An integrated centrifugal microfluidic strategy for point-of-care complete blood counting

Centrifugal microfluidics holds the potential to revolutionize point-of-care (POC) testing by simplifying laboratory tests through automating fluid and cell manipulation within microfluidic channels. This technology can facilitate blood testing, the most frequent clinical test, at the POC. However, an integrated centrifugal microfluidic device for complete blood counting (CBC) has not yet been fully realized. To address this, we propose an integrated portable system comprising a centrifuge and a hybrid microfluidic disc specifically designed for CBC analysis at the POC. The disc enables the implementation of various spin profiles in different stages of CBC to facilitate in-situ cell separation, solution metering and mixing, and differential cell counting. Furthermore, our system is coupled with a custom script that automates the process and ensures precise quantification of cells using light and fluorescent images captured from the detection chamber of the disc. We demonstrate a close correlation between the proposed method and the hematology analyzer, considered the gold standard, for quantifying hematocrit (R2 = 0.99), white blood cell count (R2 = 0.98), white blood cell differential count (granulocyte/agranulocyte; R2 = 0.89), red blood cell count (R2 = 0.97), and mean corpuscular volume (R2 = 0.94). The integration of our portable system offers significant advantages, enabling more accessible and affordable CBC testing at the POC. Considering the simplicity, affordability (∼$250 capital cost and <$2 operational cost per test), as well as low power consumption (>100 tests using a typical 24 V/10 Ah battery), this system has the potential to enhance healthcare delivery, particularly in resource-limited settings and remote areas where access to traditional laboratory facilities is limited.

GalliformeSpectra: A hen breed dataset

This article presents a comprehensive dataset featuring ten distinct hen breeds, sourced from various regions, capturing the unique characteristics and traits of each breed. The dataset encompasses Bielefeld, Blackorpington, Brahma, Buckeye, Fayoumi, Leghorn, Newhampshire, Plymouthrock, Sussex, and Turken breeds, offering a diverse representation of poultry commonly bred worldwide. A total of 1010 original JPG images were meticulously collected, showcasing the physical attributes, feather patterns, and distinctive features of each hen breed. These images were subsequently standardized, resized, and converted to PNG format for consistency within the dataset. The compilation, although unevenly distributed across the breeds, provides a rich resource, serving as a foundation for research and applications in poultry science, genetics, and agricultural studies. This dataset holds significant potential to contribute to various fields by enabling the exploration and analysis of unique characteristics and genetic traits across different hen breeds, thereby supporting advancements in poultry breeding, farming, and genetic research.

Aerial images and water quality dataset for fishpond's condition monitoring

This dataset is part of fundamental research to produce IoT monitoring in fishponds. The data consists of the results of measurements of pH, total dissolved solids (TDS), and water temperature obtained through manual sensor devices in several locations at different times. Additionally, this data also includes images taken by drones at consistent heights. These images are linked to the sensor data that has been collected. In this research, data will be used to monitor the health of fishponds through visual data. This data can be used for correlation analysis between visual data and sensor data. The hypothesis is the visual appearance of the pond (the colour) is affected by the number of mixed solid (mud and other organic material) in the water, which reflected in the TDS level of the water. In addition, the data can also be used for initial investigations into the development of machine learning models for pool condition recognition through image analysis.

Labeled dataset for bee detection and direction estimation on entrance to beehive

The datasets for bee detection, pose estimation and segmentation consist of organized folders containing both images and corresponding labels. The detection dataset comprises a total of 7200 individual frames collected at 8 different beehives. The pose dataset contains 400 images of bees annotated with two key points per bee. The first point marks a head, second point marks a stinger. All frames have a resolution of 1920×1080 pixels. The segmentation dataset contains 2300 cropped images of bees. These cropped images are annotated with triangular markers that aid in estimating directional vectors. The labels in all proposed datasets were saved in YOLO format. The labeling process was automated by training YOLOv8 model on a set of manually annotated images for bee detection. After detection, all the labels were visually revised and corrected. Frames were captured using stationary mounted camera 30 cm above beehive landing boards. The data collection period spanned from June to July 2023 in Vilnius district.

Intraprocedural assessment of ablation margins using computed tomography co-registration in hepatocellular carcinoma treatment with percutaneous ablation: IAMCOMPLETE study

PURPOSE

The primary objective of this study was to determine the feasibility of ablation margin quantification using a standardized scanning protocol during thermal ablation (TA) of hepatocellular carcinoma (HCC), and a rigid registration algorithm. Secondary objectives were to determine the inter- and intra-observer variability of tumor segmentation and quantification of the minimal ablation margin (MAM).

MATERIALS AND METHODS

Twenty patients who underwent thermal ablation for HCC were included. There were thirteen men and seven women with a mean age of 67.1 ± 10.8 (standard deviation [SD]) years (age range: 49.1-81.1 years). All patients underwent contrast-enhanced computed tomography examination under general anesthesia directly before and after TA, with preoxygenated breath hold. Contrast-enhanced computed tomography examinations were analyzed by radiologists using rigid registration software. Registration was deemed feasible when accurate rigid co-registration could be obtained. Inter- and intra-observer rates of tumor segmentation and MAM quantification were calculated. MAM values were correlated with local tumor progression (LTP) after one year of follow-up.

RESULTS

Co-registration of pre- and post-ablation images was feasible in 16 out of 20 patients (80%) and 26 out of 31 tumors (84%). Mean Dice similarity coefficient for inter- and intra-observer variability of tumor segmentation were 0.815 and 0.830, respectively. Mean MAM was 0.63 ± 3.589 (SD) mm (range: -6.26-6.65 mm). LTP occurred in four out of 20 patients (20%). The mean MAM value for patients who developed LTP was -4.00 mm, as compared to 0.727 mm for patients who did not develop LTP.

CONCLUSION

Ablation margin quantification is feasible using a standardized contrast-enhanced computed tomography protocol. Interpretation of MAM was hampered by the occurrence of tissue shrinkage during TA. Further validation in a larger cohort should lead to meaningful cut-off values for technical success of TA.

Multimodal real-time imaging with laser speckle contrast and fluorescent contrast

INTRODUCTION

Laser speckle contrast imaging (LSCI) can achieve real-time 2D perfusion maps non-invasively. However, LSCI is still difficult to use in general clinical applications because of movement sensitivity and limitations in blood flow analysis. To overcome this, fluorescence imaging (FI) is combined with LSCI using a light source with a wavelength of 785 nm in near-infrared (NIR) region and validates to visualize real-time blood perfusion.

MATERIALS AND METHODS

The system was performed using Intralipid and indocyanine green (ICG) in a flow phantom that has three tubes and controlled the flow rate in 0-150 μl/min range. First, real-time LSCI was monitored and measured the change in speckle contrast by reperfusion. Then, we visualized blood perfusion of a rabbit ear under the non-invasive condition by intravenous injection using a total of five different ICG concentration solutions from 128 μM to 3.22 mM.

RESULTS

The combined system achieved the performance of processing laser speckle images at about 37-38 fps, and we simultaneously confirmed the fluorescence of ICG and changes in speckle contrast due to intralipid as a light scatterer. In addition, we obtained real-time contrast variation and fluorescent images occurring in rabbit's blood perfusion.

CONCLUSIONS

The aim of this study is to provide a real-time diagnostic imaging system that can be used in general clinical applications. LSCI and FI are combined complementary for observing tissue perfusion using a single NIR light source. The combined system could achieve real-time visualization of blood perfusion non-invasively.

Can Digital Enhancement Restore the Image Quality of Phosphor Plate-Based Radiographs Partially Damaged by Ambient Light?

To assess the effect of digital enhancement on the image quality of radiographs obtained with photostimulable phosphor (PSP) plates partially damaged by ambient light. Radiographs of an aluminum step wedge were obtained using the VistaScan and Express systems. Half of the PSP plates was exposed to ambient light for 0, 10, 30, 60, or 90 s before being scanned. The resulting radiographs were exported with and without digital enhancement. Metrics for brightness, contrast, and contrast-to-noise ratio (CNR) were derived, and the ratio of each metric between the exposed-to-light and non-exposed-to-light halves of the radiographs was calculated. The resulting ratios of the radiographs with digital enhancement were subtracted from those without digital enhancement and compared among each other. For the VistaScan system, digital enhancement partially restored brightness, contrast, and CNR. For the Express system, digital enhancement only restored CNR and not the impact of ambient light on brightness and contrast. Specifically, digital enhancement restored 23.48% of brightness for the VistaScan, while percentages below 1% were observed for the Express. Digital enhancement restored 53.25% of image contrast for the VistaScan and 5.79% for the Express; 40.71% of CNR was restored for the VistaScan, and 35% for the Express. Digital enhancement can partially restore the damage caused by ambient light on the brightness and contrast of PSP-based radiographs obtained with the VistaScan, as well as on CNR for the VistaScan and Express systems. The exposure of PSP plates to light can lead to unnecessary retakes and increased patient exposure to X-rays.

