Predicting breast tissue deformation is of great significance in several medical applications such as surgery, biopsy and imaging. In breast surgery, surgeons are often concerned with a specific portion of the breast, e.g., tumor, which must be located accurately beforehand. Also clinically it is important for combining the information provided by images from several modalities or at different times, for the planning and guidance of interventions. Multi-modality imaging of the breast obtained by mammography, MRI and PET is thought to be best achieved through some form of data fusion technique. However, images taken by these various techniques are often obtained under entirely different tissue configurations, compression, orientation or body position. In these cases some form of spatial transformation of image data from one geometry to another is required such that the tissues are represented in an equivalent configuration. We constructed the 3D biomechanical models for this purpose using Finite Element Methods (FEM). The models were based on phantom and patient MRIs and could be used to model the interrelation between different types of tissue by applying displacements of forces and to register multimodality medical images.

Title from PDF of title page. / Document formatted into pages; contains 64 pages. / Thesis (M.S.C.S.)--University of South Florida, 2003. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: Predicting breast tissue deformation is of great significance in several medical applications such as surgery, biopsy and imaging. In breast surgery, surgeons are often concerned with a specific portion of the breast, e.g., tumor, which must be located accurately beforehand. Also clinically it is important for combining the information provided by images from several modalities or at different times, for the planning and guidance of interventions. Multi-modality imaging of the breast obtained by mammography, MRI and PET is thought to be best achieved through some form of data fusion technique. However, images taken by these various techniques are often obtained under entirely different tissue configurations, compression, orientation or body position. In these cases some form of spatial transformation of image data from one geometry to another is required such that the tissues are represented in an equivalent configuration. / ABSTRACT: We constructed the 3D biomechanical models for this purpose using Finite Element Methods (FEM). The models were based on phantom and patient MRIs and could be used to model the interrelation between different types of tissue by applying displacements of forces and to register multimodality medical images. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.

Benign breast biopsy (BBB) can be a stressful experience for many women. Few studies have examined the specific aspects of the BBB more and less distressing. However, no research studies have examined demographic and clinical variables as they relate to distress associated with specific aspects of the BBB or the informational interests of women following a BBB. This study evaluated the magnitude of distress associated with each aspect of the BBB (additional mammography, waiting for the results of the mammography, being informed of needing a biopsy, etc.) as well as the clinical (family history of BC in first degree relative, history of BBB, and type of biopsy) and demographic (age and education) variables as correlates of distress associated with each aspect of a BBB. Additionally, we examined health information interests in women following a BBB and the manner in which women preferred to have this health information communicated.

Mammography is currently used to screen women in targeted risk classes for breast cancer. Computer assisted diagnosis of mammograms attempts to lower the workload on radiologists by either automating some of their tasks or acting as a second reader. The task of mammogram segmentation based on pixel intensity is addressed in this thesis. The mammographic process leads to images where intensity in the image is related to the composition of tissue in the breast; it is therefore possible to segment a mammogram into several regions using a combination of global thresholds, local thresholds and higher-level information based on the intensity histogram. A hierarchical view is taken of the segmentation process, with a series of steps that feed into each other. Methods are presented for segmentation of: 1. image background regions; 2. skin-air interface; 3. pectoral muscle; and 4. segmentation of the database by classification of mammograms into tissue types and determining a similarity measure between mammograms. All methods are automatic. After a detailed analysis of minimum cross-entropy thresholding, multi-level thresholding is used to segment the main breast tissue from the background. Scanning artefacts and high intensity noise are separated from the breast tissue using binary image operations, rectangular labels are identified from the binary image by their shape, the Radon transform is used to locate the edges of tape artefacts, and a filter is used to locate vertical running roller scratching. Orientation of the image is determined using the shape of the breast and properties of the breast tissue near the breast edge. Unlike most existing orientation algorithms, which only distinguish between left facing or right facing breasts, the algorithm developed determines orientation for images flipped upside down or rotated onto their side and works successfully on all images of the testing database. Orientation is an integral part of the segmentation process, as skin-air interface and pectoral muscle extraction rely on it. A novel way to view the skin-line on the mammogram is as two sets of functions, one set with the x-axis along the rows, and the other with the x-axis along the columns. Using this view, a local thresholding algorithm, and a more sophisticated optimisation based algorithm are presented. Using fitted polynomials along the skin-air interface, the error between polynomial and breast boundary extracted by a threshold is minimised by optimising the threshold and the degree of the polynomial. The final fitted line exhibits the inherent smoothness of the polynomial and provides a more accurate estimate of the skin-line when compared to another established technique. The edge of the pectoral muscle is a boundary between two relatively homogenous regions. A new algorithm is developed to obtain a threshold to separate adjacent regions distinguishable by intensity. Taking several local windows containing different proportions of the two regions, the threshold is found by examining the behaviour of either the median intensity or a modified cross-entropy intensity as the proportion changes. Image orientation is used to anchor the window corner in the pectoral muscle corner of the image and straight-line fitting is used to generate a more accurate result from the final threshold. An algorithm is also presented to evaluate the accuracy of different pectoral edge estimates. Identification of the image background and the pectoral muscle allows the breast tissue to be isolated in the mammogram. The density and pattern of the breast tissue is correlated with 1. Breast cancer risk, and 2. Difficulty of reading for the radiologist. Computerised density assessment methods have in the past been feature-based, a number of features extracted from the tissue or its histogram and used as input into a classifier. Here, histogram distance measures have been used to classify mammograms into density types, and ii also to order the image database according to image similarity. The advantage of histogram distance measures is that they are less reliant on the accuracy of segmentation and the quality of extracted features, as the whole histogram is used to determine distance, rather than quantifying it into a set of features. Existing histogram distance measures have been applied, and a new histogram distance presented, showing higher accuracy than other such measures, and also better performance than an established feature-based technique.

