Automated Imaging System Research Articles

Automated food intake tracking requires depth-refined semantic segmentation to rectify visual-volume discordance in long-term care homes

Malnutrition is a multidomain problem affecting 54% of older adults in long-term care (LTC). Monitoring nutritional intake in LTC is laborious and subjective, limiting clinical inference capabilities. Recent advances in automatic image-based food estimation have not yet been evaluated in LTC settings. Here, we describe a fully automatic imaging system for quantifying food intake. We propose a novel deep convolutional encoder-decoder food network with depth-refinement (EDFN-D) using an RGB-D camera for quantifying a plate’s remaining food volume relative to reference portions in whole and modified texture foods. We trained and validated the network on the pre-labelled UNIMIB2016 food dataset and tested on our two novel LTC-inspired plate datasets (689 plate images, 36 unique foods). EDFN-D performed comparably to depth-refined graph cut on IOU (0.879 vs. 0.887), with intake errors well below typical 50% (mean percent intake error: -4.2%). We identify how standard segmentation metrics are insufficient due to visual-volume discordance, and include volume disparity analysis to facilitate system trust. This system provides improved transparency, approximates human assessors with enhanced objectivity, accuracy, and precision while avoiding hefty semi-automatic method time requirements. This may help address short-comings currently limiting utility of automated early malnutrition detection in resource-constrained LTC and hospital settings.

Automated Assessment of Cancer Drug Efficacy On Breast Tumor Spheroids in Aggrewell™400 Plates Using Image Cytometry.

Tumor spheroid models have proven useful in the study of cancer cell responses to chemotherapeutic compounds by more closely mimicking the 3-dimensional nature of tumors in situ. Their advantages are often offset, however, by protocols that are long, complicated, and expensive. Efforts continue for the development of high-throughput assays that combine the advantages of 3D models with the convenience and simplicity of traditional 2D monolayer methods. Herein, we describe the development of a breast cancer spheroid image cytometry assay using T47D cells in Aggrewell™400 spheroid plates. Using the Celigo® automated imaging system, we developed a method to image and individually track thousands of spheroids within the Aggrewell™400 microwell plate over time. We demonstrate the use of calcein AM and propidium iodide staining to study the effects of known anti-cancer drugs Doxorubicin, Everolimus, Gemcitabine, Metformin, Paclitaxel and Tamoxifen. We use the image cytometry results to quantify the fluorescence of calcein AM and PI as well as spheroid size in a dose dependent manner for each of the drugs. We observe a dose-dependent reduction in spheroid size and find that it correlates well with the viability obtained from the CellTiter96® endpoint assay. The image cytometry method we demonstrate is a convenient and high-throughput drug-response assay for breast cancer spheroids under 400μm in diameter, and may lay a foundation for investigating other three-dimensional spheroids, organoids, and tissue samples.

Clinical significance of circulating tumor cells after chemotherapy in unresectable pancreatic ductal adenocarcinoma

Circulating tumor cells (CTCs) have emerged as liquid biopsy biomarker providing non-invasive assessment of cancer progression and biology. We investigated whether longitudinal analysis of CTCs could monitor disease progression, response to chemotherapy, and survival in patients with unresectable pancreatic ductal adenocarcinoma (PDAC). A total of 52 patients with PDAC were prospectively enrolled in this study. Peripheral blood samples were serially collected at the time of diagnosis and after chemotherapy with clinical assessments. CTCs were isolated through a centrifugal microfluidic disc, enumerated with immunostaining against Epithelial cell adhesion molecule (EpCAM), Cytokeratin (CK), Plectin-1 and CD45, and identified by an automated imaging system. One or more CTCs were detected in 84.62% patients with unresectable PDAC at the time of diagnosis. CTC numbers were not statistically different across tumor sizes, location and metastatic sites. The absolute number of CTCs after chemotherapy was inversely related to overall survival (OS), and the decreased number of CTCs after chemotherapy was significantly associated with longer OS in patients with PDAC. Identifying CTCs and monitoring CTC changes after chemotherapy could be a useful prognostic marker for survival in patients with unresectable PDACs.

