Classification Metrics Research Articles

A new data complexity measure for multi-class imbalanced classification tasks

The skewed class distribution and data complexity may severely affect the imbalanced classification results. The cost of classification can be significantly reduced if these data complexity are measured and pre-processed prior to training, particularly when dealing with large-scale and high-dimensional datasets. Although many methods have been proposed to evaluate data complexity, most of them fail to fully consider the interaction among different data characteristics, or the connection between class imbalance and these characteristics, thus posing a serious challenge to effectively evaluate the difficulty of classification. This paper presents a new data complexity measure MFII (multi-factor imbalance index), which measures the combined effects of the skewed class distribution and data characteristics on classification difficulty. In particular, it further comprehensively investigates the impact of overlap size, confusion degree, and sub-cluster structure. VoR (value of resolution) and DoC (degree of consistency) are also proposed to evaluate the resolution and interpretability of complexity measures. The experimental results demonstrate that MFII has lower VoR and a stronger correlation with classification metrics, which indicates that MFII can more accurately evaluate the difficulty of multi-class imbalanced classification tasks.

Значение видео-уродинамического исследования в выборе метода лечения детей с нейрогенными дисфункциями мочевого пузыря

Video urodynamics is the standard for assessment of the lower urinary tract in children with neurogenic urinary disorders aiming to provide more information about the condition of the lower urinary tract v. retrograde urethrocystography. Video urodynamics parameters are used as possible indicators for choosing various surgical treatment options, however, all work is focused on adult patients, and data for the pediatric cohort were not available as yet. The purpose of this research was the evaluation of the role of video urodynamics and retrograde urethrocystography in the selection of effective conservative and surgical treatment of neurogenic urinary disorders in children. Materials and methods used: 112 patients aged 1,8 to 18 y/o with neurogenic urinary disorders were included in the study, of whom 101 were those who had been proven effectively treated with conservative M-cholinoblockers or had successfully undergone minimally invasive surgery as follows: intradetrusor injection of botulinum toxin (n=21), transurethral correction of VUR (n=17), simultaneous execution of two of these interventions (n=22). Based on the results of video urodynamic and cystographic examination of these patients with the CHAID technique, the classification trees were built in order to evaluate the effective treatment (conservative/surgical). Results: the median age of patients was 9,0 years [7,8-12,0]. The first classification tree containing the parameter “presence of VUR according to the results of retrograde cystography.” The sensitivity of the obtained model for the effectiveness of surgical treatment was 83,3% v. 73,2% for conservative treatment. The accuracy was 79,2%. The ROC-AUC value was 0,783. The second classification tree contained the maximum Pves value according to the results of the video urodynamics, presence of hyperactivity, presence of VUR. The sensitivity of the obtained model for the effectiveness of surgical treatment was 93,3% v. 97,6% for conservative treatment. The accuracy was 95,0%. The ROC-AUC value was 0,972. Comparison of ROC-AUC values by the Delong test revealed statistically significant differences between these binary classification metrics (p<0.001). Conclusion: the parameters of video urodynamics have greater diagnostic accuracy in effective prediction of both conservative and surgical treatment methods compared to the retrograde urethrocystography.

Radiomics signature for automatic hydronephrosis detection in unenhanced Low-Dose CT

PurposeTo investigate the diagnostic performance of an automatic pipeline for detection of hydronephrosis on kidney's parenchyma on unenhanced low-dose CT of the abdomen. MethodsThis retrospective study included 95 patients with confirmed unilateral hydronephrosis in an unenhanced low-dose CT of the abdomen. Data were split into training (n = 67) and test (n = 28) cohorts. Both kidneys for each case were included in further analyses, whereas the kidney without hydronephrosis was used as control. Using the training cohort, we developed a pipeline consisting of a deep-learning model for automatic segmentation (a Convolutional Neural Network based on nnU-Net architecture) of the kidney's parenchyma and a radiomics classifier to detect hydronephrosis. The models were assessed using standard classification metrics, such as area under the ROC curve (AUC), sensitivity and specificity, as well as semantic segmentation metrics, including Dice coefficient and Jaccard index. ResultsUsing manual segmentation of the kidney’s parenchyma, hydronephrosis can be detected with an AUC of 0.84, a sensitivity of 75% and a specificity of 82%, a PPV of 81% and a NPV of 77%. Automatic kidney segmentation achieved a mean Dice score of 0.87 and 0.91 for the right and left kidney, respectively. Additionally, automatic segmentation achieved an AUC of 0.83, a sensitivity of 86%, specificity of 64%, PPV of 71%, and NPV of 82%. ConclusionOur proposed radiomics signature using automatic kidney's parenchyma segmentation allows for accurate hydronephrosis detection on unenhanced low-dose CT scans of the abdomen independently of widened renal pelvis. This method could be used in clinical routine to highlight hydronephrosis to radiologists as well as clinicians, especially in patients with concurrent parapelvic cysts and might reduce time and costs associated with diagnosing hydronephrosis.

