Restorative artificial intelligence-driven implant dentistry for immediate implant placement with an interim crown: A clinical report.

Objective: To establish radiographic baseline measurements of key anatomical parameters of the Filipino pediatric skull base using computed tomography (CT); compare these anatomical parameters across different pediatric age groups and between sexes; and determine the feasibility of nasoseptal flap reconstruction for sellar defects in a Filipino pediatric population by calculating the nasoseptal flap to sellar defect length ratio (NSR). Methods:Design: Review of RecordsSetting: Tertiary Academic Medical CenterParticipants: Digital Imaging and Communications in Medicine (DICOM) images of patients aged 0-17 years who had high-resolution head CT scans done at the University of Santo Tomas Hospital during the period of January 2019 – January 2024 were retrieved and reviewed. The following measurements were obtained: piriform aperture width (PAW), nare to sella distance (NSD), sphenoid to sella distance (SSD), sphenoid pneumatization type (SP), sphenoid sinus width (SW), olfactory fossa depth (OFD), lateral lamella cribriform plate angles (CPA), intercarotid distances (ICD) at the superior clivus (ICD-SC) and cavernous sinus (ICD-CS), potential nasoseptal flap length (NSF), potential sellar defect length (SDL) and nasoseptal flap length to sellar defect length ratio (NSR). Participants were stratified into three age groups (<5years, 5-12 years, 13 years and older), and sex (males, females). Between-group comparisons were performed using ANOVA, chi-square and independent t-tests (α = 0.05). Results: Among the 111 participants (median age 12 years, IQR 7-15), 63.06% were males. For children <5 years (n = 23), mean values were: PAW 1.82 ± 0.15 cm, NSD 5.84 ± 0.37 cm, SSD 1.40 ± 0.35 cm, SW 1.78 ± 0.44 cm, OFD 0.53 ± 0.18 cm, ICD-SC 1.04 ± 0.20 cm, ICD-CS 1.64 ± 0.18 cm, NSF 4.95 ± 0.45 cm, and SDL 4.21 ± 0.64 cm. For ages 5-12 years (n = 39), values were: PAW 2.06 ± 0.23 cm, NSD 6.71 ± 0.50 cm, SSD 1.67 ± 0.24 cm, SW 2.55 ± 0.54 cm, OFD 0.61 ± 0.16 cm, ICD-SC 1.19 ± 0.21 cm, ICD-CS 1.86 ± 0.18 cm, NSF 5.63 ± 0.59 cm, and SDL 4.70 ± 0.85 cm. For ages ≥13 years (n = 49), values were: PAW 2.21 ± 0.26 cm, NSD 7.22 ± 0.63 cm, SSD 1.86 ± 0.33 cm, SW 3.04 ± 0.66 cm, OFD 0.64 ± 0.23 cm, ICD-SC 1.23 ± 0.26 cm, ICD-CS 1.92 ± 0.24 cm, NSF 6.50 ± 0.50 cm, and SDL 5.59 ± 0.90 cm. Most participants had sellar-type sphenoid pneumatization (n = 48, 43.24%) and Type 2 Keros classification (n = 74, 66.67%). Sphenoid pneumatization differed significantly across age groups (p = .001), with conchal type predominant in <5 years (n = 22, 95.65%), presellar in 5-12 years (n = 18, 46.15%), and sellar in ≥13 years (n = 38, 77.55%). The mean nasoseptal flap to sellar defect ratio (NSR) was 1.21 ± 0.22 overall and did not differ across age groups (p = .677), indicating adequate flap length for reconstruction across all ages. Conclusion: In this sample, Filipino pediatric skull base anatomy demonstrates significant age-related dimensional changes but no sex-dependent differences. Despite smaller absolute dimensions in younger children, nasoseptal flap reconstruction appears radiographically feasible across all pediatric age groups. Our findings provide population-specific normative data to guide preoperative planning for pediatric endoscopic endonasal skull base surgery.

