Breast cancer is currently the most common diagnosed cancer among women and a significant cause of death. Breast density is considered a significant risk factor and an important biomarker influencing the later risk of breast cancer. Therefore, ongoing epidemiological studies using MRI are evaluating quantitatively breast density in young women. One of the challenges is segmenting the breast in order to calculate total breast volume and exclude non-breast surrounding tissues. This thesis describes an automatic 3D breast volume segmentation based on 3D local edge detection using phase congruency and Poisson surface reconstruction to extract the total breast volume in 3D. The boundary localization framework is integrated on a subsequent atlas-based segmentation using a Laplacian framework. The 3D segmentation achieves breast-air and breast-chest wall boundary localization errors with a median of 1.36 mm and 2.68 mm respectively when tested on 409 MRI datasets.

Breast cancer is currently the most common diagnosed cancer among women and a significant cause of death. Breast density is considered a significant risk factor and an important biomarker influencing the later risk of breast cancer. Therefore, ongoing epidemiological studies using MRI are evaluating quantitatively breast density in young women. One of the challenges is segmenting the breast in order to calculate total breast volume and exclude non-breast surrounding tissues. This thesis describes an automatic 3D breast volume segmentation based on 3D local edge detection using phase congruency and Poisson surface reconstruction to extract the total breast volume in 3D. The boundary localization framework is integrated on a subsequent atlas-based segmentation using a Laplacian framework. The 3D segmentation achieves breast-air and breast-chest wall boundary localization errors with a median of 1.36 mm and 2.68 mm respectively when tested on 409 MRI datasets.

This dissertation presents results of a medical image analysis project leading towards development of a comprehensive set of methods and tools for computational image analysis of dynamic contrast-enhanced (DCE) breast magnetic resonance image (MRI), with the aim to aid the physician in interpreting DCE breast MRI examinations. Toward this goal, we developed image analysis methods that would be needed in a breast MRI computer aided diagnosis (CADx) system. A novel contribution of this dissertation is the performance evaluation for each of the major algorithm components developed in this dissertation project. This dissertation begins with reviewing breast imaging techniques, including routinely used modalities in current clinical practice and emerging techniques still in development. We discuss at length the principles of DCE breast MRI, a very sensitive breast imaging modality that has been increasingly used in clinical practice. Then we review the diagnostic guidelines for interpreting DCE breast MRI, and explain the needs and challenges that arise in developing computational image analysis system for breast MRI applications. In this dissertation project, both the morphological and kinetic features of the lesion are automatically extracted for diagnostic purpose. In order to extract morphological features from the segmented lesions, the lesion needs to be accurately segmented out from its surrounding tissues. We utilized a probabilistic method to obtain an optimal segmentation map based on several algorithmic segmentation outputs. In evaluating the performance of segmentation algorithms, we compared the algorithmic segmentation results against manually segmented lesions, and further assessed the segmentation impact on subsequent classification stage. In order to extract accurate kinetic information, the motion needs to be compensated across image volumes acquired sequentially. In this dissertation, we comparatively assessed the similarity metric in registering DCE breast MR images. The performance of cross correlation(CC) coefficient, and mutual information (MI) were studied in both rigid and non-rigid registration schemes. Numerical results and statistical properties were reported. The resultant image quality after registration is discussed both qualitatively and quantitatively. In this dissertation we implemented a classification system based upon quantitative morphological and kinetic features in improving the specificity of breast MRI. Morphological and kinetic features of the lesion were extracted automatically, and then the feature selection step was utilized to select the most relevant features to maximize the classifier performance. In our study, the area under the receiver operating curve (AUC) is used as the performance metric of the classifier, and our results are competitive with those of previous studies. The dissertation concludes by summarizing the contribution of this project and suggesting the future directions of quantitative and highly automated approaches to breast MR image analysis. / text