Opti-CAM: Optimizing saliency maps for interpretability

Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a saliency map directly in the image space or learn it by training another network on additional data. In this work we introduce Opti-CAM, combining ideas from CAM-based and masking-based approaches. Our saliency map is a linear combination of feature maps, where weights are optimized per image such that the logit of the masked image for a given class is maximized. We also fix a fundamental flaw in two of the most common evaluation metrics of attribution methods. On several datasets, Opti-CAM largely outperforms other CAM-based approaches according to the most relevant classification metrics. We provide empirical evidence supporting that localization and classifier interpretability are not necessarily aligned.

RailTrack-DaViT: A Vision Transformer-Based Approach for Automated Railway Track Defect Detection.

Railway track defects pose significant safety risks and can lead to accidents, economic losses, and loss of life. Traditional manual inspection methods are either time-consuming, costly, or prone to human error. This paper proposes RailTrack-DaViT, a novel vision transformer-based approach for railway track defect classification. By leveraging the Dual Attention Vision Transformer (DaViT) architecture, RailTrack-DaViT effectively captures both global and local information, enabling accurate defect detection. The model is trained and evaluated on multiple datasets including rail, fastener and fishplate, multi-faults, and ThaiRailTrack. A comprehensive analysis of the model's performance is provided including confusion matrices, training visualizations, and classification metrics. RailTrack-DaViT demonstrates superior performance compared to state-of-the-art CNN-based methods, achieving the highest accuracies: 96.9% on the rail dataset, 98.9% on the fastener and fishplate dataset, and 98.8% on the multi-faults dataset. Moreover, RailTrack-DaViT outperforms baselines on the ThaiRailTrack dataset with 99.2% accuracy, quickly adapts to unseen images, and shows better model stability during fine-tuning. This capability can significantly reduce time consumption when applying the model to novel datasets in practical applications.

“Dead or Alive?” Assessment of the Binary End-of-Event Outcome Indicator for the NEMSIS Public Research Dataset

Objectives The National Emergency Medical Services Information System (NEMSIS) provides a robust set of data to evaluate prehospital care. However, a major limitation is that the vast majority of the records lack a definitive outcome. This study aimed to evaluate the performance of a recently proposed method (“MLB” method) to impute missing end-of-EMS-event outcomes (“dead” or “alive”) for patient care reports in the NEMSIS public research dataset. Methods This study reproduced the recently published method for patient outcome imputation in the NEMSIS database and replicated the results for years 2017 through 2022 (n = 686,075). We performed statistical analyses leveraging an array of established performance metrics for binary classification from the machine learning literature. Evaluation metrics included overall accuracy, true positive rate, true negative rate, balanced accuracy, precision, F1 score, Cohen’s Kappa coefficient, Matthews’ coefficient, Hamming loss, the Jaccard similarity score, and the receiver operating characteristic/area under the curve. Results Extended metrics show consistently good imputation performance from year-to-year but reveal weakness in accurately indicating the minority class: e.g., after adjustments for conflicting labels, “dead” prediction accuracy is 77.7% for 2018 and 61.8% over the six-year NEMSIS sub-sample, even though overall accuracy is 98.8%. Slight over-fitting is also present. Conclusions This study found that the recently published MLB method produced reasonably good “dead” or “alive” indicators. We recommend reporting of True Positive Rate (“dead” prediction accuracy) and True Negative Rate (“alive” prediction accuracy) when applying the imputation method for analyses of NEMSIS data. More attention by EMS clinicians to complete documentation of target NEMSIS elements can further improve the method’s performance.