Application of Deep Learning on UAV-Based Aerial Images for Flood Detection

Floods are one of the most fatal and devastating disasters, instigating an immense loss of human lives and damage to property, infrastructure, and agricultural lands. To cater to this, there is a need to develop and implement real-time flood management systems that could instantly detect flooded regions to initiate relief activities as early as possible. Current imaging systems, relying on satellites, have demonstrated low accuracy and delayed response, making them unreliable and impractical to be used in emergency responses to natural disasters such as flooding. This research employs Unmanned Aerial Vehicles (UAVs) to develop an automated imaging system that can identify inundated areas from aerial images. The Haar cascade classifier was explored in the case study to detect landmarks such as roads and buildings from the aerial images captured by UAVs and identify flooded areas. The extracted landmarks are added to the training dataset that is used to train a deep learning algorithm. Experimental results show that buildings and roads can be detected from the images with 91% and 94% accuracy, respectively. The overall accuracy of 91% is recorded in classifying flooded and non-flooded regions from the input case study images. The system has shown promising results on test images belonging to both pre- and post-flood classes. The flood relief and rescue workers can quickly locate flooded regions and rescue stranded people using this system. Such real-time flood inundation systems will help transform the disaster management systems in line with modern smart cities initiatives.

High-Throughput Phenotyping of Leaf Discs Infected with Grapevine Downy Mildew Using Shallow Convolutional Neural Networks

Objective and standardized recording of disease severity in mapping crosses and breeding lines is a crucial step in characterizing resistance traits utilized in breeding programs and to conduct QTL or GWAS studies. Here we report a system for automated high-throughput scoring of disease severity on inoculated leaf discs. As proof of concept, we used leaf discs inoculated with Plasmopara viticola ((Berk. and Curt.) Berl. and de Toni) causing grapevine downy mildew (DM). This oomycete is one of the major grapevine pathogens and has the potential to reduce grape yield dramatically if environmental conditions are favorable. Breeding of DM resistant grapevine cultivars is an approach for a novel and more sustainable viticulture. This involves the evaluation of several thousand inoculated leaf discs from mapping crosses and breeding lines every year. Therefore, we trained a shallow convolutional neural-network (SCNN) for efficient detection of leaf disc segments showing P. viticola sporangiophores. We could illustrate a high and significant correlation with manually scored disease severity used as ground truth data for evaluation of the SCNN performance. Combined with an automated imaging system, this leaf disc-scoring pipeline has the potential to considerably reduce the amount of time during leaf disc phenotyping. The pipeline with all necessary documentation for adaptation to other pathogens is freely available.

Abstract P250: A High-throughput Nitric Oxide Measurement Assay Reveals That Angiotensin-(1-5) Is An AT2 Receptor Agonist

The angiotensin AT2-receptor (AT2R) is a key component within the protective arm of the renin-angiotensin system (RAS), being involved in nitric oxide (NO) production and vasodilation. To this date, no quantitative high-throughput assay is available to identify AT2R agonists in vitro , which may be a reason for the low number of AT2R selective ligands in drug development programs. Objective: To design and validate a high-throughput method for detection of AT2R activation in vitro . Methods and Results: NO release was selected as readout for AT2R activation in AT2R transfected (CHO-AT2) and non-transfected (CHO-NT) CHO cells using DAF-FM (5x10-6 mol/L) as NO probe. Cells were seeded on 96-well plates and stimulated for 15 minutes with C21 or Ang II (established AT2R agonists, 10-6mol/L), Ang-(1-5) (molecule with unknown biological status, 10-6 mol/L) or Ang-(1-7) (Mas-receptor agonist, 10-7 mol/L). After fixation of cells, fluorescence signals were captured by fluorescence microscopy using an automated imaging system (ImageXpress Pico, Molecular Devices, San Jose, USA) and image analysis by ImageJ. In CHO-AT2, C21 (+34.78 ± 12.09%), Ang II (+28.76 ± 17.65%) and Ang-(1-5) (+78.00 ± 23.82%) increased NO release (one-way ANOVA, p < 0.05 vs control, at least 3 independent experiments), while Ang-(1-7) had no effect (+ 0.13 ± 4.74%). In CHO-NT, none of the compounds stimulated release of NO (C21 -4.91 ±10.24%; Ang II -4.79 ± 12.44%; Ang (1-5) -8.88 ± 18.16%; Ang-(1-7) -11.57 ± 19.95%) indicating that the responses in CHO-AT2 were AT2R specific. Conclusion: Measurement of NO release from AT2R transfected CHO cells by DAF-FM fluorescence in an automated way is suitable as high-throughput assay for the identification of AT2R-agonistic compounds in vitro , Application of the assay revealed that Ang-(1-5), which is commonly regarded as an inactive metabolite of Ang II, has AT2R agonistic properties.

