An approach for extracting the radial force load on an implanted stent from medical images is proposed. To exemplify the approach, a system is presented which computes radial force estimation from computer tomography images acquired from patients who underwent Transcatheter Aortic Valve Implantation (TAVI). The deformed shape of the implanted valve prosthesis' Nitinol frame is extracted from the images. A set of displacement vectors is computed that parameterizes the observed deformation. An iterative relaxation algorithm is employed to adapt the information extracted from the images to a finite element model of the stent and the radial components of the interaction forces between stent and tissue are extracted. For evaluation of the method, tests were run using clinical data from 21 patients; stent modeling and extraction of radial forces was successful in 18 cases. Synthetic test cases were generated in addition for assessing sensitivity to measurement errors. In a sensitivity analysis, the geometric error of the stent reconstruction was below 0.3, which is below image resolution. The distribution of radial forces are qualitatively and quantitatively reasonable. An uncertainty remains in the quantitative evaluation of the radial forces due to the uncertainty in defining a radial direction on the deformed stent. With our approach, the mechanical situation of TAVI stents after implantation can be studied in-vivo, which may help to understand the mechanisms that lead to complications and improve stent design.