Ultrasound image denoising using a combination of bilateral filtering and stationary wavelet transform

Moussa, Olfa; Khlifa, Nawrès

doi:10.1109/ipas.2014.7043258

Cited by 14 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, combination of algorithms is prevalently adopted in denoising ultrasound images. For example, an optimization algorithm cascaded with Weiner filter in [11], combination of wavelet and enhanced Kuan filter in [12], and combination of wavelet and bilateral filter in [13]. Most of the despeckling algorithms have certain demerits that has to be addressed.…”

Section: Related Workmentioning

confidence: 99%

A Comparison on Speckle Noise Suppression Algorithm for Intravascular Ultrasound (Ivus) Images

Archana¹,

Vanithamani²

2021

INDJCSE

View full text Add to dashboard Cite

Accurate and reliable diagnosis of carotid artery stenosis depends on the quality of IVUS images. Especially in ultrasound images where coherent sources are involved, speckle noise causes blurring and loss of information. Thus, methods to eliminate speckle noise plays an essential part in the field of medical imaging. This paper compares various speckle noise suppression algorithms for carotid artery ultrasound images. Speckle noise reduction algorithms that are implemented includes Homomorphic Wavelet Level 1 and Level 2, Perona-Malik (PM) filter, Modified PM1, Modified PM2, Adaptive PM, Butterworth Filter, Doubly Degenerative Diffusion (DDD), Speckle Reducing Anisotropic Diffusion (SRAD) and Total Variance (TV) filter. A quantitative evaluation is carried out by estimating Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Beta Metric and Natural Image Quality Evaluator (NIQE). The performance metrics shows that Homomorphic Wavelet Level1, Modified PM 2, Adaptive PM and SRAD are robust in eliminating speckle noise from carotid artery ultrasound images, thereby increasing its diagnostic accuracy. Though DDD and TV approach have good SNR and PSNR values, their low Beta metric and high NIQE values have made them ineffective.

show abstract

Section: Related Workmentioning

confidence: 99%

A Comparison on Speckle Noise Suppression Algorithm for Intravascular Ultrasound (Ivus) Images

Archana¹,

Vanithamani²

2021

INDJCSE

View full text Add to dashboard Cite

show abstract

“…The bilateral filter is a nonlinear filter with a combination of two Gaussian filters used to smooth images (Tomasi and Manduchi, 1998;Olfa and Nawres, 2014). The first filter works in the spatial domain and the next works in the intensity domain (Mohan and Sheeba, 2013).…”

Section: Preprocessingmentioning

confidence: 99%

Detection of Pulmonary Nodules in ct Images Using Deep Learning Technique

Balachandran¹,

Divya²,

Rajendran³

et al. 2020

Journal of Computer Science

View full text Add to dashboard Cite

Lung Cancer is one of the most deadly diseases worldwide. According to the American Cancer Society, about 234,030 peoples have been suffering from lung cancer. It can be cured if it is diagnosed earlier which decreases the death rate. A computational diagnostic tool named Computer Aided Diagnosis (CAD) is used to detect pulmonary nodules. Extensive work has been made in this domain. However, previous Computer Aided Diagnosis (CAD) system are time-consuming since they needed more modules such as image modification, segmentation and the features should be extracted by the domain experts to build the entire CAD system. It is hard to examine large data using the existing CAD system. Thus, a novel framework with a Convolutional Neural Network (CNN) to detect pulmonary nodule is proposed. Firstly, a preprocessing technique named bilateral filtering is applied to increase the image quality and remove the irrelevant noise from the Computer Tomography (CT) images. Secondly, the preprocessed data are trained into a convolutional neural network to detect the nodule and classify it. The performance of this system is validated using the Lung Image Database Consortium (LIDC) dataset. The accuracy of nodule candidate detection achieves 93%. It states that the proposed method achieves better accuracy in nodule detection.

show abstract

“…It is a non-linear filter where the output is a weighted average of the input. The output of the bilateral filter for a pixel s is defined as follows: [7] ( ) ( ) ∑( )( ) Where k(s) is a normalization term:…”

Section: Bilateral Filteringmentioning

confidence: 99%