Hum Yan Chai

Multipurpose contrast enhancement on epiphyseal plates and ossification centers for bone age assessment

BackgroundThe high variations of background luminance, low contrast and excessively enhanced contrast of hand bone radiograph often impede the bone age assessment rating system in evaluating the degree of epiphyseal plates and ossification centers development. The Global Histogram equalization (GHE) has been the most frequently adopted image contrast enhancement technique but the performance is not satisfying. A brightness and detail preserving histogram equalization method with good contrast enhancement effect has been a goal of much recent research in histogram equalization. Nevertheless, producing a well-balanced histogram equalized radiograph in terms of its brightness preservation, detail preservation and contrast enhancement is deemed to be a daunting task.MethodIn this paper, we propose a novel framework of histogram equalization with the aim of taking several desirable properties into account, namely the Multipurpose Beta Optimized Bi-Histogram Equalization (MBOBHE). This method performs the histogram optimization separately in both sub-histograms after the segmentation of histogram using an optimized separating point determined based on the regularization function constituted by three components. The result is then assessed by the qualitative and quantitative analysis to evaluate the essential aspects of histogram equalized image using a total of 160 hand radiographs that are implemented in testing and analyses which are acquired from hand bone online database.ResultFrom the qualitative analysis, we found that basic bi-histogram equalizations are not capable of displaying the small features in image due to incorrect selection of separating point by focusing on only certain metric without considering the contrast enhancement and detail preservation. From the quantitative analysis, we found that MBOBHE correlates well with human visual perception, and this improvement shortens the evaluation time taken by inspector in assessing the bone age.ConclusionsThe proposed MBOBHE outperforms other existing methods regarding comprehensive performance of histogram equalization. All the features which are pertinent to bone age assessment are more protruding relative to other methods; this has shorten the required evaluation time in manual bone age assessment using TW method. While the accuracy remains unaffected or slightly better than using unprocessed original image. The holistic properties in terms of brightness preservation, detail preservation and contrast enhancement are simultaneous taken into consideration and thus the visual effect is contributive to manual inspection.

An artifacts removal post-processing for epiphyseal region-of-interest (EROI) localization in automated bone age assessment (BAA)

BackgroundSegmentation is the most crucial part in the computer-aided bone age assessment. A well-known type of segmentation performed in the system is adaptive segmentation. While providing better result than global thresholding method, the adaptive segmentation produces a lot of unwanted noise that could affect the latter process of epiphysis extraction.MethodsA proposed method with anisotropic diffusion as pre-processing and a novel Bounded Area Elimination (BAE) post-processing algorithm to improve the algorithm of ossification site localization technique are designed with the intent of improving the adaptive segmentation result and the region-of interest (ROI) localization accuracy.ResultsThe results are then evaluated by quantitative analysis and qualitative analysis using texture feature evaluation. The result indicates that the image homogeneity after anisotropic diffusion has improved averagely on each age group for 17.59%. Results of experiments showed that the smoothness has been improved averagely 35% after BAE algorithm and the improvement of ROI localization has improved for averagely 8.19%. The MSSIM has improved averagely 10.49% after performing the BAE algorithm on the adaptive segmented hand radiograph.ConclusionsThe result indicated that hand radiographs which have undergone anisotropic diffusion have greatly reduced the noise in the segmented image and the result as well indicated that the BAE algorithm proposed is capable of removing the artifacts generated in adaptive segmentation.

Performance metrics for active contour models in image segmentation

Image segmentation is one of the significant techniques in image processing to distinguish desired parts from its background for further analysis. It provides visual means for inspection of anatomical structure of human body, identification of disease, tracking of its development and input for surgical planning and simulation. Active contour models are regarded as promising and vigorously research model-based approach to computer assisted medical image analysis. However, it is not trivial to assess whether one segmentation algorithm performs more superior than the other. Therefore, a systematic assessment tool is designed and implemented to examine all the important aspects of active contour models. Meanwhile, a novel supervised evaluator including analytical method and empirical methods are proposed to acts as objective evaluator. The obtained results highlighted both the strengths and limitations of the studied active contour models. A proper area usage of each active contour model is also suggested at the end of this paper.

Improved Ultrasound Imaging for Knee Osteoarthritis Detection

Knee Osteoarthritis (OA) is most common compare to other joint OA. Ultrasound (US) imaging has a number of benefits over other medical imaging modalities. There is a significant change in the shape of cartilage due to the progression of knee OA and its associated cartilage degeneration. By using US imaging, it is possible to detect knee joint space narrowing. Nevertheless, the low contrast ratio and presence of speckle noise limit the application of US imaging. This book will present a new contrast enhancing and speckle noise reducing method which will overcome the existing limitations of US medical imaging. In this method, for contrast enhancement, optimum values of contrast, brightness and detail preservation will be considered. Most of the conventional contrast enhancing methods emphasizes only one character; in contrast, the proposed method involves establishing a separating point to segment histogram for optimal contrast, brightness and detail preservation simultaneously. Three metrics will be used in this optimization, namely Preservation of Brightness Score function (PBS), Optimum Contrast Score function (OCS), and Preservation of Detail Score function (PDS), each of which will be defined. To both reduce speckle noise and preserve edge features, anisotropic diffusion (AD) method has been improved by using a new diffusivity function and four gradient thresholds instead of one. For analyzing the performance of the proposed method, quantitative and qualitative analysis has been performed using real ultrasound images. Results prove that the proposed method out-performs other existing methods.

