Given the strong association between aberrant nuclear morphology and tumor progression, changes in nuclear structure have remained the gold standard for cancer diagnosis for over 150 years. Recently, the rapid development of imaging hardware and computation power creates the opportunity for automated computer-aided diagnosis (CAD). Developing a robust and reliable pattern recognition pipeline is a pressing need to mine and analyze tons of nuclei data being captured. Among the rich studies on pattern recognition problems in pathology, automated nuclei detection, segmentation and cancer detection are the recurring tasks due to the importance and challenges of nuclei analysis. In this thesis, we propose and investigate the state-of-art methods in the CAD modules for maximizing the overall amount of information from images for decision making. We focus on nuclei segmentation and patient cancer detection in the nuclei image analysis pipeline. As the first step in nuclei analysis, we develop an unsupervised nuclei detection and segmentation approach for pathology images. Different from many supervised segmentation methods whose performances rely on the quality and quantity of training samples, the proposed method is able to automatically search for the nucleus contour by solving the shortest path problem with little user effort. We consider the cancer detection task as a set classification problem and propose a highly discriminative predictive model in the sense that it not only optimizes the classifier decision boundary but also transfers discriminative information to set representation learning. The innovation of the model is the integration of set representation learning and classifier training into one objective function for boosting the cancer detection performance. Experimental results showed that the new model provides significant improvements compared with state-of-art methods in the diagnostic challenges. In addition, we showed that the predictive model enables visual interpretation of discriminative nuclear characteristics representing the whole nuclei set. We believe the proposed model is quite general and provide experimental validations in several extended pattern recognition problems.

Leukemi är en form av cancer som kan vara en dödlig sjukdom. För att rehabilitera och behandla sjukdomen krävs det en korrekt och tidig diagnostisering. För att minska väntetiden för testresultaten har de ordinära metoderna transformerats till automatiserade datorverktyg som kan analyser och diagnostisera symtom.I detta arbete, utfördes det en komparativ studie. Det man jämförde var två olika metoder som detekterar leukemia. Den ena metoden är en genetisk sekvenserings metod som är en binär klassificering och den andra metoden en bildbehandlings metod som är en fler-klassad klassificeringsmodell. Modellerna hade olika inmatningsvärden, däremot använde sig de båda av Convolutional neural network (CNN) som nätverksarkitektur och fördelade datavärdena med en 3-way cross-validation teknik. Utvärderings metoderna för att analysera resultaten är learning curves, confusion matrix och klassifikation rapport. Resultaten visade att den genetiska sekvenserings metoden hade fler antal värden som var korrekt förutsagda med 98 % noggrannhet. Den presterade bättre än bildbehandlings metoden som hade värde på 81% noggrannhet. Storlek på de olika datauppsättningar kan vara en orsak till algoritmernas olika testresultat. / Leukemia is a form of cancer that can be a fatal disease, and to rehabilitate and treat it requires a correct and early diagnosis. Standard methods have transformed into automated computer tools for analyzing, diagnosing, and predicting symptoms.In this work, a comparison study was performed by comparing two different leukemia detection methods. The methods were a genomic sequencing method, which is a binary classification model and a multi-class classification model, which was an images-processing method. The methods had different input values. However, both of them used a Convolutional neural network (CNN) as network architecture. They also split their datasets ​​using 3-way cross-validation. The evaluation methods for analyzing the results were learning curves, confusion matrix, and classification report. The results showed that the genome model had better performance and had several numbers of values ​​that were correctly predicted with a total accuracy of 98%. This value was compared to the image processing method results that have a value of 81% total accuracy. The size of the different data sets can be a cause of the different test results of the algorithms.

In Sweden, women of age between of 40 and 74 go through regular screening of their breasts every 18-24 months. The screening mainly involves obtaining a mammogram and having radiologists analyze them to detect any sign of breast cancer. However reading a mammography image requires experienced radiologist, and the lack of radiologist reduces the hospital's operating efficiency. What's more, mammography from different facilities increases the difficulty of diagnosis. Our work proposed a deep learning segmentation system which could adapt to mammography from various facilities and locate the position of the tumor. We train and test our method on two public mammography datasets and do several experiments to find the best parameter setting for our system. The test segmentation results suggest that our system could play as an auxiliary diagnosis tool for breast cancer diagnosis and improves diagnostic accuracy and efficiency. / I Sverige går kvinnor i åldrarna mellan 40 och 74 igenom regelbunden screening av sina bröst med 18-24 månaders mellanrum. Screeningen innbär huvudsakligen att ta mammogram och att låta radiologer analysera dem för att upptäcka tecken på bröstcancer. Emellertid krävs det en erfaren radiolog för att tyda en mammografibild, och bristen på radiologer reducerar sjukhusets operativa effektivitet. Dessutom, att mammografin kommer från olika anläggningar ökar svårigheten att diagnostisera. Vårt arbete föreslår ett djuplärande segmenteringssystem som kan anpassa sig till mammografi från olika anläggningar och lokalisera tumörens position. Vi tränar och testar vår metod på två offentliga mammografidataset och gör flera experiment för att hitta den bästa parameterinställningen för vårt system. Testsegmenteringsresultaten tyder på att vårt system kan fungera som ett hjälpdiagnosverktyg vid diagnos av bröstcancer och förbättra diagnostisk noggrannhet och effektivitet.