Background/Objectives: We aim to evaluate whether digital imaging and communications in medicine (DICOM)-level deep learning-based iodine-boosting applied to dual-source dual-energy computed tomography (DECT) source DICOM improves image quality in low-iodine-dose abdominal DECT in adults undergoing post-procedure follow-up computed tomography (CT). Methods: This retrospective study included 43 adults (April-September 2025) who underwent dynamic dual-source DECT using a low-iodine protocol. Three CT reconstructions were compared: mixed images, conventional 50-keV virtual monoenergetic images (VMIs), and 50-keV VMIs generated after applying DICOM-based deep learning iodine-boosting/denoising to the tube-specific dual-energy source DICOM series prior to VMI/iodine-map reconstruction (deep learning-based reconstruction [DLR]-VMI). Iodine material density (IMD) images were compared between the conventional and DLR-processed datasets. Quantitative attenuation and signal-to-noise ratio (SNR) were assessed using paired and repeated-measures tests. Image quality was scored by two readers using a five-point Likert scale. Results: Attenuation varied across CT reconstructions for all regions of interest in both phases (all overall p < 0.001). Liver attenuation increased from 94.9 ± 22.0 Hounsfield units (HU) (VMI) to 114.5 ± 34.6 HU (DLR-VMI) during the arterial phase and from 127.6 ± 25.6 HU to 166.6 ± 39.9 HU during the portal venous phase (both p < 0.001). Liver SNR improved with DLR-VMI compared to VMI (arterial: 9.11 ± 3.62 vs. 6.06 ± 1.90; portal: 12.74 ± 3.56 vs. 7.90 ± 1.82; both p < 0.001). On IMD images, DLR increased HU-equivalent values and liver SNR (arterial: 5.20 ± 2.89 vs. 2.61 ± 1.39; portal: 9.22 ± 2.81 vs. 4.48 ± 1.28; both p < 0.001). Qualitatively, DLR-VMI yielded the highest overall image-quality scores for both reviewers in both phases (Reviewer 1, arterial/portal: 4 (4-5)/5 (4-5); Reviewer 2, arterial/portal: 4 (3-4)/4 (4-4)). DLR also improved the overall image quality of IMD images for both reviewers (all p < 0.001). Conclusions: Raw DICOM-level iodine-boosting DLR applied to dual-source DECT-source DICOM enabled enhanced image quality and improved quantitative and qualitative metrics in low-iodine-dose abdominal DECT.

Phantom Calibration's Impact on Measuring Radiodensity Changes: Implications for Evaluating Osteosarcoma Response.

The evolving role of DICOM in digital pathology.

BackgroundFibromyalgia (FM) is a disorder characterized by chronic widespread pain and fatigue, making diagnosis challenging. Early diagnosis is essential for improving the quality of life of FM.ObjectiveThis study aimed to evaluate whether FM can be diagnosed using magnetic resonance imaging (MRI) and to determine whether lumbar paraspinal muscle volume (LPMV) reduces susceptibility to FM by providing spinal balance, based on the hypothesis that alterations in paraspinal muscle structure and lumbar sagittal alignment may reflect neuromuscular adaptations secondary to central sensitization.MethodsThis retrospective cross-sectional study was conducted between July 2020 and March 2024. Thirty-one patients with FM and 32 healthy controls underwent MRI. The parameters evaluated included the intervertebral disc angle (IDA), lumbar lordosis angle (LLA), sacral tilt (ST), lumbosacral angle (LSA), and LPMV. The IDA was measured between the superior and inferior endplates of adjacent vertebrae in the sagittal plane, whereas the LPMV was quantified using Digital Imaging and Communications in Medicine (DICOM) software.ResultsAge (OR = 1.12, p = 0.010) and IDA-4 score(OR = 1.467, p = 0.004) were independent risk factors for FM. LPMV, IDA-1, and IDA-4 values were significantly higher in FM (p < 0.05).ConclusionMRI-assessed spinal angles and LPMVs were associated with FM; however, these findings should not be interpreted as diagnostic or predictive markers. Higher paraspinal muscle volume, increased IDA-4 values, and older age were associated with FM. Given the limited sample size and potential confounders, the results should be interpreted cautiously.

Optimizing radiation dose while maintaining image quality remains a key challenge in computed tomography (CT). This study used a thorax-specific anthropomorphic phantom to assess patient dose, image quality, and artefact presence under automated tube current modulation settings and to evaluate the effect of tube voltage on Hounsfield Unit (HU) response for different iodine concentrations. Dose metrics, noise levels, and image quality indicators were extracted from Digital Imaging and Communications in Medicine (DICOM) metadata and image analysis. The study examined how patient positioning affects modulation performance and how tube voltage influences HU values in iodinated inserts. Results revealed inconsistencies in dose modulation across CT systems and highlighted the importance of synchronized protocols. A methodology was proposed to harmonize scanning protocols, ensuring consistent image quality and improved patient safety. These findings demonstrate the value of anthropomorphic phantoms in validating and optimizing CT protocols across clinical environments.