Whole-tumor histogram analysis of multiparametric breast magnetic resonance imaging to differentiate pure mucinous breast carcinomas from fibroadenomas with high-signal intensity on T2WI

PURPOSE

To investigate the utility of whole-tumor histogram analysis based on multiparametric MRI in distinguishing pure mucinous breast carcinomas (PMBCs) from fibroadenomas (FAs) with strong high-signal intensity on T2-weighted imaging (T2-SHi).

MATERIAL AND METHODS

The study included 20 patients (mean age, 55.80 ± 15.54 years) with single PBMCs and 29 patients (mean age, 42.31 ± 13.91 years) with single FAs exhibiting T2-SHi. A radiologist performed whole-tumor histogram analysis between PBMC and FA groups with T2-SHi using multiparametric MRI, including T2-weighted imaging (T2WI), diffusion weighted imaging (DWI) with apparent diffusion coefficient (ADC) maps, and the first (DCE_T1) and last (DCE_T4) phases of T1-weighted dynamic contrast-enhanced imaging (DCE) images, to extract 11 whole-tumor histogram parameters. Histogram parameters were compared between the two groups to identify significant variables using univariate analyses, and their diagnostic performance was assessed by receiver operating characteristic (ROC) curve analysis and logistic regression analyses. In addition, 15 breast lesions were randomly selected and histogram analysis was repeated by another radiologist to assess the intraclass correlation coefficient for each histogram feature. Pearson's correlation coefficients were used to analyze the correlations between histogram parameters and Ki-67 expression of PMBCs.

RESULTS

For T2WI images, mean, median, maximum, 90th percentile, variance, uniformity, and entropy significantly differed in PBMCs and FAs with T2-SHi (all P < 0.05), yielding a combined area under the curve (AUC) of 0.927. For ADC maps, entropy was significantly lower in FAs with T2-SHi than in PMBCs (P = 0.03). In both DCE_T1 and DCE_T4 sequences, FAs with T2-SHi showed significantly higher minimum values than PBMCs (P = 0.007 and 0.02, respectively). The highest AUC value of 0.956 (sensitivity, 0.862; specificity, 0.944; positive predictive value, 0.962; negative predictive value, 0.810) was obtained when all significant histogram parameters were combined.

CONCLUSIONS

Whole-tumor histogram analysis using multiparametric MRI is valuable for differentiating PBMCs from FAs with T2-SHi.

Dipper throated optimization with deep convolutional neural network-based crop classification for remote sensing image analysis

Problem

With the rapid advancement of remote sensing technology is that the need for efficient and accurate crop classification methods has become increasingly important. This is due to the ever-growing demand for food security and environmental monitoring. Traditional crop classification methods have limitations in terms of accuracy and scalability, especially when dealing with large datasets of high-resolution remote sensing images. This study aims to develop a novel crop classification technique, named Dipper Throated Optimization with Deep Convolutional Neural Networks based Crop Classification (DTODCNN-CC) for analyzing remote sensing images. The objective is to achieve high classification accuracy for various food crops.

Methods

The proposed DTODCNN-CC approach consists of the following key components. Deep convolutional neural network (DCNN) a GoogleNet architecture is employed to extract robust feature vectors from the remote sensing images. The Dipper throated optimization (DTO) optimizer is used for hyper parameter tuning of the GoogleNet model to achieve optimal feature extraction performance. Extreme Learning Machine (ELM): This machine learning algorithm is utilized for the classification of different food crops based on the extracted features. The modified sine cosine algorithm (MSCA) optimization technique is used to fine-tune the parameters of ELM for improved classification accuracy.

Results

Extensive experimental analyses are conducted to evaluate the performance of the proposed DTODCNN-CC approach. The results demonstrate that DTODCNN-CC can achieve significantly higher crop classification accuracy compared to other state-of-the-art deep learning methods.

Conclusion

The proposed DTODCNN-CC technique provides a promising solution for efficient and accurate crop classification using remote sensing images. This approach has the potential to be a valuable tool for various applications in agriculture, food security, and environmental monitoring.

Automatic 3D cell segmentation of fruit parenchyma tissue from X-ray micro CT images using deep learning

BACKGROUND

High quality 3D information of the microscopic plant tissue morphology-the spatial organization of cells and intercellular spaces in tissues-helps in understanding physiological processes in a wide variety of plants and tissues. X-ray micro-CT is a valuable tool that is becoming increasingly available in plant research to obtain 3D microstructural information of the intercellular pore space and individual pore sizes and shapes of tissues. However, individual cell morphology is difficult to retrieve from micro-CT as cells cannot be segmented properly due to negligible density differences at cell-to-cell interfaces. To address this, deep learning-based models were trained and tested to segment individual cells using X-ray micro-CT images of parenchyma tissue samples from apple and pear fruit with different cell and porosity characteristics.

RESULTS

The best segmentation model achieved an Aggregated Jaccard Index (AJI) of 0.86 and 0.73 for apple and pear tissue, respectively, which is an improvement over the current benchmark method that achieved AJIs of 0.73 and 0.67. Furthermore, the neural network was able to detect other plant tissue structures such as vascular bundles and stone cell clusters (brachysclereids), of which the latter were shown to strongly influence the spatial organization of pear cells. Based on the AJIs, apple tissue was found to be easier to segment, as the porosity and specific surface area of the pore space are higher and lower, respectively, compared to pear tissue. Moreover, samples with lower pore network connectivity, proved very difficult to segment.

CONCLUSIONS

The proposed method can be used to automatically quantify 3D cell morphology of plant tissue from micro-CT instead of opting for laborious manual annotations or less accurate segmentation approaches. In case fruit tissue porosity or pore network connectivity is too low or the specific surface area of the pore space too high, native X-ray micro-CT is unable to provide proper marker points of cell outlines, and one should rely on more elaborate contrast-enhancing scan protocols.

Phenotyping calcification in vascular tissues using artificial intelligence

Vascular calcification is implicated as an important factor in major adverse cardiovascular events (MACE), including heart attack and stroke. A controversy remains over how to integrate the diverse forms of vascular calcification into clinical risk assessment tools. Even the commonly used calcium score for coronary arteries, which assumes risk scales positively with total calcification, has important inconsistencies. Fundamental studies are needed to determine how risk is influenced by the diverse calcification phenotypes. However, studies of these kinds are hindered by the lack of high-throughput, objective, and non-destructive tools for classifying calcification in imaging data sets. Here, we introduce a new classification system for phenotyping calcification along with a semi-automated, non-destructive pipeline that can distinguish these phenotypes in even atherosclerotic tissues. The pipeline includes a deep-learning-based framework for segmenting lipid pools in noisy μ-CT images and an unsupervised clustering framework for categorizing calcification based on size, clustering, and topology. This approach is illustrated for five vascular specimens, providing phenotyping for thousands of calcification particles across as many as 3200 images in less than seven hours. Average Dice Similarity Coefficients of 0.96 and 0.87 could be achieved for tissue and lipid pool, respectively, with training and validation needed on only 13 images despite the high heterogeneity in these tissues. By introducing an efficient and comprehensive approach to phenotyping calcification, this work enables large-scale studies to identify a more reliable indicator of the risk of cardiovascular events, a leading cause of global mortality and morbidity.