Systematic review and meta-analysis on the classification metrics of machine learning algorithm based radiomics in hepatocellular carcinoma diagnosis

The aim of this systematic review and meta-analysis is to evaluate the performance of classification metrics of machine learning-driven radiomics in diagnosing hepatocellular carcinoma (HCC). Following the PRISMA guidelines, a comprehensive search was conducted across three major scientific databases—PubMed, ScienceDirect, and Scopus—from 2018 to 2022. The search yielded a total of 436 articles pertinent to the application of machine learning and deep learning for HCC prediction. These studies collectively reflect the burgeoning interest and rapid advancements in employing artificial intelligence (AI)-driven radiomics for enhanced HCC diagnostic capabilities. After the screening process, 34 of these articles were chosen for the study. The area under curve (AUC), accuracy, specificity, and sensitivity of the proposed and basic models were assessed in each of the studies. Jamovi (version 1.1.9.0) was utilised to carry out a meta-analysis of 12 cohort studies to evaluate the classification accuracy rate. The risk of bias was estimated, and Logistic Regression was found to be the most suitable classifier for binary problems, with least absolute shrinkage and selection operator (LASSO) as the feature selector. The pooled proportion for HCC prediction classification was high for all performance metrics, with an AUC value of 0.86 (95 % CI: 0.83–0.88), accuracy of 0.83 (95 % CI: 0.78–0.88), sensitivity of 0.80 (95 % CI: 0.75–0.84) and specificity of 0.84 (95 % CI: 0.80–0.88). The performance of feature selectors, classifiers, and input features in detecting HCC and related factors was evaluated and it was observed that radiomics features extracted from medical images were adequate for AI to accurately distinguish the condition. HCC based radiomics has favourable predictive performance especially with addition of clinical features that may serve as tool that support clinical decision-making.

Machine Learning Models for Predicting Risky Pregnancies in Early Clinical Interventions

Background: Risky pregnancies present significant challenges in maternal healthcare, often requiring accurate prediction to prevent adverse outcomes. Machine learning (ML) models offer a promising approach for predicting such risks, enabling timely interventions. This study evaluates five machine learning models—Logistic Regression, Decision Tree, K-Nearest Neighbors (KNN), Naive Bayes, and Support Vector Machine (SVM)—for their effectiveness in predicting risky pregnancies using clinical datasets. Methods: The study developed and evaluated five ML models, each implemented using Python’s scikit-learn library. The dataset was split into 75% for training and 25% for testing. Standard classification metrics, including accuracy, precision, recall, and F1-score, were used to assess model performance. Hyperparameter tuning was conducted using grid search and cross-validation to optimize model parameters. The models’ performance was compared to identify the most suitable for clinical applications. Results: The Decision Tree model achieved the highest accuracy (100% on training data, 95.6% on testing data), along with excellent precision, recall, and F1-scores for both classes, making it the most accurate and interpretable model for predicting risky pregnancies. Logistic Regression also performed well, particularly in identifying high-risk cases, with testing accuracy of 82%. KNN and SVM provided moderate accuracy, with KNN achieving 78% testing accuracy and SVM 80%. Naive Bayes, however, performed poorly, achieving only 43.2% accuracy due to its assumption of feature independence, which was not suitable for the dataset. Conclusion: The Decision Tree and Logistic Regression models emerged as the most effective for predicting risky pregnancies, offering high accuracy and interpretability, crucial for clinical decision-making.

DenseNet201Plus: Cost-effective transfer-learning architecture for rapid leaf disease identification with attention mechanisms

