Alzheimer’s disease (AD) is the most prevalent form of dementia. This disease significantly impacts cognitive functions and daily activities. Early and accurate diagnosis of AD, including the preliminary stage of mild cognitive impairment (MCI), is critical for effective patient care and treatment development. Although advancements in deep learning (DL) and machine learning (ML) models improve diagnostic precision, the lack of large datasets limits further enhancements, necessitating the use of complementary data. Existing convolutional neural networks (CNNs) effectively process visual features but struggle to fuse multimodal data effectively for AD diagnosis. To address these challenges, we propose NeuroNet-AD, a novel multimodal CNN framework designed to enhance AD classifcation accuracy. NeuroNet-AD integrates Magnetic Resonance Imaging (MRI) images with clinical text-based metadata, including psychological test scores, demographic information, and genetic biomarkers. In NeuroNet-AD, we incorporate Convolutional Block Attention Modules (CBAMs) within the ResNet-18 backbone, enabling the model to focus on the most informative spatial and channel-wise features. We introduce an attention computation and multimodal fusion module, named Meta Guided Cross Attention (MGCA), which facilitates effective cross-modal alignment between images and meta-features through a multi-head attention mechanism. Additionally, we employ an ensemble-based feature selection strategy to identify the most discriminative features from the textual data, improving model generalization and performance. We evaluate NeuroNet-AD on the Alzheimer’s Disease Neuroimaging Initiative (ADNI1) dataset using subject-level 5-fold cross-validation and a held-out test set to ensure robustness. NeuroNet-AD achieved 98.68% accuracy in multiclass classification of normal control (NC), MCI, and AD and 99.13% accuracy in the binary setting (NC vs. AD) on the ADNI dataset, outperforming state-of-the-art models. External validation on the OASIS-3 dataset further confirmed the model’s generalization ability, achieving 94.10% accuracy in the multiclass setting and 98.67% accuracy in the binary setting, despite variations in demographics and acquisition protocols. Further extensive evaluation studies demonstrate the effectiveness of each component of NeuroNet-AD in improving the performance.

Fault and defect detection are critical for ensuring the safety, reliability, and quality of products and infrastructure across various industries. As traditional manual inspection methods face limitations in efficiency and accuracy, advancements in artificial intelligence, particularly image segmentation, have paved the way for automated and precise fault detection processes. A significant gap exists in current research regarding the integration and comparative analysis of classical and modern segmentation approaches across diverse application domains. This study addresses this gap by providing a systematic review that bridges traditional segmentation techniques with cutting-edge deep learning methodologies. Unlike previous reviews that focus solely on isolated techniques or specific domains, this paper offers a holistic analysis of methodological innovations, application breadth, and emerging trends. Emphasis is placed on the integration of deep learning models, hybrid approaches, and advancements like attention mechanisms and lightweight architectures. Additionally, the review highlights critical challenges and proposes future research directions aimed at enhancing model scalability, robustness, and adaptability. This systematic review addresses gaps in the field and provides useful insights for academia and industry, making it a key reference in fault detection using image segmentation.

Precise medical image segmentation is important for automating diagnosis and treatment planning in healthcare. While images present the most significant information for segmenting organs using deep learning models, text reports also provide complementary details that can be leveraged to improve segmentation precision. Performance improvement depends on the proper utilization of text reports and the corresponding images. Most attention modules focus on single-modality computation of spatial, channel, or pixel-level attention. They are ineffective in cross-modal alignment, raising issues in multi-modal scenarios. This study addresses these gaps by presenting a text-assisted vision (TAV) model for medical image segmentation with a novel attention computation module named triguided attention module (TGAM). TGAM computes visual-visual, language-language, and language-visual attention, enabling the model to understand the important features and correlation between images and medical notes. This module helps the model identify the relevant features within images, text annotations, and text annotations to visual interactions. We incorporate an attention gate (AG) that modulates the influence of TGAM, ensuring it does not overflow the encoded features with irrelevant or redundant information, while maintaining their uniqueness. We evaluated the performance of TAV on two popular datasets containing images and corresponding text annotations. We find TAV to be a new state-of-the-art model, as it improves the performance by 2-7% compared to other models. Extensive experiments were performed to demonstrate the effectiveness of each component of the proposed model. The code and datasets are available on Github¹.

