Wyniki wyszukiwania - BazTech

1

Simultaneous detection and diagnosis of mammogram mass using bilateral analysis and soft label based metric learning

Ma Yingran, Peng Yanjun

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

215--232

EN

In the clinics, mammogram masses appear as asymmetric structures between the left and right breasts. In this paper, we design a bilateral image analysis method based on convolutional neural network which can detect and classify breast mass regions simultaneously. It mainly consists of three parts: a feature similarity based region matching technique, mass region of interest (ROI) selection step and a deep metric learning based classifier. Firstly, discriminative score maps are calculated relied on the deep features extracted from bilateral left and right mammograms respectively in global or local spatial image domain. The contralateral correspondences are determined by minimum discriminative scores. Secondly, to select the mass candidate ROIs and further remove false positive mass-tonormal pairs, we propose a dynamic histogram weighting mechanism with three new constrains imposed on the distribution of discriminative score histogram. In addition, a novel soft label based deep metric learning regularization is designed for mass ROI classifier to tackle the large variation of masses in shape, size, texture and breast density. We apply it to the open dataset Digital Database for Screening Mammography. Compared with other state-of-the-art approaches, the proposed scheme gives competitive results in classification and localization tasks for mammographic lesions.

2

Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention

Yan Yutong, Conze Pierre-Henri, Quellec Gwenolé, Lamard Mathieu, Cochener Beatrice, Coatrieux Gouenou

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

746--757

EN

Mammography is the primary imaging modality used for early detection and diagnosis of breast cancer. X-ray mammogram analysis mainly refers to the localization of suspicious regions of interest followed by segmentation, towards further lesion classification into benign versus malignant. Among diverse types of breast abnormalities, masses are the most important clinical findings of breast carcinomas. However, manually segmenting breast masses from native mammograms is time-consuming and error-prone. Therefore, an integrated computer-aided diagnosis system is required to assist clinicians for automatic and precise breast mass delineation. In this work, we present a two-stage multiscale pipeline that provides accurate mass contours from high-resolution full mammograms. First, we propose an extended deep detector integrating a multi-scale fusion strategy for automated mass localization. Second, a convolutional encoder-decoder network using nested and dense skip connections is employed to fine-delineate candidate masses. Unlike most previous studies based on segmentation from regions, our framework handles mass segmentation from native full mammograms without any user intervention. Trained on INbreast and DDSM-CBIS public datasets, the pipeline achieves an overall average Dice of 80.44% on INbreast test images, outperforming state-of-the-art. Our system shows promising accuracy as an automatic full-image mass segmentation system. Extensive experiments reveals robustness against the diversity of size, shape and appearance of breast masses, towards better interaction-free computer-aided diagnosis.

3

Automatic detection of microcalcification based on morphological operations and structural similarity indices

Touil Asma, Kalti Karim, Conze Pierre-Henri, Solaiman Basel, Mahjoub Mohamed Ali

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1155--1173

EN

In this paper, a new method for automatic detection of microcalcifications in digitized mammograms is proposed. Based on mathematical morphology theory to deal with the problem of low contrast between microcalcifications and their surrounding pixels, it uses various structuring elements of different sizes to reduce the sensibility to microcalcification diversity sizes. The obtained morphological results are converted to a suspicion map based on an image quality assessment metric called structural similarity index (SSIM). This continuous map is, then, locally analyzed using superpixels to automatically estimate threshold values and finally detect potential microcalcification areas. The proposed method was evaluated using the publiclyavailable INBreast dataset. Experimental results show the benefits gained in terms of improving microcalcification detection performances compared to state-of-the-art methods.

4

Obrazowanie gruczołu piersiowego ze stymulatorami serca

Sobczyk J., Gaweł G., Pusz-Sapa A., Przypek A., Król M., Babiarz E., Stępień S., Jachymek S.

Inżynier i Fizyk Medyczny

|

2018

|

Vol. 7, nr 1

57--60

PL

Początki implantacji stymulatorów serca sięgają późnych lat 50. XX wieku. Od tamtej pory odnotowano ogromny postęp w tej dziedzinie, a z roku na rok rośnie liczba osób z wszczepioną aparaturą do elektrostymulacji serca. Choć urządzenia te nie ograniczają znacząco życia pacjenta, mogą pojawić się trudności podczas badań diagnostycznych. Uwagę zwracają badania obrazowe gruczołu piersiowego u kobiet z wszczepionym stymulatorem serca. Rozważając bezpieczeństwo wykonywania badań u takich pacjentek, należy wziąć pod uwagę umiejscowienie stymulatora, źródła energii w poszczególnych badaniach oraz technikę ich wykonania.