Pathologic fractures due to metastatic disease are important predictors of worse survival1,2 and are associated with diminished quality of life and increased pain and disability. Pathologic fracture, as an initial symptom of metastatic bone disease, is observed in 10% to 15% of patients with cancer1 and signals a more advanced stage of disease. The number of patients who develop a long-bone metastasis and present with an “impending pathologic fracture” is a much smaller but important subgroup. Among these patients, 10% to 25% meet the criteria for prophylactic internal fixation due to “perceived risk” based on a model that relies on radiographic interpretation3. This is notable because patients who undergo internal fixation for impending versus completed pathologic fractures of the long bones have improved outcomes and better quality of life4. Detecting the presence of a pathologic fracture is, at times, challenging, and a valid artificial intelligence (AI)-based method to assist in the diagnosis of a pathologic fracture is clinically useful. In their study, Kim et al. asked the question: can AI accurately predict the presence of a neoplastic pathologic fracture versus nonpathologic fracture on hip radiographs with accuracy that is comparable with that of experienced observers? The answer was yes, and if they could package and franchise this AI methodology, the ability to predict that a fracture is a neoplastic fracture could be standardized and improved. Early identification of impending pathologic fractures is also important, and proper and timely intervention matters. Yet, no universally accepted definition of an impending fracture currently exists. Clinicians frequently use the Mirels score5, although this tool is limited by the observers’ experience in interpreting radiographs, which can vary across specialties and clinical settings. Even with expert radiographic interpretation, the classification of impending pathologic fractures tends to overestimate fracture risk, leading to unnecessary surgical intervention. The importance of choosing the appropriate time to intervene is not trivial because potential complications from operative intervention in this medically compromised group of patients include infection, hardware failure, nonunion or delayed healing, hemorrhage, thrombotic events, sepsis, the need for reoperation, disease progression, and persistent pain and limited function6. Going forward, the formidable challenge is how 2 technologies, one emerging and the other, old and established, can be combined to produce a more meaningful estimation of fracture risk. Having a tool that is available to all clinicians, especially those with limited experience, is valuable. Could the synergy of AI technology and radiographs advance patient care beyond matching experienced observers to also improve our ability to predict fracture risk? A comprehensive risk-assessment tool ideally should incorporate a variety of factors, including, but not limited to, age, sex, body mass index, bone mineral density, history of radiation or chemotherapy, activity level, and bone involved, in addition to standardized and enhanced radiographic criteria. While AI can learn and improve its risk-assessment capabilities, validating its predictions is a substantial hurdle. A potential solution could involve a large-scale database(s) containing clinical and radiographic data from all patients with long-bone metastatic disease. AI could then analyze both clinical and radiographic data to identify factors associated with pathologic fractures, helping us to better predict fracture risk. Another major challenge to this risk-assessment tool is the lack of standardized radiographic data. One solution is to leverage a standardized, commercial web-based system that converts radiographs into a consistent DICOM (Digital Imaging and Communications in Medicine) format for AI analysis, thereby eliminating variability in image quality. A more advanced tool would combine an AI-generated risk profile that analyzes clinical, historical, and radiographic parameters to produce a single validated and reproducible risk score. The authors should be commended for advancing our understanding of pathologic fracture risk through the application of AI. Their findings demonstrate that an AI platform can perform comparably to experienced clinicians in predicting the presence of a pathologic fracture. This raises the possibility of expanding the use of AI in conjunction with radiographic assessment to further refine risk stratification, improve clinical outcomes, and enhance quality of life for patients with metastatic bone disease.