Burn injuries present a substantial global public health challenge. The conventional approach, relying on visual inspection to compute total body surface area (TBSA) for assessing burn severity, encounters the inherent limitations of proper estimation. These limitations prompted the development of computer-based applications, particularly machine learning, and deep learning models, to enhance the performance. This paper presents a comprehensive analytical study of eight deep learning techniques designed for assessing burn severity in terms of four characteristics: inflammation, scar, uniformity, and pigmentation, in small datasets of 2-dimensional (2D) images captured using digital (smartphone) camera. The models are Convolutional Neural Network (CNN), attention-based CNN, decision-level fusion (DF) based on CNN models, DF with attention-based CNN models, autoencoder-NN (Neural Network), and hybrid VGG16-Machine Learning (ML) with Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). Each model is validated with eight datasets collected and annotated by our team at the Children’s Hospital of Michigan in two phases to classify the severity of burns in terms of inflammation, scar, uniformity, and pigmentation. The average test accuracy across the eight datasets using CNN, attention-based CNN, DF with CNN models, DF with attention-based CNN models, autoencoder-NN, VGG16-RF, VGG16-SVM, and VGG16-XGBoost are 0.87±0.04, 0.93±0.04, 0.90±0.01, 0.95±0.02, 0.87±0.03, 0.63±0.03, 0.79±0.02, 0.79±0.01, correspondingly. The research also computes and compares the computational complexity of each model in terms of FLoating point Operations Per Second (FLOPS) and Multiply-ACcumulate operations (MACs). Compared with the base CNN model, the decision-level fusion with attention mechanism model outperforms with a gain of 9.19% in test accuracy and an increase of 3321.53% in FLOPS. Considering the priority and constraint of the task, the attention-based CNN model can also be preferable as it achieves an accuracy gain of 6.90% and significantly less computational increase expense (8.62%) compared with the base CNN. The code for the best performing decision-level fusion with attention mechanism model is provided on GitHub ^a .

Accurate, reliable, and on-time diagnosis, treatment, and follow-up are crucial for effective burn wound management. Currently, the burn injury classification is performed by visual inspection by experienced clinicians and is based on a wound's size and depth. However, clinical inspection presents many shortcomings, including inter-rater variability and poor prognostic accuracy. An automated burn assessment framework could address these challenges and therefore improve burn wound outcomes. This research proposes a convolution neural network (CNN) based deep learning model to assess burn wound. In so doing, the proposed model detects the degree of inflammation of the burn wounds undergoing skin grafting treatment. The dataset used to validate the model was prepared from the 2-D images collected from the Children's Hospital of Michigan/Wayne State University, USA. Experienced burn providers performed the labeling. Based on the ground truth of the labels, the model's accuracy on the test dataset is found to be 0.8750.

Microbial communities within human tissues are increasingly recognized as promising biomarkers for cancer detection. However, leveraging microbiome data for multiclass cancer classification remains challenging due to its compositional structure, high dimensionality, and lack of model interpretability. In this study, we address these challenges by introducing MicroAIbiome, a machine learning-based artificial intelligence (AI) pipeline designed to classify five cancer types such as esophageal carcinoma (ESCA), head and neck squamous cell carcinoma (HNSC), stomach adenocarcinoma (STAD), colon adenocarcinoma (COAD), and rectum adenocarcinoma (READ), using genus-level microbial relative abundances. Our pipeline incorporates zero-replacement, centered log-ratio (CLR) transformation, correlation filtering, and recursive feature elimination (RFE) to enable robust learning from compositional data. Among five evaluated classifiers, XGBoost achieved the highest accuracy of 78.23%, outperforming prior work. We further enhance interpretability using SHapley Additive exPlanations (SHAP)-based feature attribution to uncover class-specific microbial signatures, such as Corynebacterium in ESCA and Bacteroides in COAD. Our results highlight the importance of compositional preprocessing and explainable AI in advancing microbiome-based cancer diagnostics.