PLoS One. 2025 May 21;20(5):e0323490. doi: 10.1371/journal.pone.0323490. eCollection 2025.

ABSTRACT

In clinical in-person conditions, social presence, perceived empathy, and emotional engagement are related to positive outcomes. In online settings, it is unclear how these factors affect outcomes. Here, in 10-15-minute interviews, we investigated the influence of automation. Participants (N = 75) engaged in one of three possible interviews: live semi-scripted, live scripted, or video scripted. In the first two, participants communicated with a live interviewer and, in the third, with pre-recorded interviewer questions and answers. Emotion recognition software revealed that expressed joy differed between conditions (χ2(2) = 18.08, p < .001); both live conditions had higher scores (vs. video scripted). Self-rated perceived interviewer empathy also differed between conditions in the same way (F[2, 72] = 9.445, p < 0.001). We found a positive correlation between perceived empathy and expressed joy (r = .35; p < .01). In sum, automatized interviews differed in perceived empathy and expressed emotion compared with live interviews.

PMID:40397863 | DOI:10.1371/journal.pone.0323490

Fa Yi Xue Za Zhi. 2025 Feb 25;41(1):48-58. doi: 10.12116/j.issn.1004-5619.2024.241202.

ABSTRACT

OBJECTIVES: To explore a deep learning-based automatic bone age estimation model for elbow joint X-ray images of Chinese Han adolescents and children and evaluate its performance.

METHODS: A total of 943 (517 males and 426 females) elbow joint frontal view X-ray images of Chinese Han adolescents and children aged 6.00 to <16.00 years were collected from East, South, Central and Northwest China. Three experimental schemes were adopted for bone age estimation. Scheme 1: Directly input preprocessed images into the regression model; Scheme 2: Train a segmentation network using "key elbow joint bone annotations" as labels, then input segmented images into the regression model; Scheme 3: Train a segmentation network using "full elbow joint bone annotations" as labels, then input segmented images into the regression model. For segmentation, the optimal model was selected from U-Net, UNet++ and TransUNet. For regression, VGG16, VGG19, InceptionV2, InceptionV3, ResNet34, ResNet50, ResNet101 and DenseNet121 models were selected for bone age estimation. The dataset was randomly split into 80% (754 samples) for training and validation for model fitting and hyperparameter tuning, and 20% (189 samples) as an internal test set to test the performance of the trained model. An additional 104 elbow joint X-ray images from the same demographic and age group were collected and used as an external test set. Model performance was evaluated by comparing the mean absolute error (MAE), root mean square error (RMSE), accuracies within ±0.7 years (P±0.7 years) and ±1.0 years (P±1.0 years) between the estimated age and the actual age, and by drawing radar charts, scatter plots, and heatmaps.

RESULTS: When segmented with Scheme 3, the UNet++ model achieved good segmentation performance with a segmentation loss of 0.000 4 and an accuracy of 93.8% at a learning rate of 0.000 1. In the internal test set, the DenseNet121 model with Scheme 3 yielded the best results with MAE, P±0.7 years and P±1.0 years being 0.83 years, 70.03%, and 84.30%, respectively. In the external test set, the DenseNet121 model with Scheme 3 also performed best, with an average MAE of 0.89 years and an average RMSE of 1.00 years.

CONCLUSIONS: When performing automatic bone age estimation using elbow joint X-ray images in Chinese Han adolescents and children, it is recommended to use the UNet++ model for segmentation. The DenseNet121 model with Scheme 3 achieves optimal performance. Using segmentation networks, especially that trained with annotation areas encompassing the full elbow joint including the distal humerus, proximal radius, and proximal ulna, can improve the accuracy of bone age estimation based on elbow joint X-ray images.

PMID:40397588 | DOI:10.12116/j.issn.1004-5619.2024.241202

AJR Am J Roentgenol. 2025 May 21. doi: 10.2214/AJR.25.32637. Online ahead of print.

