Search Results (2,021)

Osteonecrosis of the femoral head (ONFH) is a progressive and potentially disabling condition caused by compromised blood supply to the femoral head, leading to bone necrosis and collapse. Early diagnosis is essential to enable joint-preserving interventions and improve patient outcomes. Magnetic resonance imaging (MRI) is currently considered the most sensitive modality for early detection, whereas computed tomography (CT) provides superior assessment of subchondral bone integrity and structural collapse. In recent years, artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL) techniques, has emerged as a promising tool to enhance diagnostic accuracy, automate lesion segmentation, and predict disease progression. This review aims to provide an overview of current AI applications in MRI for ONFH, focusing on early diagnostic, disease staging and classification, volumetric assessment, differential diagnosis and prognostic prediction. A total of 61 articles were initially identified, of which 13 studies (2021–2025) met the inclusion criteria. Results indicate that DL models, particularly convolutional neural networks (CNNs), achieve excellent diagnostic performance, with reported accuracies up to 98.4% and area under the curve (AUC) values reaching 0.98 for early-stage detection. Several models demonstrated performance comparable to or exceeding that of experienced clinicians, particularly in differentiating ONFH from other hip pathologies and in early disease recognition. AI algorithms also showed high accuracy in staging and classification (AUC up to 99.7% in internal validation), as well as in automated segmentation and volumetric assessment (Dice coefficients up to 0.89), enabling objective quantification of necrotic lesions. Furthermore, prognostic models integrating radiomics and ML techniques demonstrated promising results in predicting femoral head collapse (AUC up to 0.85). From a clinical perspective, AI appears to function primarily as a supportive tool, improving diagnostic consistency, efficiency, and reproducibility, and acting as a “second reader” capable of reducing variability among less experienced clinicians. However, significant limitations remain, including dataset heterogeneity, predominance of retrospective and monocentric studies, and limited integration of clinical data. In conclusion, AI-based MRI analysis shows strong potential to enhance the diagnosis, staging, and management of ONFH. Future research should focus on multicenter prospective validation, integration of multimodal clinical data, and development of explainable and generalizable models to facilitate widespread clinical adoption. Full article

Background/Objectives: Brain tumor diagnosis using magnetic resonance imaging (MRI) plays an important role in clinical decision-making and treatment planning. However, manual interpretation of MRI scans is time-consuming and may result in variations among radiologists. This study aims to develop an automated multiclass brain tumor classification framework by integrating deep learning-based feature extraction with the Bitterling Fish Optimization (BFO) algorithm for effective feature selection. Methods: MRI images were first subjected to preprocessing to prepare them for deep learning analysis. Several pretrained convolutional neural network (CNN) architectures, including VGG16, VGG19, InceptionV3, ResNet50, EfficientNet, MobileNet, and ShuffleNet, were employed to extract informative deep features from the MRI images. The extracted features were then optimized using the BFO algorithm, which selected the most relevant features while reducing feature redundancy. The selected features were subsequently used for multiclass brain tumor classification. Model performance was evaluated using sensitivity, specificity, precision, accuracy, F1-score, and area under the curve (AUC). Results: The experimental results demonstrated that BFO-based feature selection improved the classification performance of the evaluated CNN architectures compared with their corresponding models without feature selection. Among the investigated CNN–optimizer combinations, the BFO-ShuffleNet framework achieved the best overall performance, obtaining 98.98% sensitivity, 98.99% specificity, 98.99% precision, 99.00% accuracy, and a 98.99% F1-score. These results indicate that BFO effectively identified the most discriminative features and enhanced the classification capability of the ShuffleNet architecture. Conclusions: The proposed deep learning and BFO-based framework provide an accurate and efficient approach for automated multiclass brain tumor classification from MRI images. The findings demonstrate that combining pretrained CNN models with BFO-based feature selection can reduce feature redundancy and improve diagnostic performance. In particular, BFO-ShuffleNet demonstrated the highest classification performance and shows considerable potential as a computer-aided diagnostic tool to support radiologists in brain tumor assessment and clinical decision-making. Full article

