Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
11 results
Search Results
Item Classification of cardiac abnormalities using heart rate signals: A comparative study(Springer Berlin Heidelberg, 2007) Acharya, R.; Kannathal, N.; Subbanna Bhat, P.S.; Suri, J.S.; Min, L.C.; Spaan, J.A.E.[No abstract available]Item Visualization of cardiac health using electrocardiograms(Springer Berlin Heidelberg, 2007) Acharya, R.; Subbanna Bhat, P.S.; Niranjan, U.C.; Kannathal, N.; Min, L.C.; Suri, J.S.The chapter discusses an efficient and novel method to assist the physician to visualize voluminous cardiac data acquired over several hours. The system uses different colors to identify different types of cardiogram signals. In the display strategy each ECG beat is represented by a grid. The visualization strategy is hierarchical; that is, it provides for viewing of data from different level of abstraction, and the physician can have a top down approach to narrow down the time interval and signal details. This display strategy is extended to sector graph, with a menu driven hierarchical display strategy, which progressively unfolds greater details for chosen intervals. Provision is made for changing the parameters of classification, and thus the physician has the option for fine tuning the classification. © Springer-Verlag Berlin Heidelberg 2007.Item Storage and transmission of cardiac data with medical images(Springer Berlin Heidelberg, 2007) Acharya, R.; Subbanna Bhat, P.S.; Niranjan, U.C.; Kumar, S.; Kannathal, N.; Min, L.C.; Suri, J.S.The landscape of healthcare delivery and medical data management has significantly changed over the last years, as a result of the significant advancements in information and communication technologies. Complementary and/or alternative solutions are needed to meet the new challenges, especially regarding security of the widely distributed sensitive medical information. Digital watermarking is a technique of hiding specific identification data for copyright authentication. The DICOM standard is one method to include demographic information, such as patient information and X-ray exposure facilities, in image data. The DICOM standard is a standard that can be used regularly to record demographic information onto the image data header section. Regarding DICOM format images, information on patients and X-ray exposure facilities can be obtained easily from them. On the other hand, general-purpose image formats, such as the JPEG format, offer no standard that can be used regularly to record demographic information onto the header section. Digital watermark technologies [1-8] can be used to embed demographic information in image data. Digital watermarking have several other uses, such as fingerprinting, authentication, integrity verification purposes, content labeling, usage control and content protection [9, 10]. The efficient utilization of bandwidth of communication channel and storage space can be achieved, when the reduction in data size is done. Recently, Giakoumaki et al, have presented a review of research in the area of medical-oriented watermarking and proposed a wavelet-based multiple watermarking scheme. This scheme aimed to address critical health information management issues, including origin and data authentication, protection of sensitive data, and image archiving and retrieval [11]. Their experimental results on different medical imaging modalities demonstrated the efficiency and transparency of the watermarking scheme. The digital watermarking technique is adapted in this chapter for interleaving patient information with medical images, to reduce storage and transmission overheads. The text data is encrypted before interleaving with images to ensure greater security. The graphical signals are compressed and subsequently interleaved with the image. Differential pulse code modulation and adaptive delta modulation techniques are employed for data compression as well as encryption and results are tabulated for a specific example. Adverse effects of channel induced random errors and burst errors on the text data are countered by employing repetition code, Hamming code and R-S code techniques.Item Gradient descent in sample-based single-query path planning algorithm(Institute of Electrical and Electronics Engineers Inc., 2018) Acharya, R.; Jena, D.Rapidly-exploring random tree (RRT) is a sampling based single query algorithm that is used to generate a path. This papers describes RRT algorithm, modifies RRT algorithm by applying gradient descent method for generating the path. Simulations are run in iterations and the results are compared with and without gradient descent. Finally this paper concludes with advantages and limitations of the gradient approach. © 2018 IEEE.Item Sampling based motion planning of Ackermann steering system using transformation(Institute of Electrical and Electronics Engineers Inc., 2018) Acharya, R.; Jena, D.The objective of this work is to apply sampling based algorithm to generate a path to Ackermann steering system with given constraints based on its Kinematics model. Rapidly-exploring Random Tree (RRT) is used with uniform sampling for path exploration. The configuration space is transformed and will be used for path formulation. This paper presents Gaussian sampling based strategy, path formulation meeting system kinematics, and trajectories creation over the sample points. © 2018 IEEE.Item Reliable and robust transmission and storage techniques for medical images with patient information(Springer New York LLC barbara.b.bertram@gsk.com, 2010) Nergui, M.; Acharya, U.S.; Acharya, R.; Yu, W.There is an increased emphasis on the use of digital techniques in all aspects of human life today. Broadcast radio and television, cellular phone services, consumer and entertainment electronics etc are increasingly using digital signal processing techniques to improve the quality of service. Transmission and storage of documentation and images pertaining to patient records cannot remain an exception to this global trend. Hence, patient records (text and