Artificial Intelligence for Detection of External Cervical Resorption Using Label-Efficient Self-Supervised Learning Method.

INTRODUCTION: The aim of this study was to leverage label-efficient self-supervised learning (SSL) to train a model that can detect ECR and differentiate it from caries. METHODS: Periapical (PA) radiographs of teeth with ECR defects were collected. Two board-certified endodontists reviewed PA radiographs and cone beam computed tomographic (CBCT) images independently to determine presence of ECR (ground truth). Radiographic data were divided into 3 regions of interest (ROIs): healthy teeth, teeth with ECR, and teeth with caries. Nine contrastive SSL models (SimCLR v2, MoCo v2, BYOL, DINO, NNCLR, SwAV, MSN, Barlow Twins, and SimSiam) were implemented in the assessment alongside 7 baseline deep learning models (ResNet-18, ResNet-50, VGG16, DenseNet, MobileNetV2, ResNeXt-50, and InceptionV3). A 10-fold cross-validation strategy and a hold-out test set were employed for model evaluation. Model performance was assessed via various metrics including classification accuracy, precision, recall, and F1-score. RESULTS: Included were 190 PA radiographs, composed of 470 ROIs. Results from 10-fold cross-validation demonstrated that most SSL models outperformed the transfer learning baseline models, with DINO achieving the highest mean accuracy (85.64 ± 4.56), significantly outperforming 13 other models (P < .05). DINO reached the highest test set (ie, 3 ROIs) accuracy (84.09%) while MoCo v2 exhibited the highest recall and F1-score (77.37% and 82.93%, respectively). CONCLUSIONS: This study showed that AI can assist clinicians in detecting ECR and differentiating it from caries. Additionally, it introduced the application of SSL in detecting ECR, emphasizing that SSL-based models can outperform transfer learning baselines and reduce reliance on large, labeled datasets.

Comparison of 2D and 3D convolutional neural networks in hyperspectral image analysis of fruits applied to orange bruise detection.

Recent advances in hyperspectral imaging (HSI) have demonstrated its ability to detect defects in fruit that may not be visible in RGB images. HSIs can be considered 3D images containing two spatial dimensions and one spectral dimension. Therefore, the first question that arises is how to process this type of information, either using 2D or 3D models. In this study, HSI in the 550-900 nm spectral range was used to detect bruising in oranges. Sixty samples of Thompson oranges were subjected to a mechanical bruising process, and HSIs were taken at different time intervals: before bruising, and 8 and 16 h after bruising. The samples were then classified using two convolutional neural network (CNN) models, a shallow 7-layer network (CNN-7) and a deep 18-layer network (CNN-18). In addition, two different input processing approaches are used: using 2D information from each band, and using the full 3D data from each HSI. The 3D models were the most accurate, with 94% correct classification for 3D-CNN-18, compared to 90% for 3D-CNN-7, and less than 83% for the 2D models. Our study suggests that 3D HSI may be a more effective technique for detecting fruit bruising, allowing the development of a fast, accurate, and nondestructive method for fruit sorting. PRACTICAL APPLICATION: Orange bruises can reduce the market value of food, which is why the food processing industry needs to carry out quality inspections. An effective way to perform this inspection is by using hyperspectral images that can be processed with 2D or 3D models, either with deep or shallow neural networks. The results of the comparison performed in this work can be useful for the development of more accurate and efficient bruise detection methods for fruit inspection.

Forecasting influenza hemagglutinin mutations through the lens of anomaly detection.

The influenza virus hemagglutinin is an important part of the virus attachment to the host cells. The hemagglutinin proteins are one of the genetic regions of the virus with a high potential for mutations. Due to the importance of predicting mutations in producing effective and low-cost vaccines, solutions that attempt to approach this problem have recently gained significant attention. A historical record of mutations has been used to train predictive models in such solutions. However, the imbalance between mutations and preserved proteins is a big challenge for the development of such models that need to be addressed. Here, we propose to tackle this challenge through anomaly detection (AD). AD is a well-established field in Machine Learning (ML) that tries to distinguish unseen anomalies from normal patterns using only normal training samples. By considering mutations as anomalous behavior, we could benefit existing rich solutions in this field that have emerged recently. Such methods also fit the problem setup of extreme imbalance between the number of unmutated vs. mutated training samples. Motivated by this formulation, our method tries to find a compact representation for unmutated samples while forcing anomalies to be separated from the normal ones. This helps the model to learn a shared unique representation between normal training samples as much as possible, which improves the discernibility and detectability of mutated samples from the unmutated ones at the test time. We conduct a large number of experiments on four publicly available datasets, consisting of three different hemagglutinin protein datasets, and one SARS-CoV-2 dataset, and show the effectiveness of our method through different standard criteria.

