Abstract Automated segmentation of mitochondria is crucial for statistical analysis in biological research. Existing segmentation techniques often face challenges with fluorescence images. Handcrafted methods have poor segmentation results while deep learning‐based methods lack the labeled mitochondrial data. However, although the number of labeled mitochondrial images is limited, the unlabeled fluorescent data is easy to obtain. The authors aim to leverage a large amount of unlabeled data to learn mitochondrial morphological features. The approach begins with self‐supervised learning from a vast set of unlabeled images through masked image modeling. This technique involves presenting images with randomly masked patches, prompting the model to predict the content of these masked areas. By doing so, the model learns the distinctive features of mitochondria. In the subsequent phase, the trained encoder is transferred to the segmentation task, replacing the original reconstruction decoder with the Segformer segmentation decoder. The model is then fine‐tuned using a small labeled dataset. By reconstructing mitochondria in the masked regions, the model learns features more effectively on unlabeled samples, and improves segmentation performance even with limited labeled data. Empirical results validate the effectiveness of the approach, showing an 11.8% improvement in Intersection over Union metrics compared to existing fluorescence mitochondrial segmentation techniques.

Conventional two-dimensional structured illumination microscopy (SIM) requires 9 raw images to reconstruct a super-resolved image. In order to increase the frame rate of 2DSIM, attempts are being made to reduce the number of raw SIM images. However, all the proposed SIM reconstruction algorithms (SIM-RA) capable of reconstructing super-resolution (SR) image with a reduced number of raw SIM images operate in the spatial domain. Here, we present a frequency domain SIM-RA based on ordinary least squares technique, which enables reconstruction of SR image using 4 raw SIM images. Unlike the spatial domain RA, which produces the SR image through iterative convergence, the presented RA provides a single step solution. It also reveals the fundamental limitation of least number of raw images required for resolution doubling in SIM.