Tammy Riklin Raviv (Ben-Gurion University)
Tuesday, 15.5.2018, 11:30
Recent progress in imaging technologies leads to a continuous growth in biomedical data, which can provide better insight into important clinical and biological questions. Advanced machine learning techniques, such as artificial neural networks are brought to bear on addressing fundamental medical image computing challenges such as segmentation, classification and reconstruction, required for meaningful analysis of the data. Nevertheless, the main bottleneck, which is the lack of annotated examples or ‘ground truth’ to be used for training and assessment, still remains.
In my talk, I will give a brief overview on some biomedical image analysis problems we aim to address, and suggest how prior information about the problem at hand can be utilized to compensate for insufficient or even the absence of ground-truth data. I will also suggest a way to evaluate the clinical usability of the results. Doing so I will focus on three particular studies carried out in my group for Denoising, Segmentation and Reconstruction of Biological and Medical data.