EN

The beginning of pacemakers implantation dates back to the late 1950s. Since then, great progress has been made in this area and the number of people with implanted cardiac electro-stimulation devices is growing every year. Although these devices do not significantly constrain the patient’s life, difficulties may arise during diagnostic tests. Attention is drawn to the imaging of the breast gland of women with an implanted cardiac pacemaker. Considering the safety of tests performance on such patients – the location of the pacemaker, the source of energy in individual studies and the technique of their implementation, should be taken into account.

5

Deep learning versus classical neural approach to mammogram recognition

Kurek J., Świderski B., Osowski S., Kruk M., Barhoumi W.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 6

831--840

EN

Automatic recognition of mammographic images in breast cancer is a complex issue due to the confusing appearance of some perfectly normal tissues which look like masses. The existing computer-aided systems suffer from non-satisfactory accuracy of cancer detection. This paper addresses this problem and proposes two alternative techniques of mammogram recognition: the application of a variety of methods for definition of numerical image descriptors in combination with an efficient SVM classifier (so-called classical approach) and application of deep learning in the form of convolutional neural networks, enhanced with additional transformations of input mammographic images. The key point of the first approach is defining the proper numerical image descriptors and selecting the set which is the most class discriminative. To achieve better performance of the classifier, many image descriptors were defined by means of applying different characterization of the images: Hilbert curve representation, Kolmogorov-Smirnov statistics, the maximum subregion principle, percolation theory, fractal texture descriptors as well as application of wavelet and wavelet packets. Thanks to them, better description of the basic image properties has been obtained. In the case of deep learning, the features are automatically extracted as part of convolutional neural network learning. To get better quality of results, additional representations of mammograms, in the form of nonnegative matrix factorization and the self-similarity principle, have been proposed. The methods applied were evaluated based on a large database composed of 10,168 regions of interest in mammographic images taken from the DDSM database. Experimental results prove the advantage of deep learning over traditional approach to image recognition. Our best average accuracy in recognizing abnormal cases (malignant plus benign versus healthy) was 85.83%, with sensitivity of 82.82%, specificity of 86.59% and AUC = 0.919. These results are among the best for this massive database.

6

Comparative study on the classification methods for breast cancer diagnosis

Qiu Y., Zhou G., Zhao Q., Cichocki A.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 6

841--848

EN

Digital mammography is one of the most widely used approaches for breast cancer diagnosis. Many researchers have demonstrated the superiority of machine learning methods in breast cancer diagnosis using different mammography databases. Since these methods often have different pros and cons, which may confuse doctors and researchers, an elaborate comparison and examination among them is urgently needed for practical breast cancer diagnosis. In this study, we conducted a comprehensive comparative study of the state-of-the-art machine learning methods that are promising in breast cancer diagnosis. For this purpose we analyze the largest mammography diagnosis database: Digital Database for Screening Mammography (DDSM). We considered various approaches for feature extraction including principal component analysis (PCA), nonnegative matrix factorization (NMF), spatial-temporal discriminant analysis (STDA) and those for classification including linear discriminant analysis (LDA), random forests (RaF), k-nearest neighbors (kNN), as well as deep learning methods including convolutional neural networks (CNN) and stacked sparse autoencoder (SSAE). This paper can serve as a guideline and useful clues for doctors who are going to select machine learning methods for their breast cancer computer-aided diagnosis (CAD) systems as well for researchers interested in developing more reliable and efficient methods for breast cancer diagnosis.

7

Extraction of fuzzy rules at different concept levels related to image features of mammography for diagnosis of breast cancer

Goudarzi M., Maghooli K.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 4

1004--1014

EN

Mammography is an inexpensive and non-invasive method through which one can diagnose breast cancer in its early stages. As these images need interpretation by a radiologist, this may develop some problems due to fatigue, repetition, and need for a great deal of attention to details and other factors. Thus, a method capable of diagnosing breast cancer should be employed to help physicians in this regard. In this paper, The mini Mammographic Image Analysis Society (mini-MIAS) database of mammograms is used. The aim is to distinguish between normal and abnormal classes. In the preprocessing stage, noise removal, removal of labels of images, heightening the contrast, and ROI segmentation are performed, and then compactness, entropy, mean, and smoothness are extracted from the images. In addition to classification, we have come to a new approach in order to create a complete knowledge base, which then we use this knowledge base for classification. We have a comprehensive knowledge base which covers all the conceptual levels. The extracted features are referred to as fuzzy classifiers through the look-up table method. And, for evaluation of the results, the 10-fold method is used. Discretization operations are performed on training data across 2, 3, and 4 levels to develop concept hierarchy. Concept hierarchies reduce the data by replacing low-level concepts with higher-level concepts and the outcome is more meaningful and easier to interpret. Eventually, Bagging algorithm is used for finding out the majority vote and the final result of the discretization levels. The obtained accuracy is 89.37 ± 6.62.