The huge rise in the number of medical images has caused a major problem in radiology departments. Radiologists are now working harder than ever, which affects the quality of their diagnoses and patient care. It takes 15 to 30 minutes to write a manual radiological report for each case, and different people may see things differently. Modern departments process over 230 cases a week, which causes long delays in diagnosis. Automated report generation systems that are already in use have a lot of problems, such as not being able to be interpreted clinically, not having enough Digital Imaging and Communications in Medicine (DICOM) integration, and not having the right deployment architectures. This makes it hard for medical artificial intelligence to be widely used in clinical settings. This work shows a new automated web-based system for making radiologist reports from chest X-ray pictures using cutting-edge deep learning methods. We suggest using a CheXNet-based convolutional neural network (CNN) with attention mechanisms and Gated Recurrent Units (GRU) to make diagnostic summaries that are useful in a clinical setting. The system is fully compatible with DICOM and uses Streamlit, Docker, and AWS cloud services to make clinical workflows operate together smoothly. The Indiana University Chest X-ray dataset, which has 7,491 pictures and 3,955 reports, was used for training and testing. The system did much better than the best methods available, with BLEU-1, BLEU-2, BLEU-3, and BLEU-4 scores of 0.685, 0.595, 0.533, and 0.482, respectively, as well as a METEOR score of 0.392 and a ROUGE-L score of 0.718.The deployed web application provides real-time report generation with attention heatmap visualisations enabling clinicians to understand model decision-making processes. This interpretability feature addresses critical trust barriers in clinical AI adoption whilst supporting radiologists with diagnostic assistance for routine chest imaging cases.

Patient-specific lattice implants (PSLIs) and modular porous scaffolds have emerged as promising solutions for treating diaphyseal segmental defects of the femur and tibia, particularly where conventional reconstruction methods fall short. This second part of our two-part review focuses on how current studies transform computed tomography (CT) and μCT datasets into architected lattice implants, as well as how these constructs are fabricated and numerically, mechanically, biologically, and clinically verified. We outline imaging pipelines, including Digital Imaging and Communications in Medicine (DICOM) acquisition, segmentation, contralateral mirroring, and Hounsfield Units (HU)-density-elasticity mapping, and show how these choices impact finite element (FE) models and print-ready geometries. Next, lattice design strategies and mixed-material concepts are compared and linked to specific additive manufacturing routes in metals, polymers, and bioceramics, such as laser powder bed fusion (LPBF), electron beam melting (EBM), fused deposition modeling (FDM), material jetting, and extrusion-based bioprinting. Methodological overviews of linear-elastic models and homogenized finite element (FE) models, along with bench-top mechanical tests, in vitro cell assays, in vivo animal studies, and early clinical series, are utilized to categorize the studies into four pathways: simulation (S), mechanical (E_mech), biological (E_bio), and validation (V). Based on the reviewed literature, we establish a general workflow for CT implants. We identify common gaps in the process, observe insufficient reporting of imaging and modeling details, note a lack of data on fatigue and remodeling, and recognize the limited size of clinical cohorts. Additionally, we provide practical recommendations for developing more standardized and scalable planning pipelines. Part 1 of this two-part review studied defect patterns, anatomical location, and fixation strategies for patient-specific lattice implants used in femoral and tibial segmental reconstruction, with emphasis on how defect morphology and subregional anatomy influence construct selection and mechanical behavior. It established a defect- and fixation-centered review that provides the clinical and anatomical context for the workflow and validation analysis presented in Part 2.

Quantum computing threatens the long-term security of widely deployed public-key cryptography used to protect medical image transfer. The Digital Imaging and Communications in Medicine (DICOM) standard is the dominant format and protocol suite for medical imaging workflows and is commonly transported over HTTPS. Conventional DICOM-over-HTTPS deployments rely on classical cryptographic primitives that are not resistant to quantum adversaries. This work evaluates the feasibility of integrating post-quantum cryptography (PQC) into existing DICOM transfer infrastructures without modifying DICOM applications or their cryptographic libraries. We present an empirical case study of xPIPE and RSNA MIRC-CTP as a widely deployed DICOM-over-HTTPS toolchain used in hospital environments. We propose a non-invasive proxy-based design that requires no modifications to the xPIPE client, the MIRC-CTP server, or their cryptographic libraries. The design encapsulates TLS-protected DICOM traffic within an additional PQC-secured tunnel, preserving the existing TLS channel while adding a quantum-resistant outer layer. We implement a proof of concept that preserves the existing Java TLS stack ( javax.net.ssl ) used by MIRC-CTP for the inner channel and adds a PQC-secured outer tunnel based on stunnel. We further compare alternative PQC integration strategies and discuss their security and operational trade-offs. Our results show that current PQC deployments impose an computational overhead and introduce integration constraints in heterogeneous environments. Nevertheless, the proposed approach enables incremental migration by maintaining compatibility with existing systems while providing an additional post-quantum security layer. • Non-invasive PQC Integration for Legacy Systems. • Quantum-Resistant Tunnel Layer Using OpenSSL and Stunnel. • Preservation of Regulatory Compliance. • PQC Migration Path Without System Disruption.