Predicting the quality attributes related to geographical growing regions in red-fleshed kiwifruit by data fusion of electronic nose and computer vision systems

The ability of a data fusion system composed of a computer vision system (CVS) and an electronic nose (e-nose) was evaluated to predict key physiochemical attributes and distinguish red-fleshed kiwifruit produced in three distinct regions in northern Iran. Color and morphological features from whole and middle-cut kiwifruits, along with the maximum responses of the 13 metal oxide semiconductor (MOS) sensors of an e-nose system, were used as inputs to the data fusion system. Principal component analysis (PCA) revealed that the first two principal components (PCs) extracted from the e-nose features could effectively differentiate kiwifruit samples from different regions. The PCA-SVM algorithm achieved a 93.33% classification rate for kiwifruits from three regions based on data from individual e-nose and CVS. Data fusion increased the classification rate of the SVM model to 100% and improved the performance of Support Vector Regression (SVR) for predicting physiochemical indices of kiwifruits compared to individual systems. The data fusion-based PCA-SVR models achieved validation R2 values ranging from 90.17% for the Brix-Acid Ratio (BAR) to 98.57% for pH prediction. These results demonstrate the high potential of fusing artificial visual and olfactory systems for quality monitoring and identifying the geographical growing regions of kiwifruits.

Learning Morphological, Spatial, and Dynamic Models of Cellular Components

In this chapter, we describe protocols for using the CellOrganizer software on the Jupyter Notebook platform to analyze and model cell and organelle shape and spatial arrangement. CellOrganizer is an open-source system for using microscope images to learn statistical models of the structure of cell components and how those components are organized relative to each other. Such models capture the statistical variation in the organization of cellular components by jointly modeling the distributions of their number, shape, and spatial distributions. These models can be created for different cell types or conditions and compared to reflect differences in their spatial organizations. The models are also generative, in that they can be used to synthesize new cell instances reflecting what a model learned and to provide well-structured cell geometries that can be used for biochemical simulations.

Structural Analysis of Protein Complexes by Cryo-Electron Microscopy

Structural studies of bio-complexes using single particle cryo-Electron Microscopy (cryo-EM) is nowadays a well-established technique in structural biology and has become competitive with X-ray crystallography. Development of digital registration systems for electron microscopy images and algorithms for the fast and efficient processing of the recorded images and their following analysis has facilitated the determination of structures at near-atomic resolution. The latest advances in EM have enabled the determination of protein complex structures at 1.4-3 Å resolution for an extremely broad range of sizes (from ~100 kDa up to hundreds of MDa (Bartesaghi et al., Science 348(6239):1147-1151, 2015; Herzik et al., Nat Commun 10:1032, 2019; Wu et al., J Struct Biol X 4:100020, 2020; Zhang et al., Nat Commun 10:5511, 2019; Zhang et al., Cell Res 30(12):1136-1139, 2020; Yip et al., Nature 587(7832):157-161, 2020; https://www.ebi.ac.uk/emdb/statistics/emdb_resolution_year )). In 2022, nearly 1200 structures deposited to the EMDB database were at a resolution of better than 3 Å ( https://www.ebi.ac.uk/emdb/statistics/emdb_resolution_year ).To date, the highest resolutions have been achieved for apoferritin, which comprises a homo-oligomer of high point group symmetry (O432) and has rigid organization together with high stability (Zhang et al., Cell Res 30(12):1136-1139, 2020; Yip et al., Nature 587(7832):157-161, 2020). It has been used as a test object for the assessments of modern cryo-microscopes and processing methods during the last 5 years. In contrast to apoferritin bacterial secretion systems are typical examples of multi protein complexes exhibiting high flexibility owing to their functions relating to the transportation of small molecules, proteins, and DNA into the extracellular space or target cells. This makes their structural characterization extremely challenging (Barlow, Methods Mol Biol 532:397-411, 2009; Costa et al., Nat Rev Microbiol 13:343-359, 2015). The most feasible approach to reveal their spatial organization and functional modification is cryo-electron microscopy (EM). During the last decade, structural cryo-EM has become broadly used for the analysis of the bio-complexes that comprise multiple components and are not amenable to crystallization (Lyumkis, J Biol Chem 294:5181-5197, 2019; Orlova and Saibil, Methods Enzymol 482:321-341, 2010; Orlova and Saibil, Chem Rev 111(12):7710-7748, 2011).In this review, we will describe the basics of sample preparation for cryo-EM, the principles of digital data collection, and the logistics of image analysis focusing on the common steps required for reconstructions of both small and large biological complexes together with refinement of their structures to nearly atomic resolution. The workflow of processing will be illustrated by examples of EM analysis of Type IV Secretion System.

Observation of Bacteriophage Ultrastructure by Cryo-Electron Microscopy

Transmission electron microscopy (TEM) is an ideal method to observe and determine the structure of bacteriophages. From early studies by negative staining to the present atomic structure models derived from cryo-TEM, bacteriophage detection, classification, and structure determination have been mostly done by electron microscopy. Although embedding in metal salts has been a routine method for virus observation for many years, the preservation of bacteriophages in a thin layer of fast frozen buffer has proven to be the most convenient preparation method for obtaining images using cryo-electron microscopy (cryo-EM). In this technique, frozen samples are observed at liquid nitrogen temperature, and the images are acquired using different recording media. The incorporation of direct electron detectors has been a fundamental step in achieving atomic resolution images of a number of viruses. These projection images can be numerically combined using different approaches to render a three-dimensional model of the virus. For those viral components exhibiting any symmetry, averaging can nowadays achieve atomic structures in most cases. Image processing methods have also evolved to improve the resolution in asymmetric viral components or regions showing different types of symmetries (symmetry mismatch).

Morphological alterations of lumbar intervertebral discs in patients with adolescent idiopathic scoliosis

BACKGROUND CONTEXT

Etiology of adolescent idiopathic scoliosis (AIS) is still unknown. Prior in vitro research suggests intervertebral disc pathomorphology as a cause for the initiation and progression of the spinal deformity, however, this has not been well characterized in vivo.

PURPOSE

To quantify and compare lumbar disc health and morphology in AIS to controls.

STUDY DESIGN/SETTING

Cross-sectional study.

METHODS

All lumbar discs were imaged using a 3T MRI scanner. T2-weighted and quantitative T2* maps were acquired. Axial slices of each disc were reconstructed, and customized scripts were used to extract outcome measurements: Nucleus pulposus (NP) signal intensity and location, disc signal volume, transition zone slope, and asymmetry index. Pearson's correlation analysis was performed between the NP location and disc wedge angle for AIS patients. ANOVAs were utilized to elucidate differences in disc health and morphology metrics between AIS patients and healthy controls. α=0.05.

RESULTS

There were no significant differences in disc health metrics between controls and scoliotic discs. There was a significant shift in the NP location towards the convex side of the disc in AIS patients compared to healthy controls, with an associated increase of the transition zone slope on the convex side. Additionally, with increasing disc wedge angle, the NP center migrated towards the convex side of the disc.

CONCLUSIONS

The present study elucidates morphological distinctions of intervertebral discs between healthy adolescents and those diagnosed with AIS. Discs in patients diagnosed with AIS are asymmetric, with the NP shifted towards the convex side, which was exacerbated by an increased disc wedge angle.

CLINICAL SIGNIFICANCE

Investigation of the MRI signal distribution (T2w and T2* maps) within the disc suggests an asymmetric pressure gradient shifting the NP laterally towards the convexity. Quantifying the progression of these morphological alterations during maturation and in response to treatment will provide further insight into the mechanisms of curve progression and correction, respectively.

Determining Macromolecular Structures Using Cryo-Electron Microscopy

Structural insights into macromolecular and protein complexes provide key clues about the molecular basis of the function. Cryogenic electron microscopy (cryo-EM) has emerged as a powerful structural biology method for studying protein and macromolecular structures at high resolution in both native and near-native states. Despite the ability to get detailed structural insights into the processes underlying protein function using cryo-EM, there has been hesitancy amongst plant biologists to apply the method for biomolecular interaction studies. This is largely evident from the relatively fewer structural depositions of proteins and protein complexes from plant origin in electron microscopy databank. Even though the progress has been slow, cryo-EM has significantly contributed to our understanding of the molecular biology processes underlying photosynthesis, energy transfer in plants, besides viruses infecting plants. This chapter introduces sample preparation for both negative-staining electron microscopy (NSEM) and cryo-EM for plant proteins and macromolecular complexes and data analysis using single particle analysis for beginners.

Deep learning reconstruction for improving the visualization of acute brain infarct on computed tomography

PURPOSE

This study aimed to investigate the impact of deep learning reconstruction (DLR) on acute infarct depiction compared with hybrid iterative reconstruction (Hybrid IR).