Plant leaf diseases are a significant concern in agriculture due to their detrimental impact on crop productivity and food security. Effective disease management depends on the early and accurate detection and diagnosis of these conditions, facilitating timely intervention and mitigation strategies. In this study, we address the pressing need for accurate and efficient methods for detecting leaf diseases by introducing a new architecture called DenseNet201Plus. DenseNet201 was modified by including superior data augmentation and pre-processing techniques, an attention-based transition mechanism, multiple attention modules, and dense blocks. These modifications enhance the robustness and accuracy of the proposed DenseNet201Plus model in diagnosing diseases related to plant leaves. The proposed architecture was trained using two distinct datasets: Banana Leaf Disease and Black Gram Leaf Disease. Through extensive experimentation, we evaluated the performance of DenseNet201Plus in terms of various classification metrics and achieved values of 0.9012, 0.9012, 0.9012, and 0.9716 for accuracy, precision, recall, and AUC for the banana leaf disease dataset, respectively. Similarly, the black gram leaf disease dataset model provides values of 0.9950, 0.9950, 0.9950, and 1.0 for accuracy, precision, recall, and AUC. Compared to other well-known pre-trained convolutional neural network (CNN) architectures, our proposed model demonstrates superior performance in both utilized datasets. Last but not least, we combined the strength of Grad-CAM++ with our proposed model to enhance the interpretability and localization of disease areas, providing valuable insights for agricultural practitioners and researchers to make informed decisions and optimize disease management strategies.

Image classification based on few-shot learning algorithms: a review

Image classification is a critical task in the field of computer vision, and its importance has significantly increased over the past few years. Machine learning and deep learning techniques have demonstrated immense potential in this field. However, traditional image classification models require a vast amount of training data, which can be challenging and expensive to obtain. To overcome this limitation, researchers are turning to few-shot learning, which aims to classify images with limited training samples. This paper presents a detailed analysis of the field of image classification using few-shot learning. First, it investigates the use of data augmentation, transfer learning, and meta-learning methods in this field. Then, it introduces several commonly used datasets and evaluation metrics in few-shot classification, compares several classical few-shot classification methods, and summarizes the experimental results obtained from public datasets. Finally, this paper analyzes the current challenges in few-shot image classification and suggests potential future directions.

DeepDate: A deep fusion model based on whale optimization and artificial neural network for Arabian date classification.

As agricultural technology continues to develop, the scale of planting and production of date fruit is increasing, which brings higher yields. However, the increasing yields also put a lot of pressure on the classification step afterward. Image recognition based on deep learning algorithms can help to identify and classify the date fruit species, even in natural light. In this paper, a deep fusion model based on whale optimization and an artificial neural network for Arabian date classification is proposed. The dataset used in this study includes five classes of date fruit images (Barhi, Khalas, Meneifi, Naboot Saif, Sullaj). The process of designing each model can be divided into three phases. The first phase is feature extraction. The second phase is feature selection. The third phase is the training and testing phase. Finally, the best-performing model was selected and compared with the currently established models (Alexnet, Squeezenet, Googlenet, Resnet50). The experimental results show that, after trying different combinations of optimization algorithms and classifiers, the highest test accuracy achieved by DeepDate was 95.9%. It takes less time to achieve a balance between classification accuracy and time consumption. In addition, the performance of DeepDate is better than that of many deep transfer learning models such as Alexnet, Squeezenet, Googlenet, VGG-19, NasNet, and Inception-V3. The proposed DeepDate improves the accuracy and efficiency of classifying date fruits and achieves better results in classification metrics such as accuracy and F1. DeepDate provides a promising classification solution for date fruit classification with higher accuracy. To further advance the industry, it is recommended that stakeholders invest in technology transfer programs to bring advanced image recognition and AI tools to smaller producers, enhancing sustainability and productivity across the sector. Collaborations between agricultural technologists and growers could also foster more tailored solutions that address specific regional challenges in date fruit production.

Towards Unsupervised Learning Driven Intelligence for Prediction of Prostate Cancer

Prostate cancer is a widespread and global disease which affects adult males – it is said that key causes of the cancer include age, family history and ethnicity. In this study, the Kaggle prostate cancer dataset, comprising of data of 100 patients with a mixture that both had cancer and did not have cancer, was used alongside machine learning prediction models for the design of unsupervised and automated intelligent systems for the prediction of prostate cancer. Two intelligent systems were designed and underpinned by unsupervised learning algorithms, namely, fuzzy c-means and agglomerative hierarchical clustering, where the various intelligent systems were able to make a prostate cancer prediction with accuracies of over 80% for the various classification metrics, alongside being able to predict an associated stage of the prostate cancer. Both designed intelligent systems offer a complimentary alternative to each other, and their relative merits are discussed in the paper. ry alternative to each other, and their relative merits are discussed in the paper.

