Tati L. R. Mengko

Color retinal image enhancement using CLAHE

Common method in image enhancement thats often use is histogram equalization, due to this method is simple and has low computation load. In this research, we use Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the color retinal image. To reduce this noise effect in color retinal image due to the acquisition process, we need to enhance this image. Color retinal image has unique characteristic than other image, that is, this image has important in green (G) channel. Image enhancement has important contribution in ophthalmology. In this paper, we propose new enhancement method using CLAHE in G channel to improve the color retinal image quality. The enhancement process conduct in G channel is appropriate to enhance the color retinal image quality.

Automatic classification of tuberculosis bacteria using neural network

Sputum smear microscopy analysis is the important thing for early diagnosis tuberculosis diseases. A lot of patients in tuberculosis medical center cause the doctors and the technicians have heavy duty. Our research result can be used to reduce technician involvement in screening for tuberculosis and would be useful in laboratories. This research is early step to find appropriate method for identifying tuberculosis bacteria. The analysis of sputum smear requires highly trained to avoid high errors. It needs an appropriate pattern recognition and classification of tuberculosis bacteria. Before classification, geometric features of tuberculosis cell image are found from its binary image. The geometric features of tuberculosis cell image consist of circularity, compactness, eccentricity, and tortuosity. These geometric features would become inputs to the neural network trained with backpropagation method. The 100 samples would be divided into 75 training samples and 25 testing samples. After getting optimum weights and architectures of neural network with 20 neurons hidden layer, 0.05 learning rate, and 0.9 momentum, this network is used for classifying tuberculosis bacteria into two categories: tuberculosis bacteria or not. Results presented for several image taken from different binary cell image show that neural network classifies the presence of tuberculosis bacteria image accurately with mean square error 0.000368, error classification zero in training and testing processes for the data that is used in this research.

Development of computer-aided diagnosis system for early diabetic retinopathy based on micro aneurysms detection from retinal images

As a complication of diabetes, diabetic retinopathy can be a serious threat to visual capability of patients. The occurrence of micro aneurysms is the first clinical symptom of such disease. Accordingly, micro aneurysms detection is of use to help ophthalmologist in diagnosing and treat patients. This paper proposes a development of a computer-aided system which detects the presence of micro aneurysms from retinal fundus images. The proposed system is expected to provide an early detection for diabetic retinopathy based on micro aneurysms. We present a preliminary design and the current progress of our work which is still under development. A preliminary evaluation on acquired retinal images shows encouraging results.

Wearable gait measurement system based on accelerometer and pressure sensor

This paper presents the development of wearable instrument that can be used to study the dynamics of human lower limb. Camera-based gait analysis and force plate system are expensive devices. It also requires time-consuming calibration and setup. The wearable system is much cheaper. This system uses gyroscopes and two-axis accelerometers to measure angle of patients leg and ground while the patient walks. Ground reaction forces during human walking are measured using flexible force sensors placed beneath insoles of the shoes. Communication between the wearable system and computer monitor can be performed using the wireless data communication.

Development of a Mobile Telemedicine System with Multi Communication Links for Urban and Rural Areas in Indonesia

This paper is a progress report on the development of a mobile telemedicine system with multi communication links. The system design goal is to provide patient monitoring during the prehospital transport and to offer health services, for people who lives in underserved areas. Therefore, medical information transmission becomes very crucial, since there is no a transmission link stability guarantee. To deal with this issue, multi communication links, which including VHF radio, internet, GSM/CDMA mobile phones, and GPRS are applied for the system. Selection of the communication links depends on the availability of the local communication infrastructure.

