Linear models of cumulative distribution function for content-based medical image retrieval.

We propose an Image matching technique based on Cumulative Distribution Function, which provides a considerable reduction in the retrieval time. The two novel approaches called bit plane histogram and hierarchical bit plane histogram are discussed. Next, the image matching technique based on Cumulative Distribution Function is explained and a comparison of the various techniques is brought out. The CDF of the query and the images in the database are approximated by piecewise linear models with two parameters, slope and intercept at various grayscale intervals. The contiguous set of lines approximating the CDFs enables us to compare the query image and the images in the database with corresponding estimated slopes and intercepts. As the dynamic range of CDF is from 0 to 1, images of different sizes can be compared. Approximation of CDFs with lines further reduces the dimension of the image features and thus improves the speed of matching.

Linear models of cumulative distribution function for content based medical image retrieval.

We propose an Image matching method based n Cumulative Distribution Function (CDF). The CDF f the query and database Images are approximated by piecewise linear models with two parameters, slope and intercept at various grayscale intervals. The equations solving the least squares line fitting algorithm are very simple to form, due to closed form expressions The contiguous set of lines approximating the CDFs enables us to compare query and database images with corresponding estimated slopes and intercepts. As the dynamic range f CDF is from 0 to 1, images of different sizes can be compared. Approximation of CDFs with lines further reduces the dimension f the image features and thus improves the speed f matching. Also, the monotonically increasing CDF is well suited for approximations with lines. Resolving the CDF with lines f different lengths recasts the matching to a hierarchical methodology.

Simultaneous storage of patient information with medical images in the frequency domain.

Digital watermarking is a technique of hiding specific identification data for copyright authentication. Most of the medical images are compressed by joint photographic experts group (JPEG) standard for storage. The watermarking is adapted here for interleaving patient information with medical images during JPEG compression, to reduce storage and transmission overheads. The text data is encrypted before interleaving with images in the frequency domain to ensure greater security. The graphical signals are also interleaved with the image. The result of this work is tabulated for a specific example and also compared with the spatial domain interleaving.

Comprehensive visualization of cardiac health using electrocardiograms.

A novel visualization technique for voluminous ECG data acquired over several hours is presented. The classified data is displayed in a sector graph, with a menu driven hierarchical display strategy, which progressively unfolds greater details for chosen intervals. A color code is employed to identify different types of abnormalities. Provision is made for fine tuning the classification.

Compact storage of medical images with patient information.

Digital watermarking is a technique of hiding specific identification data for copyright authentication. This technique is adapted here for interleaving patient information with medical images to reduce storage and transmission overheads. The text data are 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, and encryption and results are tabulated for a specific example.

System identification for the ECG using CZT.

A new approach for extraction of clinically useful parameters from the ECG signal is presented using the system identification technique of CZT on the DCT-transformed signal. A one to one relationship between the model singularities and the significant points in the time signal is arrived at. The method allows the determination of R-R interval needed in rhythm analysis. The complex cepstrum is used for identifying and removing the effect of zeros outside the unit circle. A significant data compression of 1 in 10 is achieved. A large number of continuous strips of ECG data are analyzed and the results are presented.

Component wave delineation of ECG by filtering in the Fourier domain.

A complete solution to the fundamental problem of delineation of an ECG signal into its component waves by filtering the discrete Fourier transform of the signal is presented. The set of samples in a component wave is transformed into a complex sequence with a distinct frequency band. The filter characteristics are determined from the time signal itself. Multiplication of the transformed signal with a complex sinusoidal function allows the use of a bank of low-pass filters for the delineation of all component waves. Data from about 300 beats have been analysed and the results are highly satisfactory both qualitatively and quantitatively.

Decomposition of ECG by linear filtering.

A simple method is developed for the delineation of a given electrocardiogram (ECG) signal into its component waves. The properties of discrete cosine transform (DCT) are exploited for the purpose. The transformed signal is convolved with appropriate filters and the component waves are obtained by computing the inverse transform (IDCT) of the filtered signals. The filters are derived from the time signal itself. Analysis of continuous strips of ECG signals with various arrhythmias showed that the performance of the method is satisfactory both qualitatively and quantitatively. The small amplitude P wave usually had a high percentage rms difference (PRD) compared to the other large component waves.