Background/Objectives: We aimed to evaluate the methodological quality, translational limitations, and clinical applicability of current artificial intelligence (AI) applications in periodontology and to propose a framework for validated prediction and decision support. Methods: A structured narrative review based on a targeted, non-systematic literature search was conducted using PubMed and cross-disciplinary sources (January 2015–April 2026). Evidence from primary studies, systematic reviews, and methodological guidance for AI prediction models and clinical decision-support systems was synthesized with a focus on clinical applicability. Results: Current periodontal AI research is dominated by retrospective studies focusing on radiographic phenotyping, where deep learning models demonstrate promising diagnostic performance for detecting and quantifying periodontal bone loss. However, substantial limitations persist, including heterogeneous endpoints, inconsistent reporting, limited external validation, and insufficient calibration assessment. Importantly, there is little evidence that AI-based tools improve clinical decision-making or patient-relevant outcomes. Emerging work on prognostic modeling and multimodal data integration highlights the potential for individualized periodontal risk prediction but remains undervalidated, with limited evidence for clinical implementation. Conclusions: Although AI-based models show promising diagnostic performance, translational progress in periodontology is currently limited by insufficient validation and the lack of evidence for clinical utility. Future research should prioritize clinically actionable prediction models, robust external validation, and prospective evaluation of AI-supported decision-making within real-world periodontal care pathways. Full article

Background and Objectives: Dentofacial deformities require a multidisciplinary surgical–orthodontic protocol (SOP) in which orthodontic preparation, orthognathic surgery, postoperative finishing, and retention are closely coordinated to achieve stable functional and aesthetic outcomes. The increasing adoption of clear aligners, digital workflows, and artificial intelligence (AI) has profoundly modified this therapeutic pathway. This communication examines the role of clear-aligner therapy and AI throughout the contemporary surgical–orthodontic protocol, with particular emphasis on their integration into clinical practice. Discussion: From the surgical perspective, clear aligners provide treatment outcomes comparable to those achieved with conventional fixed appliances while offering greater predictability of treatment duration through digital treatment planning. However, their use requires careful management of specific clinical aspects, including surgical timing, intraoperative anchorage, postoperative dentoalveolar stabilisation, transverse dimension management, and retention, all of which demand close collaboration between the orthodontist and the maxillofacial surgeon. The communication also summarises current AI applications in orthodontics and orthognathic surgery, including automated cephalometric analysis, image segmentation, treatment-decision support, virtual patient construction, clear-aligner setup, soft-tissue prediction, refinement-risk assessment, and remote monitoring. Although AI has significantly improved the efficiency, reproducibility, and standardisation of diagnosis and treatment planning, current evidence supports its use as a clinician-supervised decision-support technology rather than as an autonomous system capable of managing the entire orthodontic–surgical pathway. Conclusions: The integration of clear aligners, digital planning, and AI represents an important step toward a more personalised and efficient workflow, while continued clinical validation and multidisciplinary expertise remain essential for achieving predictable long-term outcomes. Full article

Accurate morphological analysis of blood smears is vital for hematological diagnosis, yet manual examination is labor-intensive and subjective. While deep learning offers automation, its black-box nature and computational demands often hinder clinical trust and deployment. We propose XHIC-Net, an Explainable Hybrid Involution–Convolution Network designed for efficient and transparent cell classification. By integrating spatially adaptive involution operations with convolutional layers within a residual framework, XHIC-Net captures both contextual and fine-grained features efficiently. To enhance interpretability, a Grad-CAM-based explainable AI (XAI) module visualizes the cellular regions driving model predictions. The proposed framework was evaluated on a dataset comprising 12,879 microscopic blood smear images belonging to 12 morphological cell categories. Experimental results demonstrate that XHIC-Net achieves an overall accuracy of 98.88%, precision of 98.89%, recall of 98.87%, F1-score of 0.9887, and Cohen’s Kappa score of 0.9887. It outperformed established models, including DL models such as EfficientNetV2S, MobileNet family, DenseNet family, and VGG16, while using fewer parameters and requiring shorter training times. Furthermore, the XAI maps consistently highlighted biologically relevant structures, validating the model’s decision-making process. XHIC-Net is a strong, effective, and clear research model for automated hematology. With future clinical validation, it has the potential to be modified for point-of-care diagnostics in healthcare settings with limited resources. Full article