A deep learning framework to scale linear facial measurements to actual size using horizontal visible iris diameter: a study on an Iranian population.

Digital images allow for the objective evaluation of facial appearance and abnormalities as well as treatment outcomes and stability. With the advancement of technology, manual clinical measurements can be replaced with fully automatic photographic assessments. However, obtaining millimetric measurements on photographs does not provide clinicians with their actual value due to different image magnification ratios. A deep learning tool was developed to estimate linear measurements on images with unknown magnification using the iris diameter. A framework was designed to segment the eyes' iris and calculate the horizontal visible iris diameter (HVID) in pixels. A constant value of 12.2 mm was assigned as the HVID value in all the photographs. A vertical and a horizontal distance were measured in pixels on photographs of 94 subjects and were estimated in millimeters by calculating the magnification ratio using HVID. Manual measurement of the distances was conducted on the subjects and the actual and estimated amounts were compared using Bland-Altman analysis. The obtained error was calculated as mean absolute percentage error (MAPE) of 2.9% and 4.3% in horizontal and vertical measurements. Our study shows that due to the consistent size and narrow range of HVID values, the iris diameter can be used as a reliable scale to calibrate the magnification of the images to obtain precise measurements in further research.

Single-cell RNA sequencing uncovers heterogeneous transcriptional signatures in tumor-infiltrated dendritic cells in prostate cancer.

Prostate cancer (PCa) is one of the two solid malignancies in which a higher T cell infiltration in the tumor microenvironment (TME) corresponds with a worse prognosis for the tumor. The inability of T cells to eliminate tumor cells despite an increase in their number reinforces the possibility of impaired antigen presentation. In this study, we investigated the TME at single-cell resolution to understand the molecular function and communication of dendritic cells (DCs) (as professional antigen-presenting cells). According to our data, tumor cells stimulate the migration of immature DCs to the tumor site by inducing inflammatory chemokines. Many signaling pathways such as TNF-α/NF-κB, IL2/STAT5, and E2F up-regulated after DCs enter the tumor location. In addition, some molecules such as GPR34 and SLCO2B1 decreased on the surface of DCs. The analysis of molecular and signaling alterations in DCs revealed some suppression mechanisms of tumors, such as removing mature DCs, reducing the DC's survival, inducing anergy or exhaustion in the effector T cells, and enhancing the differentiation of T cells to Th2 and Tregs. In addition, we investigated the cellular and molecular communication between DCs and macrophages in the tumor site and found three molecular pairs including CCR5/CCL5, CD52/SIGLEC10, and HLA-DPB1/TNFSF13B. These molecular pairs are involved in the migration of immature DCs to the TME and disrupt the antigen-presenting function of DCs. Furthermore, we presented new therapeutic targets by the construction of a gene co-expression network. These data increase our knowledge of the heterogeneity and the role of DCs in PCa TME.

Deep learning for tooth identification and enumeration in panoramic radiographs.

Background: Dentists begin the diagnosis by identifying and enumerating teeth. Panoramic radiographs are widely used for tooth identification due to their large field of view and low exposure dose. The automatic numbering of teeth in panoramic radiographs can assist clinicians in avoiding errors. Deep learning has emerged as a promising tool for automating tasks. Our goal is to evaluate the accuracy of a two-step deep learning method for tooth identification and enumeration in panoramic radiographs. Materials and Methods: In this retrospective observational study, 1007 panoramic radiographs were labeled by three experienced dentists. It involved drawing bounding boxes in two distinct ways: one for teeth and one for quadrants. All images were preprocessed using the contrast-limited adaptive histogram equalization method. First, panoramic images were allocated to a quadrant detection model, and the outputs of this model were provided to the tooth numbering models. A faster region-based convolutional neural network model was used in each step. Results: Average precision (AP) was calculated in different intersection-over-union thresholds. The AP50 of quadrant detection and tooth enumeration was 100% and 95%, respectively. Conclusion: We have obtained promising results with a high level of AP using our two-step deep learning framework for automatic tooth enumeration on panoramic radiographs. Further research should be conducted on diverse datasets and real-life situations.

Morphology and gene expression profiling provide complementary information for mapping cell state.

