Search Results (29)

Background/Objectives: Dental diseases represent a great problem for oral health care, and early diagnosis is essential to reduce the risk of complications. Panoramic radiographs provide a detailed perspective of dental structures that is suitable for automated diagnostic methods. This paper aims to investigate the use of an advanced deep learning (DL) model for the multiclass classification of diseases at the sub-diagnosis level using panoramic radiographs to resolve the inconsistencies and skewed classes in the dataset. Methods: To classify and test the models, rich data of 10,580 high-quality panoramic radiographs, initially annotated in 93 classes and subsequently improved to 35 consolidated classes, was used. We applied extensive preprocessing techniques like class consolidation, mislabeled entry correction, redundancy removal and augmentation to reduce the ratio of class imbalance from 2560:1 to 61:1. Five modern convolutional neural network (CNN) architectures—InceptionV3, EfficientNetV2, DenseNet121, ResNet50, and VGG16—were assessed with respect to five metrics: accuracy, mean average precision (mAP), precision, recall, and F1-score. Results: InceptionV3 achieved the best performance with a 97.51% accuracy rate and a mAP of 96.61%, thus confirming its superior ability for diagnosing a wide range of dental conditions. The EfficientNetV2 and DenseNet121 models achieved accuracies of 97.04% and 96.70%, respectively, indicating strong classification performance. ResNet50 and VGG16 also yielded competitive accuracy values comparable to these models. Conclusions: Overall, the results show that deep learning models are successful in dental disease classification, especially the model with the highest accuracy, InceptionV3. New insights and clinical applications will be realized from a further study into dataset expansion, ensemble learning strategies, and the application of explainable artificial intelligence techniques. The findings provide a starting point for implementing automated diagnostic systems for dental diagnosis with greater efficiency, accuracy, and clinical utility in the deployment of oral healthcare. Full article

Pufferfish are an economically important food in Asia despite the potential risk of tetrodotoxin (TTX) poisoning. To promote food safety by ensuring the correct identification of pufferfish species, we developed common and species-specific primer sets for four Lagocephalus species (Lagocephalus spadiceus, Lagocephalus cheesemanii, Lagocephalus wheeleri, and Lagocephalus inermis) based on analysis of mitochondrial DNA cytochrome c oxidase subunit I (COI) in various pufferfish species commonly distributed and/or legally sold in Korea. The common primers were developed based on complete sequence data acquired from GenBank. The total length of fragments amplified by the common primer set was 1280 bp. Then, species-specific multiplex polymerase chain reaction (PCR) amplification was conducted for the four target species, obtaining 980 bp for L. spadiceus, 859 bp for L. cheesemanii, 672 bp for L. wheeleri, and 563 bp for L. inermis. Multiplex PCR is an important tool for the simple, rapid, accurate, and simultaneous identification of target species. The newly developed primer sets will contribute to reducing the occurrence of TTX poisoning and protect consumer rights by eradicating the mislabeling or fraudulent use of pufferfish products. Full article

Beef fat injection technology, used to enhance the perceived quality of lower-grade meat, often results in artificially marbled beef that mimics the visual traits of Wagyu, characterized by dense fat distribution. This practice, driven by the high cost of Wagyu and the affordability of fat-injected beef, has led to the proliferation of mislabeled “Wagyu-grade” products sold at premium prices, posing potential food safety risks such as allergen exposure or consumption of unverified additives, which can adversely affect consumer health. Addressing this, this study introduces a smart sensing system integrated with handheld mobile devices, enabling consumers to capture beef images during purchase for real-time health-focused assessment. The system analyzes surface texture and color, transmitting data to a server for classification to determine if the beef is artificially marbled, thus supporting informed dietary choices and reducing health risks. Images are processed by applying a region of interest (ROI) mask to remove background noise, followed by partitioning into grid blocks. Local binary pattern (LBP) texture features and RGB color features are extracted from these blocks to characterize surface properties of three beef types (Wagyu, regular, and fat-injected). A support vector machine (SVM) model classifies the blocks, with the final image classification determined via majority voting. Experimental results reveal that the system achieves a recall rate of 95.00% for fat-injected beef, a misjudgment rate of 1.67% for non-fat-injected beef, a correct classification rate (CR) of 93.89%, and an F1-score of 95.80%, demonstrating its potential as a human-centered healthcare tool for ensuring food safety and transparency. Full article