Background/Objectives: Adrenocortical carcinoma (ACC) is a rare tumor. Diagnosis relies on combined histopathological criteria that, in a multifactorial scoring system, may suggest malignancy. The recent ADIUVO trial, a multicenter trial randomizing ACC patients between mitotane treatment or surveillance only, demonstrated that patients with localized, low-grade ACC (Ki67 labeling index (LI) ≤ 10%) have a better prognosis than historically anticipated, questioning the routine use of adjuvant mitotane. This post hoc analysis aimed to investigate whether automated, centralized Ki67 LI assessment improves prognostic stratification beyond expert manual assessment in low-risk ACC patients enrolled in the original ADIUVO trial. Methods: Ki67 LI was centrally reassessed in 70 ADIUVO patients by digitizing slides and applying an automated algorithm to manually selected hotspots. Primary endpoints were correlation between methods and the impact of automated scoring on recurrence-free survival (RFS) and overall survival (OS). Results: Automated Ki67 LI assessment was feasible in 47 patients. Manual and automated Ki67 LI values showed good agreement (mean 5.6 ± 3.1% vs. 5.4 ± 5.3%). Automated scoring identified eight patients with KI67 LI > 10%. In this subgroup, RFS and OS did not differ significantly between patients treated with mitotane and those under surveillance. Patients with an automated Ki67 LI > 10% had larger tumors (median 16.0 cm vs. 7.0 cm, p = 0.003). Conclusions: Our findings support the original ADIUVO results and support continued use of manual expert Ki67 LI scoring. This traditional approach remains robust and pragmatic for most clinical settings, especially where automated systems are not readily accessible. Full article

Background/Objectives: Paget’s disease of bone (PDB) and osteoporosis are chronic metabolic bone disorders characterized by disrupted bone remodeling and increased skeletal fragility; however, the underlying mechanism of PDB remains poorly understood. Artificial intelligence (AI) has emerged as a transformative tool in medical imaging, enabling automated feature extraction and improved diagnostic classification of skeletal disorders. This study aimed to investigate whether AI could distinguish subtle variations in bone morphology between PDB and osteoporotic bone. Methods: C57BL/6 mice femurs were scanned by µCT: 16 optineurin-knockout mice with a PDB phenotype (20–26 months), 25 genetically matched wild-type Aging mice (20–26 months), and 15 ovariectomized (OVX) mice with osteoporotic bone phenotype (4.5 months). Two AI algorithms were investigated: a machine learning (ML) model using 22 µCT-derived features trained with a Random Forest (RF) classifier, and a deep learning (DL) model using a 3D convolutional neural network (3D-CNN) trained on raw µCT images. Leave-one-out cross-validation was applied to evaluate model robustness. Results: Significant differences in volumetric, density, and morphological parameters of cortical and trabecular bone were observed between PDB and osteoporosis (p < 0.05). The RF algorithm achieved 90% accuracy in distinguishing PDB from both aging- and OVX-induced osteoporosis and provided feature importance rankings that improved model interpretability. The 3D-CNN achieved classification accuracies of 70% for PDB vs. OVX and 68% for PDB vs. aging, demonstrating the feasibility of an image-based DL approach. Conclusions: AI-based RF and 3D-CNN models demonstrated promising performance in differentiating PDB from osteoporosis using µCT-derived bone features. These findings suggest potential for using AI to assist with analyzing skeletal images in the diagnosis of metabolic bone disorders. Full article

