Search Results (17)

Detecting Escherichia coli on food preparation and processing surfaces is critical for ensuring food safety and preventing foodborne illness. This study focuses on detecting E. coli contamination on common food processing surfaces using UV-C fluorescence imaging and deep learning. Four concentrations of E. coli (0, 10⁵, 10⁷, and 10⁸ colony forming units (CFU)/mL) and two egg solutions (white and yolk) were applied to stainless steel and white rubber to simulate realistic contamination with organic interference. For each concentration level, 256 droplets were inoculated in 16 groups, and fluorescence videos were captured. Droplet regions were extracted from the video frames, subdivided into quadrants, and augmented to generate a robust dataset, ensuring 3–4 droplets per sample. Wavelet-based denoising further improved image quality, with Haar wavelets producing the highest Peak Signal-to-Noise Ratio (PSNR) values, up to 51.0 dB on white rubber and 48.2 dB on stainless steel. Using this dataset, multiple deep learning (DL) models, including ConvNeXtBase, EfficientNetV2L, and five YOLO11-cls variants, were trained to classify E. coli concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize model attention to bacterial fluorescence regions. Across four dataset groupings, YOLO11-cls models achieved consistently high performance, with peak test accuracies of 100% on white rubber and 99.60% on stainless steel, even in the presence of egg substances. YOLO11s-cls provided the best balance of accuracy (up to 98.88%) and inference speed (4–5 ms) whilst having a compact size (11 MB), outperforming larger models such as EfficientNetV2L. Classical machine learning models lagged significantly behind, with Random Forest reaching 89.65% accuracy and SVM only 67.62%. Overall, the results highlight the potential of combining UV-C fluorescence imaging with deep learning for rapid and reliable detection of E. coli on stainless steel and rubber conveyor belt surfaces. Additionally, this approach could support the design of effective interventions to remove E. coli from food processing environments. Full article

Explainability features are intended to provide insight into the internal mechanisms of an Artificial Intelligence (AI) device, but there is a lack of evaluation techniques for assessing the quality of provided explanations. We propose a framework to assess and report explainable AI features in medical images. Our evaluation framework for AI explainability is based on four criteria that relate to the particular needs in AI-enabled medical devices: (1) Consistency quantifies the variability of explanations to similar inputs; (2) plausibility estimates how close the explanation is to the ground truth; (3) fidelity assesses the alignment between the explanation and the model internal mechanisms; and (4) usefulness evaluates the impact on task performance of the explanation. Finally, we developed a scorecard for AI explainability methods in medical imaging that serves as a complete description and evaluation to accompany this type of device. We describe these four criteria and give examples on how they can be evaluated. As a case study, we use Ablation CAM and Eigen CAM to illustrate the evaluation of explanation heatmaps on the detection of breast lesions on synthetic mammographies. The first three criteria are evaluated for task-relevant scenarios. This framework establishes criteria through which the quality of explanations provided by medical devices can be quantified. Full article

Background: Diagnostic errors can be substantially diminished, and clinical decision-making can be significantly enhanced through automated image classification. Methods: We implemented a YOLO (You Only Look Once)-based system to classify diabetic retinopathy (DR) utilizing a unique retinal dataset. Although YOLO provides exceptional accuracy and rapidity in object recognition and categorization, its interpretability is constrained. Both binary and multi-class classification methods (graded severity levels) were employed. The Contrast-Limited Adaptive Histogram Equalization (CLAHE) model was utilized to improve image brightness and detailed readability. To improve interpretability, we utilized Eigen Class Activation Mapping (Eigen-CAM) to display areas affecting classification predictions. Results: Our model exhibited robust and consistent performance on the datasets for binary and 5-class tasks. The YOLO 11l model obtained a binary classification accuracy of 97.02% and an Area Under Curve (AUC) score of 0.98. The YOLO 8x model showed superior performance in 5-class classification, with an accuracy of 80.12% and an AUC score of 0.88. A simple interface was created using Gradio to enable real-time interaction. Conclusions: The suggested technique integrates robust prediction accuracy with visual interpretability, rendering it a potential instrument for DR screening in clinical environments. Full article

