Effect of structure-based training on 3D localization precision and quality
This incremental improvement could advance super-resolution microscopy for researchers studying complex biological systems at the nanoscale.
The study tackled the problem of improving single-molecule localization microscopy (SMLM) and 3D object reconstruction by introducing a structural-based training approach for CNN-based algorithms, which significantly improved detection rate and localization precision compared to traditional random-based training, particularly at varying signal-to-noise ratios (SNRs).
This study introduces a structural-based training approach for CNN-based algorithms in single-molecule localization microscopy (SMLM) and 3D object reconstruction. We compare this approach with the traditional random-based training method, utilizing the LUENN package as our AI pipeline. The quantitative evaluation demonstrates significant improvements in detection rate and localization precision with the structural-based training approach, particularly in varying signal-to-noise ratios (SNRs). Moreover, the method effectively removes checkerboard artifacts, ensuring more accurate 3D reconstructions. Our findings highlight the potential of the structural-based training approach to advance super-resolution microscopy and deepen our understanding of complex biological systems at the nanoscale.