ABSTRACT
BACKGROUND: Multiphoton microscopy (MPM) offers a feasible approach for the biopsy in clinical medicine, but it has not been used in clinical applications due to the lack of efficient image processing methods, especially the automatic segmentation technology. Segmentation technology is still one of the most challenging assignments of the MPM imaging technique. METHODS: The MPM imaging segmentation model based on deep learning is one of the most effective methods to address this problem. In this paper, the practicability of using a convolutional neural network (CNN) model to segment the MPM image of skin cells in vivo was explored. A set of MPM in vivo skin cells images with a resolution of 128×128 was successfully segmented under the Python environment with TensorFlow. A novel deep-learning segmentation model named Dense-UNet was proposed. The Dense-UNet, which is based on U-net structure, employed the dense concatenation to deepen the depth of the network architecture and achieve feature reuse. This model included four expansion modules (each module consisted of four down-sampling layers) to extract features. RESULTS: Sixty training images were taken from the dorsal forearm using a femtosecond Ti:Sa laser running at 735 nm. The resolution of the images is 128×128 pixels. Experimental results confirmed that the accuracy of Dense-UNet (92.54%) was higher than that of U-Net (88.59%), with a significantly lower loss value of 0.1681. The 90.60% Dice coefficient value of Dense-UNet outperformed U-Net by 11.07%. The F1-Score of Dense-UNet, U-Net, and Seg-Net was 93.35%, 90.02%, and 85.04%, respectively. CONCLUSIONS: The deepened down-sampling path improved the ability of the model to capture cellular fined-detailed boundary features, while the symmetrical up-sampling path provided a more accurate location based on the test result. These results were the first time that the segmentation of MPM in vivo images had been adopted by introducing a deep CNN to bridge this gap in Dense-UNet technology. Dense-UNet has reached ultramodern performance for MPM images, especially for in vivo images with low resolution. This implementation supplies an automatic segmentation model based on deep learning for high-precision segmentation of MPM images in vivo.
ABSTRACT
The backward second harmonic generation (SHG) in mouse tissues is studied with a confocal multiphoton microscopy system. The total backward collected SHG (B-SHG) consists of the backward generated SHG and the backward-scattered forward-generated SHG (BS-SHG), which can be modeled by a Gaussian and a uniform distribution, respectively, at the confocal pinhole plane. By varying the pinhole size with a series of collection fibers, the proportion of the BS-SHG to the B-SHG and the proportion of BS-SHG to the forward generated SHG can be obtained. The approach is first validated by Monte Carlo simulation. It is then applied to two types of mouse tissues: mouse tail tendon and Achilles tendon. It is found that the BS-SHG contributes less to the B-SHG for the tail tendon than Achilles tendon with thicknesses of ~300 µm. With the thickness of the Achilles tendon tissue increased to 1000 µm but the focal plane kept at the same depth, as high as ~10% of the total forward SHG is backscattered and collected. The results indicate that BS-SHG may not be the major source of B-SHG in the tail tendon, but it may be the major source in the Achilles tendon. These methods and results provide a noninvasive method and supporting information for investigating the generation mechanism of SHG and help with optimizing backward SHG microscopy and spectroscopy measurements.