We present 'Epicurrents', an open-source JavaScript library for processing and displaying neurophysiological signal data in a web browser. The library follows a modular architecture to enable support for multiple clinical neurophysiology modalities. It supports open standards such as the European Data Format (EDF) and Digital Imaging and Communications in Medicine (DICOM), with optional Python and Open Neural Network Exchange (ONNX) integrations for scientific signal processing. The application presented in this article is platform agnostic, requires no installation, and is usable both online and offline as a progressive web application. The library has been tested in real-world educational and research projects and is used by the European Academy of Neurology for hands-on EEG-education in their congresses. While JavaScript's memory management poses limitations for processing large recordings, architectural workarounds such as shared memory buffers and asynchronous processing have resulted in improved performance. The application presented here is not intended nor certified for clinical diagnostics, but its accessibility and extensibility make it a promising tool for neurophysiology education and research. Epicurrents is the first modular JavaScript library for clinical neurophysiology education and illustrates how web technologies can also enhance collaborative scientific research in the field of clinical neurophysiology.

Integration of three-dimensional (3D) facial scanning into digital workflows has become increasingly important for enhancing treatment planning and esthetic evaluation. However, limited data exists on the accuracy of various methods of merging facial scans with cone beam computed tomography (CBCT) scans. The purpose of this study is to compare the accuracy of integrating 3D facial scans with CBCT scans using the iterative closest point (ICP) algorithm versus a radiopaque (RO) marker technique. This prospective clinical study included 15 patients who received CBCT scans and 3D facial scans in repose and smile positions. The Digital Imaging and Communications in Medicine (DICOM) datasets from the CBCT scans containing RO markers were integrated with the standard tessellation language (STL) files from the facial scans in Exocad software using two methods: RO alignment and the ICP algorithm. The datasets from both groups were statistically compared using a paired t-test (α = 0.05). The means for the six subsets merged by the ICP algorithm ranged from 1.47 to 2.0mm, and the means for the RO markers were 0.13 to 0.15mm. The novel RO markers method was statistically significant and more accurate than the ICP algorithm (p < 0.001). Merging 3D facial scans to CBCT using radiopaque markers demonstrated higher trueness compared to the ICP algorithm under the conditions tested. This technique may serve as a reliable alternative for improving integration accuracy in digital dental workflows, particularly where precise facial landmark preservation is essential.

Accurate classification and early detection of lung cancer are crucial for effective treatment and improved patient outcomes. Although recent advances in medical imaging have improved diagnostic workflows, many traditional approaches remain limited in their ability to efficiently analyze large volumes of imaging data. Accordingly, this study proposes a deep learning framework for lung cancer classification using Digital Imaging and Communications in Medicine (DICOM) images. The proposed approach integrates an Intelligent Squirrel Search (ISS)–tuned VGG16 network (ISS-VGG16) to improve classification performance. A set of lung cancer DICOM images was obtained from an open-source dataset. Preprocessing steps, including image resizing and contrast enhancement, were applied to standardize the inputs for model training. ISS was used to optimize key hyperparameters of the VGG16 model, thereby improving classification performance. The model was implemented in Python. Experimental results indicate that the proposed ISS-VGG16 approach outperforms baseline methods, achieving a recall of 0.92, precision of 0.96, F1-score of 0.95, and overall accuracy of 0.97 on the evaluated lung cancer image dataset. These results demonstrate reliable classification performance across the defined lung cancer classes. Overall, the proposed framework provides an effective and dependable approach for lung cancer image classification.

Abstract Breast cancer is the leading cause of cancer-related deaths among women in Brazil, highlighting the importance of early detection to improve outcomes. Artificial intelligence (AI) has garnered considerable attention for its potential to enhance breast cancer screening by reducing unnecessary exams, minimizing diagnostic errors, and increasing efficiency and accuracy—exemplified by advanced tools like Mirai. The present retrospective study analyzed 1,000 patients who underwent bilateral mammography from December 2019 to April 2024 at Hospital Santa Casa de Porto Alegre. All mammograms extracted in digital imaging and communications in medicine (DICOM) format were anonymized and processed by the Mirai algorithm to generate risk scores. Predictive performance was evaluated using discrimination metrics, such as C-index and area under the curve (AUC), as well as threshold analyses (F1-score, Youden's J) to estimate cancer risk. Mirai obtained a C-index of 0.76 (95% CI: 0.72–0.80) and an AUC of 0.81. The analysis further evaluated the F1-score and Youden's J statistic in an attempt to establish risk thresholds for cancer development. The results suggest that the Mirai model holds promise as a valuable tool for breast cancer detection, particularly for early identification of high-risk patients.

