Content based medical image retrieval based on new efficient local neighborhood wavelet feature descriptor

This paper presents a new class of local neighborhood based wavelet feature descriptor (LNWFD) for content based medical image retrieval (CBMIR). To retrieve images effectively from large medical databases is backbone of diagnosis. Existing wavelet transform based medical image retrieval methods suffer from high length feature vector with confined retrieval performance. Triplet half-band filter bank (THFB) enhanced the properties of wavelet filters using three kernels. The influence of THFB has employed in the proposed method. First, triplet half-band filter bank (THFB) is used for single level wavelet decomposition to obtain four sub-bands. Next, the relationship among wavelet coefficients is exploited at each sub-band using 3 × 3 neighborhood window to form LNWFD pattern. The novelty of the proposed descriptor lies in exploring relation between wavelet transform values of pixels rather than intensity values which gives more detail local information in wavelet sub-bands. Thus, proposed feature descriptor is robust against illumination. Manhattan distance is used to compute similarity between query feature vector and feature vector of database. The proposed method is tested for medical image retrieval using OASIS-MRI, NEMA-CT, and Emphysema-CT databases. The average retrieval precisions achieved are 71.45%, 99.51% of OASIS-MRI and NEMA-CT databases for top ten matches considered respectively and 55.51% of Emphysema-CT database for top 50 matches. The superiority in terms of performance of the proposed method is confirmed by the experimental results over the well-known existing descriptors.

A wavelet-based method for power-line interference removal in ECG signals

Abstract Introduction The analysis of electrocardiogram (ECG) signals allows the experts to diagnosis several cardiac disorders. However, the accuracy of such diagnostic depends on the signals quality. In this paper it is proposed a simple method for power-line interference (PLI) removal based on the wavelet decomposition, without the use of thresholding techniques. Methods This method consists in identifying the ECG and noise frequency range for further zeroing wavelet detail coefficients in the subbands with no ECG coefficients in the frequency content. Afterward, the enhanced ECG signal is obtained by the inverse discrete wavelet transform (IDWT). In order to choose the wavelet function, several experiments were performed with synthetic signals with worse Signal-to-Noise Ratio (SNR). Results Considering the relative error metrics and runtime, the best wavelet function for denoising was Symlet 8. Twenty synthetic ECG signals with different features and eight real ECG signals, obtained in the Physionet Challenge 2011, were used in the experiments. Results show the advantage of the proposed method against thresholding and notch filter techniques, considering classical metrics of assessment. The proposed method performed better for 75% of the synthetic signals and for 100% of the real signals considering most of the evaluation measures, when compared with a thresholding technique. In comparison with the notch filter, the proposed method is better for all signals. Conclusion The proposed method can be used for PLI removal in ECG signals with superior performance than thresholding and notch filter techniques. Also, it can be applied for high frequencies denoising even without a priori frequencies knowledge.

The time-dependent evolution spectrum of acute care surgery patients: a real world study based on 23 795 electronic admission medical records / 中华急诊医学杂志

Objective One of the major challenges to emergency department is to provide high quality and time sensitive service under limitation of human/material resources,along with patients population with extremely complex conditions.We presented a study that based on a big data got from real world and used wavelet transform technique to analyze time-dependent diseases spectrum patterns and evolution patterns,which will provide solid methodological support for optimizing resources configuration for acute care surgery service.Methods Record data of patients admitted to acute care surgery from 2007-2014 were collected by using data management tool (Avaintec,Helsinki,Finland).The data were cleansed and were transformed to continuing spectrum according to time series of admission time points (per 9 hours).Matlab was used for wavelet transform,and applied five levels of wavelet decomposition and calculated the best decomposition levels by K-mean algorithm for each level.Then we used aprori algorithm for data mining (frequent patterns mining).Results A total of 23 795 cases were enrolled and acute abdomens were made up biggest proportion of admission.Meanwhile,it is found that the spectrum of acute care surgery admission frequency was a complex rising sequence.After wavelet decomposition,signal wave A reflexed trends evolution in a given time scale,and noise wave D reflexed minutia at relevant time scale.In another words,a principal wave A1 represented fluctuation at a cycle of 16 days.Noise wave D1 reflected intensity level in this 16 days' cycle.For example,the 5 · 12 episodes of massive earthquake in 2008 were included in the study,it is found that a significant noise wave at D3 level that indicated a 4 days' cycle.Clinically,it indicated explosive admissions to acute care surgery in 4 days.Conclusions The admission spectrum to acute care surgery is a phenomenon of multi-scale.Based on wavelet decomposing,we can easily analyze the rule of admission spectrum from electronic records of patients and can be used for optimization the emergency medicine resources.