Transfer-Learning Approach for Enhanced Brain Tumor Classification in MRI Imaging

Background: Intracranial neoplasm, often referred to as a brain tumor, is an abnormal growth or mass of tissues in the brain. The complexity of the brain and the associated diagnostic delays cause significant stress for patients. This study aims to enhance the efficiency of MRI analysis for brain tumors using deep transfer learning. Methods: We developed and evaluated the performance of five pre-trained deep learning models—ResNet50, Xception, EfficientNetV2-S, ResNet152V2, and VGG16—using a publicly available MRI scan dataset to classify images as glioma, meningioma, pituitary, or no tumor. Various classification metrics were used for evaluation. Results: Our findings indicate that these models can improve the accuracy of MRI analysis for brain tumor classification, with the Xception model achieving the highest performance with a test F1 score of 0.9817, followed by EfficientNetV2-S with a test F1 score of 0.9629. Conclusions: Implementing pre-trained deep learning models can enhance MRI accuracy for detecting brain tumors.

Classification and Severity Level Assessment of Fusarium Wilt Disease in Chickpeas using Convolutional Neural Network

Background: The fusarium wilt disease of chickpea leaves is a common illness that leads to economic problems for farmers due decreased crop yield. Early disease detection and the implementation of suitable precautions can help to increase the yield of chickpeas. This study offers an improved method for Fusarium wilt disease prediction based on severity level using a convolutional neural learning algorithm. Methods: The Convolutional Neural Network (CNN) model is utilized in this work to identify leaf disease due to wilting. The dataset contains 4,339 images of chickpea leaves that were obtained from Kaggle. After preprocessing, the data is sent into the network model for training. The model shows acceptable classification and accuracy metrics. Result: Deep learning methods are very useful tools for tracking leaf diseases at their early stages and can help farmers with the use of controlling methods. The proposed work looks for changes in the shape and color of chickpea leaves in order to predict severe fusarium disease. Training and validation accuracies show a balanced trade-off by giving satisfactory outcomes. The model shows an overall accuracy of 74.79%. The confusion matrix and classification parameters increase the model’s performance.

Prediction of adolescent idiopathic scoliosis with machine learning algorithms using brain volumetric measurements.

It is known that neuroanatomical and neurofunctional changes observed in the brain, brainstem and cerebellum play a role in the etiology of adolescent idiopathic scoliosis (AIS). This study aimed to investigate whether volumetric measurements of brain regions can be used as predictive indicators for AIS through machine learning techniques. Patients with a severe degree of curvature in AIS (n = 32) and healthy individuals (n = 31) were enrolled in the study. Volumetric data from 169 brain regions, acquired from magnetic resonance imaging (MRI) of these individuals, were utilized as predictive factors. A comprehensive analysis was conducted using the twelve most prevalent machine learning algorithms, encompassing thorough parameter adjustments and cross-validation processes. Furthermore, the findings related to variable significance are presented. Among all the algorithms evaluated, the random forest algorithm produced the most favorable results in terms of various classification metrics, including accuracy (0.9083), AUC (0.993), f1-score (0.970), and Brier score (0.1256). Additionally, the most critical variables were identified as the volumetric measurements of the right corticospinal tract, right corpus callosum body, right corpus callosum splenium, right cerebellum, and right pons, respectively. The outcomes of this study indicate that volumetric measurements of specific brain regions can serve as reliable indicators of AIS. In conclusion, the developed model and the significant variables discovered hold promise for predicting scoliosis development, particularly in high-risk individuals.