8

Automated and effective content-based mammogram retrieval using wavelet based CS-LBP feature and self-organizing map

Singh V. P., Srivastava R.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

90--105

EN

In this paper, automated, fast and effective content based-mammogram image retrieval system is proposed. The proposed pre-processing steps include automatic labelling-scratches suppression, automatic pectoral muscle removal and image enhancement. Further, for segmentation selective thresholds based seeded region growing algorithm is introduced. Furthermore, we apply 2-level discrete wavelet transform (DWT) on the segmented region and wavelet based centre symmetric-local binary pattern (WCS-LBP) features are extracted. Then, extracted features are fed to self-organizing map (SOM) which generates clusters of images, having similar visual content. SOM produces different clusters with their centres and query image features are matched with all cluster representatives to find closest cluster. Finally, images are retrieved from this closest cluster using Euclidean distance similarity measure. So, at the searching time the query image is searched only in small subset depending upon cluster size and is not compared with all the images in the database, reflects a superior response time with good retrieval performances. Descriptive experimental and empirical discussions confirm the effectiveness of this paper.

9

Sposoby wykrywania raka piersi na przykładzie województwa podkarpackiego

Gaweł G., Przypek A., Pusz-Sapa A., Sobczyk J., Król M., Misiewicz E., Lidwin B.

Inżynier i Fizyk Medyczny

|

2017

|

Vol. 6, nr 5

329--332

PL

Cel: Określenie sposobu wykrycia raka piersi ze względu na wykształcenie, wiek i miejsce zamieszkania na przykładzie grupy kobiet z województwa podkarpackiego. Materiał i metoda: Przeprowadzono analizę dokumentacji 200 kobiet z potwierdzonym rakiem piersi. Wyniki: Najczęstszym sposobem wykrycia zmian ogniskowych u kobiet – niezależnie od wykształcenia – było samobadanie. Badania przesiewowe były częstszą metodą wykrywania u kobiet miejskich, a samobadanie wiejskich. Samobadanie było najczęstszą metodą dla kobiet przed 50. i po 69. roku życia. W przedziale 50-69 lat równie często rak piersi wykrywany był badaniem przesiewowym i samobadaniem. Wnioski: Rak piersi wykrywany był poprzez: 1. Samobadanie – kobiety wiejskie, niezależnie od wieku, wykształcenie średnie. 2. Radiologiczne badanie przesiewowe – kobiety miejskie pomiędzy 50-69 lat, wykształcenie wyższe. 3. Badanie palpacyjne onkologa – kobiety wiejskie poniżej 50. roku życia, wykształcenie zawodowe. 4. Badanie palpacyjne lekarza rodzinnego – kobiety wiejskie powyżej 69. roku życia, wykształcenie podstawowe. 5. Badanie palpacyjne ginekologa – kobiety wiejskie poniżej 50. roku życia, wykształcenie podstawowe.

EN

Aim of study: Exploring methods of detection of breast cancer on the basis of education, age and place of residence in the sample group. Research was based on the example of selected group of women from Podkarpackie Province. Material and methods: An analysis of the documentation of 200 women with confirmed breast cancer. Results: The most common way to detect focal lesions – regardless of level of education - was breast self-examination (BSE). Screening was more common method of detection among urban women, and BSE in rural areas. BSE was the most popular method for women before 50 and after 69 years old. In the age range of women between 50-69 breast cancer was equally often diagnosed by screening and BSE. Conclusion: Breast cancer was detected by: 1. BSE- rural women, regardless of age, secondary education 2. Mammography screening – urban women, between 50-69, higher education 3. Clinical breast examination (CBE) by oncologist- rural women, under 50 years of age, vocational education 4. CBE by family doctor – rural women, over 69 years of age, basic education 5. CBE by gynaecologist – rural women, before 50 years of age, basic education.