ABSTRACT

Lung MRI provides both structural and functional information across a spectrum of parenchymal and airway pathologies. MRI, using current widely available conventional sequences, provides high-quality diagnostic images that allow tissue characterization and delineation of lung lesions; dynamic evaluation of expiratory central airway collapse, diaphragmatic or chest wall motion, and the relations of lung masses to the chest wall; oncologic staging; surveillance of chronic lung pathologies; and differentiation of inflammation and fibrosis in interstitial lung disease. Ongoing technologic advances, including deep-learning acceleration methods, may enable future applications in longitudinal lung cancer screening without ionizing radiation exposure and in the regional quantification of ventilation and perfusion without hyperpolarized gas or IV contrast media. Although society statements highlight appropriate indications for lung MRI, and the modality has performed favorably relative to CT or FDG PET/CT in various indications, the examination's clinical utilization remains extremely low. Ongoing barriers to adoption include limited awareness by referring physicians, as well as insufficient proficiency and experience by radiologists and technologists. In this AJR Expert Panel Narrative Review, we review clinical indications for lung MRI, describe the examination's current capabilities, provide guidance on protocols comprised of widely available pulse sequences, introduce emerging techniques, and issue consensus recommendations.

PMID:40397559 | DOI:10.2214/AJR.25.32637

J Med Internet Res. 2025 May 21;27:e60284. doi: 10.2196/60284.

ABSTRACT

BACKGROUND: The recent emergence of wearable devices has made feasible the passive gathering of intensive, longitudinal data from large groups of individuals. This form of data is effective at capturing physiological changes between participants (interindividual variability) and changes within participants over time (intraindividual variability). The emergence of longitudinal datasets provides an opportunity to quantify the contribution of such longitudinal data to the control of these sources of variability for applications such as responder analysis, where traditional, sparser sampling methods may hinder the categorization of individuals into these phenotypes.

OBJECTIVE: This study aimed to quantify the gains made in statistical power and effect size among statistical comparisons when controlling for interindividual variability and intraindividual variability compared with controlling for neither.

METHODS: Here, we test the gains in statistical power from controlling for interindividual and intraindividual variability of resting heart rate, collected in 2020 for over 40,000 individuals as part of the TemPredict study on COVID-19 detection. We compared heart rate on weekends with that on weekdays because weekends predictably change the behavior of most individuals, though not all, and in different ways. Weekends also repeat consistently, making their effects on heart rate feasible to assess with confidence over large populations. We therefore used weekends as a model system to test the impact of different statistical controls on detecting a recurring event with a clear ground truth. We randomly and iteratively sampled heart rate from weekday and weekend nights, controlling for interindividual variability, intraindividual variability, both, or neither.

RESULTS: Between-participant variability appeared to be a greater source of structured variability than within-participant fluctuations. Accounting for interindividual variability through within-individual sampling required 40× fewer pairs of samples to achieve statistical significance with 4× to 5× greater effect size at significance. Within-individual sampling revealed differential effects of weekends on heart rate, which were obscured by aggregated sampling methods.

CONCLUSIONS: This work highlights the leverage provided by longitudinal, within-individual sampling to increase statistical power among populations with heterogeneous effects.

PMID:40397926 | DOI:10.2196/60284

ACS Appl Mater Interfaces. 2025 May 21. doi: 10.1021/acsami.5c04355. Online ahead of print.

ABSTRACT

Osteoarthritis (OA) is a common joint disorder that causes significant disability. Previous studies suggested that the predominance of M1 macrophages (MΦs) exacerbates inflammation and cartilage degradation in OA, suggesting that shifting the polarization toward M2 MΦs could be a promising therapeutic strategy. We recently developed CRISPRa-engineered macrophages, termed Elite MΦs, that express IL-10 and maintain a stable M2 phenotype. However, achieving effective and sustained delivery of these cells to the OA joint remains a challenge. In this study, we synthesized two injectable aldehyde hyaluronic acid-based hydrogels, CHO/CDH and ACHO/CDH hydrogels, to serve as Elite MΦ delivery platforms. Comprehensive analyses identified the ACHO/CDH hydrogel as superior due to its enhanced suitability for encapsulating and delivering Elite MΦs. When loaded with Elite MΦs, the ACHO/CDH hydrogel was able to not only localize Elite MΦs but also enhance their anti-inflammatory and reparative effects. Furthermore, intra-articular injection of the Elite MΦ-loaded ACHO/CDH hydrogel in an OA mouse model resulted in notable improvements in the joint's cellular environment, alleviating cartilage degradation and synovial inflammation. These results highlight the ability of the ACHO/CDH hydrogel to rebalance the inflammatory imbalance and promote cartilage repair. This approach not only targets the underlying inflammatory processes more directly than traditional therapies but also harnesses the regenerative potential of macrophages, offering a transformative strategy for OA management.