Development and validation of an electronic health record-based algorithm for identifying TBI in the VA: A VA Million Veteran Program study

ABSTRACT The purpose of this study was to develop and validate an algorithm for identifying Veterans with a history of traumatic brain injury (TBI) in the Veterans Affairs (VA) electronic health record using VA Million Veteran Program (MVP) data. Manual chart review (n = 200) was first used to establish ‘gold standard’ diagnosis labels for TBI (‘Yes TBI’ vs. ‘No TBI’). To develop our algorithm, we used PheCAP, a semi-supervised pipeline that relied on the chart review diagnosis labels to train and create a prediction model for TBI. Cross-validation was used to train and evaluate the proposed algorithm, ‘TBI-PheCAP.’ TBI-PheCAP performance was compared to existing TBI algorithms and phenotyping methods, and the final algorithm was run on all MVP participants (n = 702,740) to assign a predicted probability for TBI and a binary classification status choosing specificity = 90%. The TBI-PheCAP algorithm had an area under the receiver operating characteristic curve of 0.92, sensitivity of 84%, and positive predictive value (PPV) of 98% at specificity = 90%. TBI-PheCAP generally performed better than other classification methods, with equivalent or higher sensitivity and PPV than existing rules-based TBI algorithms and MVP TBI-related survey data. Given its strong classification metrics, the TBI-PheCAP algorithm is recommended for use in future population-based TBI research.

Applications of Lidar Technology in Urban Geophysical Surveys

This research examines the utilization of mobile LiDAR technology for comprehensive urban geophysical surveys, with a specific emphasis on monitoring infrastructure and urban planning. The study challenge focuses on the requirement for precise and detailed geographical data to assist in making informed urban development and management decisions. The approach utilized a transportable LiDAR device with a laser pulse frequency of 200,000 pulses per second at 1,200 meters. Data collection employed precise GPS and IMU for positional and orientation accuracy, respectively. Statistical analysis included noise filtering and classification metrics to evaluate data quality. Results from the study demonstrated the significant capabilities of LiDAR technology: the survey captured over 10.000 points per square meter with a point accuracy of 0.150 meters. Noise filtering processes retained an average of 85% of data points, with ground classification achieving accuracies above 95%. Statistical tools included standard deviation calculations for elevation models, revealing mean elevations ranging from 13.750 to 19.400 meters across surveyed areas. In addition, LiDAR technology could identify structural deformations of up to 0.200 meters in metropolitan buildings. The study highlights the efficacy of LiDAR in offering accurate and extensive geospatial data for urban planning and infrastructure management. This research adds to the current understanding by showing how LiDAR may be used to improve decision-making and increase the ability of cities to withstand and recover from challenges.

Enhancing Water-Deficient Potato Plant Identification: Assessing Realistic Performance of Attention-Based Deep Neural Networks and Hyperspectral Imaging for Agricultural Applications.

Hyperspectral imaging has emerged as a pivotal technology in agricultural research, offering a powerful means to non-invasively monitor stress factors, such as drought, in crops like potato plants. In this context, the integration of attention-based deep learning models presents a promising avenue for enhancing the efficiency of stress detection, by enabling the identification of meaningful spectral channels. This study assesses the performance of deep learning models on two potato plant cultivars exposed to water-deficient conditions. It explores how various sampling strategies and biases impact the classification metrics by using a dual-sensor hyperspectral imaging systems (VNIR -Visible and Near-Infrared and SWIR-Short-Wave Infrared). Moreover, it focuses on pinpointing crucial wavelengths within the concatenated images indicative of water-deficient conditions. The proposed deep learning model yields encouraging results. In the context of binary classification, it achieved an area under the receiver operating characteristic curve (AUC-ROC-Area Under the Receiver Operating Characteristic Curve) of 0.74 (95% CI: 0.70, 0.78) and 0.64 (95% CI: 0.56, 0.69) for the KIS Krka and KIS Savinja varieties, respectively. Moreover, the corresponding F1 scores were 0.67 (95% CI: 0.64, 0.71) and 0.63 (95% CI: 0.56, 0.68). An evaluation of the performance of the datasets with deliberately introduced biases consistently demonstrated superior results in comparison to their non-biased equivalents. Notably, the ROC-AUC values exhibited significant improvements, registering a maximum increase of 10.8% for KIS Krka and 18.9% for KIS Savinja. The wavelengths of greatest significance were observed in the ranges of 475-580 nm, 660-730 nm, 940-970 nm, 1420-1510 nm, 1875-2040 nm, and 2350-2480 nm. These findings suggest that discerning between the two treatments is attainable, despite the absence of prominently manifested symptoms of drought stress in either cultivar through visual observation. The research outcomes carry significant implications for both precision agriculture and potato breeding. In precision agriculture, precise water monitoring enhances resource allocation, irrigation, yield, and loss prevention. Hyperspectral imaging holds potential to expedite drought-tolerant cultivar selection, thereby streamlining breeding for resilient potatoes adaptable to shifting climates.

