biostudies-literatureHaertter DStudienstiftung des Deutschen VolkesSoft Matter Center, Duke UniversityNational Institutes of HealthNIAMS NIH HHSNIH HHSNIGMS NIH HHSdev200621https://www.ebi.ac.uk/biostudies/studies/S-EPMC9686994biostudies-literatureUnknown149(21)The efficient extraction of image data from curved tissue sheets embedded in volumetric imaging data remains a serious and unsolved problem in quantitative studies of embryogenesis. Here, we present DeepProjection (DP), a trainable projection algorithm based on deep learning. This algorithm is trained on user-generated training data to locally classify 3D stack content, and to rapidly and robustly predict binary masks containing the target content, e.g. tissue boundaries, while masking highly fluorescent out-of-plane artifacts. A projection of the masked 3D stack then yields background-free 2D images with undistorted fluorescence intensity values. The binary masks can further be applied to other fluorescent channels or to extract local tissue curvature. DP is designed as a first processingDevelopment (Cambridge, England)DeepProjection: specific and robust projection of curved 2D tissue sheets from 3D microscopy using deep learning.PMC9686994R35GM127059R35 GM127059R01 AR076342R01-AR076342Haertter DCrawford JMFogerson SMDi Talia SSchmidt CFRamkumar NWang XKiehart DPPoss KDfalseDeepProjection: specific and robust projection of curved 2D tissue sheets from 3D microscopy using deep learning.The efficient extraction of image data from curved tissue sheets embedded in volumetric imaging data remains a serious and unsolved problem in quantitative studies of embryogenesis. Here, we present DeepProjection (DP), a trainable projection algorithm based on deep learning. This algorithm is trained on user-generated training data to locally classify 3D stack content, and to rapidly and robustly predict binary masks containing the target content, e.g. tissue boundaries, while masking highly fluorescent out-of-plane artifacts. A projection of the masked 3D stack then yields background-free 2D images with undistorted fluorescence intensity values. The binary masks can further be applied to other fluorescent channels or to extract local tissue curvature. DP is designed as a first processing2022-01-01T00:00:00Z2022 Nov2026-05-28T01:38:29.42Z2025-04-07T07:47:22.607ZS-EPMC96869943617810810.1242/dev.200621