Search Results (1,442)

Deep learning is increasingly integrated into oral rehabilitation workflows, particularly in implant planning, prosthodontic design automation, and peri-implant diagnosis. However, reported performance is heterogeneous and difficult to compare across tasks, modalities, and validation designs. The goal of this study was to critically analyze deep learning architecture families applied to oral rehabilitation and to provide task-driven selection guidance supported by an evidence table reporting dataset characteristics, validation strategy, and performance metrics. A focused narrative review was conducted using transparent, database-specific search criteria (final n = 10 included studies), emphasizing implant planning (cone–beam computed tomography [CBCT]-based segmentation), prosthodontic design (intraoral scan [IOS]/mesh inputs), and peri-implant diagnosis (periapical/panoramic radiographs). Evidence certainty for each clinical task was assessed using GRADE-informed ratings (High/Moderate/Low/Very Low). Extracted variables included clinical task, imaging modality, dataset size, architecture, validation strategy (internal vs. internal + external), split level, ground truth protocol, and performance metrics. A structured computational and hardware feasibility analysis was conducted for each architecture family to support real-world deployment planning. Encoder–decoder networks (U-Net/nnU-Net) dominate CBCT segmentation for implant planning, while detection architectures (Faster R-CNN, YOLO) support implant localization and peri-implant assessment on radiographs. Generative models (3D GANs, transformer-based point-to-mesh networks) enable crown design from three-dimensional scans. Hybrid CNN–Transformer architectures show promise for multimodal CBCT–IOS fusion, though direct evidence from the included studies remains limited to a single study. External validation remains uncommon yet essential given the risk of domain shift. In conclusion, architecture selection should be anchored to task geometry (2D vs. 3D), artifact burden, and required clinical output type. Reporting standards should prioritize dataset transparency, validation rigor, multi-center external testing, and uncertainty-aware outputs. Full article

Patellar maltracking is among the most common causes of anterior knee pain after total knee arthroplasty (TKA), underscoring the need for accurate prevention and treatment. Therefore, the purpose of this narrative review is to provide a comprehensive overview of current evidence on post-TKA tracking, focusing on component alignment, preoperative patient assessment, and revision treatment options. A PubMed database search was performed, leveraging the literature from the last 20 years, and the results were qualitatively synthesized. According to current studies, several precautions should be taken to prevent patellofemoral stress and, consequently, patellar maltracking, such as avoiding internal rotation, valgus alignment, and excessive flexion of the femoral component and internal rotation of the tibial component. Regarding alignment strategies, kinematic alignment appears to offer potential benefits over mechanical alignment in certain functional outcomes and patient satisfaction scores. However, these differences should be interpreted cautiously as they may not always exceed the minimal clinically important difference. Furthermore, recent evidence indicates that quadriceps biomechanics influence TKA outcomes, potentially suggesting that conventional surgical approaches may need to be individualized, though these preliminary findings require prospective validation. Currently, robotic-assisted surgery represents a developmental direction for patient-tailored interventions and offers great promise for better prosthesis customization to the individual patient. Integration of imaging data with dynamic soft-tissue assessment enables more predictable reconstruction of joint kinematics. Regarding surgical treatment, the selection of specific methods requires a prior clinical and radiographic assessment. Indications range from patellar maltracking direction and component malrotation to patient preferences and rehabilitation potential. Ultimately, the future of TKA relies on personalized interventions to prevent complications and improve patient outcomes. This evolution is driven by the shift from mechanical alignment to kinematic alignment, alongside quadriceps tendon assessment and intraoperative robotic-assisted measurement, all aimed at optimizing the accuracy of implant positioning. Full article