Morphological and gene expression profiling can cost-effectively capture thousands of features in thousands of samples across perturbations by disease, mutation, or drug treatments, but it is unclear to what extent the two modalities capture overlapping versus complementary information. Here, using both the L1000 and Cell Painting assays to profile gene expression and cell morphology, respectively, we perturb human A549 lung cancer cells with 1,327 small molecules from the Drug Repurposing Hub across six doses, providing a data resource including dose-response data from both assays. The two assays capture both shared and complementary information for mapping cell state. Cell Painting profiles from compound perturbations are more reproducible and show more diversity but measure fewer distinct groups of features. Applying unsupervised and supervised methods to predict compound mechanisms of action (MOAs) and gene targets, we find that the two assays not only provide a partially shared but also a complementary view of drug mechanisms. Given the numerous applications of profiling in biology, our analyses provide guidance for planning experiments that profile cells for detecting distinct cell types, disease phenotypes, and response to chemical or genetic perturbations.

Virtual screening for small-molecule pathway regulators by image-profile matching.

Identifying the chemical regulators of biological pathways is a time-consuming bottleneck in developing therapeutics and research compounds. Typically, thousands to millions of candidate small molecules are tested in target-based biochemical screens or phenotypic cell-based screens, both expensive experiments customized to each disease. Here, our uncustomized, virtual, profile-based screening approach instead identifies compounds that match to pathways based on the phenotypic information in public cell image data, created using the Cell Painting assay. Our straightforward correlation-based computational strategy retrospectively uncovered the expected, known small-molecule regulators for 32% of positive-control gene queries. In prospective, discovery mode, we efficiently identified new compounds related to three query genes and validated them in subsequent gene-relevant assays, including compounds that phenocopy or pheno-oppose YAP1 overexpression and kill a Yap1-dependent sarcoma cell line. This image-profile-based approach could replace many customized labor- and resource-intensive screens and accelerate the discovery of biologically and therapeutically useful compounds.

Deep learning in periodontology and oral implantology: A scoping review.

Deep learning (DL) has been employed for a wide range of tasks in dentistry. We aimed to systematically review studies employing DL for periodontal and implantological purposes. A systematic electronic search was conducted on four databases (Medline via PubMed, Google Scholar, Scopus, and Embase) and a repository (ArXiv) for publications after 2010, without any limitation on language. In the present review, we included studies that reported deep learning models' performance on periodontal or oral implantological tasks. Given the heterogeneities in the included studies, no meta-analysis was performed. The risk of bias was assessed using the QUADAS-2 tool. We included 47 studies: focusing on imaging data (n = 20) and non-imaging data in periodontology (n = 12), or dental implantology (n = 15). The detection of periodontitis and gingivitis or periodontal bone loss, the classification of dental implant systems, or the prediction of treatment outcomes in periodontology and implantology were major use cases. The performance of the models was generally high. However, it varied given the employed methods (which includes various types of convolutional neural networks (CNN) and multi-layered perceptron (MLP)), the variety in specific modeling tasks, as well as the chosen and reported outcomes, outcome measures and outcome level. Only a few studies (n = 7) showed a low risk of bias across all assessed domains. A growing number of studies evaluated DL for periodontal or implantological objectives. Heterogeneity in study design, poor reporting and a high risk of bias severely limit the comparability of studies and the robustness of the overall evidence.

Image-based cell profiling enhancement via data cleaning methods.

With the advent of high-throughput assays, a large number of biological experiments can be carried out. Image-based assays are among the most accessible and inexpensive technologies for this purpose. Indeed, these assays have proved to be effective in characterizing unknown functions of genes and small molecules. Image analysis pipelines have a pivotal role in translating raw images that are captured in such assays into useful and compact representation, also known as measurements. CellProfiler is a popular and commonly used tool for this purpose through providing readily available modules for the cell/nuclei segmentation, and making various measurements, or features, for each cell/nuclei. Single cell features are then aggregated for each treatment replica to form treatment "profiles". However, there may be several sources of error in the CellProfiler quantification pipeline that affects the downstream analysis that is performed on the profiles. In this work, we examined various preprocessing approaches to improve the profiles. We consider the identification of drug mechanisms of action as the downstream task to evaluate such preprocessing approaches. Our enhancement steps mainly consist of data cleaning, cell level outlier detection, toxic drug detection, and regressing out the cell area from all other features, as many of them are widely affected by the cell area. Our experiments indicate that by performing these time-efficient preprocessing steps, image-based profiles can preserve more meaningful information compared to raw profiles. In the end, we also suggest possible avenues for future research.

