FPGA-Based Portable Ultrasound Scanning System with Automatic Kidney Detection

R, Bharath and Kumar, P and Dusa, C and Akkala, V and Puli, S and Ponduri, H and K, Divya Krishna and P, Rajalakshmi and Merchant, S N and Mohammed, A M and Desai, U B (2015) FPGA-Based Portable Ultrasound Scanning System with Automatic Kidney Detection. Journal of Imaging, 1 (1). pp. 193-219. ISSN 2313-433X

[img]
Preview
Text (Open access)
jimaging-01-00193.pdf - Published Version

Download (6MB) | Preview

Abstract

Bedsides diagnosis using portable ultrasound scanning (PUS) offering comfortable diagnosis with various clinical advantages, in general, ultrasound scanners suffer from a poor signal-to-noise ratio, and physicians who operate the device at point-of-care may not be adequately trained to perform high level diagnosis. Such scenarios can be eradicated by incorporating ambient intelligence in PUS. In this paper, we propose an architecture for a PUS system, whose abilities include automated kidney detection in real time. Automated kidney detection is performed by training the Viola–Jones algorithm with a good set of kidney data consisting of diversified shapes and sizes. It is observed that the kidney detection algorithm delivers very good performance in terms of detection accuracy. The proposed PUS with kidney detection algorithm is implemented on a single Xilinx Kintex-7 FPGA, integrated with a Raspberry Pi ARM processor running at 900 MHz.

[error in script]
IITH Creators:
IITH CreatorsORCiD
P, RajalakshmiUNSPECIFIED
Desai, U BUNSPECIFIED
Item Type: Article
Uncontrolled Keywords: portable ultrasound scanning; FPGA; organ detection; Viola–Jones
Subjects: Others > Electronic imaging & Singal processing
Divisions: Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 21 Dec 2015 04:54
Last Modified: 28 Jan 2016 07:04
URI: http://raiith.iith.ac.in/id/eprint/2089
Publisher URL: http://dx.doi.org/10.3390/jimaging1010193
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 2089 Statistics for this ePrint Item