Accurate identification of wild edible macrofungi is essential for biodiversity conservation, food safety, and ecological sustainability, yet remains challenging due to the morphological similarity between edible and toxic species. In this study, a curated dataset of 24 wild edible macrofungi species was analyzed using six state-of-the-art convolutional neural networks (CNNs) and four ensemble configurations, benchmarked across eight evaluation metrics. Among individual models, EfficientNetB0 achieved the highest performance (95.55% accuracy), whereas MobileNetV3-L underperformed (90.55%). Pairwise ensembles yielded inconsistent improvements, highlighting the importance of architectural complementarity. Notably, the proposed Combination Model, integrating EfficientNetB0, ResNet50, and RegNetY through a hierarchical voting strategy, achieved the best results with 97.36% accuracy, 0.9996 AUC, and 0.9725 MCC, surpassing all other models. To enhance interpretability, explainable AI (XAI) methods Grad-CAM, Eigen-CAM, and LIME were employed, consistently revealing biologically meaningful regions and transforming the framework into a transparent decision-support tool. These findings establish a robust and scalable paradigm for fine-grained fungal classification, demonstrating that carefully engineered ensemble learning combined with XAI not only advances mycological research but also paves the way for broader applications in plant recognition, spore analysis, and large-scale vegetation monitoring from satellite imagery. Full article

Colorectal cancer (CRC) is one of the most common causes of cancer-related deaths globally, making a timely and reliable diagnosis essential. Manual histopathology assessment, though clinically standard, is prone to observer variability, while existing computational approaches often trade accuracy for interpretability, limiting their clinical utility. This paper introduces a deep learning framework that couples the YOLOv8 architecture for multiclass lesion classification with EigenCAM for transparent model explanations. The pipeline integrates three core stages: (i) acquisition and preprocessing of 5000 hematoxylin-and-eosin-stained slides from the University Medical Center Mannheim, categorized into eight tissue types; (ii) comparative evaluation of five YOLOv8 variants (Nano, Small, Medium, Large, XLarge); and (iii) interpretability through EigenCAM visualizations to highlight discriminative regions driving predictions. Extensive statistical validation (including box plots, empirical cumulative distribution functions, Bland–Altman plots, and pair plots) demonstrated the robustness and reliability of the framework. The YOLOv8 XLarge model achieved 99.38% training accuracy and 96.62% testing accuracy, outperforming recent CNN- and Transformer-based systems (≤95%). This framework establishes a clinically dependable foundation for AI-assisted CRC diagnosis by uniting high precision with visual interpretability. It represents a significant step toward real-world deployment in pathology workflows. Full article

The transmission of Escherichia coli through contaminated fruits and vegetables poses serious public health risks and has led to several national outbreaks in the USA. To enhance food safety, rapid and reliable detection of E. coli on produce is essential. This study evaluated the performance of the CSI-D+ system combined with deep learning for detecting varying concentrations of E. coli on citrus and spinach leaves. Eight levels of E. coli contamination, ranging from 0 to 10⁸ colony-forming units (CFU)/mL, were inoculated onto the leaf surfaces. For each concentration level, 10 droplets were applied to 8 citrus and 12 spinach leaf samples (2 cm in diameter), and fluorescence images were captured. The images were then subdivided into quadrants, and several post-processing operations were applied to generate the final dataset, ensuring that each sample contained at least 2–3 droplets. Using this dataset, multiple deep learning (DL) models, including EfficientNetB7, ConvNeXtBase, and five YOLO11 variants (n, s, m, l, x), were trained to classify E. coli concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize the spatial responses of the models to bacterial presence. All YOLO11 models outperformed EfficientNetB7 and ConvNeXtBase. In particular, YOLO11s-cls was identified as the best-performing model, achieving average validation accuracies of 88.43% (citrus) and 92.03% (spinach), and average test accuracies of 85.93% (citrus) and 92.00% (spinach) at a 0.5 confidence threshold. This model demonstrated an inference speed of 0.011 s per image with a size of 11 MB. These findings indicate that fluorescence-based imaging combined with deep learning for rapid E. coli detection could support timely interventions to prevent contaminated produce from reaching consumers. Full article

Staining-based assays are widely used for cell analysis but are invasive, alter physiology, and prevent longitudinal monitoring. Label-free, morphology-based approaches could enable real-time, non-invasive drug testing, yet detection of subtle and dynamic changes has remained difficult. We developed a deep learning framework for stain-free monitoring of leukemia cell cultures using automated bright-field microscopy in a semi-automated culture system (AICE3, LABMaiTE, Augsburg, Germany). YOLOv8 models were trained on images from K562, HL-60, and Kasumi-1 cells, using an NVIDIA DGX A100 GPU for training and tested on GPU and CPU environments for real-time performance. Comparative benchmarking with RT-DETR and interpretability analyses using Eigen-CAM and radiomics (RedTell) was performed. YOLOv8 achieved high accuracy (mAP@0.5 > 98%, precision/sensitivity > 97%), with reproducibility confirmed on an independent dataset from a second laboratory and an AICE3 setup. The model distinguished between morphologically similar leukemia lines and reliably classified untreated versus differentiated K562 cells (hemin-induced erythroid and PMA-induced megakaryocytic; >95% accuracy). Incorporation of decitabine-treated cells demonstrated applicability to drug testing, revealing treatment-specific and intermediate phenotypes. Longitudinal monitoring captured culture- and time-dependent drift, enabling separation of temporal from drug-induced changes. Radiomics highlighted interpretable features such as size, elongation, and texture, but with lower accuracy than the deep learning approach. To our knowledge, this is the first demonstration that deep learning resolves subtle, drug-induced, and time-dependent morphological changes in unstained leukemia cells in real time. This approach provides a robust, accessible framework for label-free longitudinal drug testing and establishes a foundation for future autonomous, feedback-driven platforms in precision oncology. Ultimately, this approach may also contribute to more precise and adaptive clinical decision-making, advancing the field of personalized medicine. Full article