Background: Knee Osteoarthritis (KOA) is a prevalent and debilitating joint disorder that significantly impacts quality of life, particularly in aging populations. Accurate and consistent classification of KOA severity, typically using the Kellgren-Lawrence (KL) grading system, is crucial for effective diagnosis, treatment planning, and monitoring disease progression. However, traditional KL grading is known for its inherent subjectivity and inter-rater variability, which underscores the pressing need for objective, automated, and reliable classification methods. Methods: This study investigates the performance of an EfficientNetB5 deep learning model, enhanced with transfer learning from the ImageNet dataset, for the task of classifying KOA severity into five distinct KL grades (0–4). We utilized a publicly available Kaggle dataset comprising 9786 knee X-ray images. A key aspect of our methodology was a comprehensive data-centric preprocessing pipeline, which involved an initial phase of outlier removal to reduce noise, followed by systematic label correction using the Cleanlab framework to identify and rectify potential inconsistencies within the original dataset labels. Results: The final EfficientNetB5 model, trained on the preprocessed and Cleanlab-remediated data, achieved an overall accuracy of 82.07% on the test set. This performance represents a significant improvement over previously reported benchmarks for five-class KOA classification on this dataset, such as ResNet-101 which achieved 69% accuracy. The substantial enhancement in model performance is primarily attributed to Cleanlab’s robust ability to detect and correct mislabeled instances, thereby improving the overall quality and reliability of the training data and enabling the model to better learn and capture complex radiographic patterns associated with KOA. Class-wise performance analysis indicated strong differentiation between healthy (KL Grade 0) and severe (KL Grade 4) cases. However, the “Doubtful” (KL Grade 1) class presented ongoing challenges, exhibiting lower recall and precision compared to other grades. When evaluated against other architectures like MobileNetV3 and Xception for multi-class tasks, our EfficientNetB5 demonstrated highly competitive results. Conclusions: The integration of an EfficientNetB5 model with a rigorous data-centric preprocessing approach, particularly Cleanlab-based label correction and outlier removal, provides a robust and significantly more accurate method for five-class KOA severity classification. While limitations in handling inherently ambiguous cases (such as KL Grade 1) and the small sample size for severe KOA warrant further investigation, this study demonstrates a promising pathway to enhance diagnostic precision. The developed pipeline shows considerable potential for future clinical applications, aiding in more objective and reliable KOA assessment. Full article

Labeling errors in datasets are a persistent challenge in machine learning because they introduce noise and bias and reduce the model’s generalization. This study proposes a novel methodology for detecting and correcting mislabeled samples in image datasets by using the Cumulative Spectral Gradient (CSG) metric to assess the intrinsic complexity of the data. This methodology is applied to the noisy CIFAR-10/100 and CIFAR-10n/100n datasets, where mislabeled samples in CIFAR-10n/100n are identified and relabeled using CIFAR-10/100 as a reference. The DenseNet and Xception models pre-trained on ImageNet are fine-tuned to evaluate the impact of label correction on the model performance. Evaluation metrics based on the confusion matrix are used to compare the model performance on the original and noisy datasets and on the label-corrected datasets. The results show that correcting the mislabeled samples significantly improves the accuracy and robustness of the model, highlighting the importance of dataset quality in machine learning. Full article

