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

Bounded-abstaining classification for breast tumors in imbalanced ultrasound images

Guan Hongjiao, Zhang Yingtao, Cheng Heng-Da, Tang Xianglong

International Journal of Applied Mathematics and Computer Science

|

2020

|

Vol. 30, no. 2

325--336

EN

Computer-aided breast ultrasound (BUS) diagnosis remains a difficult task. One of the challenges is that imbalanced BUS datasets lead to poor performance, especially with regard to low accuracy in the minority (malignant tumor) class. Missed diagnosis of malignant tumors can cause serious consequences, such as delaying treatment and increasing the risk of death. Moreover, many diagnosis methods do not consider classification reliability; thus, some classifications may have a large uncertainty. To resolve such problems, a bounded-abstaining classification model is proposed. It maximizes the area under the ROC curve (AUC) under two abstention constraints. A total of 219 (92 malignant and 127 benign) BUS images are collected from the First Affiliated Hospital of Harbin Medical University, China. The experiment tests BUS datasets of three imbalance levels, and the performance contours are analyzed. The results demonstrate that AUC-rejection curves are less affected by class imbalance than accuracy-rejection curves. Compared with the state-of-the-art, the proposed method yields a significantly larger AUC and G-mean using imbalanced BUS datasets.

3

Numerical prediction of breast skin temperature based on thermographic and ultrasonographic data in healthy and cancerous breasts

Korczak Ilona, Romowicz Agnieszka, Gambin Barbara, Palko Tadeusz, Kruglenko Eleonora, Dobruch-Sobczak Katarzyna

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 4

1680--1692

EN

Breast cancer is one of the most common women's cancers, so an available diagnostic modality, particularly non-invasive, is important. Infrared thermography (IRT) is a supporting diagnostic modality. Until now, many finite element methods (FEM) numerical models have been constructed to evaluate IRT's diagnostic value and to relate breast skin temperature characteristics with breast structural disorder presence, particularly to distinguish between cancerous types and normal structures. However, most of the models were not based on any clinical data, except for several papers based on clinical magnetic resonance imaging (MRI) data, wherein a three-dimensional (3D) breast model was studied. In our paper, we propose a very simplified numerical two-dimensional FEM model constructed based on clinical ultrasound data of breasts, which is much cheaper and available in real-time as opposed to MRI data. We show that our numerical simulations enabled us to distinguish between types of healthy breasts in agreement with the clinical classification and with thermographic results. The numerical breast models predicted the possibility of differentiation of cancerous breasts from healthy breasts by significantly different skin temperature variation ranges. The thermal variations of cancerous breasts were in the range of 0.5 °C–3.0 °C depending on the distance of the tumor from the skin surface, its size, and the cancer type. The proposed model, due to its simplicity and the fact that it was constructed based on clinical ultrasonographic data, can compete with the more sophisticated 3D models based on MRI.

4

Effect of despeckle filtering on classification of breast tumors using ultrasound images

Kriti, Virmani Jitendra, Agarwal Ravinder

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 2

536--560

EN

Ultrasound is the most widely used imaging modality for screening of breast tumors. However, due to the presence of speckle noise in an ultrasound image, the diagnostic information gets masked and the interpretation of the breast abnormalities becomes difficult for the radiologist. The texture of the tumor region and the shape/margin characteristics are considered to be important parameters for the analysis of the breast tumors. In the present work, exhaustive experimentation has been carried out for the design of CAD systems for classification of breast tumors by considering (a) original images only, (b) despeckled images only and (c) both original and despeckled images together (hybrid approach). Total 100 breast ultrasound images (40 benign and 60 malignant) have been used for the analysis. Initially, these images have been despeckled using six filters namely Lee sigma, BayesShrink, DPAD, FI, FB and HFB filters. Total 162 features (149 texture and 13 morphological features) have been computed from both original and despeckled breast ultrasound images and SVM classifier has been used extensively for the classification. The results of the study indicate that the hybrid approach of CAD system design using texture features computed from original images combined with morphological features computed from images despeckled by DPAD filter yield optimal performance for classifica-tion of benign and malignant breast tumors with a classification accuracy of 96.0%. From the promising results of the study it can be concluded that the proposed hybrid CAD system design could be used as a second opinion tool in clinical setting.

5

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.

6

Detekcja mikrokalcyfikacji w obrazowaniu ultrasonograficznym piersi nowe możliwości?

Fischer T., Thomas A., Rudolph B.

Acta Bio-Optica et Informatica Medica. Inżynieria Biomedyczna

|

2009

|

Vol. 15, nr 3

278-279

PL

Głównym wyzwaniem diagnostyki ultrasonograficznej piersi jest szybka ocena zmian wykrytych metodą palpacyjną. Jednym z najpoważniejszych problemów klinicznych, w znaczny sposób utrudniających prowadzenie badań, jest występujące, szczególnie u młodych kobiet, zjawisko wzmożonej gęstości sutka. Prace nad optymalizacją urządzeń wspomagających ocenę tych zmian zaowocowały opracowaniem technologii ultrasonograficznych wysokiej rozdzielczości, które w znaczny sposób poprawiły jakość otrzymywanych obrazów, rozpoznawalność detali oraz ich rozdzielczość przestrzenną. Obrazowanie harmoniczne tkanek THI (tissue harmonie imaging) oraz jednoczesne skanowanie wiązki ultradźwiękowej w różnych płaszczyznach oraz różnej charakterystyce częstotliwościowej FC (spatial/ freąuency compounding) umożliwiają wizualizację nawet najmniejszych zmian patologicznych w obrębie tkanek [A. Thomas i in., Ultraschall in Med, 2007,28, s. 387-393].