Browsing by Author "Nanayakkara, ND"

Now showing 1 - 11 of 11

item: Conference-Abstract
Automated diagnosis of cardiac abnormalities using heart sounds
(2014-06-25) Perera, IS; Muthalif, FA; Selvarathnam, M; Liyanaarachchi, MR; Nanayakkara, ND
Listening to the heart sounds is a common practice in identifying cardiac malfunctions. Since this method has many limitations, tools that aid physicians in their diagnosis of heart diseases are very useful. This paper presents a software tool to predict cardiac abnormalities which can be identified using heart sounds. Both heart sound information and symptoms are used in disease prediction. First audio inputs at four clinically important locations on the chest are acquired using an electronic stethoscope and entered to a database with symptoms for each patient. After de-noising, prominent features and statistical parameters needed for disease detection are extracted from the heart sound samples using several algorithms. Then the disease classification is performed to find out possible disease and murmur types. The software tool reported in this paper is capable of identifying normal heart sounds and abnormal heart sounds with possible kind of disease and murmurs presented there. Hence, it helps doctors to detect diseases early and can be integrated as a standard module of electronic stethoscope software.
item: Conference-Abstract
Detection of microfilariae in peripheral blood smears using image analysis
Mallawaarachchi, S; Premalal, GVA; Wimalana, KWSS; Liyanage, AS; Samarasinghe, S; Nanayakkara, ND
Lymphatic filariasis is a leading cause of permanent disability in many countries. Due to its asymptomatic and epidemiological characteristics, the whole population living in threatened areas needs to be screened. The popular diagnostic method involves the manual microscopic observation of nocturnal blood smears in order to detect the presence of microfilariae. Due its strenuous and mundane nature, considerable detection errors are observed. This paper presents an image-based technique for diagnosis of filariasis through the detection of microfilariae present in Giemsa or Hematoxylin and Eosin stained peripheral thick blood smears. The proposed method uses connected component analysis and dynamic thresholding to detect microfilariae in images acquired from the microscope eyepiece. A sensitivity of 91.42% and a specificity of 88.57% were observed on experiments conducted on a database of 70 images.
item: Conference-Full-text
Development of a pid based closed loop controller for shape memory alloy actuators
(IEEE, 2018-05) Roshan, TAU; Basnayake, BADJCK; Amarasinghe, YWR; Wijethunge, D; Nanayakkara, ND
Shape Memory Alloy (SMA) spring actuator was designed and fabricated using commercially available NiTiNOL material by shape setting with the use of a special fixture. So, before applying the actuator to an application, a force characterization was conducted and force variation respect to uncontrolled temperature was analyzed. Due to the difference between force and temperature sensor’s response time, a lag can occur between force and temperature measurements. Therefore, a more controlled technique was further implemented by developing a Proportional-Integral-Derivative (PID) based closed loop controller, together with a Graphical User Interface (GUI) which supports parameter control and sensor calibration. Finally, a force feedback controlling method also developed using the same PID technique for a force sensitive applications, where controlled forces need to be maintained by varying temperature of SMA accordingly.
item: Conference-Abstract
Hardware interface for haptic feedback in laparoscopic surgery simulators
Kannangara, SM; Ranasinghe, SC; Kumarage, SK; Nanayakkara, ND
Minimally Invasive Surgeries (MIS) such as laparoscopic procedures are increasingly preferred over conventional surgeries due to many different advantages. Laparoscopic surgical procedures are very complex compared to open surgeries and require high level of experience and expertise. Hybrid surgery simulators available for training using physical phantoms are expensive and not readily available in majority of health care facilities around the world. Therefore, computer simulation or Virtual Reality (VR) is a better way to obtain skills for MIS. A VR simulator incorporated with haptic feedback provides a comprehensive training closer to real world experience. In this paper, we present a novel approach to incorporate force feedback to VR laparoscopic surgery training. The proposed interface incorporates force feedback in all three axes to provide three levels of force feedback. Computational models of abdomen organs were generated using the cryosection data of Visible Human Project of the National Library of Medicine, USA. The organ models were developed with three basic force categories: soft, mild and hard. A hardware interface is developed to provide the force feedback for the interaction of virtual tools with the said organ models while generating the tool navigation information for the VR simulator.