METHODS

This retrospective study included 29 (75.8 ± 13.2 years, 20 males) and 26 (64.4 ± 12.4 years, 18 males) patients with and without acute infarction, respectively. Unenhanced head CT images were reconstructed with DLR and Hybrid IR. In qualitative analyses, three readers evaluated the conspicuity of lesions based on five regions and image quality. A radiologist placed regions of interest on the lateral ventricle, putamen, and white matter in quantitative analyses, and the standard deviation of CT attenuation (i.e., quantitative image noise) was recorded.

RESULTS

Conspicuity of acute infarct in DLR was superior to that in Hybrid IR, and a statistically significant difference was observed for two readers (p ≤ 0.038). Conspicuity of acute infarct with time from onset to CT imaging at < 24 h in DLR was significantly improved compared with Hybrid IR for all readers (p ≤ 0.020). Image noise in DLR was significantly reduced compared with Hybrid IR with both the qualitative and quantitative analyses (p < 0.001 for all).

CONCLUSION

DLR in head CT helped improve acute infarct depiction, especially those with time from onset to CT imaging at < 24 h.

Use of Artificial Intelligence to Improve the Calculation of Percent Adhesion for Transdermal and Topical Delivery Systems

Adhesion is a critical quality attribute and performance characteristic for transdermal and topical delivery systems (TDS). Regulatory agencies recommend in vivo skin adhesion studies to support the approval of TDS in both new drug applications and abbreviated new drug applications. The current assessment approach in such studies is based on the visual observation of the percent adhesion, defined as the ratio of the area of TDS attached to the skin to the total area of the TDS. Visually estimated percent adhesion by trained clinicians or trial participants creates variability and bias. In addition, trial participants are typically confined to clinical centers during the entire product wear period, which may lead to challenges when translating adhesion performance to the real world setting. In this work we propose to use artificial intelligence and mobile technologies to aid and automate the collection of photographic evidence and estimation of percent adhesion. We trained state-of-art deep learning models with advanced techniques and in-house curated data. Results indicate good performance from the trained models and the potential use of such models in clinical practice is further explored.

A deep learning approach for the detection and counting of colon cancer cells (HT-29 cells) bunches and impurities

HT-29 has an epithelial appearance as a human colorectal cancer cell line. Early detection of colorectal cancer can enhance survival rates. This study aims to detect and count HT-29 cells using a deep-learning approach (ResNet-50). The cell lines were procured from Procell Life Science & Technology Co., Ltd. (Wuhan, China). Further, the dataset is self-prepared in lab experiments, cell culture, and collected 566 images. These images contain two classes; the HT-29 human colorectal adenocarcinoma cells (blue shapes in bunches) and impurities (tinny circular grey shapes). These images are annotated with the help of an image labeller as impurity and cancer cells. Then afterwards, the images are trained, validated, and tested against the deep learning approach ResNet50. Finally, in each image, the number of impurity and cancer cells are counted to find the accuracy of the proposed model. Accuracy and computational expense are used to gauge the network's performance. Each model is tested ten times with a non-overlapping train and random test splits. The effect of data pre-processing is also examined and shown in several tasks. The results show an accuracy of 95.5% during training and 95.3% in validation for detecting and counting HT-29 cells. HT-29 cell detection and counting using deep learning is novel due to the scarcity of research in this area, the application of deep learning, and potential performance improvements over traditional methods. By addressing a gap in the literature, employing a unique dataset, and using custom model architecture, this approach contributes to advancing colon cancer understanding and diagnosis techniques.

Automated measurement of lamellar thickness in human bone using polarized light microscopy

Lamellar bone formed in individuals with moderate and severe osteogenesis imperfecta (OI) is often composed of lamellae that are structurally abnormal. Measuring the thickness of these lamellae can be helpful in assessing the effect of specific collagen and collagen-related mutations on OI bone synthesis. Manual measurement of lamellar thicknesses in large quantities is very time consuming. The method for automated measurement described in this article utilizes an image processing script to identify the average thickness of multiple lamellae automatically from histologic images of bone. This allows for faster measurements that are less prone to human error and can account for variability in the thickness of a lamella along its length.•OI and control bone samples are prepared per the glycol methacrylate resin (JB-4 plastic) technique and viewed using polarized light microscopy.•Ideal bone regions for measurement are identified using specific qualitative criteria designed to ensure uniform and accurate thickness measurements.•The method was validated with dataset containing 211 lamellae from control bone and 212 lamellae from OI bone.

Deep learning in mesoscale brain image analysis: A review

Mesoscale microscopy images of the brain contain a wealth of information which can help us understand the working mechanisms of the brain. However, it is a challenging task to process and analyze these data because of the large size of the images, their high noise levels, the complex morphology of the brain from the cellular to the regional and anatomical levels, the inhomogeneous distribution of fluorescent labels in the cells and tissues, and imaging artifacts. Due to their impressive ability to extract relevant information from images, deep learning algorithms are widely applied to microscopy images of the brain to address these challenges and they perform superiorly in a wide range of microscopy image processing and analysis tasks. This article reviews the applications of deep learning algorithms in brain mesoscale microscopy image processing and analysis, including image synthesis, image segmentation, object detection, and neuron reconstruction and analysis. We also discuss the difficulties of each task and possible directions for further research.

A Deep Learning Approach for Meibomian Gland Appearance Evaluation

Purpose

To develop and evaluate a deep learning algorithm for Meibomian gland characteristics calculation.

Design

Evaluation of diagnostic technology.

Subjects

A total of 1616 meibography images of both the upper (697) and lower (919) eyelids from a total of 282 individuals.

Methods

Images were collected using the LipiView II device. All the provided data were split into 3 sets: the training, validation, and test sets. Data partitions used proportions of 70/10/20% and included data from 2 optometry settings. Each set was separately partitioned with these proportions, resulting in a balanced distribution of data from both settings. The images were divided based on patient identifiers, such that all images collected for one participant could end up only in one set. The labeled images were used to train a deep learning model, which was subsequently used for Meibomian gland segmentation. The model was then applied to calculate individual Meibomian gland metrics. Interreader agreement and agreement between manual and automated methods for Meibomian gland segmentation were also carried out to assess the accuracy of the automated approach.

Main Outcome Measures

Meibomian gland metrics, including length ratio, area, tortuosity, intensity, and width, were measured. Additionally, the performance of the automated algorithms was evaluated using the aggregated Jaccard index.

Results

The proposed semantic segmentation-based approach achieved average aggregated Jaccard index of mean 0.4718 (95% confidence interval [CI], 0.4680-0.4771) for the 'gland' class and a mean of 0.8470 (95% CI, 0.8432-0.8508) for the 'eyelid' class. The result for object detection-based approach was a mean of 0.4476 (95% CI, 0.4426-0.4533). Both artificial intelligence-based algorithms underestimated area, length ratio, tortuosity, widthmean, widthmedian, width10th, and width90th. Meibomian gland intensity was overestimated by both algorithms compared with the manual approach. The object detection-based algorithm seems to be as reliable as the manual approach only for Meibomian gland width10th calculation.

Conclusions

The proposed approach can successfully segment Meibomian glands; however, to overcome problems with gland overlap and lack of image sharpness, the proposed method requires further development. The study presents another approach to utilizing automated, artificial intelligence-based methods in Meibomian gland health assessment that may assist clinicians in the diagnosis, treatment, and management of Meibomian gland dysfunction.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Effect of fiber entanglement in chopped glass fiber reinforced composite manufactured via long fiber spray-up molding

Long Fiber Spray-up Molding (LFSM) deviates from the conventional approach in liquid composite molding (LCM) processes by utilizing extremely long chopped strands of fibers as the primary reinforcement material in its fabrication process. In LFSM, chopped fibers are impregnated with resin that is sprayed vertically downwards before reaching the mold surface. The spraying mechanism is mounted on an actuator, which is capable of spraying freely in any specified pattern or direction. Under LFSM, it is extremely difficult to fabricate a composite part with uniformly distributed fiber content throughout its volume. The consequences of the non-uniform fiber volume distribution arise from the fiber entanglement as the length of the fiber reaches up to 100 mm in LFSM. In this study, the effect of fiber entanglement during LFSM was analyzed through various approaches. This included measuring the coefficient of friction between fibers in contact and examining the correlation between fiber lengths and the number of intersections. Furthermore, the viscoelastic properties of the uncured composite part were assessed by experimenting with the influence of viscosity on fiber length during compression molding. The results were then computed, modeled, and visualized in MATLAB, considering variations in viscosity and fiber length, both before and after compression molding.