Meticulous segmentation of medical images requires obtaining both local and global spatial detailed information. The conventional U-Net model excels at local spatial feature extraction through residual convolutional blocks but struggles to capture global features. To resolve this issue, we propose the vision transformer U-NeT (ViTUNet) model framework, which combines the self-attention mechanism of the vision transformer (ViT) to capture global information while maintaining the extraction of local features via U-NeT. This proposed architecture introduces vision transformers to the existing residual convolution blocks in the U-Net encoder path, thereby capturing both local and global features. The decoder path then rebuilds this information into high-quality segmentation maps with accurately highlighted boundaries/edges. This model is utilized to segment carious lesions in bitewing dental radiographs. These images are pre-processed using augmentation, morphological operations, and segmentation to identify the boundaries/edges of the regions of interest (caries/cavity). The proposed method is evaluated on an augmented dataset containing 3000 image–watershed mask pairs. It was trained on 2400 training images and tested on 600 testing images. The experimental results exemplified significant improvements in segmentation performance, achieving $98.45\%$ validation accuracy, $97.88\%$ validation Dice coefficient, and $95.87\%$ validation intersection over union (IoU) metric scores. These results are superior compared to other conventional and state-of-the-art U-NeT models, thus highlighting the impact of transformer-based hybrid architectures in improving medical image segmentation tasks. Full article

Background and Objectives: The association between spinal and pelvic alignment significantly impacts sagittal balance in adults. This study, that is retrospective, aims to investigate sagittal alignment anatomy of the pelvis and spine in juvenile idiopathic scoliosis (JIS) and adolescent idiopathic scoliosis (AIS) patients. Materials and Methods: We evaluated nine sagittal parameters from lateral radiographs of 100 JIS and AIS patients, including thoracic kyphosis (TKA), lumbar lordosis (LLA), pelvic tilt (PTA), pelvic incidence (PIA), spinosacral (SSA), sacral slope (SSLA), C7 tilt angles (C7-TA), sagittal vertical axis length (SVAL), and odontoid process hip axis angle (OPHAA) using the ImageJ program. Participants were classified based on their coronal curve group. Analysis of variance compared parameters between curve groups, and Pearson coefficients assessed the relationship between all parameters (p < 0.05). Results: Female participants had an average age of 13.4, and male participants had an average age of 13.0. Female participants had an average scoliosis degree of 19.3, while male participants had 15.2. PIA, PTA, SSLA, and SSA values were significantly higher in women participants than in men participants (p < 0.05). Additionally, PIA, PTA, SSLA, SSA, and OPHAA values were significantly lower in participants with a lower scoliosis degree (p < 0.05). We observed a moderately positive association between LLA and TKA, PIA, SSA, and C7-TA. There was also a moderate positive association between spinopelvic alignment parameters and the degree of scoliosis in participants. Conclusions: Easily measured values such as PIA, PTA, SSLA, SSA, and OPHAA may be related to severity of vertebral column deformities in patients, making them valuable for monitoring scoliosis patients. Full article

Background/Objectives: Automated localization of cystic lesions and benign tumors on panoramic radiographs may support lesion recognition in the maxillofacial region. This preliminary feasibility study aimed to develop and evaluate a deep learning model based on Mask R-CNN for the localization of dentigerous cysts (DCs), radicular cysts (RCs), odontogenic keratocysts (OKCs), and ameloblastomas using panoramic radiographs. Methods: A total of 215 panoramic radiographs were retrospectively collected from Taichung Veterans General Hospital (2018–2023). After excluding postoperative, recurrent, or low-quality images, 184 lesions were allocated to the training set and 47 lesions to the testing set. Lesions were annotated based on pathology-confirmed diagnoses. The Mask R-CNN model was trained to localize and classify four lesion types. Model performance was evaluated using precision, sensitivity (recall), and F1 score at an Intersection over Union (IoU) threshold of 0.1. Results: In the testing set (n = 47), 26 lesions were correctly localized, yielding an overall sensitivity of 55.3% and a precision of 83.9%. The corresponding F1 score was 66.7%. Lesion-specific sensitivities were 40.0% for ameloblastomas, 37.5% for OKCs, 36.8% for RCs, and 93.3% for DCs. Conclusions: This study suggests the preliminary feasibility of a deep learning-assisted approach for lesion localization on panoramic radiographs. However, the absence of lesion-free control images and the limited dataset size restrict the generalizability and clinical applicability of the findings. Further validation using larger and more balanced datasets is required. Full article

