Search Results (25)

The growing adoption of deep learning (DL) in early-stage cancer diagnosis has demonstrated remarkable performance across multiple imaging tasks. Yet, the lack of transparency in these models (“black-box” problem) limits their adoption in clinical environments. This study proposes a methodological framework for developing interpretable DL models to support the early histopathological diagnosis of lung cancer, with a focus on adenocarcinoma and squamous cell carcinoma. The approach leverages publicly available datasets (TCGA-LUAD, TCGA-LUSC, LC25000) and employs high-performing architectures such as EfficientNet, along with post hoc explainability techniques including Grad-CAM and SHAP. Data will be pre-processed and sampled using stratified purposeful strategies to ensure diversity and balance across subtypes and stages. Model evaluation will combine standard performance metrics with clinician feedback and the spatial alignment of visual explanations with ground-truth annotations. While implementation remains a future step, this paper proposes a methodological framework designed to guide the development of DL systems that are not only accurate but also interpretable and clinically meaningful. Full article

Electroencephalogram (EEG) analysis is essential for diagnosing neurological disorders but typically requires expert interpretation and significant time. Purpose: This study aims to automate the classification of normal and abnormal EEG recordings to support clinical diagnosis and reduce manual workload. Automating the initial screening of EEGs can help clinicians quickly identify potential neurological abnormalities, enabling timely intervention and guiding further diagnostic and treatment strategies. Methodology: We utilized the Temple University Hospital EEG dataset to develop a DenseNet-based deep learning model. To enable a fair comparison of different EEG representations, we used three input types: signal images, spectrograms, and scalograms. To reduce dimensionality and simplify computation, we focused on two channels: T5 and O1. For interpretability, we applied Local Interpretable Model-agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the EEG regions influencing the model’s predictions. Key Findings: Among the input types, spectrogram-based representations achieved the highest classification accuracy, indicating that time-frequency features are especially effective for this task. The model demonstrated strong performance overall, and the integration of LIME and Grad-CAM provided transparent explanations of its decisions, enhancing interpretability. This approach offers a practical and interpretable solution for automated EEG screening, contributing to more efficient clinical workflows and better understanding of complex neurological conditions. Full article

The growing demand for accurate and efficient Chest X-Ray (CXR) interpretation has prompted the development of AI-driven systems to alleviate radiologist workload and reduce diagnostic variability. This paper introduces the Intelligent Humanized Radiology Analysis System (IHRAS), a modular framework that automates the end-to-end process of CXR analysis and report generation. IHRAS integrates four core components: (i) deep convolutional neural networks for multi-label classification of 14 thoracic conditions; (ii) Grad-CAM for spatial visualization of pathologies; (iii) SAR-Net for anatomical segmentation; and (iv) a large language model (DeepSeek-R1) guided by the CRISPE prompt engineering framework to generate structured diagnostic reports using SNOMED CT terminology. Evaluated on the NIH ChestX-ray dataset, IHRAS demonstrates consistent diagnostic performance across diverse demographic and clinical subgroups, and produces high-fidelity, clinically relevant radiological reports with strong faithfulness, relevancy, and alignment scores. The system offers a transparent and scalable solution to support radiological workflows while highlighting the importance of interpretability and standardization in clinical Artificial Intelligence applications. Full article

