Multimodal registration of FISH and nanoSIMS images using convolutional neural network models

Nanoscale secondary ion mass spectrometry (nanoSIMS) and fluorescence in situ hybridization (FISH) microscopy provide high-resolution, multimodal image representations of the identity and cell activity respectively of targeted microbial communities in microbiological research. Despite its importance to microbiologists, multimodal registration of FISH and nanoSIMS images is challenging given the morphological distortion and background noise in both images. In this study, we use convolutional neural networks (CNNs) for multiscale feature extraction, shape context for computation of the minimum transformation cost feature matching and the thin-plate spline (TPS) model for multimodal registration of the FISH and nanoSIMS images. Registration accuracy was quantitatively assessed against manually registered images, at both, the pixel and structural levels using standard metrics. Although all six tested CNN models performed well, ResNet18 was observed to outperform VGG16, VGG19, GoogLeNet and ShuffleNet and ResNet101 based on most metrics. This study demonstrates the utility of CNNs in the registration of multimodal images with significant background noise and morphology distortion. We also show aggregate shape, preserved by binarization, to be a robust feature for registering multimodal microbiology-related images.