Background/Objectives: Vision-language models (VLMs) such as GPT (Generative Pre-Trained Transformer) have shown potential for medical image interpretation; however, challenges remain in generating reliable radiological findings in clinical practice, as exemplified by dental pathologies. This study proposes a Self-correction Loop with Structured Output (SLSO) framework as an integrated processing methodology to enhance the accuracy and reliability of AI-generated findings for jaw cysts in dental panoramic radiographs. Methods: Dental panoramic radiographs with jaw cysts were used to implement a 10-step integrated processing framework incorporating image analysis, structured data generation, tooth number extraction, consistency checking, and iterative regeneration. The framework functioned as an external validation mechanism for GPT outputs. Performance was compared against the conventional Chain-of-Thought (CoT) method across seven evaluation items: transparency, internal structure, borders, root resorption, tooth displacement, relationships with other structures, and tooth number. Results: The SLSO framework improved output accuracy for multiple items compared to the CoT method, with the most notable improvements observed in tooth number identification, tooth displacement detection, and root resorption assessment. In successful cases, consistently structured outputs were achieved after up to five regenerations. The framework enforced explicit negative finding descriptions and suppressed hallucinations, although accurate identification of extensive lesions spanning multiple teeth remained limited. Conclusions: This investigation established the feasibility of the proposed integrated processing methodology and provided a foundation for future validation studies with larger, more diverse datasets. Full article

Background/Objectives: This study aimed to develop and evaluate deep learning models for the detection, localization, and classification of impacted maxillary canines, and to compare their performance with cone-beam computed tomography (CBCT) as the reference standard. Methods: This cross-sectional diagnostic accuracy study was conducted at King Abdulaziz University Dental Hospital to develop and validate artificial intelligence (AI) models for detecting and localizing maxillary canine impactions using panoramic and cone-beam computed tomography (CBCT) imaging data. A total of 641 panoramic ra and 158 CBCT scans were collected, of which 158 cases had matched panoramic–CBCT pairs for localization analysis. Images were annotated and validated by expert radiologists and orthodontists, with consensus review ensuring labeling reliability. Data augmentation expanded each panoramic and CBCT category to 500 samples for panoramic and 1000 samples for CBCT, resulting in 1935 panoramic and 5703 CBCT images after preprocessing and normalization. The datasets were divided into (training + validation) (80%) and testing (20%) subsets. MobileNetV2 architectures were used for classification, and whdiographsile, a ResNet-50–based Few-Shot Learning framework, enabled spatial localization of impacted canines. Models were trained using the Adam optimizer with a learning rate of 1 × 10⁻⁴ and evaluated using accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC). Cohen’s kappa and 95% confidence intervals were used to assess agreement between AI predictions and expert annotations. Results: Panoramic classification achieved 94% accuracy, demonstrating the highest performance in normal cases and reduced recall for bilateral impactions. The CBCT classifier achieved 98% accuracy across positional categories. Cross-modality prediction reached 93.5% accuracy, with strong agreement compared to CBCT (Cohen’s kappa = 0.91). Expert review confirmed reliable localization of impacted canines on both imaging modalities. Conclusions: Artificial intelligence applied to panoramic radiographs supports the detection, localization, and characterization of impacted maxillary canines with performance comparable to CBCT. This approach may enable lower-radiation decision support for clinical triage. Full article

Background: Pediatric respiratory infections represent a leading cause of emergency department (ED) visits and hospitalizations. Chest X-rays are frequently used in their diagnostic evaluation, despite guideline recommendations advocating restrictive imaging strategies, particularly in young children with uncomplicated disease. Excessive imaging raises concerns regarding cumulative radiation exposure and inefficient resource utilization. Objectives: To quantify potentially unnecessary chest radiography use in hospitalized pediatric patients with respiratory infections and to identify age-related and diagnostic patterns suitable for targeted imaging optimization interventions. Methods: We conducted a retrospective observational study analyzing pediatric patients presented to the ED of a tertiary county hospital in Romania over a period of 12 months. Data regarding respiratory diagnoses, hospitalization status, patient age, and chest radiography utilization were extracted from electronic medical records. Results: Among more than 26,000 pediatric emergency presentations, 4139 children required hospitalization, of whom 1212 were diagnosed with respiratory infections. A total of 3414 chest radiographs were performed, with the highest imaging burden observed in children aged 0–4 years. Repeated imaging was common in interstitial pneumonia, bronchiolitis, and bronchial hyperreactivity. A strong negative correlation was identified between patient age and imaging frequency (r = −0.70, p < 0.001). Conclusions: Thoracic radiographs are disproportionately used in young children with respiratory infections, particularly in conditions with limited imaging indications. These findings provide an essential baseline for the development of targeted quality improvement interventions aimed at reducing unnecessary pediatric imaging. Full article

