International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Effect of Tissue Excitation in Breast Cancer Detection from Ultrasound RF Time Series: Phantom studies

Authors :

Elaheh Norouzi Ghehi¹ Ali Fallah² Saeid Rashidi³ Maryam Mehdizadeh Dastjerdi⁴

1- Ultrasound and Elastography group, Bimedical Engineering Faculty, Amirkabir university of Technology, Tehran, Iran 2- Bimedical Engineering Faculty, Amirkabir university of Technology, Tehran, Iran 3- Faculty of Medical Sciences and Technologies, Science and Research Branch, Islamic Azad University, Tehran, Iran 4- Ultrasound and Elastography group, Amirkabir university of Technology, Tehran, Iran

Keywords :

RF time series, tissue excitation, breast cancer, tissue classification, SVM classifiers.

Abstract :

Breast cancer is the most common women cancer. If the lesion and its type are diagnosed in the early stages, treatment will be more successful. Due to the lack of sufficient accuracy of each nowadays method to ensure the type of lesions, a biopsy is used which is invasive and imposes a lot of psychological and financial costs on the patient. Thus, it is necessary to consider a low-cost, non-radioactive and non-invasive method to determine the type of lesion. Recent studies on RF time series have shown that the interactions of this signal with tissue and echo patterns could provide useful information about the propagation environment. In this study, suggested extracting RF time series features in the progress of stimulating breast tissue. By extracting appropriate features from the RF time series, the effect of this interaction on the classification of healthy tissues, cancerous and non-cancerous lesions could also be observed. A Supersonic Imagine US system equipped with a linear probe was used to record this signal. Data were recorded from two types of agar-gelatin phantom mimicking breast tissue. Data collection was performed under a fixed probe, static and vibrational excitation. Finally, SVM classifiers have been used to classify healthy and cancerous tissues. The effect of central frequency on this classification has also been investigated. The results indicated that by applying vibrational excitation, tissue response characteristics are added more information to the RF time series and improve classification results. The best result was achieved by 6.4 central frequency ultrafast beamformed data with 98.78±2.77 % accuracy.