Elimination of character-resembling anomalies within a detected region using density-dependent reference point construction in an automated license plate recognition system

Abstract. The problem of eliminating character-resembling blobs on a detected region in the plate detection stage of an automated license plate recognition system is addressed. The proposed method amplifies the slight differences between the noncharacter blobs (anomalies) and the character blobs (true signal) to enhance the tractability. This method postulates on two propositions: (1) the anomalies are usually located around the true signal and the suspected anomalies and (2) blobs should be given less emphasis in computing a reference point. The first proposition is based on prior knowledge and observation; the second proposition is based on the fact that a reference point that takes anomalies into account is contaminated and thus misleading. The gist of the method mainly focuses on the methodology to emphasize the blobs differently in accordance to their location in computing the reference point that approximates the representative value of true signal properties more accurately, thus giving the effect of amplifying the slight differences. The performance of the method is evaluated on both its capability and consistency in solving certain types of anomalies.

Speckle noise reduction of ultrasound knee biomarker with edge and detail preservation using improved diffusivity function

Anisotropic Diffusion (AD) is a well-known method for reducing the speckle noise, especially in an ultrasound (US) image. Nonetheless, its pertinent detail preservation ability remains insufficiently robust. We propose an AD method that poses emphasis both on edge and small detail preservation during speckle noise reduction of the US image. A new diffusivity function is proposed by having simultaneous concern on edge and important detail preservation of the US image. The diffusivity function is defined with the aid of comparison and scaling on top of the method of Black et al.. Mean absolute error (MAE) stopping criterion is used for automatic stopping of the diffusion process (number of iterations). For performance evaluation of the proposed AD method, ultrasound (US) image of knee joint cartilage is adopted. Qualitative analysis is performed by using human visual perception. Different performance metrics named as peak signal to noise ratio (PSNR), figure of merits (FOM), and structure similarity index measurement (SSIM) are computed for quantitative analysis of the proposed method.

Generic computing of enhanced speckle reduction on low end ultrasound machine images

Due to the emergence of microelectronics, ultrasound diagnostic machine can now be manufactured at low cost. The affordability of low cost ultrasound diagnostic machine is of utter importance in allowing wider exposure of ultrasound technology to the general public. Nonetheless, in comparison with international standard requirements, the quality of images from low cost ultrasound machine is still lacking. Furthermore, the evaluation of the quality is subjective and the process is tedious. In this paper, an enhanced processing of ultrasound images using de-speckle diffusion method is proposed and the result is evaluated quantitatively on aspects such as vertical and horizontal distance accuracy, axial and lateral resolution, near field distance, penetration depth and high scatter accuracy. It comprises of the directions north, south, east and west, and the average is taken into calculation by utilizing the instantaneous coefficient of variation (ICOV) method. Algorithms are verified according to its performance in speckle reduction and edge preservation based on root mean square error (RMSE), signal-to-noise ratio (SNR) and peak signal-to-noise ratio (PSNR). The result indicates that de-speckle diffusion is more robust compared to adaptive speckle reduction method. The results obtained proved that the proposed technique could greatly improve the low cost ultrasound image quality.

Comparative studies of two dimensional and three dimensional ultrasonic nuchal translucency in trisomy assessments.

Current two-dimensional (2D) ultrasonic marker measurements are inherent with intra- and inter-observer variability limitations. The objective of this paper is to investigate the performance of conventional 2D ultrasonic marker measurements and proposed programmable interactive three-dimensional (3D) marker evaluation. This is essentially important to analyze that the measurement on 3D volumetric measurement possesses higher impact and reproducibility vis-à-vis 2D measurement. Twenty three cases of prenatal ultrasound examination were obtained from collaborating hospital after Ethical Committees approval. The measured 2D ultrasonic marker is Nuchal Translucency or commonly abbreviated as NT. Descriptive analysis of both 2D and 3D ultrasound measurement were calculated. Three trial measurements were taken for each method. Both data were tested with One-Sample Kolmogorov-Smirnov Test and results indicate that markers measurements were distributed normally with significant parametric values at 0.621 and 0.596 respectively. Computed mean and standard deviation for both measurement methods are 1.4495 ± 0.46490 (2D) and 1.3561 ± 0.50994 (3D). ANOVA test shows that computerized 3D measurements were found to be insignificantly different from the mean of conventional 2D at the significance level of 0.05. With Pearsons correlation coefficient value or R = 0.861, the result proves strong positive linear correlation between 2D and 3D ultrasonic measurements. Reproducibility and accuracy of 3D ultrasound in NT measurement was significantly increased compared with 2D B-mode ultrasound prenatal assessment. 3D reconstructed imaging has higher clinical values compare to 2D ultrasound images with less diagnostics information.

An object-oriented approach of generic diffusion computing for three dimensional ultrasound volumetric images

Medical image information representation using two dimensional image planes have major drawbacks on the grounds that the there are technical constrains in providing the optimized spatial orientation and physical limitations. In comparison, three dimensional imaging shows higher degree of versatility in clinical application. Conventional anisotropic diffusion and speckle removal might have promising performance on 2D ultrasonic images, but it is not effective in 3D ultrasonic images. In this paper, we have developed extension algorithms for 3D diffusion in ultrasonic volume rendering using open source visualization toolkits. Investigations have been conducted on 3D volume rendering based on visualization toolkit (VTK) generic computing and the simulation results were compared with ordinary 2D diffusion in 3D ultrasonic image. Obstructive effect was eliminated with the proposed technique by conserving information between neighboring 2D slices. The experimental results show the significant improvement of 3D diffusion on 3D ultrasound volume rendering.