Compact imaging system and deep learning based segmentation for objective longissimus muscle area in Korean beef carcass

With growing consumer interest in meat quality, the need for accurate quality assessment becomes increasingly important. One crucial factor of Korean beef quality is the longissimus muscle area, which is closely associated with both quality and yield grade. Currently, the measurement is visually assessed, introducing subjectivity and placing a substantial burden on inspectors in terms of labor. To address these challenges, we have developed a compact image acquisition system designed to acquire accurate grading assessment images of beef carcasses. Several preprocessing steps after image acquisition were conducted, including radial distortion correction and color calibration. We have employed conventional image-processing techniques and four deep-learning models to segment the longissimus muscle area using the calibrated images. Among the segmentation models, DeepLab model based on ResNet50 achieved the highest accuracy. It demonstrated a Global Accuracy, Weighted IoU, and Mean BF Score of approximately 99.26%, 98.54%, and 95.70%, respectively. The results of our study are expected to contribute to the development of objective criteria for loin area assessment. By enabling precise and consistent determination of beef carcass quality, our research has the potential to reduce labor requirements for inspectors and provide a standardized approach to assessing loin area.

IS2aR, a computational tool to transform voxelized reference phantoms into patient-specific whole-body virtual CTs for peripheral dose estimation

BACKGROUND

The risk of radiogenic cancer induction due to radiotherapy depends on the dose received by the patient's organs. Knowing the position of all organs is needed to assess this dose in a personalized way. However, radiotherapy planning computed tomography (pCT) scans contain truncated patient anatomy, limiting personalized dose evaluation.

PURPOSE

To develop a simple and freely available computational tool that adapts an ICRP reference computational phantom to generate a patient-specific whole-body CT for peripheral dose computations.

METHODS

Various bone-segmentation methods were explored onto fifteen pCTs, and the one with the highest Sørensen-Dice coefficient was implemented. The reference phantom is registered to the pCT, obtaining a registration transform matrix, which is then applied to create the whole-body virtual CT. Additional validation involved a comparison of absorbed doses to organs delineated on both the pCT and the virtual CT.

RESULTS

A dedicated graphical user interface was designed and implemented to house the developed functions for i) selecting a registration region on which automatic bone segmentation and rigid registration will occur, ii) displaying the results of these processes under selectable views, and iii) exporting the final patient-specific whole-body CT. This software was termed IS2aR. The tested whole-body virtual CT generated by IS2aR fulfilled our requirements.

CONCLUSIONS

IS2aR is a user-friendly computational software to create a personalized whole-body CT containing the original structures in the reference phantom. The personalized dose deposited in peripheral organs can be estimated further to assess second cancer induction risk in epidemiological studies.

A new method based on deep learning and image processing for detection of strabismus with the Hirschberg test

Strabismus is a condition in which one or both eyes do not work in parallel or in harmony. People with strabismus have one eye looking straight ahead while the other eye looks inwards, outwards, upwards or downwards. This condition can affect both eyes. Strabismus is a common eye condition that affects about 4 % of the world's population. Tests such as Hirschberg, Cover and Krimsky are used to detect strabismus. In the Hirschberg test, a light source is held at a distance of 50 cm so that it falls on the centre of each eye. The horizontal and vertical distance between the centre of gravity of the light reflected from the cornea and the centre of the pupil indicates the degree of strabismus. In this study, deep learning and image processing algorithms are used to detect the eye, corneal reflection, iris and pupil on a patient's facial image. Based on the Hirschberg test, the horizontal and vertical shifts for both eyes were measured to determine the patient's degree of strabismus. In this way, the Hirschberg test used in strabismus screening was performed automatically by software. The correct detection of the pupil and the light reflected from the cornea by the algorithm means that the eye has been measured correctly. The software was tested on the facial images of 88 strabismic patients of different sexes and ages. 91 % of the 88 patients, or 80 patients, had their left eye measured correctly. 90 % of the 88 patients, or 79 patients, had their right eye measured correctly. The results for each eye obtained from the correct measurements were found to have an error of maximum ± 2°. This error is due to the fact that a real eye is in three-dimensional space, while the digital eye image is in two-dimensional space, and was only observed in the test results of some patients. This algorithm can be tested on patients of all ages and is not affected by morphological differences in the patients' faces. Successful results have been observed experimentally that this newly proposed method can be used in strabismus screening.

Dataset for Sun dynamics from topological features

The present study presents an extensive dataset meticulously curated from solar images sourced from the Solar and Heliospheric Observatory (SOHO), encompassing a range of spectral bands. This collaborative effort spans multiple disciplines and culminates in a robust and automated methodology that traverses the entire spectrum from solar imaging to the computation of spectral parameters and relevant characteristics. The significance of this undertaking lies in the profound insights yielded by the dataset. Encompassing diverse spectral bands and employing topological features, the dataset captures the multifaceted dynamics of solar activity, fostering interdisciplinary correlations and analyses with other solar phenomena. Consequently, the data's intrinsic value is greatly enhanced, affording researchers in solar physics, space climatology, and related fields the means to unravel intricate processes. To achieve this, an open-source Python library script has been developed, consolidating three pivotal stages: image acquisition, image processing, and parameter calculation. Originally conceived as discrete modules, these steps have been unified into a single script, streamlining the entire process. Applying this script to various solar image types has generated multiple datasets, subsequently synthesised into a comprehensive compilation through a data mining procedures. During the image processing phase, conventional libraries like OpenCV and Python's image analysis tools were harnessed to refine images for analysis. In contrast, image acquisition utilised established URL libraries in Python, facilitating direct access to original SOHO repository images and eliminating the need for local storage. The computation of spectral parameters involved a fusion of standard Python libraries and tailored algorithms for specific attributes. This approach ensures precise computation of a diverse array of attributes crucial for comprehensive analysis of solar images.

A robust motion correction technique for infrared thermography during awake craniotomy

PURPOSE

Intraoperative infrared thermography is an emerging technique for image-guided neurosurgery, whereby physiological and pathological processes result in temperature changes over space and time. However, motion during data collection leads to downstream artifacts in thermography analyses. We develop a fast, robust technique for motion estimation and correction as a preprocessing step for brain surface thermography recordings.

METHODS

A motion correction technique for thermography was developed which approximates the deformation field associated with motion as a grid of two-dimensional bilinear splines (Bispline registration), and a regularization function was designed to constrain motion to biomechanically feasible solutions. The performance of the proposed Bispline registration technique was compared to phase correlation, a band-stop filter, demons registration, and the Horn-Schunck and Lucas-Kanade optical flow techniques.

RESULTS

All methods were analyzed using thermography data from ten patients undergoing awake craniotomy for brain tumor resection, and performance was compared using image quality metrics. The proposed method had the lowest mean-squared error and the highest peak-signal-to-noise ratio of all methods tested and performed slightly worse than phase correlation and Demons registration on the structural similarity index metric (p < 0.01, Wilcoxon signed-rank test). Band-stop filtering and the Lucas-Kanade method were not strong attenuators of motion, while the Horn-Schunck method was well-performing initially but weakened over time.

CONCLUSION

Bispline registration had the most consistently strong performance out of all the techniques tested. It is relatively fast for a nonrigid motion correction technique, capable of processing ten frames per second, and could be a viable option for real-time use. Constraining the deformation cost function through regularization and interpolation appears sufficient for fast, monomodal motion correction of thermal data during awake craniotomy.

Focused classifications and refinements in high-resolution single particle cryo-EM analysis

Recent advances in cryo electron microscopy (cryo-EM) and image processing provide new opportunities to analyse drug targets at high resolution. However, structural heterogeneity limits resolution in many practical cases, hence restricting the level at which structural details can be analysed and drug design be performed. As structural disorder is not spread throughout the entire structure of a given macromolecular complex but instead is found in certain regions that move with respect to others and covering molecular scales from domain conformational changes up to the level of side chain conformations in ligand binding pockets, it is possible to focus the attention on those regions and the associated relative movements. Here we show how the usage of focused classifications and refinements provide insights into global conformational arrangements, exemplified on the human ribosome and on the cannabinoid G protein coupled receptor (GPCR), and how they can improve the local map resolution from an essentially disordered region to the 3-4 Å and finally to the 2 Å resolution range. A systematic analysis with variable spherical masks during focused refinement is presented showing that the choice of an optimal mask size helps refining to high resolution. This study covers several practical approaches on 4 examples illustrating how important mask size & shape and including neighbouring structural elements are for a focused analysis of a macromolecular complex. Such methods will be crucial for cryo-EM structure-based drug design of various medical targets and are applicable to single particle cryo-EM and electron tomography data.