Management of unstable upper lumbar fractures with corpectomy and posterior fixation is technically demanding, and conventional workflows may require intraoperative repositioning, increasing operative complexity. Lateral mini-open upper lumbar corpectomy (LMULC) paired with robotic-assisted (RA) posterior percutaneous pedicle screw fixation (PPPSF) can be performed in a single position to facilitate ventral spinal decompression and stabilization in the anatomically constrained upper lumbar spine. In this study, we describe the operative technique and report four illustrative cases of unstable L1 or L2 fractures treated with single-position LMULC, RA-PPPSF, and short-segment fusion. Clinical, radiological, intraoperative variables and postoperative outcomes were evaluated. The mean age was 52.3 ± 17.7 years. The median operation time was 314 min (range 268–361 min); the median estimated blood loss (EBL) was 225 mL (range 100–400 mL). The median preoperative kyphosis was 10.15° (range 8.4–14.6°), the median postoperative kyphosis measured 6.65° (range 1.7–10.8°) and the median correction achieved was 3.5° (range −2.4–12.9°). The median visual analog scale (VAS) pain score reduced from 7 (range 7–9) preoperatively to 4.5 (range 2–6) postoperatively at discharge. At a median follow-up of 12 months (range 6–15 months), all patients had uncomplicated recoveries, demonstrated solid fusion on imaging, and reported favorable MacNab outcomes. Single-position LMULC with RA-PPPSF was technically feasible in this preliminary illustrative series and resulted in favorable clinical and radiographic outcomes. However, further studies in larger cohorts are warranted to help confirm these findings and better define the potential advantages and limitations of this technique. Full article

Background: The Lapidus procedure has become a cornerstone in the surgical management of hallux valgus, especially in cases with associated tarsometatarsal instability. This study investigated and compared the radiographic outcomes of three distinct Lapidus constructs, aiming to provide valuable insights into the optimal fusion configurations for achieving long-term stability improvement and maintaining the intermetatarsal angle (IMA) postoperatively. Methods: In this retrospective study, the objective was to assess and compare the outcomes of three different fusion constructs used in the Lapidus procedure: group 1, transverse screw fixation; group 2, metatarsal cuneiform screw fixation; and group 3, combined transverse and metatarsal cuneiform screw fixation. The study encompassed 32 feet: 11 in group 1, 8 in group 2, and 13 in group 3. The primary focus was to evaluate postoperative stability through radiographic imaging complemented by clinical assessments and an examination of complications. Statistical analyses were used to compare outcomes across the three fixation groups immediately, 3 months, 6 months, and 1 year postoperatively. Results: Radiographic assessments demonstrated successful fusion, and patients reported improvements in pain and function and overall satisfaction with the procedure. Complication rates were within an acceptable range. The IMA in all three groups exhibited a significant reduction postoperatively compared with preoperative measurements. Group 3 demonstrated a notably stronger initial reduction in the IMA compared with groups 1 and 2, and they maintained a statistically significantly more stable IMA value and exhibited a lower recurrence rate compared with the other two groups 1 year postoperatively. Conclusions: These findings endorse the use of Lapidus fusion with these three constructs, particularly with combined transverse and metatarsal cuneiform screw fixation, as a dependable and efficacious surgical approach in addressing hallux valgus with concomitant tarsometatarsal instability. Full article

