"Enhancing 3D Widefield Microscopy with Weak-Labelling and Deep Learning for Precise Object Segmentation"
Originally Published 2 years ago — by Nature.com
Researchers have developed a deep learning model for in-focus object segmentation in 3D widefield microscopy. By using weak labels generated algorithmically, the model was trained to detect in-focus pixels in widefield microscopy images. The model was fine-tuned using manually segmented ground truth data. The results showed that the model successfully separated in-focus and out-of-focus parts of each focal slice, enabling precise 3D reconstruction of specimens. This approach makes in vivo 3D imaging more accessible and affordable for laboratories with limited resources.