Yes / An ultra-wideband microstrip antenna design is considered with respect to applications in breast cancer detection. The underlying design concept is based on ground penetrating radar (GPR). Simulated and measured prototype performance show excellent performance in the input impedance and radiation pattern over the target range from 4 GHz to 8 GHz. The 4 GHz to 8GHz frequency band for microwave imaging perform better in comparison with other microwave frequencies. The antenna also shows a reasonable uniform radiation performance in the broadside direction which contributes to the reduction of clutter levels, thus aiding the reconstruction quality of the final image.

The CD-ROM disc containing supplementary material is kept in the cardboard box in the Systems Office. / The heterogeneity of breast cancer (disease stage and phenotype) makes it challenging to differentiate between each subtype; luminal A, luminal B, HER2, basal-like and claudin-low, on the basis of a single gene or protein. Therefore, a collection of markers is required that can serve as a signature for diagnosing different types of breast cancer. New developments in proteomics have provided the opportunity to look at phenotype-specific breast cancer cell lines and stage-specific liquid biopsies (nipple aspirate fluid [NAF], plasma samples) to identify disease and phenotype specific signature. An 8-plex iTRAQ quantification strategy was employed to compare proteomic profiles of a range of breast cancer and ‘normal-like’ cell lines with primary breast epithelial cells. From this, 2467 proteins were identified on Orbitrap Fusion and Ultraflex II, of which 1430 were common. Matched pairs of NAF samples from four patients with different stages of breast cancer, were analysed by SCX-LC-MS and a total of 1990 unique gene products were identified. More than double the number of proteins previously published data, were detected in NAF, including 300 not detected in plasma. The NAF from the diseased patients have 138 potential phenotype biomarkers that were significantly changed compared to the healthy volunteer (7 for luminal A, 9 for luminal B, 11 for HER2, 14 for basal-like and 52 for claudin-low type). The average coefficient of variation for triplicate analyses by multiple reaction monitoring mass spectrometry (MRM-MS), was 9% in cell lines, 17 % in tissue biopsies, 22% in serum samples and 24% in NAF samples. Overall, the results provide a strong paradigm to develop a clinical assay based on proteomic changes in NAF samples for the early detection of breast cancer supplementary to established mammography programmes. / The supplementary material submitted with the thesis is not available online.

No description available.

No description available.

No description available.

No description available.

Our aim was to determine the characteristics, treatments and outcomes of patients with primary spinal glioblastomas (GB) or gliosarcomas (GS) reported in literature until March 2015. PubMed and Web of Science were searched for peer-reviewed articles pertaining to cases of glioblastomas / gliosarcomas with primary spinal origin, using predefined search terms. Furthermore we performed hand searches tracking the references from the selected papers. Eighty-two articles published between 1938 and March 2015 were eligible. They reported on 157 patients. Median age at diagnosis was 22 years. The proportion of patients who received adjuvant chemo- or radiotherapy clearly increased from the time before 1980 until present. Median overall survival from diagnosis was 8.0 ± 0.9 months. On univariate analysis age influenced overall survival, whereas tumor location, gender and the extent of initial resection did not. Outcomes did not differ between children (< 18 years) and adults. However, the patients who were treated after 1980 achieved longer survival times than the patients treated before. On multivariable analysis only age (< 60 years) and the time period of treatment (>1980) were confirmed as positive independent prognostic factors. In conclusion, primary spinal GB / GS mainly affect younger patients and are associated with a dismal prognosis. However, most likely due to the increasing use of adjuvant treatment, modest therapeutic progress has been achieved over recent decades. The characteristics and treatments of primary spinal glioblastomas should be entered into a central registry in order to gain more information about the ideal treatment approach in the future.