Additive manufacturing enables the rapid fabrication of radiographic phantoms for X-ray and CT imaging, supporting applications such as patient simulation, dosimetry, imaging protocol optimization, and quality assurance. Polylactic acid (PLA) and acrylonitrile butadiene styrene (ABS) are among the most widely used printing polymers in phantoms; however, their X-ray attenuation properties can vary substantially among manufacturers, product lines within manufacturers, and even between colors of the same product. Cylindrical samples of 34 PLA filaments from 11 manufacturers and 13 ABS filaments from 9 manufacturers were evaluated for X-ray attenuation and energy dependence between 70 and 140 kV using a clinical CT scanner. Measured mass densities ranged from 1.17 to 1.34 g/cm³ for PLA and 1.03–1.11 g/cm³ for ABS. At 120 kV, Hounsfield unit (HU) values spanned 109 to 424 HU for PLA and −34 to 40 HU for ABS. Energy dependence, quantified as the HU at 70 kV minus HU at 140 kV, ranged from −29 to +172 HU for PLA filaments and −52 to −4 HU for ABS filaments. Identical products differing only in color showed HU variations from <2 HU to >90 HU at 120 kV, with no consistent pattern linking specific colors to highest or lowest attenuation. These findings demonstrate that 3D printing materials require individual characterization, as base polymer designation alone does not predict X-ray behavior accurately. The observed variability, however, enables the design of phantoms with tailored attenuation and energy-dependent contrast. Referring only to base polymers when specifying 3D printing materials for radiographic phantoms or suggesting printing materials as radiographic substitutes to mimic a specified tissue or reference material without naming the actual product, including color, is, thus, insufficient. Full article

Background: In children with cerebral palsy, bony acetabular deficiencies are common and may be associated with progressive hip subluxation, abnormal joint loading, and ultimately hip dislocation. Hip reconstruction surgery is typically performed to prevent dislocation, and this includes acetabular reshaping using acetabuloplasty. The location of acetabular deficiency may vary among individuals; however, only radiographs are used for planning and intraoperative correction in many centers. Precise reconstruction and preop planning are necessary for the accurate correction of acetabular coverage. This study compares conventional hip reconstruction with a 3D-guided technique using individual preop 3D planning and 3D-printed guides during surgery to determine which method allows for a more accurate correction. We hypothesize that the patient-specific 3D planning leads to more precise anatomical correction of acetabular coverage compared to conventional freehand osteotomy. Methods: This study was registered in the German Clinical Trial Register (DRKS-ID: DRKS00031356) on 14 July 2023. In a randomized controlled trial, various imaging-based parameters were used to assess the bony anatomy preoperatively and postoperatively. Preoperative and 6-week postoperative computed tomography (CT) scans are part of routine clinical care. Additionally, an immediate postoperative CT scan was performed. One hip was operated on using individualized 3D preoperative planning, while the other hip was corrected using a conventional surgical approach. A standardized subtrochanteric osteotomy was performed for the varisation, derotation, and shortening of the proximal femur. This osteotomy was followed by acetabuloplasty under fluoroscopic control. For the 3D-planned operation, patient-specific cutting and repositioning guides were produced based on preoperative CT imaging. Patients with bilateral cerebral palsy (GMFCS levels I–V), aged 4–18 years, with an open triradiate growth plate and a migration index ≥ 40% in at least one hip were included. In a preliminary retrospective part, this project reproduces the existing three-dimensional acetabular index (3-DAI) and compares it with established radiographic methods to determine the utility and reliability of a reconstructed 3D CT measurement technique. A further component of the retrospective part is the creation of an age-adjusted database of typically developed hips and the development of a 3D head coverage index (3D-HCI) as a new 3D parameter to express acetabular coverage; therefore, it will be used as a secondary parameter and correlated to the 3DAI in the prospective part. Conclusions: Improved precision may have meaningful clinical implications for long-term joint congruency, load distribution, pain, and mobility outcomes. Full article

