No description available.

In 2016, there were 250,000 new cases of invasive cancer and 60,000 of ductal carcinoma in situ. Mammograms are used to screen for cases of disease, but the literature shows that mammograms are highly dependent on patient characteristics and do not majorly impact mortality rates from invasive cancer. Additionally, they are prone to false-positives, false-negatives, and overdiagnosis in cases of in situ cancer, with overdiagnosis exposing patients to the side effects of treatment. Better screening tests are needed, and a potential solution can be to extend molecular screening methods often used in advanced stage 1 and higher cancers to stage 0 ductal carcinoma in situ cases. This new test would prevent overdiagnosis, be more accurate, and prevent unnecessary screening as well as be in line with the future of cancer care in the US.

No description available.

The presence of distributed micro-calcifications can be an indicator of early breast cancer. On the mammogram, they appear as bright smooth particles superimposed on the normal breast image background. Radiologists determine the occurrence of this lesion by detecting the individual micro-calcifications and then examining their distribution within the breast tissue. Due to the visual complexity of the mammogram, the detection sensitivity is usually less than 100%. The digital environment has the potential to increase the radiologist's accuracy. We have developed a computer aided detection (CAD) scheme that can identify clinically indicative clusters of micro-calcifications. The CAD algorithm emulates some aspects of the radiologists' approach by using contrast texture energy segmentation and morphological distribution analysis. On a local database of 61 mammograms digitised at 100μm with 8 bits intensity resolution, the CAD returns: a) 85% sensitivity (91% for malignant lesions and 78% for those that are benign), b) 0.33 false positive clusters (FPC) per image and c) 92% specificity. Therefore, the output from the CAD is shown to compare favourably with the performance of an expert radiologist. It also compares favourably with other CAD techniques, exceeding many algorithms which employ a higher level of mathematical complexity. The scheme is tested on an international database provided by the Mammographic Image Analysis Society. In this case it returns a) 96.4% sensitivity (100% for malignant lesions and 92% for those that are benign) b) 2.35 FPC rate per image and c) 33% specificity. The higher FPC rate is attributed to the different acquisition and production of the digital mammograms. It is concluded that this can be reduced by employing a shape analysis procedure to the CAD's final output. It is shown that the image processing principles we have implemented are generally successful on databases which are produced at other centres under different technical conditions.

Orientador: Aledir Silveira Pereira / Banca: Roberto Marcondes Cesar Junior / Banca: Norian Marranghello / Resumo: O câncer de mama é uma das doenças que mais matam mulheres com idade acima de quarenta anos no Brasil atualmente. A fim de prevenir e tratar essa doença, o exame mais indicado é a análise de mamografias, imagens obtidas da mama fazendo uso de aplicações de raios-x, que podem indicar a presença ou não de tumores. Neste trabalho é apresentado um método para melhorar o contraste da imagem das mamas, classificando o formato de microcalcificações a fim de auxiliar médicos a decidir se este tumor é maligno. O método apresentado é baseado na transformada wavelet, que decompõe uma imagem em bandas de diferentes freqüências, permitindo a detecção destes objetos através da característica de freqüência deles. A utilização da família Symmlets gerou melhores resultados, tanto no realce da imagem de microcalcificações quanto na classificação das bordas desses objetos. / Abstract: Breast cancer is one of the diseases that kills most of women older than forty in Brazil nowadays. In order to prevent and treat it, the most appropriate exam is the analysis of mammograms, images obtained from the breast by applying x-rays on it, indicating whether or not tumors are present. In this work a method to enhance breast images is presented, classifying the format of microcalcifications in order to help doctors decide whether or not this tumor is malign. The proposed method is based on the wavelet transform, which decomposes an image into different frequency bands, allowing the detection of these elements by their frequency features. Utilization of the Symmlets family achieved the best results, on the microcalcification image enhancement and on the classification of the borders of these elements. / Mestre

Bakgrund: I Sverige inbjuds alla kvinnor i åldern 40 till 74 år regelbundet till mammografi som hälsokontroll. Undersökningen är frivillig och syftet är att minska dödligheten i bröstcancer. För att kvinnor ska kunna fatta ett välgrundat beslut om att medverka vid mammografi som hälsokontroll eller inte, bör informationen vara relevant och sanningsenlig. Evidensbaserad information som beskriver både för- och nackdelar med mammografi som hälsokontroll är därför av stor vikt. Syftet: Syftet med denna studie var att undersöka innehållet i den information som skickas till kvinnor i Sverige i samband med kallelsen till mammografi som hälsokontroll. Metod: Studien var av deskriptiv design med en kvantitativ och kvalitativ ansats. Kallelser som skickas till kvinnor inför sin mammografi som hälsokontroll, samlades in från alla mammografimottagningarna i Sverige som bedriver mammografi som hälsokontroll. Resultat: Studien visade tydligt att de allra flesta kallelser som skickas till kvinnor i Sverige inför mammografi som hälsokontroll saknade information som beskriver både för- och nackdelar med mammografiscreening. De flesta kvinnor i Sverige får allmän information och till viss del information som betonar fördelarna med mammografiscreening. Beträffande nackdelar med mammografi som hälsokontroll saknades den informationen i de allra flesta kallelser. Slutsats: De flesta kvinnorna i Sverige får inte relevant evidensbaserad information inför sin mammografi som hälsokontroll.

