Agung W. Setiawan

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.

Implementation of electronic medical record in community health center towards medical big data analytics application

Electronic Medical Record (EMR) is digitized version of medical record. Medical record is the file that contains notes and documents about patients identity, examination, therapy, treatments, and other services that have been given to the patient. The EMR is part of Management Information System for Community Health Center (MISCHC). In this paper, we discussed about the EMR that we designed and implemented based on the business process at one of Community Health Center in Bandung. This designed MISCHC also tries to support medical big data analytics application because the designed database is expected to be used in Decision Support System for City Health Office.

Extracting blood flow parameters from Photoplethysmograph signals: A review

Infrared sensors are used in Photoplethysmography measurements (PPG) to get blood flow parameters in the vascular system. It is a simple, low-cost non-invasive optical technique that is commonly placed on a finger or toe, to detect blood volume changes in the micro-vascular bed of tissue. The sensor use an infrared source and a photo detector to detect the infrared wave which is not absorbed. The recorded infrared waveform at the detector side is called the PPG signal. This paper reviews the various blood flow parameters that can be extracted from this PPG signal including the existence of an endothelial disfunction as an early detection tool of vascular diseases.

Performing high accuracy of the system for cataract detection using statistical texture analysis and K-Nearest Neighbor

Early detection of cataract considered as an important solution to prevent the increasing number of cataract in developing country, especially in Indonesia. A cataract will be a serious public health problem as a leading cause of blindness if there is a delay in handling it. In this paper, we discuss about the performing high accuracy of the system for cataract detection using statistical texture analysis and K-Nearest Neighbor (K-NN). In training steps, the feature extraction method uses Gray Level Co-occurrence Matrix (GLCM) to get the texture feature value of contrast, dissimilarity and uniformity that appearance in the pupil area of the training images. In testing steps, the testing images will be classified using K-NN method to normal or cataract condition. Based on the result of 10 times experiments for 160 eyes images that consist of 40 normal images and 40 cataract images as the training data and 40 normal images and 40 cataract images as the testing data, the statistical texture analysis and K-NN perform high accuracy for detecting cataract with average accuracy 94.5%.

A comparative study of colour retinal image coding using vector quantization: K-Means & Fuzzy C-Means

Retinal colour images play an important role in supporting medical diagnosis. Digital retinal image usually are represented in such a large data volume that takes a considerable amount of time to be accessed and displayed. Digital medical image coding therefore become crucial in medical image transfer and storage in electronic medical record server. This paper is concerned to compare the vector quantization (VQ) coding using K-Means and Fuzzy C-Means algorithms. This research investigates the performance of each algorithm: objective (PSNR value) and subjective (visual). The VQ coding scheme is conducted separately to image components in each RGB channel. Reconstructed colour image is obtained by combining the VQ decoding result of each image channel. The 444 combination (coding of the R, G and B channels by the size of 4×4) produces the best subjective and objective quality of image coding. However, the optimum colour models for teleophthalmology and electronic medical record is 848 combination due to the file size, objective and subjective quality.

A Review of the OpenEHR Implementation in Indonesian National Health Information System: Integrated Health Post

In this research, we developed an e-health application to assist Posyandu (Pos Pelayanan Terpadu), integrated health post, operators in managing health examination reports. The development processes involves four steps: Analysis I (Health services requirements), Analysis II (Integration to OpenEHR concept), Analysis III (E-health application requirements), Design and development of e-health application telemedicine. The proposed system collects data from several Posyandu to an Electronic Health Record (EHR) system, based on OpenEHR standards. The stored data may be accessed, processed, and presented in a different way, depends on its type and the handled situation. E-health implementation will also actively involve the collaboration and coordination of each stakeholder in the planning, design, implementation, and evaluation of projects Further works to be considered will include the implementation of e-health application software as well as its performance and sustainability investigation.

Mobile cataract detection using optimal combination of statistical texture analysis

Cataract is one of potentially dangerous disease that will be causing the blindness as an impact of the belated in handling cataract. Cataract is not only disrupting productivity and mobility of patients, but also causing the social-economic impact that will decrease the quality of life. Early detection of cataract reputed as a principal arrangement in restraining the increasing number of blindness caused by cataract. Commonly, an ophthalmologist uses a slit lamp camera to diagnose a cataract. Lacking of ophthalmologist and slit lamp camera in rural areas are the main problem of the belated in diagnosing cataract. In this paper, we investigate the optimal combination candidate of statistical texture features that is provide highest accuracy for cataract detection. In this research, we use K-Nearest Neighbor (k-NN) as classification method that will be implemented on android smartphone. Our result show that the optimal combination of texture features are dissimilarity, contrast, and uniformity. The highest accuracy of the system is 97.5%. The system is implemented on mobile smartphone.

Performance Evaluation of Color Retinal Image Quality Assessment in Asymmetric Channel VQ Coding

The RGB color retinal image has an interesting characteristic, i.e. the G channel contains more important information than the other ones. One of the most important features in a retinal image is the retinal blood vessel structure. Many diseases can be diagnosed based on in the retinal blood vessel, such as micro aneurysms that can lead to blindness. In the G channel, the contrast between retinal blood vessel and its background is significantly high. The authors explore this retinal image characteristic to construct a more suitable image coding system. The coding processes are conduct in three schemes: weighted R channel, weighted G channel, and weighted B channel coding. Their hypothesis is that allocating more bits in the G channel will improve the coding performance. The authors seek for image quality assessment (IQA) metrics that can be used to measure the distortion in retinal image coding. Three different metrics, namely Peak Signal to Noise Ratio (PSNR), Structure Similarity (SSIM), and Visual Information Fidelity (VIF) are compared as objective assessment in image coding and to show quantitatively that G channel has more important role compared to the other ones. The authors use Vector Quantization (VQ) as image coding method due to its simplicity and low-complexity than the other methods. Experiments with actual retinal image shows that the minimum value of SSIM and VIF required in this coding scheme is 0.9940 and 0.8637.

Color retinal image coding based on entropy-constrained vector quantization

Retinal color images play an important role in supporting medical diagnosis. Digital retinal image usually are represented in such a large data volume that takes a considerable amount of time to be accessed and displayed from remote site. This paper aims to conduct a color retinal image coding using Entropy-Constrained Vector Quantization (ECVQ). In this paper, we use two objective parameters: Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). Coded image which has the best quality of subjective and objective is the image coded with the value of λ = 0.1 and rate = 4.5 bpp.

Implementation of Project-Based Learning in Biomedical Engineering Course in ITB: Opportunities and Challenges

Introduction to Biomedical Engineering is an elective course for final year undergraduate student. For the last two years, 2015–2016, the traditional learning was implemented in this course. In 2017, project-based learning (PBL), was applied to the course. The goals is to enable students to take initiative, identify and solve the problems, work and communicate ideas in team, build responsibility and confidence. This paper will focus on implementation of PBL, specifically on the opportunities and challenges. The students choose their own topic, identify and explain what is the topic, why they choose that, and how they solve the problem. They have to review the existing solution and they should propose a new solution. Finally, they have to submit a report, then present their work in class attended by all the students and instructor. Using this learning approach, the students become more active to present their ideas, give some comments and questions.