Abstract 588: Mesenchymal markers: The new avenue for circulating tumor cells detection

Abstract Introduction: Unlike tissue biopsy, liquid biopsy allows the routine, repeat characterization of cancer at genetic, transcriptional and protein levels. Isolation of circulating tumor cells (CTCs) from a blood draw offers the potential for cancer screening, management and monitoring. Most CTC isolation systems are based on epitope-dependent CTC capture using epithelial markers. However, it is known that tumor cells can undergo epithelial-to-mesenchymal transition (EMT) when extravasating from the primary tumor to enter the bloodstream and eventually establish distant metastases. Epitope-dependent CTC detection platforms have limited sensitivity for detection of mesenchymal CTCs, leading to the inability to harvest clinically relevant CTCs for analysis, particularly in cancers with high mesenchymal phenotype such as non-small cell lung cancer (NSCLC). We developed a research use only assay for enrichment and identification of CTCs based on epithelial and mesenchymal markers using the Parsortix® system, a label-independent microfluidic device that isolates cells based on their size and compressibility. Methods: Peripheral blood (8 – 10mL) was drawn into K2EDTA tubes from 47 metastatic breast cancer (MBC) patients and 48 metastatic NSCLC patients and processed on Parsortix systems within 36 hours after collection. Harvested CTCs were cytospun and immunofluorescently stained using an optimized panel of antibodies for detection of epithelial and mesenchymal markers. Stained slides were imaged using a BioView AllegroPlus automated imaging system. Results: CTCs were captured from both MBC and NSCLC patients. 330 CTCs were identified from 19 MBC patients (mean: 17; range: 1-96). 58 CTCs were identified from 15 NSCLC patients (mean: 4; range: 1-22). Similarly, CTC clusters were observed in 63% (12/19) of the CTC-positive MBC patients and in 33% (5/15) of CTC-positive NSCLC patients. Cluster size ranged from 2-22 CTCs per cluster (2-17 in MBC and 2-22 in NSCLC), and the number of clusters per patient ranged from 1-13 in MBC and 1-2 in NSCLC. Phenotypically, more CTCs expressing only mesenchymal markers were harvested from NSCLC patients compared to MBC patients (38% vs 25%), with a larger proportion of CTCs expressing both epithelial and mesenchymal markers being harvested in both cancer types (59% in NSCLC and 74% in MBC). Only a small percentage of the CTCs harvested expressed just the epithelial markers. Conclusions: This study highlights the importance of the inclusion of mesenchymal markers into CTC characterization, as the majority of the CTCs captured by the Parsortix system from MBC and NSCLC patients expressed mesenchymal markers. The assay developed in this study successfully allowed phenotyping of the harvested cells using epithelial AND mesenchymal markers, with the results suggesting that a large proportion of the CTCs harvested would have been missed with an epithelial-only based approach, particularly in NSCLC. Citation Format: Mariacristina Ciccioli, Natalia Bravo-Santano, Amy Davis, Jolie Lewis, Ross Malcolm, Anne-Sophie Pailhes-Jimenez. Mesenchymal markers: The new avenue for circulating tumor cells detection [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 588.

Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system

Pollen foraging efficiency provides vital information for the behavioral research on honey bees. The pollen production of beehives can be measured by manually weighing the pollen collected from pollen traps. For long-term pollen foraging monitoring, this approach is both inefficient and laborious. This study presents an efficient method for automatically monitoring the pollen foraging behavior and environmental conditions through an embedded imaging system. The imaging system uses an off-the-shelf camera installed at the beehive entrance to acquire video streams that are processed using the developed image processing algorithm. A lightweight real-time object detection and deep learning-based classification model, supported by an object tracking algorithm, was trained for counting and recognizing honey bee into pollen or non-pollen bearing class. The F1-score was 0.94 for pollen and non-pollen bearing honey bee recognition, and the precision and recall values were 0.91 and 0.99, respectively. For foraging trip counting algorithm, the mean average percent errors of the pollen bearing honey bee count and the total incoming honey bee count were 8.45 ± 2.72% and 10.55 ± 2.10%, respectively. An experiment was performed to test the performance of the imaging system in continuous monitoring of honey bee pollen foraging behavior as well as to investigate the effect caused by weather factors. The incoming and outgoing honey bee count were recorded and used to calculate indices based on the hourly and daily recorded counts for further analyses. The experimental results and analyses revealed that the daily pollen foraging trip ratio was 24.5 ± 3.5%; a single beehive collected about 49.1 ± 11.0 g of pollen per day. The pollen foraging trip count increased with increasing temperature and light intensity, and decreased with increasing relative humidity, rain level and wind speed. A significant reduction of pollen foraging activities was observed in heavy rainfall or gentle breeze conditions. This study not only quantitatively presents the effect of environmental factors on pollen foraging behavior, but also demonstrates the efficacy of the proposed imaging system. The automated imaging system can be applied as an efficient and reliable tool for researchers to gain deeper insights into honey bee foraging behavior, and help beekeepers achieve beehive management.