Breast cancer is the most commonly diagnosed cancer among Canadian women; x-ray mammography is the leading screening technique for early detection. This work introduces a semi-automated technique for analyzing mammographic x-ray images to measure their degree of suspiciousness for containing abnormalities. The designed system applies the discrete wavelet transform to parse the images and extracts statistical features that characterize an images content, such as the mean intensity and the skewness of the intensity. A naïve Bayesian classifier uses these features to classify the images, achieving sensitivities as high as 99.5% for a data set containing 1714 images. To generate confidence levels, multiple classifiers are combined in three possible ways: a sequential series of classifiers, a vote-taking scheme of classifiers, and a network of classifiers tuned to detect particular types of abnormalities. The third method offers sensitivities of 99.85% or higher with specificities above 60%, making it an ideal candidate for pre-screening images. Two confidence level measures are developed: first, a real confidence level measures the true probability that an image was suspicious; and second, a normalized confidence level assumes that normal and suspicious images were equally likely to occur. The second confidence measure allows for more flexibility and could be combined with other factors, such as patient age and family history, to give a better true confidence level than assuming a uniform incidence rate. The system achieves sensitivities exceeding those in other current approaches while maintaining reasonable specificity, especially for the sequential series of classifiers and for the network of tuned classifiers.

Breast cancer is the most commonly diagnosed cancer among Canadian women; x-ray mammography is the leading screening technique for early detection. This work introduces a semi-automated technique for analyzing mammographic x-ray images to measure their degree of suspiciousness for containing abnormalities. The designed system applies the discrete wavelet transform to parse the images and extracts statistical features that characterize an images content, such as the mean intensity and the skewness of the intensity. A naïve Bayesian classifier uses these features to classify the images, achieving sensitivities as high as 99.5% for a data set containing 1714 images. To generate confidence levels, multiple classifiers are combined in three possible ways: a sequential series of classifiers, a vote-taking scheme of classifiers, and a network of classifiers tuned to detect particular types of abnormalities. The third method offers sensitivities of 99.85% or higher with specificities above 60%, making it an ideal candidate for pre-screening images. Two confidence level measures are developed: first, a real confidence level measures the true probability that an image was suspicious; and second, a normalized confidence level assumes that normal and suspicious images were equally likely to occur. The second confidence measure allows for more flexibility and could be combined with other factors, such as patient age and family history, to give a better true confidence level than assuming a uniform incidence rate. The system achieves sensitivities exceeding those in other current approaches while maintaining reasonable specificity, especially for the sequential series of classifiers and for the network of tuned classifiers.