A deep learning-based pipeline for analyzing the influences of interfacial mechanochemical microenvironments on spheroid invasion using differential interference contrast microscopic images

Metastasis is the leading cause of cancer-related deaths. During this process, cancer cells are likely to navigate discrete tissue-tissue interfaces, enabling them to infiltrate and spread throughout the body. Three-dimensional (3D) spheroid modeling is receiving more attention due to its strengths in studying the invasive behavior of metastatic cancer cells. While microscopy is a conventional approach for investigating 3D invasion, post-invasion image analysis, which is a time-consuming process, remains a significant challenge for researchers. In this study, we presented an image processing pipeline that utilized a deep learning (DL) solution, with an encoder-decoder architecture, to assess and characterize the invasion dynamics of tumor spheroids. The developed models, equipped with feature extraction and measurement capabilities, could be successfully utilized for the automated segmentation of the invasive protrusions as well as the core region of spheroids situated within interfacial microenvironments with distinct mechanochemical factors. Our findings suggest that a combination of the spheroid culture and DL-based image analysis enable identification of time-lapse migratory patterns for tumor spheroids above matrix-substrate interfaces, thus paving the foundation for delineating the mechanism of local invasion during cancer metastasis.

Motion Characterization of Pacemaker Lead Wire In Vivo for Piezoelectric Energy Harvesting Applications

PURPOSE

Piezoelectric energy harvesters (PEH) for cardiac pacemakers typically use animal models to assess the performance of the PEH. However, if considering multiple designs, the use of animal models and prototyping increases costs and time. To reduce the use of animal models in research for pacemaker energy harvesting applications, this study investigates the motion of a pacemaker lead wire (PLW) in vivo using fluoroscopy imaging to quantify the position and displacements as a function of time, such that the data can be used in computer simulations.

METHODS

The proposed technique uses fluoroscopy imaging video data of a dual chamber pacemaker implanted in a patient, and image processing allows for the motion of the PLW captured. The motion is discretized into nodes for ease of implementation in finite element software. FEA simulation is presented using a piezoelectric energy harvester design integrated in the lead wire, and the energy output is predicted by finite element computer simulation.

RESULTS

A 2-dimensional analysis is conducted with the fluoroscopy imaging video data to characterize the PLW motion and results show close agreement with literature values. Simulations with an energy harvesting circuit using the nodal position and displacement data shows that a PEH integrated in the PLW can generate a direct current voltage of 1.12 V and power output of 0.125 μW, potentially extending the battery life of pacemakers by 0.75-1 years.

CONCLUSIONS

The results suggest that fluoroscopy imaging data can be effective in evaluating PEH designs rather than using animal models, saving time and costs.

Evaluation of cortical and trabecular bone structure of the mandible in patients using L-Thyroxine

BACKGROUND

Long-term use of L-Thyroxine (LT4), the synthetic thyroxine hormone used for thyroid hormone replacement therapy, is an important risk factor for osteoporosis. The aim of this study was to investigate the differences between mandibular cortical index (MCI) and trabecular bone fractal dimension (FD) values on panoramic radiographs of patients using LT4 and control subjects.

METHODS

A total of 142 female patients, 71 cases and 71 controls, were analyzed in the study. Ages were matched in case and control groups and the mean age was 36.6 ± 8.2 (18 to 50) years. MCI consisting of C1 (Normal Mandibular Cortex), C2 (Moderately Resorbed Mandibular Cortex) and, C3 (Severely Resorbed Cortex) scores was determined for case and control groups. Fractal analysis was performed using ImageJ on selected regions of interest from the gonial and interdental regions. The box-count method was used to calculate FD values. Wilcoxon signed-rank test, Mann-Whitney U test, and Spearman correlation analysis were applied to compare the measurements. Statistical significance of differences was established at P < 0.05 level.

RESULTS

FD values did not show statistically significant differences between case and control groups (p > 0.05). The mean FD in the right gonial region was 1.38 ± 0.07 in the case group and 1.38 ± 0.08 in the control group (p = 0.715). The mean FD in the right interdental region was 1.37 ± 0.06 in the cases and 1.36 ± 0.06 in the control group (p = 0.373). The mean FD in the left gonial region was 1.39 ± 0.07 in the cases and 1.39 ± 0.07 in the control group (p = 0.865). The mean FD in the left interdental region is 1.37 ± 0.06 in the cases and 1.38 ± 0.05 in the control group (p = 0.369). The most common MCI score was C1, with 62% in the cases and 83.1% in the control group. MCI scores showed a statistically significant difference between cases and controls (p = 0.016, p < 0.05). While the C2 score was higher in the cases, the C1 score was higher in the controls.

CONCLUSIONS

LT4 use was not associated with the FD of mandibular trabecular bone, but was associated with MCI values of cortical bone. Further studies on larger samples with different imaging modalities and image processing methods are needed.

Revisiting bilateral bony orbital volumes comparison using 3D reconstruction in Korean adults: a reference study for orbital wall reconstruction, 3D printing, and navigation by mirroring

BACKGROUND

Orbital wall fractures can result in changes to the bony orbital volume and soft tissue. Restoring the bony orbital and intraconal fat volumes is crucial to prevent posttraumatic enophthalmos and hypoglobus. We aimed to establish an evidence-based medical reference point for "mirroring" in orbital wall reconstruction, which incorporates three-dimensional (3D)-printing and navigation-assisted surgery, by comparing bilateral bony orbital volumes.

METHODS

We retrospectively analyzed the data obtained from 100 Korean adults who did not have orbital wall fractures, categorized by age groups. The AVIEW Research software (Coreline Soft Inc., Seoul, South Korea) was used to generate 3D reformations of the bony orbital cavity, and bony orbital volumes were automatically calculated after selecting the region of interest on consecutive computed tomography slices.

RESULTS

The mean left and right orbital volume of males in their 20 s was 24.67 ± 2.58 mL and 24.70 ± 2.59 mL, respectively, with no significant difference in size (p = 0.98) and Pearson's correlation coefficient of 0.977 (p < 0.001). No significant differences were found in orbital volumes in other age groups without fractures or in patients with nasal bone fractures (p = 0.84, Pearson's correlation coefficient 0.970, p < 0.001). The interclass correlation coefficients (2,1) for inter- and intrarater reliability were 0.97 (p < 0.001) and 0.99 (p < 0.001), respectively.

CONCLUSIONS

No significant differences were found in the bilateral bony orbital volumes among males of any age. Thus, the uninjured orbit can be used as a volumetric reference point for the contralateral injured orbit during orbital wall reconstruction.

Image calibration in choroidal vascularity index measurement

Choroid is a tissue with a very high blood flow which is a metabolic supporter of the retina. Recently, the study of choroidal blood flow in ocular and systemic disorders is a hot topic in scientific research. With the advent of enhanced depth imaging OCT (EDI-OCT), it is possible to measure the entire choroidal thickness. The choroidal vascularity index (CVI) is a relatively new index in studying choroidal hemodynamics. However, the CVI measurement needs image processing. Image calibration is a necessary step before any image processing with software such as ImageJ.

Application research of AI-assisted compressed sensing technology in MRI scanning of the knee joint: 3D-MRI perspective

OBJECTIVE

To investigate the potential applicability of AI-assisted compressed sensing (ACS) in knee MRI to enhance and optimize the scanning process.

METHODS

Volunteers and patients with sports-related injuries underwent prospective MRI scans with a range of acceleration techniques. The volunteers were subjected to varied ACS acceleration levels to ascertain the most effective level. Patients underwent scans at the determined optimal 3D-ACS acceleration level, and 3D compressed sensing (CS) and 2D parallel acquisition technology (PAT) scans were performed. The resultant 3D-ACS images underwent 3.5 mm/2.0 mm multiplanar reconstruction (MPR). Experienced radiologists evaluated and compared the quality of images obtained by 3D-ACS-MRI and 3D-CS-MRI, 3.5 mm/2.0 mm MPR and 2D-PAT-MRI, diagnosed diseases, and compared the results with the arthroscopic findings. The diagnostic agreement was evaluated using Cohen's kappa correlation coefficient, and both absolute and relative evaluation methods were utilized for objective assessment.