China is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varieties. The detection of cottonseed variety information has become a critical issue for the Chinese cotton industry. In this study, we collected near-infrared (NIR) spectral data from six cottonseed varieties and constructed a GAN for cottonseed NIR data (GAN-CNIRD) model to generate additional cottonseed NIR data. The Euclidean distance method was used to label the generated NIR data according to the characteristics of the true NIR data. We then applied Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Normalization algorithms to preprocess the combined dataset of generated and real cottonseed NIR data. Feature wavelengths were extracted using Bootstrap Soft Shrinkage (BOSS) and Competitive Adaptive Reweighted Sampling (CARS) algorithms. Subsequently, we developed Linear Discriminant Analysis (LDA), Random subspace method (RSM), and convolutional neural network (CNN) models to classify the cottonseed varieties. The results showed that for the LDA model, the use of feature wavelengths extracted after Normalization-BOSS processing achieved the best performance with an accuracy of 97.00%. For the RSM model, the use of feature wavelengths extracted after SNV-CARS processing achieved the best performance with an accuracy of 98.00%. For the CNN model, the use of feature wavelengths extracted after MSC-CARS processing achieved the best performance with an accuracy of 100.00%. Data augmentation using GAN-CNIRD-generated cottonseed data improved the accuracy of the three optimal models by 6%, 5%, and 6%, respectively. This study provides a crucial reference for the rapid detection of cottonseed variety information and has significant implications for the standardized management of cottonseed varieties. Full article

Introduction: The frozen section intra-operative consultation is a pathology procedure that provides real-time evaluations of tissue samples during surgery, enabling quick and informed decisions. In the pre-analytical phase, errors related to sample collection, transport, and identification are common, and tools like failure mode, effects, and criticality analysis help identify and prevent risks. This study aims to enhance patient safety and diagnostic quality by analyzing risks and optimizing sample management. Materials and Methods: The failure mode, effects, and criticality analysis was conducted by a multidisciplinary team to analyze the workflow of frozen section sample handling from collection in the operating theater to acceptance at the pathology lab. Six steps were identified, each assigned tasks and responsibilities, with risks assessed through the risk priority number, calculated from severity, occurrence, and detectability. Severity was classified based on the WHO framework, ranging from “No Harm” to “Death”, to prioritize risks effectively. Results: The study identified 12 failure modes across 11 sub-processes, prioritized by risk. Key failures included missing patient identification, incorrect sample retrieval, missing labels, misdirected samples, and samples sent to the wrong lab. Discussion: Pre-analytical errors in pathology pose risks to diagnosis and patient care, with most errors occurring in this phase. A multidisciplinary team identified key issues, such as sample mislabeling and delays due to staff unavailability, and implemented corrective actions, including improved signage, staff re-training, and sample tracking systems. Monitoring and regular checks ensured ongoing adherence to protocols and reduced the risks of misidentification, transport delays, and procedural errors. Conclusions: The frozen section intra-operative consultation is vital in surgical pathology, with the pre-analytical phase posing significant risks due to potential errors in sample handling and labeling. Failure mode, effects, and criticality analysis has proven effective in identifying and prioritizing these failures, despite resource demands, by allowing corrective actions that enhance patient safety and healthcare quality. Full article

Cacao (Theobroma cacao L.) is a tropical tree species belonging to the Malvaceae, which originated in the lowland rainforests of the Amazon. It is a major agricultural commodity, which contributes towards the Gross Domestic Product of West African countries, where it accounts for about 70% of the world’s production. Understanding the genetic diversity of genetic resources in a country, especially for an introduced crop such as cacao, is crucial to their management and effective utilization. However, very little is known about the genetic structure of the cacao germplasm from Sierra Leone and Togo based on molecular information. We assembled cacao germplasm accessions (235 from Sierra Leone and 141 from Togo) from different seed gardens and farmers’ fields across the cacao-producing states/regions of these countries for genetic diversity and population structure studies based on single nucleotide polymorphism (SNP) markers using 20 highly informative and reproducible KASP–SNPs markers. Genetic diversity among these accessions was assessed with three complementary clustering methods, including model-based population structure, discriminant analysis of principal components (DAPC), and phylogenetic trees. STRUCTURE and DAPC exhibited some consistency in the allocation of accessions into subpopulations or groups, although some discrepancies in their groupings were noted. Hierarchical clustering analysis grouped all the individuals into two major groups, as well as several sub-clusters. We also conducted a network analysis to elucidate genetic relationships among cacao accessions from Sierra Leone and Togo. Analysis of molecular variance (AMOVA) revealed high genetic diversity (86%) within accessions. A high rate of mislabeling/duplicate genotype names was revealed in both countries, which may be attributed to errors from the sources of introduction, labeling errors, and lost labels. This preliminary study demonstrates the use of KASP–SNPs for fingerprinting that can help identify duplicate/mislabeled accessions and provide strong evidence for improving accuracy and efficiency in cacao germplasm management as well as the distribution of correct materials to farmers. Full article

