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.

No abstract

Cemented paste backfill (CPB, a mixture of tailings, water and binder) is widely utilized to fill underground mine voids. To achieve a good, economical performance, one approach is to proportionally use mineral admixtures such as fly ash and slag as partial substitutes for Portland cement. Binder hydration is one of the most significant factors that can generate heat within hydrating CPB structures, which in turn, influences the mechanical and hydraulic properties of CPB, as well as the pore structure within CPB. However, the temperature evolution due to the hydration of Portland cement that contains fly ash or slag is different from that of hydration with solely Portland cement. Hence, in consideration of the heat generated by both binder hydration and transferred between CPB and its surrounding media, a numerical model is developed to predict and determine the temperature development within CPB that contains mineral admixtures. After that, data from field and laboratory studies are employed to validate the developed model. The validation results demonstrate a good consistency between the model and the field and laboratory studies. Consequently, the proposed model is applied to simulate and determine the temperature evolution with time via mineral admixtures, binder content, initial rock and CPB temperatures, stope geometry, backfilling rate, curing time and backfilling strategy. The obtained results will contribute to better designs and preparation of CPB mixtures, as well as predict the temperature distribution within CPB structures.

A coupled thermo-hydro-chemical (THC) model has been developed to study the thermally and hydraulically coupled processes in hydrating cemented paste backfill (CPB). Afterwards, the THC model is validated against laboratory data (CPB made of Portland cement and CPB that contains mineral admixtures) and field CPB column studies (CPB cured in underground mine environments). In addition, the validated THC model is applied to simulate and predict the thermal (e.g. temperature development and thermal conductivity), hydraulic (e.g. water drainage, suction or negative pore-water pressure development and hydraulic conductivity) and physical (porosity) evolutions of the CPB columns under different conditions, such as various CPB temperatures and water-to-binder ratios. The presented outcomes can contribute to a better understanding of the coupled thermal-hydraulic processes that occur in CPB and the thermal and hydraulic behaviours of CPB structures, as well as a better design of stable, durable and cost-effective CPB mixtures. IntroductionThe technology of cemented paste backfill (CPB, a mixture of binders, water and tailings) [1-5] is widely used in underground mining practices all around the world [6][7][8][9][10][11][12]. The utilisation of CPB technology not only allows a significant reduction in the cost and environmental issues associated with surface tailings storage facilities (e.g. tailings dams), but also provides a safe working environment for miners by supporting the surrounding ore body and rock [13][14][15][16].Mechanical stability, environmental and durability properties, as well as thermal properties, are important performance characteristics of CPB structures [17][18][19]. Once placed into underground openings, CPB structures should bear enough strength or show acceptable mechanical stability to support adjacent stopes during mining operations, and thereby ensure the safety of the mine workers. The uniaxial compressive strength (UCS) is the most common parameter used to evaluate the stability of CPB structures in practice. However, the strength (UCS and shear strength) and effective stress development within the CPB are strongly affected by the thermal (e.g. heat induced by the binder hydration) and hydraulic (e.g. positive pore-water pressure, negative pore-water pressure or suction) processes that occur within the CPB and their interactions