RESULTS

The study involved 15 volunteers and 53 patients. An acceleration factor of 10.69 × was identified as optimal. The quality evaluation showed that 3D-ACS provided poorer bone structure visualization, and improved cartilage visualization and less satisfactory axial images with 3.5 mm/2.0 mm MPR than 2D-PAT. In terms of objective evaluation, the relative evaluation yielded satisfactory results across different groups, while the absolute evaluation revealed significant variances in most features. Nevertheless, high levels of diagnostic agreement (κ: 0.81-0.94) and accuracy (0.83-0.98) were observed across all diagnoses.

CONCLUSION

ACS technology presents significant potential as a replacement for traditional CS in 3D-MRI knee scans, allowing thinner MPRs and markedly faster scans without sacrificing diagnostic accuracy.

CLINICAL RELEVANCE STATEMENT

3D-ACS-MRI of the knee can be completed in the 160 s with good diagnostic consistency and image quality. 3D-MRI-MPR can replace 2D-MRI and reconstruct images with thinner slices, which helps to optimize the current MRI examination process and shorten scanning time.

KEY POINTS

• AI-assisted compressed sensing technology can reduce knee MRI scan time by over 50%. • 3D AI-assisted compressed sensing MRI and related multiplanar reconstruction can replace traditional accelerated MRI and yield thinner 2D multiplanar reconstructions. • Successful application of 3D AI-assisted compressed sensing MRI can help optimize the current knee MRI process.

Semantic segmentation of plant roots from RGB (mini-) rhizotron images-generalisation potential and false positives of established methods and advanced deep-learning models

BACKGROUND

Manual analysis of (mini-)rhizotron (MR) images is tedious. Several methods have been proposed for semantic root segmentation based on homogeneous, single-source MR datasets. Recent advances in deep learning (DL) have enabled automated feature extraction, but comparisons of segmentation accuracy, false positives and transferability are virtually lacking. Here we compare six state-of-the-art methods and propose two improved DL models for semantic root segmentation using a large MR dataset with and without augmented data. We determine the performance of the methods on a homogeneous maize dataset, and a mixed dataset of > 8 species (mixtures), 6 soil types and 4 imaging systems. The generalisation potential of the derived DL models is determined on a distinct, unseen dataset.

RESULTS

The best performance was achieved by the U-Net models; the more complex the encoder the better the accuracy and generalisation of the model. The heterogeneous mixed MR dataset was a particularly challenging for the non-U-Net techniques. Data augmentation enhanced model performance. We demonstrated the improved performance of deep meta-architectures and feature extractors, and a reduction in the number of false positives.

CONCLUSIONS

Although correction factors are still required to match human labelled root lengths, neural network architectures greatly reduce the time required to compute the root length. The more complex architectures illustrate how future improvements in root segmentation within MR images can be achieved, particularly reaching higher segmentation accuracies and model generalisation when analysing real-world datasets with artefacts-limiting the need for model retraining.

Novel plant disease detection techniques-a brief review

Plant pathogens cause severe losses to agricultural yield worldwide. Tracking plant health and early disease detection is important to reduce the disease spread and thus economic loss. Though visual scouting has been practiced from former times, detection of asymptomatic disease conditions is difficult. So, DNA-based and serological methods gained importance in plant disease detection. The progress in advanced technologies challenges the development of rapid, non-invasive, and on-field detection techniques such as spectroscopy. This review highlights various direct and indirect ways of detecting plant diseases like Enzyme-linked immunosorbent assay, Lateral flow assays, Polymerase chain reaction, spectroscopic techniques and biosensors. Although these techniques are sensitive and pathogen-specific, they are more laborious and time-intensive. As a consequence, a lot of interest is gained in in-field adaptable point-of-care devices with artificial intelligence-assisted pathogen detection at an early stage. More recently computer-aided techniques like neural networks are gaining significance in plant disease detection by image processing. In addition, a concise report on the latest progress achieved in plant disease detection techniques is provided.

Skin pore imaging using spectral-domain optical coherence tomography: a case report

Sebum is an important component of the skin that has attracted attention in many fields, including dermatology and cosmetics. Pore expansion due to sebum on the skin can lead to various problems. Therefore, it is necessary to analyze the morphological characteristics of sebum. In this study, we used optical coherence tomography (OCT) to evaluate facial sebum areas. We obtained the OCT maximum amplitude projection (MAP) image and a cross-sectional image of skin pores in the facial area. Subsequently, we detected the sebum in skin pores using the detection algorithm of the ImageJ software to quantitatively determine the size of randomly selected pores in the proposed MAP images. Additionally, the pore size was analyzed by acquiring images before and after facial sebum extraction. According to our research, facial sebum can be morphologically described using the OCT system. Since OCT imaging enables specific analysis of skin parameters, including pores and sebum, skin analysis employing OCT could be an effective method for further research.

Exploring the role of texture features in deep convolutional neural networks: Insights from Portilla-Simoncelli statistics

It is well-understood that the performance of Deep Convolutional Neural Networks (DCNNs) in image recognition tasks is influenced not only by shape but also by texture information. Despite this, understanding the internal representations of DCNNs remains a challenging task. This study employs a simplified version of the Portilla-Simoncelli Statistics, termed "minPS," to explore how texture information is represented in a pre-trained VGG network. Using minPS features extracted from texture images, we perform a sparse regression on the activations across various channels in VGG layers. Our findings reveal that channels in the early to middle layers of the VGG network can be effectively described by minPS features. Additionally, we observe that the explanatory power of minPS sub-groups evolves as one ascends the network hierarchy. Specifically, sub-groups termed Linear Cross Scale (LCS) and Energy Cross Scale (ECS) exhibit weak explanatory power for VGG channels. To investigate the relationship further, we compare the original texture images with their synthesized counterparts, generated using VGG, in terms of minPS features. Our results indicate that the absence of certain minPS features suggests their non-utilization in VGG's internal representations.

A comparative study of Machine Learning-based classification of Tomato fungal diseases: Application of GLCM texture features

Globally, agriculture remains an important source of food and economic development. Due to various plant diseases, farmers continue to suffer huge yield losses in both quality and quantity. In this study, we explored the potential of using Artificial Neural Networks, K-Nearest Neighbors, Random Forest, and Support Vector Machine to classify tomato fungal leaf diseases: Alternaria, Curvularia, Helminthosporium, and Lasiodiplodi based on Gray Level Co-occurrence Matrix texture features. Small differences between symptoms of these diseases make it difficult to use the naked eye to obtain better results in detecting and distinguishing these diseases. The Artificial Neural Network outperformed other classifiers with an overall accuracy of 94% and average scores of 93.6% for Precision, 93.8% for Recall, and 93.8% for F1-score. Generally, the models confused samples originally belonging to Helminthosporium with Curvularia. The extracted texture features show great potential to classify the different tomato leaf fungal diseases. The results of this study show that texture characteristics of the Gray Level Co-occurrence Matrix play a critical role in the establishment of tomato leaf disease classification systems and can facilitate the implementation of preventive measures by farmers, resulting in enhanced yield quality and quantity.

Artificial Intelligence Optical Biopsy for Evaluating the Functional State of Wounds

INTRODUCTION

The clinical characterization of the functional status of active wounds in terms of their driving cellular and molecular biology remains a considerable challenge that currently requires excision via a tissue biopsy. In this pilot study, we use convolutional Siamese neural network (SNN) architecture to predict the functional state of a wound using digital photographs of wounds in a canine model of volumetric muscle loss (VML).

METHODS

Digital images of VML injuries and tissue biopsies were obtained in a standardized fashion from an established canine model of VML. Gene expression profiles for each biopsy site were obtained using RNA sequencing. These profiles were converted to functional profiles by a manual review of validated gene ontology databases in which we determined a hierarchical representation of gene functions based on functional specificity. An SNN was trained to regress functional profile expression values, informed by an image segment showing the surface of a small tissue biopsy.

RESULTS

The SNN was able to predict the functional expression of a range of functions based with error ranging from ∼5% to ∼30%, with functions that are most closely associated with the early state of wound healing to be those best-predicted.

CONCLUSIONS

These initial results suggest promise for further research regarding this novel use of machine learning regression on medical images. The regression of functional profiles, as opposed to specific genes, both addresses the challenge of genetic redundancy and gives a deeper insight into the mechanistic configuration of a region of tissue in wounds.