Deep learning for caries detection: A systematic review.

OBJECTIVES: Detecting caries lesions is challenging for dentists, and deep learning models may help practitioners to increase accuracy and reliability. We aimed to systematically review deep learning studies on caries detection. DATA: We selected diagnostic accuracy studies that used deep learning models on dental imagery (including radiographs, photographs, optical coherence tomography images, near-infrared light transillumination images). The latest version of the quality assessment tool for diagnostic accuracy studies (QUADAS-2) tool was used for risk of bias assessment. Meta-analysis was not performed due to heterogeneity in the studies methods and their performance measurements. SOURCES: Databases (Medline via PubMed, Google Scholar, Scopus, Embase) and a repository (ArXiv) were screened for publications published after 2010, without any limitation on language. STUDY SELECTION: From 252 potentially eligible references, 48 studies were assessed full-text and 42 included, using classification (n = 26), object detection (n = 6), or segmentation models (n = 10). A wide range of performance metrics was used; image, object or pixel accuracy ranged between 68%-99%. The minority of studies (n = 11) showed a low risk of biases in all domains, and 13 studies (31.0%) low risk for concerns regarding applicability. The accuracy of caries classification models varied, i.e. 71% to 96% on intra-oral photographs, 82% to 99.2% on peri-apical radiographs, 87.6% to 95.4% on bitewing radiographs, 68.0% to 78.0% on near-infrared transillumination images, 88.7% to 95.2% on optical coherence tomography images, and 86.1% to 96.1% on panoramic radiographs. Pooled diagnostic odds ratios varied from 2.27 to 32,767. For detection and segmentation models, heterogeneity in reporting did not allow useful pooling. CONCLUSION: An increasing number of studies investigated caries detection using deep learning, with a diverse types of architectures being employed. Reported accuracy seems promising, while study and reporting quality are currently low. CLINICAL SIGNIFICANCE: Deep learning models can be considered as an assistant for decisions regarding the presence or absence of carious lesions.

Deep learning for the classification of cervical maturation degree and pubertal growth spurts: A pilot study.

Objective: This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. Methods: The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. Results: The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. Conclusions: The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.

A multiparametric activity profiling platform for neuron disease phenotyping and drug screening.

Patient stem cell-derived models enable imaging of complex disease phenotypes and the development of scalable drug discovery platforms. Current preclinical methods for assessing cellular activity do not, however, capture the full intricacies of disease-induced disturbances and instead typically focus on a single parameter, which impairs both the understanding of disease and the discovery of effective therapeutics. Here, we describe a cloud-based image processing and analysis platform that captures the intricate activity profile revealed by GCaMP fluorescence recordings of intracellular calcium changes and enables the discovery of molecules that correct 153 parameters that define the amyotrophic lateral sclerosis motor neuron disease phenotype. In a high-throughput screen, we identified compounds that revert the multiparametric disease profile to that found in healthy cells, a novel and robust measure of therapeutic potential quite distinct from unidimensional screening. This platform can guide the development of therapeutics that counteract the multifaceted pathological features of diseased cellular activity.

Nondestructive nitrogen content estimation in tomato plant leaves by Vis-NIR hyperspectral imaging and regression data models.

The present study aims to estimate nitrogen (N) content in tomato (Solanum lycopersicum L.) plant leaves using optimal hyperspectral imaging data by means of computational intelligence [artificial neural networks and the differential evolution algorithm (ANN-DE), partial least squares regression (PLSR), and convolutional neural network (CNN) regression] to detect potential plant stress to nutrients at early stages. First, pots containing control and treated tomato plants were prepared; three treatments (categories or classes) consisted in the application of an overdose of 30%, 60%, and 90% nitrogen fertilizer, called N-30%, N-60%, N-90%, respectively. Tomato plant leaves were then randomly picked up before and after the application of nitrogen excess and imaged. Leaf images were captured by a hyperspectral camera, and nitrogen content was measured by laboratory ordinary destructive methods. Two approaches were studied: either using all the spectral data in the visible (Vis) and near infrared (NIR) spectral bands, or selecting only the three most effective wavelengths by an optimization algorithm. Regression coefficients (R) were 0.864±0.027 for ANN-DE, 0.837±0.027 for PLSR, and 0.875±0.026 for CNN in the first approach, over the test set. The second approach used different models for each treatment, achieving R values for all the regression methods above 0.96; however, it needs a previous classification stage of the samples in one of the three nitrogen excess classes under consideration.