The aim of this thesis is to investigate the effects of JPEG2000 compression on texture feature extraction from digitized mammograms. A partially automated computer aided diagnosis system is designed, implemented, and tested for this analysis. The system is tested on a database of 60 digital mammograms obtained from the Digital Database for Screening Mammography at the University of South Florida. Using JPEG2000, the mammograms are compressed at 20 different compression ratios ranging from 17:1 to 10,000:1. Two approaches to texture feature extraction are investigated: (i) region of interest (ROI), which is a bounding box around the segmented mass and (ii) rubber band straightening transform (RBST), which is a band of pixels around the segmented mass transformed to a rectangular strip. The gray tone spatial dependent matrices are computed from the ROI and the RBST for the original uncompressed mammograms as well as each group of compressed images. Feature selection and optimization is achieved via stepwise linear discriminant analysis. The efficacy of the features is measured using receiver operator characteristic (ROC) curves. The efficacy of the texture features obtained from the original mammograms is compared to those of the compressed mammograms. Overall, the texture feature efficacy was preserved even for relatively high compression ratios. For example, the area under the ROC curve was greater than 0.99 for compression ratios as high as 5000:1, when the RBST method was utilized. Overall, the JPEG2000 compression distorted the RBST texture features lesser than the ROI texture features.

No description available.

Made available in DSpace on 2014-06-11T19:29:40Z (GMT). No. of bitstreams: 0 Previous issue date: 2008-05-28Bitstream added on 2014-06-13T20:48:22Z : No. of bitstreams: 1 docusse_ta_me_sjrp.pdf: 2737007 bytes, checksum: 136d52dde1692e02c17ad1383702808c (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / O câncer de mama é uma das doenças que mais matam mulheres com idade acima de quarenta anos no Brasil atualmente. A fim de prevenir e tratar essa doença, o exame mais indicado é a análise de mamografias, imagens obtidas da mama fazendo uso de aplicações de raios-x, que podem indicar a presença ou não de tumores. Neste trabalho é apresentado um método para melhorar o contraste da imagem das mamas, classificando o formato de microcalcificações a fim de auxiliar médicos a decidir se este tumor é maligno. O método apresentado é baseado na transformada wavelet, que decompõe uma imagem em bandas de diferentes freqüências, permitindo a detecção destes objetos através da característica de freqüência deles. A utilização da família Symmlets gerou melhores resultados, tanto no realce da imagem de microcalcificações quanto na classificação das bordas desses objetos. / Breast cancer is one of the diseases that kills most of women older than forty in Brazil nowadays. In order to prevent and treat it, the most appropriate exam is the analysis of mammograms, images obtained from the breast by applying x-rays on it, indicating whether or not tumors are present. In this work a method to enhance breast images is presented, classifying the format of microcalcifications in order to help doctors decide whether or not this tumor is malign. The proposed method is based on the wavelet transform, which decomposes an image into different frequency bands, allowing the detection of these elements by their frequency features. Utilization of the Symmlets family achieved the best results, on the microcalcification image enhancement and on the classification of the borders of these elements.

M.Tech. / Mammography is most important in the detection of breast cancer but due to its intimate nature and the perception that it is uncomfortable and painful, many women do not optimally support mammography as a diagnostic and screening tool for breast cancer. Many factors influence the mammogram experience of patients. This research explored the preferences and perceptions of patients regarding mammographer gender and personality traits as well as student involvement in mammogram procedures. To promote positive perceptions of mammography and to ensure the availability of adequately trained mammographers to meet the future demands of the profession, the preferences and perceptions of patients and training needs of students should be carefully balanced. The study was empirical in nature and data was collected using a valid and reliable self-formulated questionnaire. The approach was quantitative and a small qualitative component added dimension to the quantitative results. A nonprobability, convenience sampling method was employed and questionnaires were distributed in radiography training centres affiliated to the University of Johannesburg. Data analysis indicated that while many women accept males in the mammography setting, most prefer female mammographers and -students. In general, women accept student presence during mammogram procedures. Personality traits that enhance effective communication and promote patient emotions such as trust, being safe and being cared for are favoured by patients. This research adhered to stipulations of the South African Patients' Rights Charter and the call of the Breast Cancer Advocacy Coalition for South African research into breast health care. The findings serve as benchmarks for patient opinions regarding mammography staff and will be of use in various fields concerning mammography, such as human resources, training and education and quality assurance of care.