COVID-19 still poses a global public health challenge, exerting pressure on radiology services. Chest X-ray (CXR) imaging is widely used for respiratory assessment due to its accessibility and cost-effectiveness. However, its interpretation is often challenging because of subtle radiographic features and inter-observer variability. Although recent deep learning (DL) approaches have shown strong performance in automated CXR classification, their black-box nature limits interpretability. This study proposes an explainable deep learning framework for COVID-19 detection from chest X-ray images. The framework incorporates anatomically guided preprocessing, including lung-region isolation, contrast-limited adaptive histogram equalization (CLAHE), bone suppression, and feature enhancement. A novel four-channel input representation was constructed by combining lung-isolated soft-tissue images with frequency-domain opacity maps, vessel enhancement maps, and texture-based features. Classification was performed using a modified Xception-based convolutional neural network, while Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to provide visual explanations and enhance interpretability. The framework was evaluated on the publicly available COVID-19 Radiography Database, achieving an accuracy of 95.3%, an AUC of 0.983, and a Matthews Correlation Coefficient of approximately 0.83. Threshold optimisation improved sensitivity, reducing missed COVID-19 cases while maintaining high overall performance. Explainability analysis showed that model attention was primarily focused on clinically relevant lung regions. Full article

Introduction: Spondyloenchondrodysplasia with immune dysregulation (SPENCDI) is a rare autosomal recessive disorder caused by biallelic variants in the tartrate-resistant acid phosphatase 5 (ACP5) and characterized by variable skeletal, immunological, and neurological manifestations. Because early skeletal abnormalities may be subtle, diagnosis can be challenging in infancy. Materials and methods: We conducted a detailed clinical, immunological, radiological, and molecular evaluation of an infant with early-onset cytopenia, recurrent infections, seizures, and developmental delay. Genomic analysis was performed using whole exome sequencing (WES) and copy number variation sequencing (CNV-seq). In addition, we performed a structured narrative review of published ACP5-related SPENCDI cases to summarize the clinical spectrum and the currently reported use of Janus kinase (JAK) inhibitors. Results: Genomic analysis identified an ACP5 stop-gain variant (c.311G>A; p.Trp104*) with an apparently homozygous signal on WES. Re-evaluation of the copy-number data demonstrated an overlapping heterozygous 19p13.2–p13.13 deletion encompassing ACP5, indicating biallelic ACP5 defects consisting of a sequence variant on one allele and deletion of the other allele. Clinically, the patient showed prominent extra-osseous manifestations, including impaired T- and NK-cell cytotoxicity, before the emergence of definite radiographic skeletal abnormalities. Our literature review showed that skeletal abnormalities were repeatedly documented across published ACP5-related SPENCDI reports, although radiographic changes were often subtle and could be preceded by immune manifestations. Reported use of JAK inhibitors suggests potential benefit for immune dysregulation in selected patients, whereas the neurological response remains uncertain. Conclusions: This study reports a novel ACP5 variant and expands the known phenotypic spectrum of SPENCDI. SPENCDI should be considered in children with unexplained immune dysfunction and developmental delay, and suggestive neuroimaging findings, even when overt skeletal deformities are absent. Early genetic testing and targeted skeletal imaging may facilitate diagnosis. Full article

Background/Objective: Chest radiography (CXR) is routinely used in the evaluation of respiratory disease; however, differentiating COVID-19 from other viral pneumonias on CXR remains challenging due to substantial radiographic overlap. In this study, a deep learning-based CXR classification model using a ResNet-50 architecture was developed to categorize images as normal, COVID-19, or non-COVID viral pneumonia, with emphasis on bias mitigation and external validation. Methods: Model training and internal validation were performed using harmonized publicly available datasets with patient-level stratified five-fold cross-validation, while generalizability was evaluated using an independent real-world institutional dataset from Adan Hospital, Kuwait, which was excluded from all training, validation, and hyperparameter tuning stages. Results: On the public validation dataset (n = 847), the model achieved an overall accuracy of 96.8% with balanced class-wise performance, whereas performance on the independent institutional dataset (n = 320) decreased to 93.7%, consistent with expected domain shift. Calibration analyses demonstrated well-aligned probabilistic estimates on validation data and acceptable calibration on institutional data. Negative predictive values remained high for normal and COVID-19 classes across datasets. Exploratory decision curve analysis demonstrated net benefit patterns for COVID-19 predictions under hypothetical threshold assumptions. Conclusions: These findings indicate that, when developed with explicit bias-mitigation strategies and evaluated using independent institutional data, deep learning-based CXR analysis may provide supportive, non-diagnostic decision signals for radiology triage workflows; however, prospective multicenter validation is required prior to clinical adoption. Full article