ARAE: Adversarially robust training of autoencoders improves novelty detection.

Autoencoders have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while failing to regenerate the anomalous data. Based on this assumption, one could utilize the AE for novelty detection. However, it is known that this assumption does not always hold. Such an AE can often perfectly reconstruct the anomalous data due to modeling low-level and generic features in the input. We propose a novel training algorithm for the AE that facilitates learning more semantically meaningful features to address this problem. For this purpose, we exploit the fact that adversarial robustness promotes the learning of significant features. Therefore, we force the AE to learn such features by making its bottleneck layer more stable against adversarial perturbations. This idea is general and can be applied to other autoencoder-based approaches as well. We show that despite using a much simpler architecture than the prior methods, the proposed AE outperforms or is competitive to the state-of-the-art on four benchmark datasets and two medical datasets.

Machine learning and orthodontics, current trends and the future opportunities: A scoping review.

INTRODUCTION: In recent years, artificial intelligence (AI) has been applied in various ways in medicine and dentistry. Advancements in AI technology show promising results in the practice of orthodontics. This scoping review aimed to investigate the effectiveness of AI-based models employed in orthodontic landmark detection, diagnosis, and treatment planning. METHODS: A precise search of electronic databases was conducted, including PubMed, Google Scholar, Scopus, and Embase (English publications from January 2010 to July 2020). Quality Assessment and Diagnostic Accuracy Tool 2 (QUADAS-2) was used to assess the quality of the articles included in this review. RESULTS: After applying inclusion and exclusion criteria, 49 articles were included in the final review. AI technology has achieved state-of-the-art results in various orthodontic applications, including automated landmark detection on lateral cephalograms and photography images, cervical vertebra maturation degree determination, skeletal classification, orthodontic tooth extraction decisions, predicting the need for orthodontic treatment or orthognathic surgery, and facial attractiveness. Most of the AI models used in these applications are based on artificial neural networks. CONCLUSIONS: AI can help orthodontists save time and provide accuracy comparable to the trained dentists in diagnostic assessments and prognostic predictions. These systems aim to boost performance and enhance the quality of care in orthodontics. However, based on current studies, the most promising application was cephalometry landmark detection, skeletal classification, and decision making on tooth extractions.

Classification of Cucumber Leaves Based on Nitrogen Content Using the Hyperspectral Imaging Technique and Majority Voting.

Improper usage of nitrogen in cucumber cultivation causes nitrate accumulation in the fruit and results in food poisoning in humans; therefore, mandatory evaluation of food products becomes inevitable. Hyperspectral imaging has a very good ability to evaluate the quality of fruits and vegetables in a non-destructive manner. The goal of the present paper was to identify excess nitrogen in cucumber plants. To obtain a reliable result, the majority voting method was used, which takes into account the unanimity of five classifiers, namely, the hybrid artificial neural network-imperialism competitive algorithm (ANN-ICA), the hybrid artificial neural network-harmonic search (ANN-HS) algorithm, linear discrimination analysis (LDA), the radial basis function network (RBF), and the K-nearest-neighborhood (KNN). The wavelengths of 723, 781, and 901 nm were determined as optimal wavelengths using the hybrid artificial neural network-biogeography-based optimization (ANN-BBO) algorithm, and the performance of classifiers was investigated using the optimal spectrum. The results of a t-test showed that there was no significant difference in the precision of the algorithm when using the optimal wavelengths and wavelengths of the whole range. The correct classification rate of the classifiers ANN-ICA, ANN-HS, LDA, RBF, and KNN were 96.14%, 96.11%, 95.73%, 64.03%, and 95.24%, respectively. The correct classification rate of majority voting (MV) was 95.55% for test data in 200 iterations, which indicates the system was successful in distinguishing nitrogen-rich leaves from leaves with a standard content of nitrogen.

Publisher Correction: Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

Capturing single-cell heterogeneity via data fusion improves image-based profiling.

Single-cell resolution technologies warrant computational methods that capture cell heterogeneity while allowing efficient comparisons of populations. Here, we summarize cell populations by adding features' dispersion and covariances to population averages, in the context of image-based profiling. We find that data fusion is critical for these metrics to improve results over the prior alternatives, providing at least ~20% better performance in predicting a compound's mechanism of action (MoA) and a gene's pathway.