Monogenic defects of beta cell function refer to a group of rare disorders that are characterized by early-onset diabetes mellitus due to a single gene mutation affecting insulin secretion. It accounts for up to 5% of all pediatric diabetes cases and includes transient or permanent neonatal diabetes, maturity-onset diabetes of the young (MODY), and various syndromes associated with diabetes. Causative mutations have been identified in genes regulating the development or function of the pancreatic beta cells responsible for normal insulin production and/or release. To date, more than 40 monogenic diabetes subtypes have been described, with those caused by mutations in HNF1A and GCK genes being the most prevalent. Despite being caused by a single gene mutation, each type of monogenic diabetes, especially MODY, can appear with various clinical phenotypes, even among members of the same family. This clinical heterogeneity, its rarity, and the fact that it shares some features with more common types of diabetes, can make the clinical diagnosis of monogenic diabetes rather challenging. Indeed, several cases of MODY or syndromic diabetes are accurately diagnosed in adulthood, after having been mislabeled as type 1 or type 2 diabetes. The recent widespread use of more reliable sequencing techniques has improved monogenic diabetes diagnosis, which is important to guide appropriate treatment and genetic counselling. The current review aims to summarize the latest knowledge on the clinical presentation, genetic confirmation, and therapeutic approach of the various forms of monogenic defects of beta cell function, using three imaginary clinical scenarios and highlighting clinical and laboratory features that can guide the clinician in reaching the correct diagnosis. Full article

Ensuring food safety and protecting consumers are major aspects for commercialized products. Honey, the most prominent in the class of bee products, requires special regulations due to its origin as a natural product. Mislabeling, imitation, and adulteration represent a source of risks for human health. Specific determinations and analyses are essential for controlling the sector and preventing unfair competition. To compare and establish the correct labeling of several different honeys, melissopalynological, physicochemical, mineral content, and microbiological analyses were carried out on 18 samples commercially available in different countries, namely Türkiye, Romania, Bulgaria, and Northern Cyprus. The honey labels were in accordance with the determined pollen content. The physiochemical parameters showed high variability: 4.07–5.25 (pH), 79.95–83.45 (°Brix), 0.262–1.452 µS/cm (electrical conductivity), and 14.6–18.4% (moisture). The samples were quantitatively high in K, P, Na, and Ca, with the highest cumulative mineral content being found for honeys containing Fagaceae pollen. Additionally, the antimicrobial potential of the various honey samples was evaluated against selected bacteria, employing the disk diffusion and serial dilution methods. Results revealed that the honey samples exhibited increased antibacterial activity against Gram-negative bacteria, with notable activity against S. typhimurium, and moderate activity against Gram-positive S. aureus. Full article

Deep learning models can enhance the detection efficiency and accuracy of rapid on-site screening for imported grains at customs, satisfying the need for high-throughput, efficient, and intelligent operations. However, the construction of datasets, which is crucial for deep learning models, often involves significant labor and time costs. Addressing the challenges associated with establishing high-resolution instance segmentation datasets for small objects, we integrate two zero-shot models, Grounding DINO and Segment Anything model, into a dataset annotation pipeline. Furthermore, we encapsulate this pipeline into a software tool for manual calibration of mislabeled, missing, and duplicated annotations made by the models. Additionally, we propose preprocessing and postprocessing methods to improve the detection accuracy of the model and reduce the cost of subsequent manual correction. This solution is not only applicable to rapid screening for quarantine weeds, seeds, and insects at customs but can also be extended to other fields where instance segmentation is required. Full article

