna characterizations. The datasets were processed by using I-MUSIC, noncoherent migration, and wideband MUSIC under equivalent conditions (i.e., operative bandwidth, frequency samples, and scanning positions). SCR, SMR, and SD figures were measured from all reconstructed images. In order to benchmark experimental results, numerical simulations of equivalent scenarios were carried out by using CST Microwave Studio. The three numerical datasets were then processed following the same procedure that was designed for the experimental case.
Detection results are presented for both experimental and numerical phantoms, and higher performance of the I-MUSIC method in comparison with the WB-MUSIC and noncoherent migration is achieved. This finding is confirmed for the three different antennas in this study. Although a delocalization effect occurs, experimental datasets show that the signal-to-clutter ratio and the signal-to-mean performance with the I-MUSIC are at least 5 and 2.3 times better than the other methods, respectively. The numerical datasets calculated on an equivalent phantom for cross-testing confirm the improved performance of the I-MUSIC in terms of SCR and SMR. In numerical simulations, the delocalization effect is dramatically reduced up to an SD value of 1.61 achieved with the I-MUSIC in combination with the antipodal Vivaldi antenna. This shows that mechanical uncertainties are the main reason for the delocalization effect in the measurements.
Experimental results show that the I-MUSIC generates images with signal-to-clutter levels higher than 5.46 dB across all working conditions and it reaches 7.84 dB in combination with the antipodal Vivaldi antenna. Numerical simulations confirm this trend and due to ideal mechanical conditions return a signal-to-clutter level higher than 7.61 dB. The I-MUSIC largely outperforms the methods under comparison and is able to detect a 5-mm tumor with a permittivity contrast of 1.5.