Advancements in oral and maxillofacial surgery medical images segmentation techniques: An overview

OBJECTIVES

This article reviews recent advances in computer-aided segmentation methods for oral and maxillofacial surgery and describes the advantages and limitations of these methods. The objective is to provide an invaluable resource for precise therapy and surgical planning in oral and maxillofacial surgery. Study selection, data and sources: This review includes full-text articles and conference proceedings reporting the application of segmentation methods in the field of oral and maxillofacial surgery. The research focuses on three aspects: tooth detection segmentation, mandibular canal segmentation and alveolar bone segmentation. The most commonly used imaging technique is CBCT, followed by conventional CT and Orthopantomography. A systematic electronic database search was performed up to July 2023 (Medline via PubMed, IEEE Xplore, ArXiv, Google Scholar were searched).

RESULTS

These segmentation methods can be mainly divided into two categories: traditional image processing and machine learning (including deep learning). Performance testing on a dataset of images labeled by medical professionals shows that it performs similarly to dentists' annotations, confirming its effectiveness. However, no studies have evaluated its practical application value.

CONCLUSION

Segmentation methods (particularly deep learning methods) have demonstrated unprecedented performance, while inherent challenges remain, including the scarcity and inconsistency of datasets, visible artifacts in images, unbalanced data distribution, and the "black box" nature.

CLINICAL SIGNIFICANCE

Accurate image segmentation is critical for precise treatment and surgical planning in oral and maxillofacial surgery. This review aims to facilitate more accurate and effective surgical treatment planning among dental researchers.

An experimental setup and segmentation method for CFU counting on agar plate for the assessment of drinking water

Quantification of bacterial colonies on an agar plate is a daily routine for a microbiologist to determine the number of viable microorganisms in the sample. In general, microbiologists perform a visual assessment of bacterial colonies which is time-consuming (takes 2 min per plate), tedious, and subjective. Some automatic counting algorithms are developed that save labour and time, but their results are affected by the non-illumination on an agar plate. To improve this, the present manuscript aims to develop an inexpensive and efficient device to acquire S.aureus images via an automatic counting method using image processing techniques under real laboratory conditions. The proposed method (P_ColonyCount) includes the region of interest extraction and color space transformation followed by filtering, thresholding, morphological operation, distance transform, and watershed technique for the quantification of isolated and overlapping colonies. The present work also shows a comparative study on grayscale, K, and green channels by applying different filter and thresholding techniques on 42 images. The results of all channels were compared with the score provided by the expert (manual count). Out of all the proposed method (P_ColonyCount), the K channel gives the best outcome in comparison with the other two channels (grayscale and green) in terms of precision, recall, and F-measure which are 0.99, 0.99, and 0.99 (2 h), 0.98, 0.99, and 0.98 (4 h), and 0.98, 0.98, 0.98 (6 h) respectively. The execution time of the manual and the proposed method (P_ColonyCount) for 42 images ranges from 19 to 113 s and 15 to 31 s respectively. Apart from this, a user-friendly graphical user interface is also developed for the convenient enumeration of colonies without any expert knowledge/training. The developed imaging device will be useful for researchers and teaching lab settings.

Simulation-aided infrared thermography with decomposition-based noise reduction for detecting defects in ancient polyptychs

In recent years, the conservation and protection of ancient cultural heritage have received increasing attention, and non-destructive testing (NDT), which can minimize the damage done to the test subject, plays an integral role therein. For instance, NDT through active infrared thermal imaging can be applied to ancient polyptychs, which can realize accurate detection of damage and defects existing on the surface and interior of the polyptychs. In this study, infrared thermography is used for non-invasive investigation and evaluation of two polyptych samples with different pigments and artificial defects, but both reproduced based on a painting by Pietro Lorenzetti (1280/85-1348) using the typical tempera technique of the century. It is noted that, to avoid as far as possible secondary damages done to the ancient cultural heritages, repeated damage-detection experiments are rarely carried out on the test subjects. To that end, numerical simulation is used to reveal the heat transfer properties and temperature distributions, as to perform procedural verification and reduce the number of experiments that need to be conducted on actual samples. Technique-wise, to improve the observability of the experimental results, a total variation regularized low-rank tensor decomposition algorithm is implemented to reduce the background noise and improve the contrast of the images. Furthermore, the efficacy of image processing is quantified through the structural-similarity evaluation.

Identification and estimation of lodging in bread wheat genotypes using machine learning predictive algorithms

BACKGROUND

Lodging or stem bending decreases wheat yield quality and quantity. Thus, the traits reflected in early lodging wheat are helpful for early monitoring to some extent. In order to identify the superior genotypes and compare multiple linear regression (MLR) with support vector regression (SVR), artificial neural network (ANN), and random forest regression (RF) for predicting lodging in Iranian wheat accessions, a total of 228 wheat accessions were cultivated under field conditions in an alpha-lattice experiment, randomized incomplete block design, with two replications in two cropping seasons (2018-2019 and 2019-2020). To measure traits, a total of 20 plants were isolated from each plot and were measured using image processing.

RESULTS

The lodging score index (LS) had the highest positive correlation with plant height (r = 0.78**), Number of nodes (r = 0.71**), and internode length 1 (r = 0.70**). Genotypes were classified into four groups based on heat map output. The most lodging-resistant genotypes showed a lodging index of zero or close to zero. The findings revealed that the RF algorithm provided a more accurate estimate (R2 = 0.887 and RMSE = 0.091 for training data and R2 = 0.768 and RMSE = 0.124 for testing data) of wheat lodging than the ANN and SVR algorithms, and its robustness was as good as ANN but better than SVR.

CONCLUSION

Overall, it seems that the RF model can provide a helpful predictive and exploratory tool to estimate wheat lodging in the field. This work can contribute to the adoption of managerial approaches for precise and non-destructive monitoring of lodging.

On the utility of Colour in shape analysis: An introduction to Colour science via palaeographical case studies

In this article, we explore the use of colour for the analysis of shapes in digital images. We argue that colour can provide unique information that is not available from shape alone, and that familiarity with the interdisciplinary field of colour science is essential for unlocking the potential of colour. Within this perspective, we offer an illustrated overview of the colour-related aspects of image management and processing, perceptual psychology, and cultural studies, using for exemplary purposes case studies focused on computational palaeography. We also discuss the changing roles of colour in society and the sciences, and provide technical solutions for using digital colour effectively, highlighting the impact of human factors. The article concludes with an annotated bibliography. This work is a primer, and its intended readership are scholars and computer scientists unfamiliar with colour science.

Widefield oct-angiography-based classification of sickle cell retinopathy

PURPOSE

To assess the capillary non-perfusion in different concentric sectors on widefield optical coherence tomography angiography (WF-OCTA) and to correlate the ratio of non-perfusion (RNP) to the severity of sickle cell retinopathy (SCR).

METHODS

This retrospective, cross-sectional study included eyes of patients with various sickle cell disease (SCD) genotypes having undergone WF-OCTA and ultra-widefield color fundus photography (UWF-CFP). Eyes were grouped as no SCR, non-proliferative SCR or proliferative SCR. RNP was assessed on WF-OCTA montage in different field-of-view (FOV) sectors centered on the fovea: 0-10-degrees circle excluding the foveal avascular zone, the 10-30-degrees circle excluding the optic nerve, the 30-60-degrees circle, and the full 60-degrees circle.

RESULTS

Forty-two eyes of twenty-eight patients were included. Within each SCR group, mean RNP of the FOV 30-60 sector was higher than all other sectors (p < 0.05). Mean RNP of all sectors were significatively different between no SCR group and proliferative SCR group (p < 0.05). To distinguish no SCR versus non-proliferative SCR FOV 30-60 had a good sensitivity and specificity of 41.67% and 93.33%, respectively (cutoff RNP > 22.72%, AUC = 0.75, 95% CI 0.56-0.94, p = 0.028). To differentiate non-proliferative versus proliferative SCR, FOV 0-10 had good sensitivity and specificity of 33.33% and 91.67%, respectively (cutoff RNP > 18.09, AUC = 0.73, 95% CI 0.53 to 0.93, p = 0.041). To discern no SCR versus proliferative SCR, all sectors had optimal sensitivity and specificity (p < 0.05).

CONCLUSION

WF OCTA-based RNP provides non-invasive diagnostic information regarding the presence and severity of SCR, and correlates with disease stage in certain FOV sectors.