Submitted by Luciana Sebin (lusebin@ufscar.br) on 2016-10-06T13:19:49Z No. of bitstreams: 1 DissAOS.pdf: 12231590 bytes, checksum: 0d013d4adc46d9e7c5828719c8c6951f (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-13T20:24:59Z (GMT) No. of bitstreams: 1 DissAOS.pdf: 12231590 bytes, checksum: 0d013d4adc46d9e7c5828719c8c6951f (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-13T20:25:09Z (GMT) No. of bitstreams: 1 DissAOS.pdf: 12231590 bytes, checksum: 0d013d4adc46d9e7c5828719c8c6951f (MD5) / Made available in DSpace on 2016-10-13T20:25:19Z (GMT). No. of bitstreams: 1 DissAOS.pdf: 12231590 bytes, checksum: 0d013d4adc46d9e7c5828719c8c6951f (MD5) Previous issue date: 2016-02-26 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Mammography is considered the “gold standard"in the early detection of breast cancer, being this disease one of the greatest health problems of women worldwide. Clustered microcalcifications detected on mammograms are very important findings in asymptomatic patients with early breast cancer and may be considered one of the first signs of malignancy. However, due to the small size of these structures, associated with the visual fatigue of radiologists resulting from the analysis of a large volume of images, clinical studies indicate that from 10 to 30% of microcalcifications presented in mammograms are lost during diagnosis. Within this scenario, this master thesis aims to develop an automatic system for the detection of clustered microcalcifications in digitized mammography images. To solve this problem, we use the transformed dua-three complex wavelet to detect the microcalsifications since this technique has some important characteristics for the signal analysis, for instance, good directional selectivity, approximate shift invariance and it provides both information - magnitude and phase. After the detection of isolated microcalcifications, a post-processing step is used to automatically demarcate regions containing clusters of microcalcifications. Furthermore, three techniques were investigated for the analysis of each clustered detection in order to identify false-positive clusters, such as: the Hessian matrix, the groups exclusion and the gray level co-occurrence matrix technique and SVM classifiers. For the development and testing of the algorithms one digitized mammogram database were used. The analysis of the results were performed by using ROC and FROC curves. The method achieved good results when compared to the mark made by experts. / A mamografia é considerada o "padrão ouro"na detecção precoce do câncer de mama, sendo essa doença um dos maiores problemas de saúde da mulher no mundo. Agrupamentos de microcalcificações detectados nos mamogramas são achados muito importantes em pacientes assintomáticas com câncer de mama e podem representar o primeiro sinal de malignidade. No entanto, devido ao reduzido tamanho dessas estruturas, associado à fadiga visual dos radiologistas resultante da análise de grandes volumes de imagens, estudos clínicos indicam que de 10 a 30% das microcalcificações presentes nos mamogramas são perdidas durante o diagnóstico. Diante deste quadro, este trabalho de mestrado tem por objetivo o desenvolvimento de um sistema automático para a detecção de agrupamentos de microcalcificações em imagens de mamogramas digitalizados. Para isso, utilizou-se a transformada wavelet complexa de árvore dupla (DT-CWT) para a detecção das microcalcificações, visto que essa técnica possui características importantes para a análise de sinais como, por exemplo, boa seletividade direcional, invariância aproximada ao deslocamento e fornece ambas informações – magnitude e fase. Após a detecção das microcalcificações isoladas, uma etapa de pós-processamento foi utilizada para demarcar automaticamente regiões contendo agrupamentos de microcalcificações. Além disso, três técnicas foram investigadas para a análise de cada agrupamento detectado, com o intuito de identificar agrupamentos falsopositivos, sendo elas: a matriz Hessiana, a exclusão de agrupamentos e a técnica de matriz de coocorrência de níveis de cinza e classificadores SVMs. Uma base de dados de mamogramas digitalizados foi utilizada para o desenvolvimento e testes dos algoritmos. A análise dos resultados foi realizada usando curvas ROC e FROC. O método obteve bons resultados quando comparado às marcações realizadas por especialistas e presentes na base de dados.

La tomographie ultrasonore assistée par ordinateur possède un fort potentiel en tant que moyen d'inspection des tissus mammaires pour le dépistage du cancer du sein; cette technique permet de réduire la dépendance à l'opérateur constatée avec l'échographie conventionnelle. Une antenne de transducteurs (3 MHz) à géométrie semi-circulaire conformée à l'anatomie du sein a été développée pour réaliser une imagerie de réflectivité des structures d'intérêt en employant une procédure de reconstruction tomographique. L'antenne comporte 1024 éléments répartis sur un arc de 190 degrés ayant un rayon de courbure de 100 mm. Les acquisitions sont gérées par une électronique à 32 voies parallèles indépendantes en émission/réception et par un multiplexer pour l'adressage des voies vers les éléments de l'antenne. Les circuits d'émission et de réception ont une fréquence d'échantillonnage allant jusqu'à 80 MHz avec une précision de 12 bits. Des formes d'ondes arbitraires (pseudo-chirp, codes de Golay) sont transmises afin d'améliorer le rapport signal sur bruit. L'électroacoustique a été caractérisée avec des objets académiques et un hydrophone afin de déterminer les propriétés d'émission du système d'imagerie (réponses impulsionnelles et distribution spatiale du champ) et de développer des outils de correction des données; ces résultats sont mis en regard avec le formalisme de résolution du problème inverse (algorithme de sommation des rétroprojections elliptiques filtrées en champ proche). L'évaluation du système d'imagerie est réalisées sur des objets ponctuels, des objets bidimensionnels à faible contraste d'impédance et un fantôme anthropomorphique de sein contenant des inclusions / Ultrasound computed tomography has considerable potential as a means of breast cancer detection since it reduces the operator-dependency observed in echography. A half-ring transducer array was designed based on the breast anatomy, to obtain reflectivity images of the ductolobular structures using tomographic reconstruction procedures. The 3-MHz transducer array comprises 1024 elements set, in a 190-degree circular arc with a radius of 100 mm. The front-end electronics incorporate 32 independent parallel transmit/receive channels and a 32-to-1024 multiplexer unit. The transmit and receive circuitries have a variable sampling frequency of up to 80 MHz and a 12-bit precision. Arbitrary waveforms are synthesized to improve the signal-to-noise ratio. The set-up was calibrated with academic objects and a needle hydrophone to develop the data correction tools and specify the properties of the system; results are compared with the formalism of inverse problem (elliptical back-projection summation algorithm).The backscattering field was recorded using a restricted aperture, and tomographic acquisitions were performed with a pair of 0.08 mm diameter steel threads, a low contrast 2-D breast phantom, and a breast-shaped phantom containing inclusions. The pulse compression is used and the contribution of this technique to ultrasound computed tomography is evaluated with respect to the use of a standard broadband pulse. Prospects for development of inspection methods and also adaptations of the electroacoustic set-up dedicated to the anatomical tomographic imaging are proposed relative to conducted studies during this thesis.

