D-LMBmap: A fully automated deep learning pipeline for whole-brain profiling of neural circuitry

Abstract Recent proliferation and integration of tissue-clearing methods and light-sheet fluorescence microscopy has created new opportunities to achieve mesoscale 3D whole-brain connectivity mapping with exceptionally high throughput. With the rapid generation of massive high-quality imaging datasets, downstream analysis is becoming the major technical bottleneck for mesoscale connectomics. Current computational solutions are labour-intensive with limited applications because of the exhaustive manual annotation and heavily customised training. Meanwhile, whole-brain data analysis always requires combining multiple packages and secondary development by users. To address these challenges, we developed D-LMBmap, an end-to-end package providing an integrated workflow containing three modules based on novel deep-learning algorithms for whole-brain connectivity mapping: axon segmentation, brain region segmentation and whole-brain registration. D-LMBmap is the first method that does not require manual annotation for axon segmentation, and achieves quantitative analysis of whole-brain projectome in a single workflow with superior accuracy for multiple cell types in all of the modalities tested.