Background: Accurate identification and classification of white blood cell (WBC) subtypes in peripheral blood smears (PBS) is essential for the diagnosis and monitoring of hematological malignancies, including leukemia. Conventional manual microscopy, although clinically established, is labor-intensive and subject to inter- and intra-observer variability. Deep learning-based object detection offers a route to automation, yet most prior studies are limited by small datasets, restricted cell taxonomies, or single-microscope acquisition. This study evaluates a YOLOv11-large (YOLOv11L) detector for simultaneous localization and classification of 13 leukemia-relevant WBC subtypes plus an artifact class (14 classes total), trained on the large-scale, multi-domain, open-source LeukemiaAttri dataset. Methods: From the LeukemiaAttri dataset, 18,664 annotated images (67,347 objects) acquired at 40× and 100× magnification were partitioned by stratified sampling into training (70%), validation (15%), and test (15%) sets. The training set was expanded to 65,785 images through extensive geometric, photometric, and AugMix augmentation. A YOLOv11L model pretrained on MS COCO was fine-tuned for 250 epochs (640 × 640 input) on a single NVIDIA H200 SXM GPU, using an auto-selected optimizer (momentum 0.9; weight decay 5 × 10⁻⁴), automatic mixed precision (AMP), and mosaic augmentation for the first 240 epochs. Results: On an internal held-out test set, the model achieved an mAP50 of 93.9%, mAP50-95 of 77.9%, precision of 94.1%, recall of 88.8%, and an F1 score of 0.913, with similar performance in the validation and test sets. Class-wise average precision (AP) ranged from 89.3% (monocyte) to 98.2% (monoblast), confirming consistent detection across morphologically diverse subtypes. Conclusions: The YOLOv11L detector achieved high performance across all 14 categories on the internal test set, with metrics exceeding those previously reported for subset-specific baselines. These findings support further evaluation of the model as a decision-support tool for peripheral blood smear analysis. External validation is required to determine its clinical utility and generalizability. Full article

Globally, respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD) and pneumonia affect populations significantly, requiring early and accurate diagnosis for effective clinical management. Manual auscultation and expert interpretation are the common shortcomings in conventional diagnostic approaches, as they lead to time-consuming and inconsistent analysis. To address these limitations, an artificial intelligence-driven framework for respiratory disease classification using multi-spectral feature extraction and deep learning architectures is proposed to classify four different respiratory conditions: Asthma, COPD, Pneumonia and Healthy. The dataset is collected from Kaggle’s respiratory sound database and the COUGHVID V3 database, which together contain 322 Asthma signals, 746 COPD signals, 323 Pneumonia signals and 174 Healthy signals. Subsequently, the features are extracted using four different feature extraction techniques—Constant Q Transform (CQT), a Gammatone spectrogram, Mel-Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP)—and these extracted spectral representations are provided as inputs to various deep learning models such as a Deep Convolutional Neural Network (Deep CNN), a Temporal Attention Network (TAN) and an Autoencoder for automated feature learning and disease classification. The proposed framework is evaluated using several performance metrics, and the experimental results clearly indicate that the performance of the proposed classification framework strongly depends on the selection of spectral feature extraction techniques and deep learning models. Among all the evaluated combinations, it is evident that the Autoencoder model integrated with CQT features exhibited the best classification performance, with an accuracy of 98.72%, precision of 98.74%, recall of 98.72%, Matthews correlation coefficient (MCC) of 98.11%, Cohen’s kappa value of 98.10% and the least log loss of 0.025. The proposed artificial intelligence (AI)-enabled respiratory disease classification framework has demonstrated the ability to produce a reliable computer-aided diagnostic system which is suitable for smart healthcare applications and automated pulmonary disease screening. Full article