Democratising "Microscopi": a 3D printed automated XYZT fluorescence imaging system for teaching, outreach and fieldwork.

Commercial fluorescence microscope stands and fully automated XYZt fluorescence imaging systems are generally beyond the limited budgets available for teaching and outreach. We have addressed this problem by developing "Microscopi", an accessible, affordable, DIY automated imaging system that is built from 3D printed and commodity off-the-shelf hardware, including electro-mechanical, computer and optical components. Our design features automated sample navigation and image capture with a simple web-based graphical user interface, accessible with a tablet or other mobile device. The light path can easily be switched between different imaging modalities. The open source Python-based control software allows the hardware to be driven as an integrated imaging system. Furthermore, the microscope is fully customisable, which also enhances its value as a learning tool. Here, we describe the basic design and demonstrate imaging performance for a range of easily sourced specimens.

Design and research of fully automatic push-broom hyperspectral microscopic imaging system

The predecessor of China Optics was China Optics and Applied Optics Digest, which was founded in 1985. At that time, it was the only retrieval journal in the field of optics in China. At the end of 2008, China Optics and Applied Optics Digest was renamed

Improved SMD Image Evaluation Function Based on Pixel Difference

In order to improve the noise immunity and sensitivity of the definition evaluation function in the remote sensing automatic imaging system, this paper proposes an improved SMD evaluation function. This function increases the difference between images by accumulating pixel differences in multiple directions, and achieves the ability to distinguish finely defocused images. In order to verify its performance, this article compares the performance of this function with other common spatial domain functions in the same set of image sequences with different definitions. It is found that compared with the common evaluation function, this function has better sensitivity, stronger robustness and moderate image processing speed. This function has certain reference value for imaging systems with high accuracy requirements.

Automated immunohistochemical assessment ability to evaluate estrogen and progesterone receptor status compared with quantitative reverse transcription-polymerase chain reaction in breast carcinoma patients.

BackgroundThis study aimed to investigate the capability of an automated immunohistochemical (IHC) evaluation of hormonal receptor status in breast cancer patients compared to a well-validated quantitative reverse transcription–polymerase chain reaction (RT-qPCR) method.MethodsThis study included 93 invasive breast carcinoma cases that had both standard IHC assay and Oncotype Dx assay results. The same paraffin blocks on which Oncotype Dx assay had been performed were selected. Estrogen receptor (ER) and progesterone receptor (PR) receptor status were evaluated through IHC stains using SP1 monoclonal antibody for ER, and 1E2 monoclonal antibody for PR. All ER and PR immunostained slides were scanned, and invasive tumor areas were marked. Using the Quant-Center image analyzer provided by 3DHISTECH, IHC staining of hormone receptors was measured and converted to histochemical scores (H scores). Pearson correlation coefficients were calculated between Oncotype Dx hormone receptor scores and H scores, and between Oncotype Dx scores and Allred scores.ResultsH scores measured by an automated imaging system showed high concordance with RT-qPCR scores. ER concordance was 98.9% (92/93), and PR concordance was 91.4% (85/93). The correlation magnitude between automated H scores and RT-qPCR scores was high and comparable to those of Allred scores (for ER, 0.51 vs. 0.37 [p = .121], for PR, 0.70 vs. 0.72 [p = .39]).ConclusionsAutomated H scores showed a high concordance with quantitative mRNA expression levels measured by RT-qPCR.

