Deep learning enabled label-free microfluidic droplet classification for single cell functional assays.

Droplet-based microfluidics techniques coupled to microscopy allow for the characterization of cells at the single-cell scale. However, such techniques generate substantial amounts of data and microscopy images that must be analyzed. Droplets on these images usually need to be classified depending on the number of cells they contain. This verification, when visually carried out by the experimenter image-per-image, is time-consuming and impractical for analysis of many assays or when an assay yields many putative droplets of interest. Machine learning models have already been developed to classify cell-containing droplets within microscopy images, but not in the context of assays in which non-cellular structures are present inside the droplet in addition to cells. Here we develop a deep learning model using the neural network ResNet-50 that can be applied to functional droplet-based microfluidic assays to classify droplets according to the number of cells they contain with >90% accuracy in a very short time. This model performs high accuracy classification of droplets containing both cells with non-cellular structures and cells alone and can accommodate several different cell types, for generalization to a broader array of droplet-based microfluidics applications.

CHiMP: deep-learning tools trained on protein crystallization micrographs to enable automation of experiments.

A group of three deep-learning tools, referred to collectively as CHiMP (Crystal Hits in My Plate), were created for analysis of micrographs of protein crystallization experiments at the Diamond Light Source (DLS) synchrotron, UK. The first tool, a classification network, assigns images into categories relating to experimental outcomes. The other two tools are networks that perform both object detection and instance segmentation, resulting in masks of individual crystals in the first case and masks of crystallization droplets in addition to crystals in the second case, allowing the positions and sizes of these entities to be recorded. The creation of these tools used transfer learning, where weights from a pre-trained deep-learning network were used as a starting point and repurposed by further training on a relatively small set of data. Two of the tools are now integrated at the VMXi macromolecular crystallography beamline at DLS, where they have the potential to absolve the need for any user input, both for monitoring crystallization experiments and for triggering in situ data collections. The third is being integrated into the XChem fragment-based drug-discovery screening platform, also at DLS, to allow the automatic targeting of acoustic compound dispensing into crystallization droplets.

Prairie Dog Optimization Algorithm with deep learning assisted based Aerial Image Classification on UAV imagery.

This study presents a Prairie Dog Optimization Algorithm with a Deep learning-assisted Aerial Image Classification Approach (PDODL-AICA) on UAV images. The PDODL-AICA technique exploits the optimal DL model for classifying aerial images into numerous classes. In the presented PDODL-AICA technique, the feature extraction procedure is executed using the EfficientNetB7 model. Besides, the hyperparameter tuning of the EfficientNetB7 technique uses the PDO model. The PDODL-AICA technique uses a convolutional variational autoencoder (CVAE) model to detect and classify aerial images. The performance study of the PDODL-AICA model is implemented on a benchmark UAV image dataset. The experimental values inferred the authority of the PDODL-AICA approach over recent models in terms of dissimilar measures.

Bangladeshi crops leaf disease detection using YOLOv8.

The agricultural sector in Bangladesh is a cornerstone of the nation's economy, with key crops such as rice, corn, wheat, potato, and tomato playing vital roles. However, these crops are highly vulnerable to various leaf diseases, which pose significant threats to crop yields and food security if not promptly addressed. Consequently, there is an urgent need for an automated system that can accurately identify and categorize leaf diseases, enabling early intervention and management. This study explores the efficacy of the latest state-of-the-art object detection model, YOLOv8 (You Only Look Once), in surpassing previous models for the automated detection and categorization of leaf diseases in these five major crops. By leveraging modern computer vision techniques, the goal is to enhance the efficiency of disease detection and management. A dataset comprising 19 classes, each with 150 images, totaling 2850 images, was meticulously curated and annotated for training and evaluation. The YOLOv8 framework, known for its capability to detect multiple objects simultaneously, was employed to train a deep neural network. The system's performance was evaluated using standard metrics such as mean Average Precision (mAP) and F1 score. The findings demonstrate that the YOLOv8 framework successfully identifies leaf diseases, achieving a high mAP of 98% and an F1 score of 97%. These results underscore the significant potential of this approach to enhance crop disease management, thereby improving food security and promoting agricultural sustainability in Bangladesh.

Identifying images in the biology literature that are problematic for people with a color-vision deficiency.

To help maximize the impact of scientific journal articles, authors must ensure that article figures are accessible to people with color-vision deficiencies (CVDs), which affect up to 8% of males and 0.5% of females. We evaluated images published in biology- and medicine-oriented research articles between 2012 and 2022. Most included at least one color contrast that could be problematic for people with deuteranopia ('deuteranopes'), the most common form of CVD. However, spatial distances and within-image labels frequently mitigated potential problems. Initially, we reviewed 4964 images from eLife, comparing each against a simulated version that approximated how it might appear to deuteranopes. We identified 636 (12.8%) images that we determined would be difficult for deuteranopes to interpret. Our findings suggest that the frequency of this problem has decreased over time and that articles from cell-oriented disciplines were most often problematic. We used machine learning to automate the identification of problematic images. For a hold-out test set from eLife (n=879), a convolutional neural network classified the images with an area under the precision-recall curve of 0.75. The same network classified images from PubMed Central (n=1191) with an area under the precision-recall curve of 0.39. We created a Web application (https://bioapps.byu.edu/colorblind_image_tester); users can upload images, view simulated versions, and obtain predictions. Our findings shed new light on the frequency and nature of scientific images that may be problematic for deuteranopes and motivate additional efforts to increase accessibility.

Compost incorporation and wildflowers introduction for stormwater infiltration and erosion-control vegetation cover establishment in post-construction landscapes.