The diagnosis and clinical management of myelodysplastic neoplasms are increasingly challenged by the disease’s inherent heterogeneity, particularly with respect to the diagnosis of low-grade variants. While standardized flow cytometric protocols traditionally rely on static biomarkers for lineage assignment, these often fail to capture the dynamic biological behavior of the malignant clone. This review synthesizes studies on the integration of functional biomarkers, specifically the nuclear proliferation marker Ki-67 and the anti-apoptotic protein Bcl-2, into the diagnostic and prognostic workflow. By utilizing high-dimensional multiparameter flow cytometry (MFC) and software-based maturation continuum analysis, the survival and growth kinetics of the myeloid, erythroid, and monocytic lineages can be quantified. These findings redefine myelodysplastic syndromes (MDS) as characterized by a significant decrease in cell-cycle progression and an increase in anti-apoptotic activity during early stages of maturation. Recent studies demonstrate that integrating the erythroid Ki-67 proliferation index as a fifth parameter into the conventional Ogata score dramatically improves diagnostic sensitivity for detecting MDS from 66% to 90% while maintaining 100% specificity. In particular, the sensitivity for detecting low-grade MDS improved from 56% to 91%. Additionally, a reduced erythroid Ki-67 index (≤28%) is a powerful independent predictor of transfusion dependence within 1 year. Beyond diagnostics, the introduction of the Bcl-2:Ki-67 ratio provides a superior metric for biological aggressiveness and a potential predictive tool for precision medicine. A high ratio identifies a quiescent, apoptosis-resistant cell population that is likely refractory to standard chemotherapy but is an ideal candidate for targeted Bcl-2 inhibition with Venetoclax. The integration of functional biomarkers bridges the gap between complex mutational landscapes and clinical manifestations. While digital imaging and artificial intelligence (AI) are beginning to automate blast enumeration and maturation analysis, functional kinetics may provide a necessary biological readout for personalized therapy. Full article

Detection of brain tumors through MRI scans is a difficult and crucial process since medical imaging is complex and there are not enough experts to analyze these images in many countries. The timely detection of diseases such as gliomas, meningiomas, and pituitary tumors is critical because delayed detection may have adverse impacts on the patient’s condition and result in incorrect treatment. These difficulties are why automated deep learning models were introduced to help diagnose brain tumors. In this research, we introduce a multi-stage sequential pipeline for brain tumor classification, localization, explainability, and report generation in a radiologist-style structured format based on MRI imaging data, with each stage trained and evaluated independently on its respective dataset. Specifically, an Xception-based classifier was used to classify MRI images into one of four classes, achieving 98.96% accuracy and an F1-score of 0.9876. To enhance interpretability, the Grad-CAM technique was used to visualize image patches the model used during prediction. If the tumor was present, U-Net was used to perform localization, giving a Dice score of 0.7835 and an IoU of 0.6919 with the use of T1-weighted MRI images. Finally, the obtained features were passed as input to a QLoRA fine-tuned language model that generates structured radiology reports, including such components as Technique, Findings, and Impression.The proposed framework was evaluated on a hold-out subset of publicly available T1-weighted MRI data, achieving LLM-as-a-Judge scores of 4.92/5 for accuracy and 4.95/5 for fluency. These results suggest that the proposed approach is promising and provide an initial proof of concept. However, additional validation on independent multi-center datasets and multimodal MRI data is still needed before considering its use in clinical practice. Full article

The modernization of legacy industrial machines is a major challenge in intelligent automation, particularly when critical assets must be upgraded without replacing high-value mechanical and hydraulic infrastructure. This paper presents an industrial case study on the intelligent PLC-based retrofit of an obsolete Neyrpic Digipid speed governor installed in a Kaplan turbine. The proposed solution replaces a closed, vendor-dependent controller with an open Siemens ET 200SP architecture programmed in TIA Portal, integrating existing sensors, hydraulic actuators, redundant speed acquisition, sequential state-machine control, and a digital distributor–runner blade Cam Curve. A key technical contribution is the diagnosis and mitigation of hydraulic hunting in the distributor position loop. The instability was traced to the interaction between integral control action and the intrinsic integrating behavior of the hydraulic actuator, leading to the adoption of a proportional-only position tracking strategy. The system was validated through Factory Acceptance Tests (FATs) and Site Acceptance Tests (SATs), including signal verification, startup, synchronization, load acceptance and emergency load rejection. Quantitative results demonstrate that during initial commissioning of the new PLC-based PI position loop, the LVDT position error reached 41.59% peak-to-peak, with 351.2 servo-valve reversals per minute. Disabling the integral action reduced the peak-to-peak position error to below 1.5% and eliminated steady-state valve reversals under the tested operating conditions. Separately, the historical 0.966 V oscillation detected in the legacy analog-input chain was resolved during the retrofit. During no-load startup, the unit reached 97% of nominal speed in 49.4 s, with a maximum overshoot of 2.3% and a speed tracking standard deviation of 1.1%. The complete operational cycle was successfully validated under real industrial conditions, including a near-nominal load-rejection test (approximately 2.25 MW), during which the measured speed peaked at 126.4% of nominal speed and the shutdown sequence was completed without protection-system malfunction. The results show that open PLC-based retrofits can improve maintainability, diagnostics and operational reliability in safety-critical industrial machines, while establishing a foundation for future SCADA integration and condition-based maintenance. Full article