Reproducibility of Standing Posture for X-Ray Radiography: A Feasibility Study of the BalancAid with Healthy Young Subjects

Unreliable spinal X-ray radiography measurement due to standing postural variability can be minimized by using positional supports. In this study, we introduce a balancing device, named BalancAid, to position the patients in a reproducible position during spinal X-ray radiography. This study aimed to investigate the performance of healthy young subjects’ standing posture on the BalancAid compared to standing on the ground mimicking the standard X-rays posture in producing a reproducible posture for the spinal X-ray radiography. A study on the posture reproducibility measurement was performed by taking photographs of 20 healthy young subjects with good balance control standing on the BalancAid and the ground repeatedly within two consecutive days. We analyzed nine posterior–anterior (PA) and three lateral (LA) angles between lines through body marks placed in the positions of T3, T7, T12, L4 of the spine to confirm any translocations and movements between the first and second day measurements. No body marks repositioning was performed to avoid any error. Lin’s CCC test on all angles comparing both standing postures demonstrated that seven out of nine angles in PA view, and two out of three angles in LA view gave better reproducibility for standing on the BalancAid compared to standing on the ground. The PA angles concordance is on average better than that of the LA angles.

3D ultrasound reconstruction of spinal images using an improved Olympic Hole-filling method

We propose a new Hole-filling algorithm by improving the Olympic operator, and we also apply it to generate the volume in our freehand 3D ultrasound reconstruction of the spine. First, the ultrasound frames and position information are compounded into a 3D volume using the Bin-filling method. Then, the Hole-filling method is used to repair gaps in the volume. The conventional Olympic operator defines the empty voxels by sorting the neighboring voxels, removing the n% of the upper and lower values, and averaging them to attain the value to fill the empty voxels. The empty voxel estimation can be improved by thresholding the range width of its neighboring voxels and adjusting it to the average values. The method is tested on a hole-manipulated volume derived from a cropped 3D ultrasound volume of a part of the spine. Our MAE calculation on the proposed technique shows improved result compared to all tested existing methods.

Camera object tracking system

This paper presents a pan and tilt camera system that can follow a predefined object that move freely under a specific constraint. We use a stepping motor that work in a half step mode, provides a minimum of 0.9 degree movement, but it is adequate as a pan and tilt actuator system for the specified usage. A Kalman filter is used to estimate the object motion in the block matching process due to disorder changes due to the image being close to other views for several frames. A Motorola DSP 56002 is used as a controller processor for the actuator driver and the frame grabber Visionetics International installed in the Pentium 100. The sampling time is 3 frame/second.

Performance comparison of denoising methods for heart sound signal

This paper presents the performance analysis and comparison of three denosing methods for heart sound signal based on wavelet transform (WT), total variation (TV), and empirical mode decomposition (EMD). Extensive simulations are performed using normal and abnormal heart sound data and the performance is evaluated in terms of signal-to-noise ratio (SNR), root mean square error (RMSE), and percent root mean square difference (PRD). The simulation results show that EMD based denosing method outperforms two other methods.

Vessel enhancement algorithm in digital retinal fundus microaneurysms filter for nonproliferative diabetic retinopathy classification

Diabetic Retinopathy is one of a complication of diabetes which can cause blindness. There are two levels of diabetic retinopathy which are nonproliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). The presence of microaneurysms in the eye is one of the early signs of diabetic retinopathy. Automated detection of microaneurysms in digital color fundus photographs is developed to help opthalmologist to detect the emergence of its early symptoms and determine the next action step for the patient. In this study we developed microaneurysms filter algorithm with the concept of vessel enhancement in order to extract the structure of microaneurysms in medical imagery, especially in the retinal image. Microaneurysms filter algorithm has been able to extract part of microaneurysms in the retinal image and detect pretty well. In addition, microaneurysms filters can also be developed to detect the next symptoms of diabetic retinopathy-hemorraghes (bleeding) that has features in common with microaneurysms which are larger and have irregular shape. Furthermore, the nonproliferative diabetic retinopathy (NPDR) classification system was developed based on the microaneurysms and hemorraghes detection. The system was tested against the patient data. Microanuerisyms detection results on DiaRetDB data has sensitivity value by 57,4% to ophthalmlogist 1, 35,37% for opthalmologist 2 and 62,68% for opthalmologist 3.