Urban and suburban development frequently disturbs and compacts soils, reducing infiltration rates and fertility, posing challenges for post-development vegetation establishment, and contributing to soil erosion. This study investigated the effectiveness of compost incorporation in enhancing stormwater infiltration and vegetation establishment in urban landscapes. Experimental treatments comprised a split-split plot design of vegetation mix (grass, wildflowers, and grass-wildflowers) as main plot, ground cover (hydro-mulch and excelsior) as subplot, and compost (30% Compost and No-Compost) as sub-subplot factors. Wildflower inclusion was motivated by their recognized ecological benefits, including aesthetics, pollinator habitat, and deep root systems. Vegetation cover was assessed using RGB (Red-Green-Blue) imagery and ArcGIS-based supervised image classification. Over a 24-month period, bulk density, infiltration rate, soil penetration resistance, vegetation cover, and root mass density were assessed. Results highlighted that Compost treatments consistently reduced bulk density by 19-24%, lowered soil penetration resistance to under 2 MPa at both field-capacity and water-stressed conditions, and increased infiltration rate by 2-3 times compared to No-Compost treatments. Vegetation cover assessment revealed rapid establishment with 30% compost and 60:40 grass-wildflower mix, persisting for an initial 12 months. Subsequently, all treatments exhibited similar vegetation coverage from 13 to 24 months, reaching 95-100% cover. Compost treatments had significantly higher root mass density within the top 15 cm than No-Compost, but compost addition did not alter the root profile beyond the 15 cm depth incorporation depth. The findings suggest that incorporating 30% compost and including a wildflower or grass-wildflower mix appears to be effective in enhancing stormwater infiltration and provides rapid erosion control vegetation cover establishment in post-construction landscapes.

AI-based seagrass morphology measurement.

Seagrass meadows are an essential part of the Great Barrier Reef ecosystem, providing various benefits such as filtering nutrients and sediment, serving as a nursery for fish and shellfish, and capturing atmospheric carbon as blue carbon. Understanding the phenotypic plasticity of seagrasses and their ability to acclimate their morphology in response to environ-mental stressors is crucial. Investigating these morphological changes can provide valuable insights into ecosystem health and inform conservation strategies aimed at mitigating seagrass decline. Measuring seagrass growth by measuring morphological parameters such as the length and width of leaves, rhizomes, and roots is essential. The manual process of measuring morphological parameters of seagrass can be time-consuming, inaccurate and costly, so researchers are exploring machine-learning techniques to automate the process. To automate this process, researchers have developed a machine learning model that utilizes image processing and artificial intelligence to measure morphological parameters from digital imagery. The study uses a deep learning model called YOLO-v6 to classify three distinct seagrass object types and determine their dimensions. The results suggest that the proposed model is highly effective, with an average recall of 97.5%, an average precision of 83.7%, and an average f1 score of 90.1%. The model code has been made publicly available on GitHub (https://github.com/sajalhalder/AI-ASMM).

Dataset for image classification with knowledge.

Deep learning applied to raw data has demonstrated outstanding image classification performance, mainly when abundant data is available. However, performance significantly degrades when a substantial volume of data is unavailable. Furthermore, deep architectures struggle to achieve satisfactory performance levels when distinguishing between distinct classes, such as fine-grained image classification, is challenging. Utilizing a priori knowledge alongside raw data can enhance image classification in demanding scenarios. Nevertheless, only a limited number of image classification datasets given with a priori knowledge are currently available, thereby restricting research efforts in this field. This paper introduces innovative datasets for the classification problem that integrate a priori knowledge. These datasets are built from existing data typically employed for multilabel multiclass classification or object detection. Frequent closed itemset mining is used to create classes and their corresponding attributes (e.g. the presence of an object in an image) and then to extract a priori knowledge expressed by rules on these attributes. The algorithm for generating rules is described.

Efficient adaptive learning rate for convolutional neural network based on quadratic interpolation egret swarm optimization algorithm.

Convolutional neural network (CNN) has recently become popular for addressing multi-domain image classification. However, most existing methods frequently suffer from poor performance, especially in performance and convergence for various datasets. Herein, we have proposed an algorithm for multi-domain image classification by introducing a novel adaptive learning rate rule to the conventional CNN. Specifically, we adopt the CNN to extract rich feature representations. Given that the hyperparameters of the learning rate have a positive effect on the prediction error, the Egret Swarm Optimization Algorithm (ESOA) is introduced to update the learning rate, which can jump out of local extrema during exploration. Therefore, combined with quadratic interpolation, the objective function can be approximated by a polynomial, thereby improving its prediction accuracy. To verify the robustness of the proposed algorithm, we conducted comprehensive experiments in five domain public datasets to fulfil the task of image classification. Meanwhile, the highest accuracy rate of 97.15 % was obtained on the test set. The performances of our method on 24 benchmark functions (CEC2017 and CEC2022) are compared with Particle Swarm Optimization (PSO), Genetic Algorithm(GA), Whale Optimization Algorithm(WOA), Catch Fish Optimization Algorithm(CFOA), GOOSE Algorithm(GO) and ESOA. In two benchmark sets, the performance metric values of our algorithm rank no. 1, especially in all unimodal functions in contrast with other baseline algorithms.

Deep Learning-Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.

BACKGROUND: Artificial intelligence (AI)-based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error. OBJECTIVES: This systematic review and meta-analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI-based medical image analysis studies. METHODS: Diagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS-2 tool was utilized to assess quality. The meta-analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets. RESULTS: Of 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS-2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta-analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity. CONCLUSION: Application of AI-based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI-based models cannot replace a well-trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.