image information) are increasingly stored and processed in digital form. Currently, text and image information, which constitute two separate pieces of data are handled as different files. Thus, there is a possibility of the text and message information, pertaining to different patients, being interchanged and thus mishandled. This can be avoided by merging text and image information in such a manner that the two can be separated without perceptible damage to information contained in either file. Digital watermarking techniques can be used to interleave patient information with medical images. In this work, we have employed digital watermarking along with strong cryptographic protocols and powerful error correcting codes. This reduces the probability of sensitive patient information falling into the wrong hands and ensures information integrity when it is conveyed over noisy channels. © 2009 Springer Science+Business Media, LLC.Item Automated identification of diabetic retinopathy stages using digital fundus images(2008) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.; Lim, C.M.; Kagathi, M.Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources for mass screening of diabetic retinopathy. In this work, we have proposed a computer-based approach for the detection of diabetic retinopathy stage using fundus images. Image preprocessing, morphological processing techniques and texture analysis methods are applied on the fundus images to detect the features such as area of hard exudates, area of the blood vessels and the contrast. Our protocol uses total of 140 subjects consisting of two stages of DR and normal. Our extracted features are statistically significant (p<0.0001) with distinct mean±SD as shown in Table 1. These features are then used as an input to the artificial neural network (ANN) for an automatic classification. The detection results are validated by comparing it with expert ophthalmologists. We demonstrated a classification accuracy of 93%, sensitivity of 90% and specificity of 100%. © 2007 Springer Science+Business Media, LLC.Item Automatic identification of diabetic maculopathy stages using fundus images(2009) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.Diabetes mellitus is a major cause of visual impairment and blindness. Twenty years after the onset of diabetes, almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will have some degree of retinopathy. Prolonged diabetes retinopathy leads to maculopathy, which impairs the normal vision depending on the severity of damage of the macula. This paper presents a computer-based intelligent system for the identification of clinically significant maculopathy, non-clinically significant maculopathy and normal fundus eye images. Features are extracted from these raw fundus images which are then fed to the classifier. Our protocol uses feed-forward architecture in an artificial neural network classifier for classification of different stages. Three different kinds of eye disease conditions were tested in 350 subjects. We demonstrated a sensitivity of more than 95% for these classifiers with a specificity of 100%, and results are very promising. Our systems are ready to run clinically on large amounts of datasets. © 2009 Informa Healthcare USA, Inc.Item Efficient storage and transmission of digital fundus images with patient information using reversible watermarking technique and error control codes(2009) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.; Kumar, M.Handling of patient records is increasing overhead costs for most of the hospitals in this digital age. In most hospitals and health care centers, the patient text information and corresponding medical images are stored separately as different files. There is a possibility of mishandling the text file containing patient history. We are proposing a novel method for the compact storage and transmission of patient information with the medical images. In this technique, we are using a reversible watermarking technique to hide the patient information within the retinal fundus image. There is a possibility that these medical images, which carry patient information, can get corrupted by the noise during the storage or transmission. The safe recovery of patient information is important in this situation. So, to recover the maximum amount of text information in the noisy environment, the encrypted patient information is coded with error control coding (ECC) techniques. The performance of three types of ECC for various levels of salt & pepper (S & P) noise is tabulated for a specific example. The proposed system is more reliable even in a noisy environment and saves memory. © 2008 Springer Science+Business Media, LLC.Item Computer-based identification of cataract and cataract surgery efficacy using optical images(2009) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.; Faust, O.; Min, L.C.The eyes are complex sensory organs, they are designed to capture images under varying light conditions. Eye disorders, such as cataract, among the elderly are a major health problem. Cataract is a painless clouding of the eye lens which develops over a long period of time. During this time, the eyesight gradually worsens. It can eventually lead to blindness and, is common in older people. In fact, about a third of people over 65 have cataracts in one or both eyes. In this paper, we made use of two types of classifiers for identification of normal, cataract (early and developed stage), and post-cataract eyes using features extracted from optical images. These classifiers are artificial neural network and support vector machine. A database of 174 subjects, using the cross-validation strategy, is used to test the effectiveness of both classifiers. We demonstrate a sensitivity of more than 90% for both of these classifiers. Furthermore, they have a specificity of 100% and, as such, the results obtained are very promising. The proposed feature extraction and classification systems are ready clinically to run on a large amount of data sets. © 2009 World Scientific Publishing Company.