As charismatic sentinel species, California sea lions (Zalophus californianus) are commonly found in professional care settings such as zoos, aquariums, and rehabilitation facilities, in addition to their free-ranging coastal populations. These animals frequently strand due to illness, trauma, or environmental stressors, including toxic algal blooms such as domoic acid poisoning, underscoring the need for innovative tools and training methods to improve diagnostic care, monitoring, and veterinary intervention. This study presents a systematic approach for developing scalable, 3D-printable phantoms of a California sea lion pelvis using DICOM (Digital Imaging and Communications in Medicine) standard images from computed tomography (CT) scans to aid in veterinary blood collection training. The CT image data was processed using Simpleware ScanIP software to create detailed anatomical models, emphasizing the blood collection site at the caudal gluteal region and optimized for 3D printing. Through threshold-based segmentation of the DICOM data, several distinct anatomical layers were modeled separately, including a combined epidermal and dermal compliant skin shell, an adipose-rich blubber layer, a muscular layer derived from lower-density soft tissue regions, and a skeletal structure segmented from high-density bone data. This separation enabled each component to be fabricated independently using materials that closely matched their biological counterparts. Prior to fabrication, a material characterization study was conducted using dynamic mechanical analysis (DMA) to evaluate the compressive viscoelastic properties of multiple Humimic medical gelatin compositions (Gels 0 through 5), each with distinct mechanical profiles. The apparent elastic modulus of each gel under cyclic loading was calculated from stress-strain hysteresis data. Based on these results, individual gel types were selected to best match the mechanical properties of biological tissues, including blubber, skin, muscle, and bone. The quad-layered phantom was then fabricated using a combination of high-resolution stereolithography (SLA), fused deposition modeling (FDM), and gel casting techniques. This process resulted in the successful creation of 3D-printed anatomical phantoms that mimic both the mechanical and anatomical properties of the California sea lion pelvis. The methodology presented here provides a framework for creating engineered medical training models with anatomical fidelity and tunable material properties, offering a scalable alternative to traditional approaches in both veterinary and human health education, and the potential for personalized compatible implant design and biomimetic soft robotics.

BackgroundComputer-aided detection (CAD) software provides scalable, standardized chest X-ray (CXR) interpretation, helping address the global shortage of radiologists and inter-reader variability. Printed X-ray films remain common in many low-resource settings, yet most CAD software can only process Digital Imaging and Communications in Medicine (DICOM) files. Genki software (DeepTek, India) is one of the few World Health Organization (WHO)–recommended CAD software capable of interpreting both DICOM files and photographs of printed X-ray films (Joint Photographic Experts Group [JPEG] files), but its performance using JPEG files has not been independently evaluated.MethodsWe evaluated Genki software using a test library of 1466 CXR images from adults screened for tuberculosis (TB) in Ho Chi Minh City, Viet Nam. Each participant’s TB status was determined using a composite reference standard, based on radiological findings and Xpert MTB/RIF Ultra testing. Each CXR image was blindly re-read by 10 human readers and processed by Genki software using both DICOM and JPEG files. Genki software performance was evaluated using median abnormality scores, area under the receiver operating characteristic curves (AUC), and sensitivity/specificity comparisons at different abnormality score thresholds.ResultsGenki software abnormality scores were significantly higher when using JPEG files, but this did not translate into significant differences in AUCs between the file types (DICOM AUC = 0.94 vs JPEG AUC = 0.92, p = 0.190). When abnormality score thresholds were calibrated to match average human reader sensitivity (79.0%), Genki achieved significantly higher specificity with both DICOM (95.2% vs 84.8%, p < 0.001) and JPEG (92.1% vs 84.8%, p < 0.001) files. When the software’s abnormality score thresholds were calibrated to achieve 90% sensitivity, Genki maintained high specificity with both DICOM (89.3%) and JPEG (81.1%) file types, meeting the minimum Target Product Profile (TPP) criteria for a high-sensitivity, high-specificity screening test.ConclusionsGenki software performs comparably when interpreting DICOM and JPEG files, outperforming human readers and meeting TPP criteria with both file types. This capability enhances its usability in resource-limited settings where digital infrastructure is lacking, supporting its broader deployment for TB screening. Further research is needed to assess real-world implementation feasibility and performance in diverse populations and clinical environments.Supplementary InformationThe online version contains supplementary material available at 10.1186/s44263-025-00237-8.