item: Article-Full-text
In situ 4D tomography image analysis framework to follow sintering within 3D-printed glass scaffolds
(Wiley-Blackwell on behalf of the American Ceramic Society, 2022) Kondarage, AI; Poologasundarampillai, G; Nommeots-Nomm, A; Lee, PD; Lalitharatne, TD; Nanayakkara, ND; Jones, JR; Karunaratne, A
We propose a novel image analysis framework to automate analysis of X-ray microtomography images of sintering ceramics and glasses, using open-source toolkits and machine learning. Additive manufacturing (AM) of glasses and ceramics usually requires sintering of green bodies. Sintering causes shrinkage, which presents a challenge for controlling the metrology of the final architecture. Therefore, being able to monitor sintering in 3D over time (termed 4D) is important when developing new porous ceramics or glasses. Synchrotron X-ray tomographic imaging allows in situ, real-time capture of the sintering process at both micro and macro scales using a furnace rig, facilitating 4D quantitative analysis of the process. The proposed image analysis framework is capable of tracking and quantifying the densification of glass or ceramic particles within multiple volumes of interest (VOIs) along with structural changes over time using 4D image data. The framework is demonstrated by 4D quantitative analysis of bioactive glass ICIE16 within a 3D-printed scaffold. Here, densification of glass particles within 3 VOIs were tracked and quantified along with diameter change of struts and interstrut pore size over the 3D image series, delivering new insights on the sintering mechanism of ICIE16 bioactive glass particles in both micro and macro scales.
item: Conference-Full-text
Mobile based wound measurement
(2015-07-06) Hettiarachchi, NDJ; Mahindaratne, RBH; Mendis, GDC; Nanayakkara, HT; Nanayakkara, ND; Dayananda, NWN
This paper proposes a portable wound area measurement method based on the segmentation of digital images. Its objective is to provide a practical, fast and non-invasive technique for medical staff to monitor the healing process of chronic wounds. Segmentation is based on active contour models which identifies the wound border irrespective of coloration and shape. The initial segmentation can also be modified by the user, providing higher control and accuracy. Area measurements are further normalized to remove effects of camera distance and angle. The application has been implemented for the Android platform version 2.2 with a prototype model running on Samsung Galaxy Tab. The results to evaluate the efficacy of the application have been encouraging with an accuracy level of 90%
item: Conference-Full-text
Non-invasive blood glucose monitoring using a hybrid technique
(IEEE, 2018-05) Nanayakkara, ND; Munasingha, SC; Ruwanpathirana, GP; Chathuranga, D
Diabetes needs regular blood glucose monitoring to control it. Invasive blood glucose measuring is the current gold standard. It causes discomfort for the patient and sometimes even infections. Researchers around the world have reported different techniques to measure blood glucose levels non-invasively, but a universally acceptable method with required accuracy is not yet available. We proposed a novel approach to measure blood glucose level non-invasively using a hybrid technique combining Near InfraRed (NIR) absorption and bio-impedance measurements. We tested the methods individually first. Then Artificial Neural Network (ANN) and least squares regression were used to integrate the two methods. The combined methods showed better accuracy compared to the individual measurements. The hybrid technique developed using the linear regression models showed a superior outcome with 90% and 10% of the data points in the regions A and B of the Clarke error grid, which are considered acceptable.