10

A classification framework for prediction of breast density using an ensemble of neural network classifiers

Kumar I., Bhadauria H. S., Virmani J., Thakur S.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 1

217--228

EN

The present work proposes a classification framework for the prediction of breast density using an ensemble of neural network classifiers. Expert radiologists, visualize the textural characteristics of center region of a breast to distinguish between different breast density classes. Accordingly, ROIs of fixed size are cropped from the center location of the breast tissue and GLCM mean features are computed for each ROI by varying interpixel distance 'd' from 1 to 15. The proposed classification framework consists of two stages, (a) first stage: this stage consists of a single 4-class neural network classifier NN0 (B-I/B-II/B-III/B-IV) which yields the output probability vector [PB-I PB-II PB-III PB-IV] indicating the probability values with which a test ROI belongs to a particular breast density class. (b) second stage: this stage consists of an ensemble of six binary neural network classifiers NN1 (B-I/B-II), NN2 (B-I/B-III), NN3 (B-I/B-IV), NN4 (B-II/B-III), NN5 (B-II/B-IV) and NN6 (B-III/B-IV). The output of the first stage of the classification framework, i.e. output on NN0 is used to obtain the two most probable classes for a test ROI. In the second stage this test ROI is passed through one of the binary neural networks, i.e. NN1 to NN6 corresponding to the two most probable classes predicted by NN0. [...]

11

Mammografia – refleksje technika elektroradiologii

Gaweł G.

Inżynier i Fizyk Medyczny

|

2016

|

Vol. 5, nr 6

309--310

PL

Celem artykułu jest przedstawienie różnych aspektów pracy technika elektroradiologii wykonującego badania mammograficzne. Aby obrazy mammograficzne mogły być prawidłowo ocenione przez lekarza radiologa, oprócz dobrania właściwych parametrów ekspozycyjnych należy zastosować właściwe ułożenie piersi. Konieczne jest także zachowanie zasad higieny, ochrony radiologicznej oraz rzetelne wypełnienie ankiety wraz z pacjentką. Za to wszystko odpowiada technik elektroradiologii.

EN

The aim of this paper is to present various work aspects of the electroradiology technician who performs mammography tests. To obtain images acceptable for evaluation by the radiologist, the proper selection of examination parameters, as well as adequate positioning of the breast need be introduced. The higiene practices, radiation protection, reliable filling out the survey with the patients, are also necessary. The electroradiology technican is responsible for all above mentioned.

12

Tomosynteza : nowa nadzieja mammografii

Rogaliński M.

Inżynier i Fizyk Medyczny

|

2014

|

Vol. 3, nr 2

91

13

Pozycjonowanie w mammografii

Łuczyńska E.

Inżynier i Fizyk Medyczny

|

2014

|

Vol. 3, nr 1

11--18

PL

W pracy przedstawiono techniki pozycjonowania w badaniu mammograficznym. Omówiono przygotowanie do badania oraz jego realizację w projekcjach podstawowych oraz dodatkowych, diagnostycznych. Zwrócono uwagę na procedury oraz błędy, których należy unikać.

EN

The techniques of positioning in mammography, were presented in the article. The preparation for examination and as its realization in views considered as a gold standard as well as additional diagnostic views, were discussed.

14

Ocena wyników audytu klinicznego w Populacyjnym Programie Wczesnego Wykrywania Raka Piersi w województwie małopolskim w latach 2007-2012

Tomera M., Podloch M.

Inżynier i Fizyk Medyczny

|

2014

|

Vol. 3, nr 3

135--139

PL

W Polsce od 2005 roku realizowany jest program skryningowy raka piersi. Od 2007 roku jego jakość jest monitorowana poprzez coroczne kontrole jakości oraz audyt kliniczny. Celem pracy była analiza wyników audytu klinicznego przeprowadzonego w pracowniach mammograficznych województwa małopolskiego w latach 2007-2012.

EN

Since 2005 a special breast cancer screening program has been realized in Poland. Its quality has been monitored through annual quality controls and clinical audit since 2007. The aim of this study was to analyze the results of the clinical audit which was carried out in mammography laboratories in the province of Małopolska in 2007-2012.

15

Mammografia : nowe wyzwania

Kowski R.