Gait analysis is increasingly used as a dynamic functional biomarker for computer-aided diagnosis (CADx), although strong internal performance alone does not establish clinical utility. This targeted narrative review examines Parkinson’s disease (PD) and knee osteoarthritis (KOA) as its primary clinical contexts while treating fall risk and other mobility disorders as contextual extensions. A structured literature search and source-verification process covered studies available through 31 July 2026. The review corpus comprised 118 sources spanning clinical evidence, measurement validation, datasets, algorithmic architectures, and methodological guidance. This review critically compares sensing modalities, public and proprietary datasets, feature-based models, CNN/RNN architectures, graph neural networks, Transformers, state-space models, and trust-supporting approaches, including explainable artificial intelligence, automated machine learning, federated learning, and multimodal fusion. Using an explicit coverage rule, a common validation audit was applied to 15 empirical or measurement-validation studies. The audited evidence did not demonstrate mature independent multisite validation for disease-focused gait CADx. Formal probability calibration and quantitative testing of explanation stability were also absent, while publicly available KOA-specific multimodal benchmarks remained scarce. Based on these findings, this review proposes a six-level validation-readiness ladder in which independent external evidence at Level 3 represents the minimum threshold for initiating a supervised clinical pilot. The framework prioritizes subject-level separation, leakage control, calibration, clinically meaningful reference standards, and prospective workflow evaluation. Full article

This paper proposes a novel methodology to help clinicians automatically diagnose spinal stenosis, one of the leading causes of chronic lower back pain (CLBP), from lumbar spine Magnetic Resonance Imaging (MRI) scans. The approach mirrors standard clinical practice, in which spinal canal stenosis is diagnosed by manually inspecting lumbar spine MRI scans. Detection is achieved by segmenting the area between the anterior and posterior vertebral elements (AAP) and then locating the key points within the delineated boundaries. Semantic segmentation and a Fine Gaussian Support Vector Machine (SVM) are used to perform this delineation, achieving pixel accuracies of 94% and 92%, respectively. An anonymized dataset of 101 patients is used, in addition to the radiologist’s report for each patient, to compare the system’s results with the corresponding reports. The minimum and maximum diagnostic accuracies achieved by the developed methodology were 76.5% and 90%, respectively. The results show that the developed methodology can speed up the diagnosis process for patients with chronic lower back pain, thereby saving lives and time and reducing costs. Full article

Early warning has been widely proven to be reliable in lowering the risk of instability for biological processes. However, it is very difficult for the warning systems used currently to achieve satisfactory accuracy, timeliness and universality simultaneously. This study developed a novel early warning system for instability in food waste anaerobic digestion (FWAD) by bioimitating the human disease screening paradigm. It consists of single, comprehensive and microbiological indicators. Findings showed that single-factor early warning systems resembled acute patient diagnosis, having high accuracy but low timeliness and poor universality. Each of the chosen single indicators showed distinct early warning performances and clear preferences for diverse inhibitions concerning the instabilities of high organic load rate, high ammonia, and high fat in FWAD. Then, a new comprehensive indicator was developed using the entropy weights of several indicators. Confirmatory tests revealed that the comprehensive indicator-based early warning system was analogue to the resident sub-health diagnostic regarding superior foresight and good operability but poor targeting. Therefore, an early warning system based on microbial changes was proposed for potential instability in FWAD by bioimitating human periodic physical examination. The sensitive bacteria were identified as norank_o_ norank_c_Dojkabacteria and Rikenellaceae_RC9_gut_group. Enlarged tests showed that the developed system could be used for emergent, indistinct and potential early warnings simultaneously while avoiding the shortcomings of existing systems. More preciously, this study provided a paradigm for developing early warning systems of FWAD, which is also suitable to be applied to the intelligent systems that rely on automated machine learning. Full article