· · · Repository hosted by TU Delft Library

We present a computational method that combines genome-wide DNA methylation and copy number variation data in an integrated fashion withthe aim of finding mechanistic associations between genome instability and local DNA methylation changes. The method is applied to Luminal A breast cancer early-stage tumour samples and focuses on methylation events occurring at frequently rearranged genome locations. Our method accommodates array and sequencing platforms for methylationand DNA copy number estimates. We find significant local methylation changes in tumours tend to occur in the viscinity of breakpoint rich regions, with 80% of the differentially methylated regions occurring within 2Mb from a breakpoint rich locus.

We investigate the potential to enhance breast cancer event predictors by exploiting subtype information. We do this with a two-stage approach that first determines a sample's subtype using a recent module-driven approach, and secondly constructs a subtype-specific predictor to predict a metastasis event within five years. Our methodology is validated on a large compendium of microarray breast cancer datasets,including 43 replicate array pairs for assessing subtyping stability. Note that stratifying by subtype strongly reduces the training set sizes available to construct the individual predictors, which may decrease performance. Besides sample size, other factors likeunequal class distributions and differences in the number of samplesper subtype, easily obscure a fair comparison between subtype-specific predictors constructed on different subtypes, but also between subtype specific and subtype a-specific predictors. Therefore, we constructed a completely balanced experimental design, in which none ofthe above factors play a role and show that subtype-specific eventpredictors clearly outperform predictors that do not take subtype information into account.

Motivation: In recent years increasing evidence appeared that breastcancer may not constitute a single disease at the molecular level,but comprises a heterogeneous set of subtypes. This suggests that instead of building a single predictor, better predictors might be constructed that solely target samples of a designated subtype. An unavoidable drawback of developing subtype-specific predictors, however,is that a stratification by subtype drastically reduces the numberof samples available for their construction. It is therefore questionable whether the potential benefit of subtyping can outweigh the drawback of a severe loss in sample size. Factors like unequal class distributions and differences in the number of samples per subtype, further complicate comparisons. Results: We present several evaluation strategies that facilitate a comprehensive comparison between subtype-specific predictors and predictors that do not take subtype information into account. Emphasis lies on careful control of sample size as well as class and subtype distributions. The methodology is applied to a large breast cancer compendium involving over 1500 arrays,using a state-of-the-art subtyping scheme. We show that the resulting subtype-specific predictors outperform those that do not take subtype information into account, especially when taking sample size considerations into account.

We report on the use of diffuse optical spectroscopy analysis of breast spectra acquired in the wavelength range from 500 to 1600 nm with a fiber optic probe. A total of 102 ex vivo samples of five different breast tissue types, namely adipose, glandular, fibroadenoma, invasive carcinoma and ductal carcinoma in situ from 52 patients weremeasured. A model deriving from the diffusion theory was applied tothe measured spectra in order to extract clinically relevant parameters such as blood, water, lipid, and collagen volume fractions, b-carotene concentration, average vessels radius, reduced scattering amplitude, Mie slope and Mie-to-total scattering fraction. Based on a classification and regression tree algorithm applied to the derived parameters, a sensitivity-specificity of 98%-99%, 84%-95%, 81%-98%, 91%-95%, and 83%-99% were obtained for discrimination of adipose, glandular, fibroadenoma, invasive carcinoma, and ductal carcinomain situ, respectively; and a multiple classes overall diagnostic performance of 94%. Sensitivity-specificity values obtained for discriminating malignant from non-malignant tissue were compared to existing reported studies by applying the different classification methodsthat were used in each of these studies. Furthermore, in these reported studies, either lipid or b-carotene was considered as adipose tissue precursors. We estimate both chromophore concentrations and demonstrate that lipid is a better discriminator for adipose tissue than b-carotene.

Rational: An experiment is described whose purpose is to extract those image characteristics that radiologists use in diagnostic decision making. It is one phase in the development of a clinical decisionsupport system to assist radiologists using DCE-MRI (dynamic contrast-enhanced MRI) for breast cancer diagnosis. The results of this experiment will be used to develop a case-based reasoning system, whichrelies on presenting prior similar cases with known diagnosis froma database to aid decision making. Methods: Clinical similarity formass lesions was established by four expert radiologists who systematically sorted lesions visualized by DCE-MRI into similarity clusters using a proprietary software tool. Cognitive analysis was used toidentify the relevant perceptual features characterizing each cluster, such that the list of features and clusters define the clinicalsimilarity. There were no constraints on the number or size of clusters that could be created. The radiologists first individually clustered a total of 214 lesions. A subsequent phase required all radiologists to agree on both a cluster designation and assignment of eachlesion into a cluster. Results: Radiologists created individually10, 10, 12, and 16 clusters. Of this initial cluster assignment, there was unanimous agreement in ~20% of the lesions, and majority agreement of ~60%. The final consensus assignment created 16 clusters; two consisted of all malignant lesions; two consisted of a majority of benign lesions, three were large approximately equal mixes of benign and malignant lesions, while the remaining nine were small clusters representing lesions with clinically relevant special characteristics of low clinical prevalence. Conclusions: The cognitive analysis revealed that the image characteristics differentiating the clusters are highly correlated to BI-RADS lesion descriptors. The radiologists were excellent in clustering certain malignant lesions, very good with some benign lesions; while as expected there was large variability in the majority of lesions.