Savita Gupta

A wavelet based statistical approach for speckle reduction in medical ultrasound images

A novel speckle-reduction method is introduced, based on soft thresholding of the wavelet coefficients of a logarithmically transformed medical ultrasound image. The method is based on the generalised Gaussian distributed (GGD) modelling of sub-band coefficients. The method used was a variant of the recently published BayesShrink method by Chang and Vetterli, derived in the Bayesian framework for denoising natural images. It was scale adaptive, because the parameters required for estimating the threshold depend on scale and sub-band data. The threshold was computed by Kσ/σx, where σ and σx were the standard deviation of the noise and the sub-band data of the noise-free image, respectively, and K was a scale parameter. Experimental results showed that the proposed method outperformed the median filter and the homomorphic Wiener filter by 29% in terms of the coefficient of correlation and 4% in terms of the edge preservation parameter. The numerical values of these quantitative parameters indicated the good feature preservation performance of the algorithm, as desired for better diagnosis in medical image processing.

A versatile technique for visual enhancement of medical ultrasound images

The paper presents a versatile wavelet domain despeckling technique to visually enhance the medical ultrasound (US) images for improving the clinical diagnosis. The method uses the two-sided generalized Nakagami distribution (GND) for modeling the speckle wavelet coefficients and the signal wavelet coefficients are approximated using the generalized Gaussian distribution (GGD). Combining these statistical priors with the Bayesian maximum a posteriori (MAP) criterion, the thresholding/shrinkage estimators are derived for processing the wavelet coefficients of detail subbands. Consequently, two blind speckle suppressors named as GNDThresh and GNDShrink have been implemented and evaluated on both the artificial speckle simulated images and real US images. The experimental results demonstrate the superiority of the suggested technique both quantitatively and qualitatively as compared to other competitive schemes reported in the image denoising literature, e.g., the proposed method yields a gain of more than 0.36 dB over the best state-of-the-art despeckling method (GenLik), 0.93 dB over SRAD filter, 2.35 dB over Lee filter, and 1.34 dB over Kuan filter in terms of signal-to-noise ratio, when tested on the realistic US images. The visual comparison of despeckled US images and the higher values of quality metrics (coefficient of correlation, edge preservation index, quality index, and structural similarity index) indicate that the new method suppresses the speckle noise well while preserving the texture and organ surfaces. Further, the proposed method will be evaluated on other class of images as well as by employing multiple observer evaluation.

Robust non-homomorphic approach for speckle reduction in medical ultrasound images

Most existing wavelet-based image denoising techniques are developed for additive white Gaussian noise. In applications to speckle reduction in medical ultrasound (US) images, the traditional approach is first to perform the logarithmic transform (homomorphic processing) to convert the multiplicative speckle noise model to an additive one, and then the wavelet filtering is performed on the log-transformed image, followed by an exponential operation. However, this non-linear operation leads to biased estimation of the signal and increases the computational complexity of the filtering method. To overcome these drawbacks, an efficient, non-homomorphic technique for speckle reduction in medical US images is proposed. The method relies on the true characterisation of the marginal statistics of the signal and speckle wavelet coefficients. The speckle component was modelled using the generalised Nakagami distribution, which is versatile enough to model the speckle statistics under various scattering conditions of interest in medical US images. By combining this speckle model with the generalised Gaussian signal first, the Bayesian shrinkage functions were derived using the maximum a posteriori (MAP) criterion. The resulting Bayesian processor used the local image statistics to achieve soft-adaptation from homogeneous to highly heterogeneous areas. Finally, the results showed that the proposed method, named GNDShrink, yielded a signal-to-noise ratio (SNR) gain of 0.42 dB over the best state-of-the-art despeckling method reported in the literature, 1.73 dB over the Lee filter and 1.31 dB over the Kaun filter at an input SNR of 12.0 dB, when tested on a US image. Further, the visual comparison of despeckled US images indicated that the new method suppressed the speckle noise well, while preserving the texture and organ surfaces.

Image Recognition using Coefficient of Correlation and Structural SIMilarity Index in Uncontrolled Environment

The goal of this paper is to analyse and improve the performance of metrics like Coefficient of Correlation (CoC) and Structural Similarity Index (SSIM) for image recognition in real-time environment. The main novelties of the methods are; it can work under uncontrolled environment and no need to store multiple copies of the same image at different orientations. The values of CoC and SSIM get changed if images are rotated or flipped or captured under bad/highly illuminated conditions. To increase the recognition accuracy, the input test image is pre-processed. First, discrete wavelet transform is applied to recognize the image captured under bad illuminated and dull lightning conditions. Second, to make the method rotation invariant, the test image is compared against the stored database image without and with rotations in the horizontal, vertical, diagonal, reverse diagonal and flipped directions. The image recognition performance is evaluated using the Recognition Rate and Rejection Rate. The results indicate that recognition performance of Correlation Coefficient and SSIM gets improved with rotations and discrete wavelet transform. Also it was observed that CoC with proposed modifications yield better results as compared to state of the art enhanced Principal Component Analysis and Enhanced Subspace Linear Discriminant Analysis. Keywords—Image Recognition, Discrete Wavelet Transforms, Correlation Coefficient, Structural Similarity Index Metrics.

Performance Improvement of Fuzzy C-mean Algorithm for Tumor Extraction in MR Brain Images

Aim of this paper is to develop an efficient fuzzy c-mean based segmentation algorithm to extract tumor region from MR brain images. First, cluster centroids are initialized through data analysis of tumor region, which optimizes the standard fuzzy cmean algorithm. Next, reconstruction based morphological operations are applied to enhance its performance for brain tumor extraction. The results show that simple fuzzy c-mean could not segment the region of interest properly, whereas enhanced algorithm effectively extracts the tumor region. From comparison with existing segmentation methods, enhanced fuzzy c-mean algorithm emerges as the most effective algorithm for extracting region of interest.

Modified spatial neutrosophic clustering technique for boundary extraction of tumours in B-mode BUS images

Breast ultrasound (BUS) images are of poor quality, contain inherent noise and shadow regions. Consequently, the task of tumour segmentation from these images becomes more difficult. In this study, a modified spatial neutrosophic clustering technique has been proposed for automatic boundary extraction of tumours in B-mode BUS images. The contributions of the work are two-fold: (i) spatial information is incorporated in the neutrosophic l -means (NLM) clustering method for better cluster formation and (ii) membership values are updated by using type-2 membership function, which helps in converging the cluster centres to more desirable locations than ordinary fuzzy membership functions. BUS images with manually marked lesions by an experienced radiologist have been used as gold standard/reference images for quantitative comparison. The proposed method has been applied to 60 BUS images and results are recorded in the form of area and boundary error metrics. The performance of the proposed method has been compared with the region growing, fuzzy c-means clustering, watershed segmentation, neutrosophic c-means clustering and NLM clustering methods. From the quantitative and visual results, it has been observed that the proposed method can extract the tumour boundaries more precisely as compared with the other state-of-the-art clustering techniques.