R. Bharath

FPGA-Based Portable Ultrasound Scanning System with Automatic Kidney Detection

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.

FPGA based preliminary CAD for kidney on IoT enabled portable ultrasound imaging system

Ultrasound imaging has been widely used for preliminary diagnosis as it is non-invasive and has good scope for the doctors to analyze many diseases. Lack of trained sonographers make ultrasound imaging diagnosis time consuming to detect any abnormality. Sometimes the problem cannot exactly be identified which may lead to error in diagnosis. Hence in this paper we present computer aided automatic detection of abnormality in kidney on the ultrasound system itself, to decrease the time for reports and not to depend on the sonographer. We classified the kidney as normal and abnormal case. Segment the kidney region and extract Intensity histogram features and Haralick features from Gray Level Cooccurnace Matrix (GLCM). These features are calculated for a set of large data containing both normal and abnormal cases. Abnormal case includes kidney stone, cyst and bacterial infection. Standard deviation for each parameter is observed, considered only those features with less deviation and implemented on FPGA Kintex board. If the range of mean value is 1.08 to 1.336, skewness is 2.882 to 7.708, Kurtosis is 1.06 to 71.152, Cluster Shade is 72 to 243, Homogeneity is 0.993 to 0.998, the observed kidney image is normal otherwise abnormal.

Multi-level classification: A generic classification method for medical datasets

Classification of medical data is one of the most challenging pattern recognition problems. As stated in literature a single classifier is unable to solve all medical image classification problems due to high sensitivity to noise and other imperfections like data imbalance. So, several individual classifiers have been studied to solve the different types of classification problems arising in medical datasets but all have proven to be useful on some specific datasets. Hence, in this paper, we propose a generic multi-level classification approach for medical datasets using sparsity based dictionary learning and support vector machine approaches. The proposed technique demonstrates the following advantages: 1) gives better performance of classification accuracy over all datasets 2) solves imbalanced data problems 3) needs no fusion and ensemble methods in multi-level classification. The results presented on the 5 standard UCI medical datasets demonstrate that the efficacy of the proposed multi-level classification technique.

Implementation of diagnostically driven compression algorithms via WebRTC for IoT enabled tele-sonography

In this paper, we have proposed novel framework for compressing the ultrasound images for IoT enabled telesonography. In ultrasound images, the diagnostic information is constrained to a particular region in the image, and sonographers look for that particular region for doing diagnosis. Therefore, by transmitting only that particular region to the remote sonographer, a significant compression can be achieved. Diagnostic information present in an image is organ specific, hence we came up with a framework to detect the organs and compress accordingly. We developed automated, semi-automated and manual algorithms for detecting the organs in an image. The automated and semi-automated algorithms for organ detection are based on Viola Jones and active shape model respectively. The detected organ is JPEG compressed and transmitted to remote sonographer through WebRTC technology. WebRTC enables direct browser-to-browser connection enabling fast and secure transmission of data. Organ detection algorithms are implemented through WebRTC and hence there is no need to install any softwares at the end devices. With the proposed framework, any ultrasound scanner can access service from the server, compress it and transmit to the expert end. The remote sonographer from anywhere can connect to the ultrasound scanner with his laptop, mobile, tablet etc., for doing diagnosis. The performance of proposed framework is evaluated by computing the compression efficiency on ten kidney ultrasound images.

Compression techniques for IoT enabled handheld ultrasound imaging system

Received echo signals of transducer in ultrasound imaging have a high dynamic range of 12 bits and hence cannot be displayed on Cathode Ray Tube (CRT), Liquid Crystal Display (LCD) monitors of ultrasound machine. Log compression is being used to compress the data to 8 bits. Since log compression is a non linear compression it is very difficult to trace the original characteristics of the signal. In this paper various global and local compression techniques were studied as a replacement for log compression so that the dynamic range of image can be retrieved if the physician has a better monitor for display, and also ensure minimum error in the retrieved signal leading to minimum error in retrieved image. From the results it is observed that Structural SIMilarity (SSIM) of wavelet compressed image is 1.02 times more and that of gamma compressed image is 2.24 times more than log compressed image. Gamma based compression can be preferred to log and wavelet based compression, as it gives good quality image when compared with other compression techniques, but cannot be used to retrieve the statistical properties when expanded, since these statistical properties are helpful for doctors for better analysis. Wavelet based compression serves this purpose and hence is best suited for Internet of Things (IoT) enabled ultrasound system for remote diagnosis in the cloud.

