Filtering Super-Resolution Scan Conversion of Medical Ultrasound Frames
- PDF / 3,315,285 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 0 Downloads / 167 Views
Filtering Super‑Resolution Scan Conversion of Medical Ultrasound Frames Dipannita Ghosh1 · Amish Kumar1 · Palash Ghosal1 · Amritendu Mukherjee2 · Debashis Nandi1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, we consider a challenging problem of reconstruction of high resolution (HR) B-mode ultrasound (US) image by proposing a novel multi-frame based super-resolution (SR) scan conversion framework. This new framework of SR scan conversion reconstructs an improved HR frame by using the scan data of several low resolution (LR) frames. It also unifies the speckle reduction and HR scan conversion in such a way that it has become a single operation to generate a super-resolved image with lesser loss of information. We evaluated the performance of the proposed model on synthetic images, ultrasound simulated (by Field II software) images and real ultrasound image dataset and the comparison is performed against some of the publicly available state-of-the-art ultrasound image enhancement techniques. Significant improvement in image quality has been achieved due to utilization of non-redundant information present in the scan data of the LR frames. We demonstrate the improvement of the proposed technique through the computation of perceptual and quantitative quality metrics, such as, SSIM, PSNR etc. over the recent competing methods. Keywords Ultrasonic imaging · Scan conversion · Super-resolution reconstruction · Image registration · Despeckling
* Dipannita Ghosh [email protected] Amish Kumar [email protected] Palash Ghosal [email protected] Amritendu Mukherjee [email protected] Debashis Nandi [email protected] 1
Department of Computer Science and Engineering, National Institute of Technology, MG Avenue, Durgapur, India
2
Department of Radiology, Zulekha Hospital, Dubai, United Arab Emirates
13
Vol.:(0123456789)
D. Ghosh et al.
1 Introduction The application of ultrasound imaging is expanding its coverage and showing unprecedented potential in medical science for its non-invasive and non-ionising nature and has traditionally been an important area of research, attracting researchers to work on different areas, such as cardiology, gastroenterology, gynaecology, neurology, ophthalmology, urology etc. But the barrier due to poor resolution may lead to diagnosis error and largely impact the degree of precision of the decisions made by the experts. The reasons lying behind the poor resolution of ultrasound images are the physical phenomena of the acoustic wave transmission, frequency of the acoustic wave, pulse repetition frequency, beamwidth, number of array elements, number of scan lines per frame, B-mode image reconstruction technique etc. Specially, in an ultrasound sector scanner, the data is described in the polar coordinate system, which is to be converted to a raster scan using scan conversion for displaying the image on the Cartesian co-ordinate supported video monitor. Since the distance between two successive scan lines increase
Data Loading...
