Change Point Detection is a well-established and long-standing field in statistics. My focus is on applying it to multidimensional data, such as MRI. This includes, but is not limited to, improving models to enhance detection power while reducing bias and leveraging optimization techniques to address the computational complexity that arises. 

My research interest lies in using image data for medical diagnosis to reduce errors caused by subjective judgment. This involves areas such as computer image recognition and survival analysis. Due to the complexity of image data itself, techniques like deep learning may be involved. 

Due to the trade-off between computational complexity and accuracy brought by multidimensional data, I am dedicated to discovering better optimization tools to achieve a balance between computation and precision. 

Traditional statistical models struggle to explain complex nonlinear relationships. I am focused on combining them with traditional statistical survival models to achieve better effectiveness in automated diagnosis.