Transcriptomic correlates of neurite degeneration due to human brain‐derived Aβ and protection by clinical anti‐Aβ antibodies

AbstractBackgroundThe proximate cause of dementia in Alzheimer disease (AD) is the dystrophy and loss of synapses and neurites, and the eventual death of neurons. Upstream events include hyperphosphorylation and aggregation of tau, and further upstream is the formation of soluble oligomers of Aβ. The molecular details which link these three and other events within the “amyloid cascade” remain murky, but elucidating them will likely reveal new therapeutic targets.MethodTo dissect early steps in the Aβ oligomer‐driven neuritotoxicity, we recently developed an in vitro system in which human brain‐derived soluble Aβ is applied to iPSC‐derived human neurons (iNs) to induce neurite degeneration (Jin et al, Nat Commun. 2018; 9(1):2676). Soluble extracts from AD brain were either immunodepleted of Aβ with a polyclonal antiserum or mock‐immunodepleted with rabbit IgG, then applied at 21 DIV to iPSC‐derived neurons that had been induced by Neurogenin‐2 expression. Neurite integrity was tracked using the NeuroTrack module of the IncuCyte ZOOM system for live‐cell analysis. Various humanized anti‐Aβ antibodies were added at concentrations from 0.5 to 3 ug/mL along with the control antibody bevacizumab (Avastin).ResultImmunodepletion with the polyclonal antibody resulted in efficient removal of Aβ. Mock‐immunodepleted, but not immunodepleted, human soluble brain extracts caused quantifiable neuritotoxicity using this unbiased, automated imaging system. These effects were rescued to different degrees by different anti‐Aβ antibodies but not by Avastin.ConclusionHuman AD brain‐derived soluble extracts cause neuritotoxicity to human neurons in an Aβ oligomer‐dependent manner. This effect can be decreased by anti‐Aβ antibodies currently in clinical trials, including aducanumab and BAN2401. We are now performing unbiased transcriptomic and proteomic profiling of the iNs after treatment with human‐derived soluble Aβ oligomers to determine the immediate molecular events that precede and accompany Aβ‐dependent neuritotoxicity. These results will be compared with recently‐published single‐cell transcriptomic data from AD brain to identify potential therapeutic targets.

Microscopy automation on a budget: capturing high-speed multi-labelled events with LED Illumination Systems.

Capturing fast cellular processes with widefield fluorescence microscopy and multiple fluorophores has historically required the addition of motorised components. The light source has often been overlooked as an affordable means of achieving multi-wavelength imaging, but LEDs have changed the game. Here we compare typical configurations for automated illumination systems in terms of speed, cost and signal-to-noise ratio (i.e. image contrast). We also explore how to transform a manual microscope into a powerful automated imaging system by capitalising on LED switching speeds, with lower cost filters and minimal requirement for expensive motorised components.

Measuring the Confluence of iPSCs using an Automated Imaging System.

This study focuses on understanding how growing iPSCs on different ECM coating substrates can affect cell confluence. A protocol to assess iPSC confluence in real time has been established without the need to count cells in single cell suspension to avoid any growth perturbation. A high-content image analysis system was used to assess iPCS confluence on 4 different ECMs over time in an automated manner. Different analysis settings were used to assess cell confluence of adherent iPSCs and only a slight difference (at 24 and 48 hours with laminin) has been observed whether a 60, 80 or 100% mask was applied. We also show that laminin lead to the best confluence compared to Matrigel, vitronectin and fibronectin.

Embedded Imaging System Based Behavior Analysis of Dairy Cow

It is essential to develop ambient environmental conditions for counteracting the heat stress in dairy cows by efficient and reliable monitoring of the activities of the cow and existing environmental conditions. For this purpose, we present a system with an array of integrated sensor modules that continuously measure and record humidity and ambient temperature while simultaneously monitoring the dairy cows drinking behavior using a cost-efficient embedded imaging system. Video streams are collected by installing embedded imaging modules over the drinking troughs for testing and experimentation in the dairy farm. Convolutional neural network (CNN) model using deep learning techniques is used for analysis of the video stream by detection of the head of the dairy cow above the drinking trough. The values obtained as true positive rate and F1 score of the detection of the head of the cow are both 0.98. The dairy cows drinking behavior and the effect of heat stress is analyzed and recorded for varied environmental conditions over a period of twelve months. Based on the results of analysis, it is evident that the temperature and humidity index (THI) greatly influence the total frequency and length of everyday drinking habits of dairy cows. The drinking behavior of dairy cows and the effects of heat stress is demonstrated clearly using the automated imaging system with long-term monitoring and data collection. Quantitative assessment and automation are possible using this novel monitoring system to be implemented in dairy farms.

