Image preprocessing to improve the accuracy and robustness of mutual-information-based automatic image registration in proton therapy

•Accuracy of mutual information for automatic registration of medical images is not enough.•A contrast enhancement filter was applied to convert the image characteristics.•Filter preprocessing enabled more accurate and robust automatic image registration.•Accuracy equivalent to experts was achieved in 15 s in proposed method. We propose a method that potentially improves the outcome of mutual-information-based automatic image registration by using the contrast enhancement filter (CEF). Seventy-six pairs of two-dimensional X-ray images and digitally reconstructed radiographs for 20 head and neck and nine lung cancer patients were analyzed retrospectively. Automatic image registration was performed using the mutual-information-based algorithm in VeriSuite®. Images were preprocessed using the CEF in VeriSuite®. The correction vector for translation and rotation error was calculated and manual image registration was compared with automatic image registration, with and without CEF. In addition, the normalized mutual information (NMI) distribution between two-dimensional images was compared, with and without CEF. In the correction vector comparison between manual and automatic image registration, the average differences in translation error were