Intelligent tongue diagnosis model for gastrointestinal diseases based on tongue images

BackgroundCurrently, the diagnosis of gastrointestinal diseases relies heavily on electronic endoscopy, which is not suitable for all individuals and insufficient for dynamic patient monitoring. Therefore, there is an urgent need for a convenient and noninvasive examination method to enhance the diagnosis and monitoring of gastrointestinal diseases. MethodsSince the tongue is a significant reflection of the digestive system and closely associated with gastrointestinal diseases, our study aims to develop a diagnostic framework based on tongue features. We have collected a dataset of 2,167 tongue coating images from 949 consecutive patients, including 905 images from healthy individuals and 1,262 images from patients with various gastrointestinal conditions. Notably, each patient sample may represent distinct gastrointestinal diseases. This study introduces a novel approach to information fusion detection, integrating hand-crafted and auto-encoded features, alongside disease detection employing Squeeze and Excitation (SE) and Slot attention mechanisms. These two branches respectively analyze image feature and spatial position information when utilizing tongue images for diagnosing gastrointestinal diseases. The amalgamation of predictions from both aspects yields the final detection outcome. ResultsFor both healthy and diseased cohorts, the optimal classification metrics were achieved: AUC = 0.886, ACC = 0.849, and TPR = 0.965, indicating satisfactory performance. Notably, our framework demonstrated promising results in detecting five common gastrointestinal diseases: Helicobacter pylori infection, bile reflux, reflux esophagitis, gastric erosion, and duodenal erosion. Ablation experiments underscored the efficacy of mixed features in multi-color space, showcasing an increase in AUC and ACC by 13.48 % and 12.05 % respectively. Furthermore, the attention mechanism, by focusing on the middle region of tongue images, contributed to a 6.12 % increase in AUC and a 6.35 % increase in ACC. ConclusionsIn this study, we successfully develop and validate a diagnosis framework for gastrointestinal diseases based on tongue image features. By utilizing tongue images, we achieve intelligent diagnosis of gastrointestinal diseases, establishing tongue diagnosis as a convenient, cost-effective, and noninvasive method for diagnosing and screening gastrointestinal diseases.

Standardization of body composition parameters between GE Lunar iDXA and Hologic Horizon A and their clinical impact.

Body composition (BC) measured by DXA differs between devices. We aimed to compare regional and total BC measurements assessed by the Hologic Horizon A and the GE Lunar iDXA devices; to determine device-specific calibration equations for each BC parameter; and to assess the impact of this standardization procedure on the assessment of sarcopenia, lipedema, obesity, and cardiovascular risk with DXA. A total of 926 postmenopausal women (aged 72.9 ± 6.9yr, height 160.3 ± 6.6cm, weight 66.1 ± 12.7kg) underwent BC assessment on each device within 1 h, following the ISCD guidelines. The included sample was split into 80% train and 20% test datasets stratified by age, height, and weight. Inter-device differences in BC parameters were assessed with Bland-Altman analysis, Pearson or Spearman correlation coefficients, and t-tests or Wilcoxon tests. The equations were developed in the train dataset using backward stepwise multiple linear regressions and were evaluated in the test dataset with the R-squared and mean absolute error. We compared the abovementioned BC-derived health conditions before and after standardization in the test set with respect to relative risk, accuracy, Kappa score, and McNemar tests. Total and regional body masses were similar (p>.05) between devices. BMC was greater for all regions in the Lunar device (p<.05), while fat and lean masses differed among regions. Regression equations showed high performance metrics in both datasets. The BC assessment from Hologic classified 2.13 times more sarcopenic cases (McNemar: p<.001), 1.39 times more lipedema (p<.001), 0.40 times less high cardiovascular risk (p<.001), and similarly classified obesity (p>.05), compared to Lunar. After standardization, the differences disappeared (p>.05), and the classification metrics improved. This study discusses how hardware and software differences impact BC assessments. The provided standardization equations address these issues and improve the agreement between devices. Future studies and disease definitions should consider these differences.