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.
Pesticides,
extensively used in agriculture production, have received
enormous attention because of their potential threats to the environment
and human health. Hence, in this study, a kind of highly sensitive
and stable hybrid surface-enhanced Raman scattering (SERS)-active
substrates constructed with flower-like two-dimensional molybdenum
sulfide and Ag (MoS2@Ag) has been developed, and then the
above substrate was sequentially utilized in the recyclable detection
of pesticide residues on several kinds of fruits and vegetables. In
the first place, the excellent photocatalytic performance of the MoS2@Ag hybrid substrate was demonstrated, which was attributed
to the inhibition of electron–hole combination after the formation
of Schottky barrier between the Ag NPs and MoS2 matrix.
Thereafter, two calibration curves with ultra-low limits of detection
(LOD) as 6.4 × 10–7 and 9.8 × 10–7 mg/mL were established for the standard solutions of thiram (tetramethylthiuram
disulfide, TMTD) and methyl parathion (MP), and then the recyclable
assay of their single and mixed residues on eggplant, Chinese cabbage,
grape, and strawberry was successfully realized. It is interesting
to note that the detection recoveries from 95.5 to 63.1% for TMTD
and 92.3 to 62.6% for MP are greatly dependent on the size and surface
roughness of these foods. In a word, the MoS2@Ag composite
matrix shows attractive SERS and photocatalysis performance, and it
is expected to have the potential application on food safety monitoring.
The magnetic properties of porous silicon/Fe3O4 composites are investigated with respect to the adjustability of the blocking temperature along with an evaluation of any size-dependent changes in cytocompatibility. Fe3O4-nanoparticles have been infiltrated within mesoporous silicon, resulting in a system with tunable magnetic properties due to the matrix-morphology, the loading of the nanoparticles, and their size. In order to provide basic information regarding its suitability as a therapeutic platform, the cytotoxicity of these composites have been investigated by a trypan blue exclusion assay with respect to human embryonic kidney 293 cells, and the results compared with cell-only and known cytotoxic controls.
This article presents an improved nonlinear ultrasonic technique for fatigue damage detection utilizing a kind of carefully designed aluminum-lead composite metamaterial. It focuses on developing a bandgap metamaterial to improve the accuracy and identifiability of the superharmonic features from fatigue cracks by eliminating the inherent nonlinear components in the nonlinear ultrasonic technique. The study starts with the unit cell design through modal analysis by applying the Bloch-Floquet boundary condition to obtain the band structure. Based on the local resonance mechanism, by adjusting the height ratio between the aluminum and lead cylinders, the bandgaps covering the required frequency ranges can be opened up. Then, a chain of regularly arranged unit cells is modeled to analyze the spectral response and verify the bandgap effect through harmonic analysis. The targeted ultrasonic frequency component of guided waves within the bandgap can be mechanically filtered out. Subsequently, a finite element model of the pitch-catch active sensing procedure for fatigue crack detection is constructed via the coupled-field transient dynamic analysis. Nonlinear ultrasonic experiments with the designed metamaterial are carried out to verify the theoretical and numerical investigations. This paper demonstrates that the metamaterial, with its outstanding wave manipulation capability, shows great potential on structural health monitoring and nondestructive evaluation applications. The paper finishes with summary, concluding remarks, and suggestions for future work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.