In the automotive domain, object detection is pivotal for enhancing safety and autonomy through the identification of various objects of interest. However, insights into the influential image pixels in the detection process are often lacking. Recognizing these significant regions within the image not only enriches our qualitative understanding of the model’s functionality but also empowers us to refine and optimize its performance. Employing Explainable Artificial Intelligence (XAI), we present an XAI component in this paper. This component explains the predictions made by a pre-trained object detection model for a given image by generating heatmaps that highlight the most critical regions in the image for the detected objects. Full article

As Android malware grows increasingly sophisticated, traditional detection methods struggle to keep pace, creating an urgent need for robust, interpretable, and real-time solutions to safeguard mobile ecosystems. This study introduces YoloMal-XAI, a novel deep learning framework that transforms Android application files into RGB image representations by mapping DEX (Dalvik Executable), Manifest.xml, and Resources.arsc files to distinct color channels. Evaluated on the CICMalDroid2020 dataset using YOLO11 pretrained classification models, YoloMal-XAI achieves 99.87% accuracy in binary classification and 99.56% in multi-class classification (Adware, Banking, Riskware, SMS, and Benign). Compared to ResNet-50, GoogLeNet, and MobileNetV2, YOLO11 offers competitive accuracy with at least 7× faster training over 100 epochs. Against YOLOv8, YOLO11 achieves comparable or superior accuracy while reducing training time by up to 3.5×. Cross-corpus validation using Drebin and CICAndMal2017 further confirms the model’s generalization capability on previously unseen malware. An ablation study highlights the value of integrating DEX, Manifest, and Resources components, with the full RGB configuration consistently delivering the best performance. Explainable AI (XAI) techniques—Grad-CAM, Grad-CAM++, Eigen-CAM, and HiRes-CAM—are employed to interpret model decisions, revealing the DEX segment as the most influential component. These results establish YoloMal-XAI as a scalable, efficient, and interpretable framework for Android malware detection, with strong potential for future deployment on resource-constrained mobile devices. Full article

Unmanned aerial vehicles are increasingly used in civil Search and Rescue operations due to their rapid deployment and wide-area coverage capabilities. However, detecting missing persons from aerial imagery remains challenging due to small object sizes, cluttered backgrounds, and limited onboard computational resources, especially when managed by civil agencies. In this work, we present a comprehensive methodology for optimizing YOLO-based object detection models for real-time Search and Rescue scenarios. A two-stage transfer learning strategy was employed using VisDrone for general aerial object detection and Heridal for Search and Rescue-specific fine-tuning. We explored various architectural modifications, including enhanced feature fusion (FPN, BiFPN, PB-FPN), additional detection heads (P2), and modules such as CBAM, Transformers, and deconvolution, analyzing their impact on performance and computational efficiency. The best-performing configuration (YOLOv5s-PBfpn-Deconv) achieved a mAP@50 of 0.802 on the Heridal dataset while maintaining real-time inference on embedded hardware (Jetson Nano). Further tests at different flight altitudes and explainability analyses using EigenCAM confirmed the robustness and interpretability of the model in real-world conditions. The proposed solution offers a viable framework for deploying lightweight, interpretable AI systems for UAV-based Search and Rescue operations managed by civil protection authorities. Limitations and future directions include the integration of multimodal sensors and adaptation to broader environmental conditions. Full article

In recent years, most Explainable Artificial Intelligence methods have primarily focused on image classification. Although research on interpretability in image segmentation has been increasing, it remains relatively limited. As an extension of Grad-CAM, several methods have been proposed and applied to image segmentation with the aim of enhancing existing techniques and adapting their properties. However, in this study, we highlight a common issue with gradient-based methods when generating visual explanations—these methods tend to emphasize background information, resulting in significant noise, especially when dealing with image segmentation tasks involving complex or cluttered backgrounds. Inspired by the widely used Eigen-CAM method, this study proposes a novel explainability approach tailored for semantic segmentation. By integrating gradient information and introducing a sign correction strategy, our method enhances spatial localization and reduces background noise, particularly in complex scenes. Through empirical studies, we compare our method with several representative methods, employing multiple evaluation metrics to quantify explainability and validate the advantages of our method. Overall, this study advances explainability methods for convolutional neural networks in semantic segmentation. Our approach not only preserves localized attention but also offers a simpler and more intuitive CAM, which has the potential to play a crucial role in sensitive application scenarios, fostering the development of trustworthy AI models. Full article