Inżynier i Fizyk Medyczny

|

2014

|

Vol. 3, nr 2

89--90

PL

Ósme „ŁOSiowe Spotkanie Szkoleniowe”, które odbyło się 4-5 kwietnia 2014 roku w Łodzi, poświęcono trzem tematom przewodnim: nowe techniki i wyzwania pomiarowe w mammografii, monitory medyczne, ich główne parametry, możliwości i ograniczenia oraz oprogramowanie ułatwiające nadzór nad dawkami i realną ich optymalizację.

16

Procedura oceny mammogramów w ramach audytu klinicznego

Tomera M.

Inżynier i Fizyk Medyczny

|

2013

|

Vol. 2, nr 4

211--212

PL

Celem pracy jest przedstawienie sposobu oceny mammografów przeprowadzanej w ramach audytu klinicznego.

EN

The aim of the study is to present a method for assessing mammograms as part of clinical audit.

17

Pomiar średniej dawki gruczołowej w mammografii

Jankowski P., Jędrzejewska M., Węckowski B.

Inżynier i Fizyk Medyczny

|

2013

|

Vol. 2, nr 6

287--290

PL

Wiele nowych aparatów rentgenowskich wyposażonych jest w systemy mierzące lub podające wartości dawek. W przypadku radiologii ogólnej, zabiegowej i pantomografii jest to najczęściej iloczyn dawki/kermy i powierzchni pola promieniowania (DAP/KAP). W tomografach rentgenowskich, w dokumencie generowanym po badaniu pacjenta podawane są indeksy dawek oraz iloczyny dawki i długości (DLP). W odniesieniu do mammografii jest to wartość średniej dawki gruczołowej AGD ( Average Glandular Dose) lub MGD (Mean Glandular Dose), rzadziej dawki wejściowej ESD (Entrance Skin Dose).

18

Mammografia - kontrola jakości „punktowa” czy długoterminowa?

Trybusz A., Grobelna G., Jankowski P., Jędrzejewska M., Węckowski B.

Inżynier i Fizyk Medyczny

|

2013

|

Vol. 2, nr 2

57--59

PL

Obecnie kontrola jakości skupia się na sprawdzeniu parametrów wyszczególnionych w załączniku nr 6 do Rozporządzenia Ministra Zdrowia z 18.02.2011 r. [1] interpretowanych jako parametry niezależne, wzajemnie niepowiązane. Równie ważna jak bieżąca sprawność jest kontrola stałości tak zwanej długotrwałej. W obecnej sytuacji, gdy w ramach akredytacji wprowadzono obowiązek porównań międzylaboratoryjnych, jest ona możliwa nawet w przypadku przeprowadzania sprawności technicznej aparatury rentgenowskiej każdorazowo przez inne laboratorium badawcze. Dla celów porównawczych przedstawiono wyniki sprawności technicznej mammografu z okresu trzech kolejnych testów specjalistycznych. Na potrzeby opisu pominięto nazwy aparatu oraz użytych błon mammograficznych.

19

Metody analizy obrazu – analiza obrazu mammograficznego na podstawie cech wyznaczonych z tekstury

Lazarek J.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2013

|

nr 4

10--13

PL

W artykule przedstawiono analizę możliwości zastosowania cech wyznaczanych z tekstury do klasyfikacji wykrytych, na obrazie mammograficznym, obszarów zainteresowania – jako obszarów niezmienionych lub zmienionych chorobowo. Cechy tekstury wyznaczono na podstawie histogramu, macierzy gradientu, macierzy długości pasm oraz macierzy zdarzeń. Klasyfikację przeprowadzono z wykorzystaniem klasyfikatora k-NN. W wyniku przeprowadzonych eksperymentów poprawnie rozpoznano wszystkie zmienione chorobowo próbki.

EN

This paper presents an analysis of the possibility of using textural features for mammographic images classification. Textural features are calculated base on histogram, gradient matrix, run-length matrix, co-occurence matrix. Classification is based on k-NN classifier, the regions of interest can be classified as normal or abnormal. Results of some experiments are presented. All of abnormal regions were classified correctly.

20

Multiscale modeling of local directional mammogram findings

Jasionowska M, Przelaskowski A.

Journal of Medical Informatics & Technologies

|

2011

|

Vol. 17

183--190

EN

In this paper two multiresolution transforms (discrete 2D wavelets and complex wavelets) are compared for their capabilities to enhance local texture orientation of mammograms. The local orientation of image texture is useful feature to detect one of the typical types of abnormal findings in mammography - architectural distortions. Our research was directed to define an effective, more reliable directional model of local directional findings in mammograms. Computer-aided diagnosis was considered as a concept of accurate model application.