Assessment of dairy cow heat stress by monitoring drinking behaviour using an embedded imaging system

To counteract heat stress in dairy cows, a more reliable and efficient method for monitoring the activity of dairy cows and ambient environmental conditions should be developed. This research presents a cost-effective embedded imaging system that is capable of monitoring the drinking behaviour of dairy cows, while ambient temperature and humidity are simultaneously and continuously recorded with the integrated sensor modules. The embedded imaging system was implemented and tested on an experimental dairy farm, with imaging modules installed above the drinking troughs to collect video streams. To estimate the drinking time and frequency of dairy cows, detections of the dairy cow's head over the drinking troughs was performed on video stream using a deep learning convolutional neural network (CNN) model. The F1 score and true positive rate of the cow head detection were 0.987 and 0.983, respectively. The drinking behaviour data and environmental conditions were recorded and analysed to further assess the effects of heat stress on the drinking behaviour of dairy cows. The experimental results show that the daily total length and frequency of drinking bouts of the dairy cows were highly related to the temperature and humidity index (THI). Data from long-term monitoring using the automated imaging system clearly demonstrated that drinking behaviour reflects the effects of heat stress on dairy cows. The proposed monitoring system offers a novel approach for automatic and quantitative assessment of the drinking behaviours of dairy cows.

Apparent protein cloud point temperature determination using a low volume high-throughput cryogenic device in combination with automated imaging.

Short-term parameters correlating to long-term protein stability, such as the protein cloud point temperature (Tcloud), are of interest to improve efficiency during protein product development. Such efficiency is reached if short-term parameters are obtained in a low volume and high-throughput (HT) manner. This study presents a low volume HT detection method for (sub-zero) Tcloud determination of lysozyme, as such an experimental method is not available yet. The setup consists of a cryogenic device with an automated imaging system. Measurement reproducibility (median absolute deviation of 0.2°C) and literature-based parameter validation (Pearson correlation coefficient of 0.996) were shown by a robustness and validation study. The subsequent case study demonstrated a partial correlation between the obtained apparent Tcloud parameter and long-term protein stability as a function of lysozyme concentration, ion type, ionic strength, and freeze/thaw stress. The presented experimental setup demonstrates its ability to advance short-term strategies for efficient protein formulation development.

Preliminary clinical application of fluorescence microscopic imaging and computer-aided diagnosis system in the diagnosis of superficial cutaneous fungal infections

Objective To evaluate the accuracy of automated fluorescence microscopic imaging and computer-aided diagnosis system (AFMICADS) in the auxiliary diagnosis of superficial cutaneous fungal infections. Methods Totally, 106 outpatients and inpatients with suspected superficial fungal infections were enrolled from clinical departments of Union Hospital, Tongji Medical College, Huazhong University of Science and Technology between July 2018 and September 2018. A total of 126 specimens were collected, including 83 skin scales and 43 nail parings. Each specimen was divided into 3 groups to be examined by conventional fungal microscopy, culture with modified Sabouraud dextrose agar and fluorescence microscopy (artificial fluorescence microscopy and AFMICADS-based fluorescence microscopy) respectively. A positive result was defined as that conventional fungal microscopy and/or fungal culture was positive. Consistency rate, sensitivity and specificity of the 3 microscopic methods were calculated. Statistical analysis was carried out with SPSS 10.0 software by using McNemar test and Kappa test for analyzing difference in the positive rate, as well as consistency, between the 3 microscopic methods and the positive standard, and by using efficiency test for comparing the consistency rate among the 3 microscopic methods. Results Of 126 specimens, 124 (98.4%) were positive for artificial fluorescence microscopy, and 123 (97.6%) for AFMICADS-based fluorescence microscopy. Both positive rates of the above 2 microscopic methods were significantly higher than the positive rate of the positive standard (77.8%, both P 0.05) . Conclusion The accuracy of AFMICADS-based fluorescence microscopy in the diagnosis of superficial cutaneous fungal infections is similar to that of artificial fluorescence microscopy. Key words: Fungi; Microscopy, fluorescence; Diagnosis, computer-assisted; Fluorescence stain; Machine vision; Automated fluorescence microscopic imaging

Development of an all-sky imaging system for cloud cover assessment.

This study develops a novel automatic all-sky imaging system, namely, an all-sky camera (ASC) system, for cloud cover assessment. The proposed system does not require conventional solar occulting devices and can capture complete hemispheric sky images. Cloud detection is performed innovatively using a convolutional neural network model (i.e., the optimized U-Net model). Experiments demonstrate that the optimized U-Net model can effectively detect clouds from sky images. In terms of cloud cover, the estimation results of the ASC system exhibit a high correlation with those obtained via manual observation, thereby indicating the applicability of the ASC system in ground-based cloud observation and analysis.