Showing papers in "Journal of Medical Imaging and Health Informatics in 2015"

Multiple Watermarking on Medical Images Using Selective Discrete Wavelet Transform Coefficients

Abstract: This paper presents a new spread-spectrum based secure multiple watermarking scheme on medical images in wavelet transform domain by using selective discrete wavelet transform (DWT) coefficients for embedding. The proposed algorithm is applied for embedding text watermarks like patient identification/source identification represented in binary arrays using ASCII code and doctor’s signature or telemedicine centre name represented in binary image format into host digital radiological image for potential telemedicine applications. The algorithm is based on secure spread-spectrum technique where pseudo-noise (PN) sequences are generated corresponding to each watermarking bit and embedding of these sequences is done column wise into the selected DWT coefficients in the subband. Selection of DWT coefficient for embedding is done by thresholding the coefficient values present in that column. In the embedding process, the cover image is decomposed at second level DWT. The image and text watermark is embedded into the selective coefficients of the first level and second level DWT respectively. In order to enhance the robustness of text watermarks like patient identity code, error correcting code (ECC) is applied to the ASCII representation of the text watermark before embedding. Results are obtained by varying the gain factor, subband decomposition levels, size of watermark, and medical image modalities. Performace of the proposed watermarking algorithm is analyzed against numerous known attacks like compression, filtering, noise, sharpening, scaling and histogram equalization and desired outcome is obtained without much degradation in extracted watermarks and watermarked image quality. The method is compared with other reported techniques and has been found to be giving superior performance for robustness and imperceptibility suggested by other authors.

Automated Classification of Depression Electroencephalographic Signals Using Discrete Cosine Transform and Nonlinear Dynamics

Abstract: Depression is a mental disorder that affects emotional and physical state of a person. It is a state of extreme sadness and dejection. The electroencephalographic (EEG) signals can be used to detect the alterations in the brain’s electrochemical potential. The highly irregular and complex EEG signal variations can be determined by different processing tools. The present work is based on the automated classification of the normal and depression EEG signals. The discrete cosine transform (DCT) decomposes the normal and depression EEG signals into different frequency sub-bands. Nonlinear methods such as sample entropy, correlation dimension, fractal dimension, largest Lyapunov exponent, Hurst exponent and detrended fluctuation analysis are applied to the DCT coefficients and the extracted characteristic features are ranked using t-value. These significant features are fed to decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN) and naive Bayes (NB) classifiers. Five significant features are selected and the SVM classifier with radial basis function (RBF) results in a classification accuracy of 93.8%, sensitivity of 92% and specificity of 95.8%.

Evaluation of Quality of Service in Smart-Hospital Communications

Abstract: This work was supported by Spanish Government MEC Project TIN2013-47272-C2-1-R and by ITACA (Universitat Politecnica de Valencia).

Automatic Landmark Identification in Lateral Cephalometric Images Using Optimized Template Matching

Abstract: Cephalometric analysis has long helped researchers and orthodontic practitioners for evaluation of facial growth, understanding facial morphology and its ethnic variations, orthodontic diagnosis and treatment planning for patients presenting with malocclusion and dentofacial deformities. Mostly, inaccuracy in cephalometric measurements is a reflection of errors in identification and accurate localization of anatomical landmarks. The accuracy of landmark identification is greatly influenced by knowledge of the operator and experience. Moreover, the process of manual detection is tedious and time consuming. Therefore, a need for development of robust and accurate algorithms for automatic detection of landmarks on cephalometric images has been comprehended. In this work, we hereby propose an optimized template matching (OTM) algorithm which could automatically localize hard and soft tissue anatomical landmarks on lateral cephalometric images. This algorithm was tested for sixteen hard and eight soft tissue landmarks chosen in 12 regions on 37 lateral cephalograms obtained from subjects of either sex covering wide spectrum of malocclusion cases. The results of proposed automatic algorithm were compared to that of manual marking conducted by three experienced orthodontic specialists. All the 24 landmarks (100%) were detected within 3.0 mm error range of manual marking, 23 (96%) were detected within 2.5 mm error range and 16 (66.6%) landmarks were detected within 2.0 mm error range. The optimized template matching (OTM) algorithm may prove to be a promising approach in automatic detection of anatomical landmarks on cephalometric images.