Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge
This work addresses a challenging but incremental problem for biomedical imaging researchers by improving registration accuracy in a specific domain.
The paper tackled the problem of automatically registering second-harmonic generation microscopy images to H&E slides, a multi-modal task with missing data, by proposing a method based on keypoint matching and deformable registration, achieving an 88% success rate in initial alignment and an average target registration error of 2.48 on an external validation set.
The automatic registration of noninvasive second-harmonic generation microscopy to hematoxylin and eosin slides is a highly desired, yet still unsolved problem. The task is challenging because the second-harmonic images contain only partial information, in contrast to the stained H&E slides that provide more information about the tissue morphology. Moreover, both imaging methods have different intensity distributions. Therefore, the task can be formulated as a multi-modal registration problem with missing data. In this work, we propose a method based on automatic keypoint matching followed by deformable registration based on instance optimization. The method does not require any training and is evaluated using the dataset provided in the Learn2Reg challenge by the COMULIS organization. The method achieved relatively good generalizability resulting in 88% of success rate in the initial alignment and average target registration error equal to 2.48 on the external validation set. We openly release the source code and incorporate it in the DeeperHistReg image registration framework.