Unmanned Aerial Vehicles (UAVs) are increasingly utilized for bridge inspections and play a crucial role in detecting defects. Nevertheless, accurately identifying defects at various scales in complex contexts remains a significant challenge. To address this issue, we propose RDS-YOLO, an advanced algorithm based on YOLOv8n, designed to enhance small-scale defect detection through the integration of shallow, high-resolution features. The introduction of the RFW (Receptive Field Weighting) module dynamically expands the receptive field and balances multi-scale detection accuracy. Additionally, the DSF-Bottneck (Dilated Separable Fusion) module further optimizes feature extraction, emphasizing the representation of small defects against complex backgrounds. The SA-Head (Shuffle Attentio) module, with shared parameters, precisely localizes defect zones while reducing computational costs. Furthermore, the EigenCAM technique improves the interpretability of the model’s output, offering valuable insights for maintenance and monitoring tasks. The experimental results demonstrate that RDS-YOLO outperforms YOLOv8n, achieving a 3.7% increase in average detection precision and a 6.7% improvement in small defect detection accuracy. Full article

Early fire detection is the key to saving lives and limiting property damage. Advanced technology can detect fires in high-risk zones with minimal human presence before they escalate beyond control. This study focuses on providing a more advanced model structure based on the YOLOv8 architecture to enhance early recognition of fire. Although YOLOv8 is excellent at real-time object detection, it can still be better adjusted to the nuances of fire detection. We achieved this advancement by incorporating an additional context-to-flow layer, enabling the YOLOv8 model to more effectively capture both local and global contextual information. The context-to-flow layer enhances the model’s ability to recognize complex patterns like smoke and flames, leading to more effective feature extraction. This extra layer helps the model better detect fires and smoke by improving its ability to focus on fine-grained details and minor variation, which is crucial in challenging environments with low visibility, dynamic fire behavior, and complex backgrounds. Our proposed model achieved a 2.9% greater precision rate, 4.7% more recall rate, and 4% more F1-score in comparison to the YOLOv8 default model. This study discovered that the architecture modification increases information flow and improves fire detection at all fire sizes, from tiny sparks to massive flames. We also included explainable AI strategies to explain the model’s decision-making, thus adding more transparency and improving trust in its predictions. Ultimately, this enhanced system demonstrates remarkable efficacy and accuracy, which allows additional improvements in autonomous fire detection systems. Full article

The increasing complexity of deep learning models can make it difficult to interpret and fit models beyond a purely accuracy-focused evaluation. This is where interpretable and eXplainable Artificial Intelligence (XAI) come into play to facilitate an understanding of the inner workings of models. Consequently, alternatives have emerged, such as class activation mapping (CAM) techniques aimed at identifying regions of importance for an image classification model. However, the behavior of such models can be highly dependent on the type of architecture and the different variants of convolutional neural networks. Accordingly, this paper evaluates three Convolutional Neural Network (CNN) architectures (VGG16, ResNet50, ConvNext-T) against seven CAM models (GradCAM, XGradCAM, HiResCAM, LayerCAM, GradCAM++, GradCAMElementWise, and EigenCAM), indicating that the CAM maps obtained with ConvNext models show less variability among them, i.e., they are less dependent on the selected CAM approach. This study was performed on an image dataset for the classification of coffee leaf rust and evaluated using the RemOve And Debias (ROAD) metric. Full article

Patients suffering from Parkinson’s disease suffer from voice impairment. In this study, we introduce models to classify normal and Parkinson’s patients using their speech. We used an AST (audio spectrogram transformer), a transformer-based speech classification model that has recently outperformed CNN-based models in many fields, and a CNN-based PSLA (pretraining, sampling, labeling, and aggregation), a high-performance model in the existing speech classification field, for the study. This study compares and analyzes the models from both quantitative and qualitative perspectives. First, qualitatively, PSLA outperformed AST by more than 4% in accuracy, and the AUC was also higher, with 94.16% for AST and 97.43% for PSLA. Furthermore, we qualitatively evaluated the ability of the models to capture the acoustic features of Parkinson’s through various CAM (class activation map)-based XAI (eXplainable AI) models such as GradCAM and EigenCAM. Based on PSLA, we found that the model focuses well on the muffled frequency band of Parkinson’s speech, and the heatmap analysis of false positives and false negatives shows that the speech features are also visually represented when the model actually makes incorrect predictions. The contribution of this paper is that we not only found a suitable model for diagnosing Parkinson’s through speech using two different types of models but also validated the predictions of the model in practice. Full article