Since the start of 2020, the outbreak of the Coronavirus disease (COVID-19) has been a global public health emergency, and it has caused unprecedented economic and social disaster. In order to improve the diagnosis efficiency of COVID-19 patients, a number of researchers have conducted extensive studies on applying artificial intelligence techniques to the analysis of COVID-19-related medical images. The automatic segmentation of lesions from computed tomography (CT) images using deep learning provides an important basis for the quantification and diagnosis of COVID-19 cases. For a deep learning-based CT diagnostic method, a few of accurate pixel-level labels are essential for the training process of a model. However, the translucent ground-glass area of the lesion usually leads to mislabeling while performing the manual labeling operation, which weakens the accuracy of the model. In this work, we propose a method for correcting rough labels; that is, to hierarchize these rough labels into precise ones by performing an analysis on the pixel distribution of the infected and normal areas in the lung. The proposed method corrects the incorrectly labeled pixels and enables the deep learning model to learn the infected degree of each infected pixel, with which an aiding system (named DLShelper) for COVID-19 CT image diagnosis using the hierarchical labels is also proposed. The DLShelper targets lesion segmentation from CT images, as well as the severity grading. The DLShelper assists medical staff in efficient diagnosis by providing rich auxiliary diagnostic information (including the severity grade, the proportions of the lesion and the visualization of the lesion area). A comprehensive experiment based on a public COVID-19 CT image dataset is also conducted, and the experimental results show that the DLShelper significantly improves the accuracy of segmentation for the lesion areas and also achieves a promising accuracy for the severity grading task. Full article

This paper aims to quantify the errors in the provided agricultural crop types, estimate the possible error rate in the available dataset, and propose a correction strategy. This quantification could establish a confidence criterion useful for decisions taken on this data or to have a better apprehension of the possible consequences of using this data in learning downstream functions such as classification. We consider two agricultural label errors: crop type mislabels and mis-split crops. To process and correct these errors, we design a two-step methodology. Using class-specific convolutional autoencoders applied to synthetic aperture radar (SAR) time series of free-to-use and temporally dense Sentinel-1 data, we detect out-of-distribution temporal profiles of crop time series, which we categorize as one out of the three following possibilities: crop edge confusion, incorrectly split crop areas, and potentially mislabeled crop. We then relabel crops flagged as mislabeled using an Otsu threshold-derived confidence criteria. We numerically validate our methodology using a controlled disruption of labels over crops of confidence. We then compare our methods to supervised algorithms and show improved quality of relabels, with up to 98% correct relabels for our method, against up to 91% for Random Forest-based approaches. We show a drastic decrease in the performance of supervised algorithms under critical conditions (smaller and larger amounts of introduced label errors), with Random Forest falling to 56% of correct relabels against 95% for our approach. We also explicit the trade-off made in the design of our method between the number of relabels, and their quality. In addition, we apply this methodology to a set of agricultural labels containing probable mislabels. We also validate the quality of the corrections using optical imagery, which helps highlight incorrectly cut crops and potential mislabels. We then assess the applicability of the proposed method in various contexts and scales and present how it is suitable for verifying and correcting farmers’ crop declarations. Full article

A small portion of mislabeled data can easily limit the performance of deep neural networks (DNNs) due to their high capacity for memorizing random labels. Thus, robust learning from noisy labels has become a key challenge for deep learning due to inadequate datasets with high-quality annotations. Most existing methods involve training models on clean sets by dividing clean samples from noisy ones, resulting in large amounts of mislabeled data being unused. To address this problem, we propose categorizing training samples into five fine-grained clusters based on the difficulty experienced by DNN models when learning them and label correctness. A novel fine-grained confidence modeling (FGCM) framework is proposed to cluster samples into these five categories; with each cluster, FGCM decides whether to accept the cluster data as they are, accept them with label correction, or accept them as unlabeled data. By applying different strategies to the fine-grained clusters, FGCM can better exploit training data than previous methods. Extensive experiments on widely used benchmarks CIFAR-10, CIFAR-100, clothing1M, and WebVision with different ratios and types of label noise demonstrate the superiority of our FGCM. Full article

Optical motion capture systems are prone to errors connected to marker recognition (e.g., occlusion, leaving the scene, or mislabeling). These errors are then corrected in the software, but the process is not perfect, resulting in artifact distortions. In this article, we examine four existing types of artifacts and propose a method for detection and classification of the distortions. The algorithm is based on the derivative analysis, low-pass filtering, mathematical morphology, and loose predictor. The tests involved multiple simulations using synthetically-distorted sequences, performance comparisons to human operators (concerning real life data), and an applicability analysis for the distortion removal. Full article