Image processing is one area of signal analysis. This thesis is involved in feature extraction from image data and its implementation using Java programming language. The main contribution of this thesis lies in develop features extractors and their implementation in the program RapidMiner. The result is a robust tool for image analysis. The functionality of each operator is tested on mammogram images. A function model was developed for the removal of artifacts from the mammography images. The success rate of removal is comparable with other similar works. Furthermore, learning algorithms were compared on example detection of ventricle in ultrasound image.

Breast cancer is the most common form of cancer among women, with around 9000 new diagnoses in Sweden yearly. Detecting and localizing risk of breast cancer could give the opportunity for individualized examination programs and preventative measures if necessary, and potentially be lifesaving. In this study, two deep learning methods have been designed, trained and evaluated on mammograms from healthy patients whom were later diagnosed with breast cancer, to examine how well deep learning models can localize suspicious areas in mammograms. The first proposed model is a ResNet-18 regression model which predicts the pixel coordinates of the annotated target pixel in the prior mammograms. The regression model produces predictions with an average of 44.25mm between the predictions and targets on the test set, which for average sized breasts correspond to a general area of the breast, and not a specific location. The regression network is hence not able to accurately localize suspicious areas in mammograms. The second model is a U-net segmentation model that segments out a risk area in the mammograms. The segmentation model had a 25% IoU, meaning that there is on average a 25% overlap between the target area and the prediction area. 57% of the predictions of the segmentation network had some overlap with the target mask, and predictions that did not overlap with the target often marked high density areas that are traditionally associated with high risk. Overall, the segmentation model did better than the regression model, but needs further improvement before it can be considered adequate to merge with a risk value model and used in practice. However, it is evident that there is sufficient information present in many of the mammogram images to localize the risk, and the research area holds potential for future improvements. / Bröstcancer är den vanligaste cancerformen bland kvinnor, med cirka 9000 nya diagnoser i Sverige årligen. Att upptäcka och lokalisera risken för bröstcancer kan möjliggöra individualiserade undersökningsprogram och förebyggande åtgärder vid behov och kan vara livräddande. I denna studie har två djupinlärningsmodeller designats, tränats och utvärderats på mammogram från friska patienter som senare diagnostiserades med bröstcancer, för att undersöka hur väl djupinlärningsmodeller kan lokalisera misstänkta områden i mammogram. Den första föreslagna modellen är en ResNet-baserad regressionsmodell som förutsäger pixelkoordinaterna för den utmarkerade målpixeln i de friska mammogrammen. Regressionsmodellen producerar förutsägelser med ett genomsnitt på 44,25 mm mellan förutsägelserna och målpunkterna för testbilderna, vilket för medelstora bröst motsvarar ett allmänt bröstområde och inte en specifik plats i bröstet. Regressionsnätverket kan därför inte med precision lokalisera misstänkta områden i mammogram. Den andra modellen är en U-net segmenteringsmodell som segmenterar ut ett riskområde ur mammogrammen. Segmenteringsmodellen hade ett IoU på 25%, vilket innebär att det i genomsnitt fanns en 25-procentig överlappning mellan målområdet och förutsägelsen. 57% av förutsägelserna från segmenteringsnätverket hade viss överlappning med målområdet, och förutsägelser som inte överlappade med målet markerade ofta områden med hög täthet som traditionellt är förknippade med hög risk. Sammantaget presterade segmenteringsmodellen bättre än regressionsmodellen, men behöver ytterligare förbättring innan den kan anses vara adekvat nog att sammanfogas med en riskvärdesmodell och användas i praktiken. Det är dock uppenbart att det finns tillräcklig information i många av mammogrambilderna för att lokalisera risken, och att forskningsområdet har potential för framtida förbättringar.