Wyniki wyszukiwania - BazTech

1

A method for segmentation of tumors in breast ultrasound images using the variant enhanced deep learning

Ilesanmi Ademola Enitan, Chaumrattanakul Utairat, Makhanov Stanislav S.

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

802--818

EN

Background: Breast cancer is a deadly disease responsible for statistical yearly global death. Identification of cancer tumors is quite tasking, as a result, concerted efforts are thus devoted. Clinicians have used ultrasounds as a diagnostic tool for breast cancer, though, poor image quality is a major limitation when segmenting breast ultrasound. To address this problem, we present a semantic segmentation method for breast ultrasound (BUS) images. Method: The BUS images were resized and then enhanced with the contrast limited adaptive histogram equalization method. Subsequently, the variant enhanced block was used to encode the preprocessed image. Finally, the concatenated convolutions produced the segmentation mask. Results: The proposed method was evaluated with two datasets. The datasets contain 264 and 830 BUS images respectively. Dice measure (DM), Jaccard measure, and Hausdroff distance were used to evaluate the methods. Results indicate that the proposed method achieves high DM with 89.73% for malignant and 89.62% for benign BUSs. Moreover, the results obtained validate the capacity of the proposed method to achieve higher DM in comparison with reported methods. Conclusion: The proposed algorithm provides a deep learning segmentation procedure that can segment tumors in BUS images effectively and efficiently.

2

Speckle noise reduction and image segmentation based on a modified mean filter

Arulpandy P., Trinita-Pricilla M.

Computer Assisted Methods in Engineering and Science

|

2020

|

Vol. 27, no. 4

221--239

EN

Image segmentation is an essential process in many fields involving digital images. In gen-eral, segmentation is the process of dividing the image into objects and background image.Image segmentation is an important step in the object detection process. It becomes morecritical if a given image is corrupted by noise. Most digital images are corrupted by noisessuch as salt and pepper noise, Gaussian noise, Poisson noise, speckle noise, etc. Specklenoise is a multiplicative noise that affects pixels in a gray-scale image, and mainly occursin low level luminance images such as Synthetic Aperture Radar (SAR) images and Mag-netic Resonance Image (MRI) images. Image enhancement is an essential task to reducespecklenoise prior to performing further image processing such as object detection, imagesegmentation, edge detection, etc. Here, we propose a neighborhood-based algorithm toreduce speckle noise in gray-scale images. The main aim of the noise reduction technique isto segment the noisy image. So that the proposed algorithm applies some luminance to theoriginal image. The proposed technique performs well at maximum noise variance. Finally,the segmentation process is done by the modified mean filter. The proposed technique hasthree phases. In phase 1, the speckle noise is reduced and the contrast adjustment is made.In phase 2, the segmentation of the enhanced image is processed. Finally, in phase 3, theisolated pixels in the segmented image are eliminated and the final segmented image isgenerated. This technique does not require any threshold value to segment the image; itwill be automatically calculated based on the mean value.

3

Assessment of despeckle filtering algorithms for segmentation of breast tumours from ultrasound images

Kriti, Virmani Jitendra, Agarwal Ravinder

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 1

100--121

EN

In the present work, the performance assessment of despeckle filtering algorithms has been carried out for (α) noise reduction in breast ultrasound images and (b) segmentation of benign and malignant tumours from breast ultrasound images. The despeckle filtering algorithms are broadly classified into eight categories namely local statistics based filters, fuzzy filters, Fourier filters, multiscale filters, non-linear iterative filters, total variation filters, non-local mean filters and hybrid filters. Total 100 breast ultrasound images (40 benign and 60 malignant) are processed using 42 despeckle filtering algorithms. A despeckling filter is considered to be appropriate if it preserves edges and features/structures of the image. Edge preservation capability of a despeckling filter is measured by beta metric (β) and feature/structure preservation capability is quantified using image quality index (IQI). It is observed that out of 42 filters, six filters namely Lee Sigma, FI, FB, HFB, BayesShrink and DPAD yield more clinically acceptable images in terms of edge and feature/structure preservation. The qualitative assessment of these images has been done on the basis of grades provided by the experienced participating radiologist. The pre-processed images are then fed to a segmentation module for segmenting the benign or malignant tumours from ultrasound images. The performance assessment of segmentation algorithm has been done quantitatively using the Jaccard index. The results of both quantitative and qualitative assessment by the radiologist indicate that the DPAD despeckle filtering algorithm yields more clinically acceptable images and results in better segmentation of benign and malignant tumours from breast ultrasound images.

4

Digital processing of speckle images in special optical-electronic devices

Pau V., Cretu E.

Elektronika : konstrukcje, technologie, zastosowania

|

2004

|

Vol. 45, nr 8-9

296-298

EN

A digital model of an image with speckle noise was constructed and verified by comparison to optically generated images with speckle noise, captured by image intensifier and image acquisition optical-electronics devices. The model was then used to obtain g technique of image based on statistical properties of speckle noise and to evaluate several digital-filtering techniques applied on the same set of images.

PL

Zbudowany zostal cyfrowy model obrazu z szumem plamkowym, który zweryfikowano przez porównanie z wygenerowanymi na drodze optycznej obrazami z szumem plamkowym, zapisanymi za pomocą optoelektronicznych urządzeń do wzmacniania oraz akwizycji obrazu. Model wykorzystano do uzyskania dyskretnej techniki filtrowania obrazu bazującej na statystycznych własnościach szumu plamkowego oraz do oceny kilku technik cyfrowego filtrowania, zastosowanych do tego samego zbioru obrazów.