Fast Region of Interest detection for fetal genital organs in B-mode ultrasound images

Genital organ detection of fetus in B-mode ultrasound images has a considerable significance. It is useful to know any malformations present in the genital organs and also to determine the sex of the fetus. In this paper we propose a Feature from Accelerated Segment Test (FAST) technique for approximate detection of fetal genitals in ultrasound images. FAST algorithm is capable of producing the corner points at a higher speed which falls on the fetal genital organs. A window of size 60×60 pixels being corner point as a center is considered as Region of Interest (ROI), where genital organ of fetus is anticipated. The efficiency of the algorithm is calculated as the ratio of number of images where corner points are placed on the fetus genital organ to the total number of images tested. FAST algorithm is robust to speckles present in the image, machine independent, fast and also computationally less intensive to implement in real time with an efficiency of 96.7%.

Smartphone based automatic abnormality detection of kidney in ultrasound images

Telesonography suffers from inherent limitations due to the need of all time availability of experts in cloud and data connectivity to the device. Computer-aided diagnosis (CAD) used for automatic detection of abnormalities without manual intervention can overcome these limitations. Commercially available ultrasound scanners restrict the installation of new softwares and hence CAD algorithms cannot be integrated into the existing ultrasound scanners. There is a need for an external computing device, which can acquire image data from ultrasound scanners, perform CAD and generate result. Smart-phones are now widely used in personalized healthcare due to its ubiquitous computing capability. Smartphones with embedded CAD can be used as a computing device for automated diagnosis. In this paper, we have developed an Application (APP) for a smartphone to automatically diagnose the kidney in the ultrasound image. With the developed APP, the smartphone can acquire images from any ultrasound scanner, process it and give the diagnostic result. Automatic abnormality detection of kidney is based on Viola Jones algorithm, texture feature extraction followed by SVM classifier. Stones and cysts are the abnormalities detected using the algorithm. The developed APP resulted with an accuracy of 90.91% in detecting the abnormalities.

Sparseland model for speckle suppression of B-mode ultrasound images

Speckle is a multiplicative noise which is inherent in medical ultrasound images. Speckles contributes high variance between neighboring pixels reducing the visual quality of an image. Suppression of speckle noise significantly improves the diagnostic content present in the image. In this paper, we propose how sparseland model can be used for speckle suppression. The performance of the model is evaluated based on variance to mean ratio of a patch in the filtered image. The algorithm is tested on both software generated images and real time ultrasound images. The proposed algorithm has performed similar to past adaptive speckle suppression filters and seems promising in improving diagnostic content.

Novel architecture for wireless transducer based ultrasound imaging system

In medical ultrasound scanning, coaxial cables connects the transducer elements to the computing platforms. During scanning, these probes are hanging from sonographer hand and slides on the patient body providing discomfort for both patient and sonographer. To address this issue, we discussed the feasibility of realizing wireless ultrasound transducer and as a proof of concept we built the prototype of wireless ultrasound transducer based scanning system. The proposed system has two parts: wireless transducer with embedded pre-processing unit, and back-end module for image reconstruction and display purpose. The embedded pre-processing unit consist of analog and digital integrated circuits, transmit beamforming, low noise amplification, time gain compensation and receive beam forming. The output of wireless transducer is scanline data, which is transmitted to back-end module via wireless communication transceiver. The complete back-end module is implemented on a Zedboard platform which comes with FPGA and ARM processor. The signal processing algorithms, which include envelope detection, log compression, scan conversion, interpolation and decimation algorithms are implemented on FPGA, while ARM processor is used to control and coordinate between signal processing modules. The Wi-Fi 802.11n standard is used as a wireless communication transceiver between wireless transducer and back-end module. The wireless transducer prototype is designed for 64 element, 8 channel linear transducer. The proposed prototype of wireless transducer based scanning system is successfully tested by scanning a phantom.

Compressive sensing ultrasound beamformed imaging in time and frequency domain

High sampling rate is necessary for a quality ultrasound image, which demands expensive data-acquisition and computing devices. Compressive sensing(CS) can reconstruct high quality image with less data. It can give optimal solution to high sampling problem in ultrasound imaging. Ultrasound imaging is performed using beamforming of transducer array elements. In this work we present time and frequency domain beamforming matrices and demonstrates how it can be used as CS-matrix to reconstruct ultrasound images. Feasibility of CS with the beamforming matrices are studied using transfer point spread function. Compared to previous work in ultrasound using CS where signal reconstruction is used from undersampled data, we present direct ultrasound image reconstruction from highly undersampled received data. Image reconstruction with time and frequency domain beamformed CS-matrix are showed. Through our results it is clear that compressive sensing in ultrasound imaging can significantly reduce sampling rate by maintaining same image quality as traditional ultrasound imaging.