京都大学 / 0048 / 新制・論文博士 / 博士(医学) / 乙第13218号 / 論医博第2165号 / 新制||医||1033(附属図書館) / 京都大学大学院医学研究科内科系専攻 / (主査)教授 溝脇 尚志, 教授 黒田 知宏, 教授 鈴木 実 / 学位規則第4条第2項該当 / Doctor of Medical Science / Kyoto University / DFAM

Ziel: Untersuchung des Stellenwertes der HR-MRT bei Frauen mit suspekten Mikroverkalkungen der Kategorie BIRADS 4 und 5, die im Rahmen des Mammographie-Screenings, der weiteren Diagnostik oder der Nachsorge nach brusterhaltender Karzinomtherapie detektiert wurden. Methoden: Retrospektive Studie von Mai 2003 bis Mai 2014. 139 Frauen mit mammographisch nachgewiesenen Mikroverkalkungen und Anfertigung einer hochauflösenden Mamma-MRT sowie stereotaktischer Vakuumstanzbiopsie oder primär offener Exzision. Ergebnisse: Bei 52 Patientinnen wurde ein Mammakarzinom diagnostiziert. 34 DCIS (65%), 2 DCIS (4%) mit minimal invasiver Komponente (pTmic) und 18 invasive Karzinome (31%). In der Mammographie wurden die Kalzifikationen in 80% (111/139) BIRADS-Kategorie 4 und in 20% (27/139) BIRADS-Kategorie 5 zugeordnet. In der HR-Mamma-MRT wurden knapp 40% (55/139) der mammographisch suspekten Mikroverkalkungen ebenfalls als malignomverdächtig eingestuft, davon 70% (38/55) in BIRADS 4 und 30% (17/55) in BIRADS 5. Unter Berücksichtigung des vorselektionierten Studienkollektivs ergibt sich Folgendes: Der PPV der Mammographie betrug 37% (52/139). Der PPV und NPV des HR-MRT betrug 76% (42/55) und 88% (74/84). Das MRT wies eine Sensitivität von 80% (42/52) und eine Spezifität von 85% (74/87) auf. Schlussfolgerung: Bei mammographisch suspekten Mikroverkalkungen der Kategorie BIRADS 4 und 5 ist die hochauflösende Mamma-MRT in der Lage das Karzinomrisiko vor bioptischer Abklärung einzuordnen. Die artefaktfreie HR-MRT kann somit die Anzahl unnötiger Biopsien deutlich reduzieren, sofern falsch negative (fast ausnahmslos Frühstkarzinome) und falsch positive Befunde akzeptiert werden.

L’IRM mammaire a une place prépondérante dans l’imagerie mammaire. Son utilisation plus large est limitée notamment par son coût et le nombre limité de machines. Nous avons travaillé sur plusieurs aspects de cette problématique. Dans un premier temps, nous avons modifié le positionnement en passant du procubitus au décubitus. Ceci a permis de montrer que le décubitus permettait une meilleure corrélation topographique des lésions avec l’échographie et était mieux toléré par les patientes. Dans un deuxième temps, nous avons étudié les facteurs de réduction du temps d’acquisition par l’intermédiaire des séquences à haute résolution temporelle et d’un protocole abrégé. Ces changements devraient permettre de faciliter l’accessibilité de l’IRM aux patientes, de réduire son coût tout en conservant les mêmes valeurs de sensibilité et spécificité que le protocole standard / Breast MRI has a prominent place in breast imaging. Its wider use is limited in particular by its cost and the limited number of machines. We have worked on several aspects of this problem. In a first step, we changed the positioning from procubitus to decubitus. This showed that the decubitus allowed a better topographic correlation of the lesions with the ultrasound and was better tolerated by the patients. In a second step, we studied the factors of reduction of the acquisition time via the sequences with high temporal resolution and an abbreviated protocol. These changes should make it easier for patients to access MRI, reduce costs while maintaining the same sensitivity and specificity values as the standard protocol

No description available.

No description available.

No description available.

No description available.