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training. Full article

In recent years, heavy metal contamination in agricultural products has become a growing concern in the field of food safety. Copper (Cu) stress in crops not only leads to significant reductions in both yield and quality but also poses potential health risks to humans. This study proposes an efficient and precise non-destructive detection method for Cu stress in oilseed rape, which is based on hyperspectral false-color image construction using principal component analysis (PCA). By comprehensively capturing the spectral representation of oilseed rape plants, both the one-dimensional (1D) spectral sequence and spatial image data were utilized for multi-class classification. The classification performance of models based on 1D spectral sequences was compared from two perspectives: first, between machine learning and deep learning methods (best accuracy: 93.49% vs. 96.69%); and second, between shallow and deep convolutional neural networks (CNNs) (best accuracy: 95.15% vs. 96.69%). For spatial image data, deep residual networks were employed to evaluate the effectiveness of visible-light and false-color images. The RegNet architecture was chosen for its flexible parameterization and proven effectiveness in extracting multi-scale features from hyperspectral false-color images. This flexibility enabled RegNetX-6.4GF to achieve optimal performance on the dataset constructed from three types of false-color images, with the model reaching a Macro-Precision, Macro-Recall, Macro-F₁, and Accuracy of 98.17%, 98.15%, 98.15%, and 98.15%, respectively. Furthermore, Grad-CAM visualizations revealed that latent physiological changes in plants under heavy metal stress guided feature learning within CNNs, and demonstrated the effectiveness of false-color image construction in extracting discriminative features. Overall, the proposed technique can be integrated into portable hyperspectral imaging devices, enabling real-time and non-destructive detection of heavy metal stress in modern agricultural practices. Full article

We introduce a lightweight 1D ConvNeXtV2–based neural network for the robust detection of atrial fibrillation (AFib) and atrial flutter (AFL) from single-lead ECG signals. Trained on multiple public datasets (Icentia11k, CPSC-2018/2021, LTAF, PTB-XL, PCC-2017) and evaluated on MIT-AFDB, MIT-ADB, and NST, our model attained a state-of-the-art F1-score of 0.986 on MIT-AFDB. With only 770 k parameters and 46 MFLOPs per 10 s window, the network remained computationally efficient. Guided Grad-CAM visualizations confirmed attention to clinically relevant P-wave morphology and R–R interval irregularities. This interpretable architecture is, therefore, well-suited for deployment in resource-constrained wearable or bedside monitors. Future work will extend this framework to multi-lead ECGs and a broader spectrum of arrhythmias. Full article

Background: Survival prediction in patients with brain metastases remains a major clinical challenge, where timely and individualized prognostic estimates are critical for guiding treatment strategies and patient counseling. Methods: We propose a novel hybrid deep learning framework that integrates volumetric MRI-derived imaging biomarkers with structured clinical and demographic data to predict overall survival time. Our dataset includes 148 patients from three institutions, featuring expert-annotated segmentations of enhancing tumors, necrosis, and peritumoral edema. Two convolutional neural network backbones—ResNet-50 and EfficientNet-B0—were fused with fully connected layers processing tabular data. Models were trained using mean squared error loss and evaluated through stratified cross-validation and an independent held-out test set. Results: The hybrid model based on EfficientNet-B0 achieved state-of-the-art performance, attaining an R² score of 0.970 and a mean absolute error of 3.05 days on the test set. Permutation feature importance highlighted edema-to-tumor ratio and enhancing tumor volume as the most informative predictors. Grad-CAM visualizations confirmed the model’s attention to anatomically and clinically relevant regions. Performance consistency across validation folds confirmed the framework’s robustness and generalizability. Conclusions: This study demonstrates that multimodal deep learning can deliver accurate, explainable, and clinically actionable survival predictions in brain metastases. The proposed framework offers a promising foundation for integration into real-world oncology workflows to support personalized prognosis and informed therapeutic decision-making. Full article

This study investigates the potential of gradient-weighted class activation mapping (Grad-CAM++) in enhancing land cover and land use (LCLU) classification using deep learning models. A U-Net and an Attention U-Net model were trained on Sentinel-2 imagery to classify 10 LCLU classes in a study area in Northern Ontario, Canada (centered at 49.17° N, 83.03° W). The classes included water, wetland, deciduous forest, mixed forest, coniferous forest, barren, urban/development, agriculture, shrubland, and no data (masked areas). The U-Net model achieved overall accuracy of 70.68%, a mean intersection over union (IoU) of 0.4852, and an F1 score of 0.7150, slightly outperforming the Attention U-Net model. Grad-CAM++ visualizations revealed that both models correctly focused on relevant features for each LCLU class, enhancing the interpretability of deep learning models in remote sensing applications. The findings suggest that integrating Grad-CAM++ with deep learning architectures can improve model transparency and guide future enhancements in LCLU classification tasks. Full article

Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of diseases using medical imaging. The paper introduces a computational model for classifying melanoma skin cancer images using convolutional neural networks (CNNs) and vision transformers (ViT) with the HAM10000 dataset. Both approaches utilize mask-guided techniques, employing a specialized U2-Net segmentation module to generate masks. The CNN-based approach utilizes ResNet50, VGG16, and Xception with transfer learning. The training process is enhanced using a Bayesian hyperparameter tuner. Moreover, this study applies gradient-weighted class activation mapping (Grad-CAM) and Grad-CAM++ to generate heatmaps to explain the classification models. These visual heatmaps elucidate the contribution of each input region to the classification outcome. The CNN-based model approach achieved the highest accuracy at 98.37% in the Xception model with a sensitivity and specificity of 95.92% and 99.01%, respectively. The ViT-based model approach achieved high values for accuracy, sensitivity, and specificity, such as 92.79%, 91.09%, and 93.54%, respectively. Furthermore, the performance of the model was assessed through intersection over union (IOU) and other qualitative evaluations. Finally, we developed the proposed model as a web application that can be used as a support tool for medical practitioners in real-time. The system usability study score of 86.87% is reported, which shows the usefulness of the proposed solution. Full article

This study delves into the heightened efficiency and accuracy of 11 deep learning models classifying 11 dynamograph classes in the oil production sector. Introducing a novel framework with the Grad–CAM method, we address the “black box” issue, providing transparency in the models’ decision-making processes. Our analysis includes a comparative study with human experts, revealing a comprehensive understanding of both machine and human interpretive strategies. Results highlight the notable speed and precision of machine learning models, marking a significant advancement in rapid, reliable dynamograph classification for oil production decision-making. Additionally, nuanced findings in the model’s diagnostic accuracy reveal limitations in situations featuring the simultaneous occurrence of multiple pump issues. This underscores the need for additional features and domain-specific logic to enhance discernment and diagnostic precision in complex scenarios. The exploration of qualitative aspects distinguishes interpretive approaches, highlighting strengths and limitations. Machines, driven by algorithmic patterns and data processing, excel in rapid identification, albeit with occasional misclassifications. In contrast, human experts leverage experience and domain-specific knowledge for nuanced interpretation, providing a comprehensive understanding of both quantitative metrics and qualitative nuances. In conclusion, this study not only demonstrates the accelerated and enhanced accuracy of dynamograph classification by machine learning models compared to junior and medior domain experts, but also provides valuable insights into specific features and patterns guiding the decision-making process. This understanding allows continuous refinement, combining machine speed with human understanding for improved results in oil production. The potential for further studies and improvements in this domain is substantial. Full article

A thyroid nodule, a common abnormal growth within the thyroid gland, is often identified through ultrasound imaging of the neck. These growths may be solid- or fluid-filled, and their treatment is influenced by factors such as size and location. The Thyroid Imaging Reporting and Data System (TI-RADS) is a classification method that categorizes thyroid nodules into risk levels based on features such as size, echogenicity, margin, shape, and calcification. It guides clinicians in deciding whether a biopsy or other further evaluation is needed. Machine learning (ML) can complement TI-RADS classification, thereby improving the detection of malignant tumors. When combined with expert rules (TI-RADS) and explanations, ML models may uncover elements that TI-RADS misses, especially when TI-RADS training data are scarce. In this paper, we present an automated system for classifying thyroid nodules according to TI-RADS and assessing malignancy effectively. We use ResNet-101 and DenseNet-201 models to classify thyroid nodules according to TI-RADS and malignancy. By analyzing the models’ last layer using the Grad-CAM algorithm, we demonstrate that these models can identify risk areas and detect nodule features relevant to the TI-RADS score. By integrating Grad-CAM results with feature probability calculations, we provide a precise heat map, visualizing specific features within the nodule and potentially assisting doctors in their assessments. Our experiments show that the utilization of ResNet-101 and DenseNet-201 models, in conjunction with Grad-CAM visualization analysis, improves TI-RADS classification accuracy by up to 10%. This enhancement, achieved through iterative analysis and re-training, underscores the potential of machine learning in advancing thyroid nodule diagnosis, offering a promising direction for further exploration and clinical application. Full article