This study aimed to design and characterize a compressible phantom that simulates adipose, glandular, and mixed breast tissues for mammography applications. Samples were prepared using paraffin gel wax, silicone oil, glass microspheres, and silicone. The linear attenuation coefficients and effective atomic numbers calculated at 15keV were 0.986cm-1 and 5.97 for adipose tissue, 1.381cm-1 and 7.81 for glandular tissue, and 1.772cm-1 and 6.91 for the mixed sample. Densities and Young's modulus values obtained from computed tomography and compression tests were 0.89g·cm-3 and 24.75kPa for adipose, 0.98g·cm-3 and 31.26kPa for glandular, and 0.95g·cm-3 and 26.27kPa for the mixed composition. Mammographic images were satisfactory, and the calculated mean glandular dose values closely matched those extracted from Digital Imaging and Communications in Medicine (DICOM) headers, with mixed and glandular samples showing similar values to patient data. Slight deviations from previously published results suggest potential areas for further refinement of phantom properties.

Introduction: Lumbar spine magnetic resonance imaging (MRI) is a high-volume diagnostic examination, yet increasing caseloads and reporting complexity continue to strain radiology workflows. Emerging artificial intelligence (AI)-assisted reading tools may help streamline interpretation and reduce report turnaround times, but their real-world impact on efficiency remains insufficiently quantified. Objective: To evaluate the impact of an AI-based reading tool on lumbar spine MRI interpretation and reporting time. Methods: We randomly selected 236 lumbar spine MRI examinations performed between 2018 and 2023 in patients aged 18 and older. Cases with prior lumbar surgery or scoliosis were excluded. Digital imaging and communications in medicine (DICOM) data were processed using a commercial deep-learning software package, and outputs were reviewed in a standard DICOM viewer. Five radiologists participated. Studies 1 and 2 assessed the effect of AI on interpretation time using a within-reader design: radiologists interpreted each examination with AI support and then reinterpreted the same examinations 2 months later without AI, enabling direct comparison of interpretation times. Study 3 evaluated the effect of AI by comparing AI-assisted and unassisted interpretations in 146 randomly selected examinations. Results: AI assistance significantly accelerated report generation. Across the full dataset, AI-supported interpretation reduced time by approximately 52% compared with unassisted reading. AI-assisted generation of preliminary reports reduced radiologists&amp;rsquo; overall time by nearly 30%. Linear mixed-effects modeling indicated that these reductions were statistically significant. The smaller reduction observed in Study 3 (9.21%) may reflect limited familiarity with the software&amp;rsquo;s reporting style and occasional instances in which the AI outputs did not fully support the radiologists&amp;rsquo; findings. Conclusion: AI assistance improves the efficiency of lumbar spine MRI reporting and shortens reporting time.

Background: The methodology of a retrospective cohort study designed to evaluate pelvic ring injury radiographic images in three steps is presented: first, computed tomography (CT) alone; second, standard anteroposterior pelvic radiograph with a pelvic binder added; finally, standard anteroposterior pelvic radiograph without a pelvic binder added. The evaluations were performed by various international pelvic experts. Methods: The authors encountered several challenges during the study design, which were addressed through the following methodological strategies: 1) transferring a large volume of anonymized data [specifically DICOM (Digital Imaging and Communication in Medicine) CT images] to remote centers where the experts were located; 2) providing a high-quality DICOM viewer that enabled optimal image analysis, including the creation of multiplanar reconstructions; 3) designing a survey that prevented users from returning to previously completed steps, thereby avoiding potential modifications to initial analyses based on subsequent images; 4) utilizing free software whenever possible to ensure cost-effectiveness. Results: A total of 28 image series were thoroughly evaluated by six experts. No difficulties were reported regarding the reception and analysis of the image series, the installation and use of the DICOM viewer, or access to and completion of the online survey. The overall workflow, including the distribution of image series and the DICOM viewer, the development and distribution of the survey, and the collection of responses, proceeded without complications. The only notable challenge was encouraging timely participation from some experts to complete the analysis. Conclusion: A robust and effective methodology was developed for this study. The use of free software, applications, and online resources allowed the study to be cost-effective. Sharing this methodology may assist other research teams in the design and implementation of future similar studies.