item: Conference-Extended-Abstract
Online status monitoring system for patients in intensive care unit
(2010) Hennayaka, HMSK; Hemachandra, MGNB; Jayasinghe, JMUUK; Hemachandra, MGND; Nanayakkara, ND
Continuous monitoring of patient's vital signs presides by the sophistical monitoring equipments in modern ICUs. Various health parameters provided by the continuous monitoring of these quipments has to be observed continuously to take necessary actions at the unstable situations of the patient. So it is very critical to be aware of the real-time health parameter indications of the patient all the time. We have introduced a remotely accessible centralized monitoring system in order to provide a single observation point for the health professionals remotely and locally. The proposed system is capable of access the most critical information displayed in ICU monitoring equipments in to one observation point. Therefore, the doctors can observe patient information real time from anywhere. The system also address the issues of mistakes happen due to unawareness of the time critical situations when observing information separately from each every device around the patient bed. The proposed system interconnects stand-alone ICU equipments and send these data to a database. A web applications running on top of the database will provide the real-time information about the patient to the doctor.
item: Conference-Abstract
Real time endoscope trajectory tracking in the 3D space using MEMS sensors
(2014-06-23) Kulatunga, TN; Ranasinghe, RAGP; Ranathunga, RAC; Ratnayake, RACH; Nanayakkara, ND
Colonoscopy is one of most widely used screening procedures conducted for detection colon cancers. Nevertheless, since the procedure is extremely uncomfortable, willingness to have a colonoscopy is very low. The endoscope looping, which is a common occurrence during colonoscopy procedures can cause severe pain to the patients. The detection of endoscope looping is difficult just from the feel of the endoscope, because of the endoscope stiffness and the high tension developed in the twisted endoscope inside the colon. The occurrence of Endoscope looping can be detected or prevented if the surgeon has sufficient spatial and orientation information of the endoscope. Hence, our goal is to develop a technique to track the three dimensional representation of the endoscope and develop a navigational aid for the surgeon to guide the colonoscopy. We used 8 inertial sensor systems, which are small enough to incorporate into the endoscope tube at predetermined locations. Then the firmware platform gathers data from these systems in real time. The data gathered from sensor systems are processed and fused to form a complete orientation description of sensor modules in 3D space. The processed orientation data is then sent to the PC and the Software application we developed interpolates the sent data in order to get the real time 3D visualization of the Endoscope. The developed prototype was tested using a model phantom. After testing for accuracy between the real shape and the calculated shape from our method we found out that the shape very closely resembles the real shape, quantitatively.
item: Conference-Abstract
Synchronized medical image viewer for remote consultation
Karunaratne, PM; Jayasuriya, DPN; Karunaratne, MBRD; Karunasekera, HHR; Nanayakkara, ND
The collaborative analysis between radiologists and surgeons of digitized medical images in the surgical planning phase is a critical step in the process of patient treatment. The shortage of radiologists who are qualified to carry out this task has proven detrimental to patient care. The proposed solution is a tool for collaboration where a radiologist and a surgeon are able to analyze scans while being in geographically disparate locations. Though a superficial examination of the options currently available would suggest the use of an off-the-shelf desktop sharing software solution, these fall well short of the performance and quality requirements of such an application which is to be used in a medical setting. We propose a novel approach, based on low-level command capturing that enables near-real-time synchronization with zero loss of information or distortion of the images. We discuss the underlying technology of our implementation of the synchronization solution as well as present the manifest performance gains of our solution in comparison with the highly popular commercial desktop sharing solution TeamViewer.
item: Conference-Abstract
Toolkit for extracting electrocardiogram signals from scanned trace reports
Mallawaarachch, S; Perera, MPN; Nanayakkara, ND
Cardiovascular disease (CVD) is the leading cause of death throughout the world. Since electrocardiogram-reports (ECG) have a great CVD predicting potential, the demand for their real-time analysis is high. Although algorithms are present to perform analysis, most countries still use analogue acquisition systems that can only output a printed trace. It is necessary to extract the signal from these printouts to perform analysis. With time, as the reports pile up and the trace fades from the printout, the task becomes increasingly difficult. The method presented specifically focuses on extracting signals from faded traces. Due to the large variability of scans, it is difficult to automate this task completely. In this paper, we propose several tools for ECG extraction while maintaining a minimum user involvement requirement. The proposed method was tested on a dataset of 550 trace snippets and comparative analysis shows an average accuracy of 96%.