dSphere is a wappier web3 spin-off, aiming to empower brands and Dapps to thrive in the web3 world.

wappier is the world leader in Intelligent Revenue Management. Its Next Generation Marketing Technology is transforming the way app developers and marketers maximize consumer revenue by using powerful AI that goes beyond marketing automation. wappier’s cloud-based platform models consumer behavior and recommends the next best action for each consumer real-time leading to Consumer Lifetime Value uplifts of 30-50%.

Project I: “Segmentation and quantification of bone marrow edema lesions in MR images of axial psoriatic arthritis patients”In this project, we aimed to develop objective quantitative MR image-based measured to assist in the diagnosis of axial psoriatic arthritis patients.• The main aim of this project was to implement an automatic method for the quantification of bone marrow edema and compare it to the semi-quantitative gold standard method (SPARCC method). Two methods were implemented and tested: simple thresholding and pixel-wise classification using textural and gradient features as predictors.• For the pixel-wise classification, a supervised machine-learning algorithm was used. Additional statistical analysis was performed in SPSS.Project II: “Contrast enhanced MRI derived textural features for prediction of overall survival in locally advanced breast cancer”In this project, we investigated the predictive value of textural features extracted from pre-treatment magnetic resonance (MR) images of breast cancer patient in their long-term survival. • The main hypothesis for this project was that MR images acquired prior to therapy could predict the long-term disease outcome in locally advanced breast cancer as well or better than clinical prognostic factors. We also investigated the added value of textural features in the prediction of long-term survival when used in combination with the clinical prognostic factors.• Advanced statistical analysis methods used: partial least-squares discriminant analysis (PLS toolbox in MATLAB), Kaplan-Meier survival analysis (implemented in MATLAB), lineal mixed-effects models (implemented in R). Additional statistical analysis was performed in SPSS.My thesis is entitled “Radiomics in psoriatic arthritis and breast cancer: Assessing disease burden and predicting survival through MR image analysis”.Estimated defence date: January 2019* Statistics* Data analysis* Machine learning* Image processing* MRI

In this project, I investigated how combining molecular and imaging MR methods will give new diagnostic options for treatment stratification of brain tumor patients. • I implemented and tested magnetic resonance imaging (MRI) acquisition protocols for advanced imaging of aggressive brain cancer tumors (gliomas). • I established methods from the analysis of the acquired images in MATLAB.