At present, multi-disease fundus image classification tasks still have the problems of small data volumes, uneven distributions, and low classification accuracy. In order to solve the problem of large data demand of deep learning models, a multi-disease fundus image classification ensemble model based on gradient-weighted class activation mapping (Grad-CAM) is proposed. The model uses VGG19 and ResNet50 as the classification networks. Grad-CAM is a data augmentation module used to obtain a network convolutional layer output activation map. Both the augmented and the original data are used as the input of the model to achieve the classification goal. The data augmentation module can guide the model to learn the feature differences of lesions in the fundus and enhance the robustness of the classification model. Model fine tuning and transfer learning are used to improve the accuracy of multiple classifiers. The proposed method is based on the RFMiD (Retinal Fundus Multi-Disease Image Dataset) dataset, and an ablation experiment was performed. Compared with other methods, the accuracy, precision, and recall of this model are 97%, 92%, and 81%, respectively. The resulting activation graph shows the areas of interest for model classification, making it easier to understand the classification network. Full article

Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN−) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN−, 130 PN+) was used to train (n = 200), validate (n = 18), and test (n = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141), and pre-diabetes (n = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79–1.0), a specificity of 0.93 (95%CI: 0.83–1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83–0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes. Full article

The process of categorizing sounds into distinct phonetic categories is known as categorical perception (CP). Response times (RTs) provide a measure of perceptual difficulty during labeling decisions (i.e., categorization). The RT is quasi-stochastic in nature due to individuality and variations in perceptual tasks. To identify the source of RT variation in CP, we have built models to decode the brain regions and frequency bands driving fast, medium and slow response decision speeds. In particular, we implemented a parameter optimized convolutional neural network (CNN) to classify listeners’ behavioral RTs from their neural EEG data. We adopted visual interpretation of model response using Guided-GradCAM to identify spatial-spectral correlates of RT. Our framework includes (but is not limited to): (i) a data augmentation technique designed to reduce noise and control the overall variance of EEG dataset; (ii) bandpower topomaps to learn the spatial-spectral representation using CNN; (iii) large-scale Bayesian hyper-parameter optimization to find best performing CNN model; (iv) ANOVA and posthoc analysis on Guided-GradCAM activation values to measure the effect of neural regions and frequency bands on behavioral responses. Using this framework, we observe that $\alpha -\beta$ (10–20 Hz) activity over left frontal, right prefrontal/frontal, and right cerebellar regions are correlated with RT variation. Our results indicate that attention, template matching, temporal prediction of acoustics, motor control, and decision uncertainty are the most probable factors in RT variation. Full article

Neurodegenerative diseases, tauopathies, constitute a serious global health problem. The etiology of these diseases is unclear and an increase in their incidence has been projected in the next 30 years. Therefore, the study of the molecular mechanisms that might stop these neurodegenerative processes is very relevant. Classification of neurodegenerative diseases using Machine and Deep Learning algorithms has been widely studied for medical imaging such as Magnetic Resonance Imaging. However, post-mortem immunofluorescence imaging studies of the brains of patients have not yet been used for this purpose. These studies may represent a valuable tool for monitoring aberrant chemical changes or pathological post-translational modifications of the Tau polypeptide. We propose a Convolutional Neural Network pipeline for the classification of Tau pathology of Alzheimer’s disease and Progressive Supranuclear Palsy by analyzing post-mortem immunofluorescence images with different Tau biomarkers performed with models generated with the architecture ResNet-IFT using Transfer Learning. These models’ outputs were interpreted with interpretability algorithms such as Guided Grad-CAM and Occlusion Analysis. To determine the best classifier, four different architectures were tested. We demonstrated that our design was able to classify diseases with an accuracy of 98.41% on average whilst providing an interpretation concerning the proper classification involving different structural patterns in the immunoreactivity of the Tau protein in NFTs present in the brains of patients with Progressive Supranuclear Palsy and Alzheimer’s disease. Full article