In patients with acute PE, MDCT might be used as a single procedure for diagnosis and risk stratification. Patients without right ventricular dysfunction at MDCT have a low risk of in-hospital adverse outcome.
Breast lesion detection employing state of the art microwave systems provide a safe, non-ionizing technique that can differentiate healthy and non-healthy tissues by exploiting their dielectric properties. In this paper, a microwave apparatus for breast lesion detection is used to accumulate clinical data from subjects undergoing breast examinations at the Department of Diagnostic Imaging, Perugia Hospital, Perugia, Italy. This paper presents the first ever clinical demonstration and comparison of a microwave ultra-wideband (UWB) device augmented by machine learning with subjects who are simultaneously undergoing conventional breast examinations. Non-ionizing microwave signals are transmitted through the breast tissue and the scattering parameters (S-parameter) are received via a dedicated moving transmitting and receiving antenna set-up. The output of a parallel radiologist study for the same subjects, performed using conventional techniques, is taken to pre-process microwave data and create suitable data for the machine intelligence system. These data are used to train and investigate several suitable supervised machine learning algorithms nearest neighbour (NN), multi-layer perceptron (MLP) neural network, and support vector machine (SVM) to create an intelligent classification system towards supporting clinicians to recognise breasts with lesions. The results are rigorously analysed, validated through statistical measurements, and found the quadratic kernel of SVM can classify the breast data with 98% accuracy.
This paper presents preliminary results of an innovative microwave imaging apparatus for breast lesions detection. Specifically, a Huygens Principle based method is employed to process the microwave signals and to build the respective microwave images. The apparatus has been first tested on phantoms. Next, its performance has been verified through clinical examinations on 22 healthy breasts and on 29 breast having lesions, using as gold standard the output of the radiologist study review obtained using conventional techniques. Specifically, we introduce a metric, which is the ratio between maximum and average of the image intensity (MAX/AVG). We found that MAX/AVG of microwave images can be used for classifying breasts containing lesions. In addition, using MAX/AVG as classification parameter, receiver operating characteristic curves have been empirically determined. Furthermore, for one randomly selected breast having lesion, we have demonstrated that the localization of the inclusion acquired through microwave imaging is compatible with mammography images.
Microwave imaging has received increasing attention in the last decades, motivated by its application in diagnostic imaging. Such effort has been encouraged by the fact that, at microwave frequencies, it is possible to distinguish between tissues with different dielectric properties. In such framework, a novel microwave device is presented here. The apparatus, consisting of two antennas operating in air, is completely safe and non-invasive since it does not emit any ionizing radiation and it can be used for breast lesion detection without requiring any breast crushing. We use Huygens Principle to provide a novel understanding into microwave imaging; specifically, the algorithm based on this principle provides images which represent homogeneity maps of the dielectric properties (dielectric constant and/or conductivity). The experimental results on phantoms having inclusions with different dielectric constants are presented here. In addition, the capability of the device to detect breast lesions has been verified through clinical examinations on 51 breasts.We introduce a metric to measure the non-homogenous behaviour of the image, establishing a modality to detect the presence of inclusions inside phantoms and, similarly, the presence of a lesion inside a breast.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.