PMID:40397763 | DOI:10.1021/acsami.5c04355

J Burn Care Res. 2025 May 21:iraf012. doi: 10.1093/jbcr/iraf012. Online ahead of print.

ABSTRACT

A dysregulated immune response after severe burn injury is associated with detrimental short and long-term clinical outcomes. Key changes to gene expression within the first 24 h after burn injury have been identified, but longitudinal data is lacking. Therefore, this study aims to characterize gene expression during the first 3 weeks after burn injury and identify specific genes and pathways associated with distinct clinical outcomes. Patients presenting within 4 h of injury had blood RNA isolated for microarray gene expression at admission and set timepoints to 21 days. Inter- and intra-group comparisons were performed between 4 groups (G1 died within 7 days; G2 died after 7 days; G3 discharged after 7 days; and G4 discharged within 7 days). A total of 17 289 transcripts were quantified from 116 patients. At admission, there were 110, 80, and 31 differentially expressed genes in G1, G2, and G3, respectively, compared to G4, and were largely nonoverlapping. Longitudinal intra-group analyses also showed distinct group- and time-dependent patterns. Upregulation of genes and pathways related to the innate immune response and unfolded protein response predominated during early time points, while persistent upregulation of coagulation pathways and downregulation of immune-related pathways were identified days to weeks following injury. Overall, burn injury induces widespread transcriptomic responses, with larger and more sustained changes observed in patients with worse clinical outcomes. These gene expression signatures reveal underlying molecular mechanisms that occur immediately following injury and may have prognostic and diagnostic utility in the care of burn-injured patients.

PMID:40397518 | DOI:10.1093/jbcr/iraf012

Nutr Res Rev. 2025 May 21:1-54. doi: 10.1017/S0954422425100061. Online ahead of print.

ABSTRACT

To achieve infectivity, severe acute respiratory syndrome coronavirus 2 (SARS-CoV2), the virus responsible for COVID-19, must first traverse the upper respiratory tract mucosal barrier. Once infection is established, the cascading complexities of the pathophysiology of COVID-19 makes intervention extremely difficult. Thus, enhancing the defensive properties of the mucosal linings of the upper respiratory tract may reduce infection by SARS-CoV2 and indeed by other viruses such as influenza, which have been responsible for the two major pandemics of the last century. In this review we summarise potential opportunities for foods and nutrients to promote an adequate mucosal immune preparedness with an aim to assist protection against infection by SARS-CoV-2; to maximise the mucosal vaccination (IgA inducing) response to existing systemic vaccines; and to play a role as adjuvants to intranasal vaccines. We identify opportunities for vitamins A, and D, zinc, probiotics, bovine colostrum and resistant starch to promote mucosal immunity and enhance the mucosal response to systemic vaccines, and for vitamin A to also improve the mucosal response to intranasal vaccination. It is possible that an entirely different virus may in the future, by way of convergent evolution, utilise a similar upper respiratory tract infection pathway. A greater research focus on mucosal lymphoid immune protection in partnership with nutrition would result in greater preparedness for such an event.

PMID:40396597 | DOI:10.1017/S0954422425100061

Pharmacogenomics. 2025 May 21:1-14. doi: 10.1080/14622416.2025.2504862. Online ahead of print.

ABSTRACT

BACKGROUND: Pharmacogenetics uses individuals' genetic profiles to optimize drug treatment and prevent adverse reactions. One strategy to obtain information on pharmacogenes is to reuse sequencing data for a pharmacogenetic passport, providing information preemptively to healthcare professionals for utilization throughout a patient's lifetime.

AIM: To explore stakeholders' perceived barriers and facilitators and future perspectives of implementing a pharmacogenetic passport based on experiences from reusing sequencing data, in a Dutch University Medical Center.

METHODS: Semi-structured interviews were conducted among 21 stakeholders. Interviews were analyzed using thematic analysis, and themes were grouped under the constructs of structure, culture, and practice.

RESULTS: Perceived implementation barriers included inadequate data infrastructure, limited knowledge of pharmacogenetics, lack of (visible) guidelines, unequal access, unclear division of tasks and unclear procedures, and other hospital priorities. Perceived facilitators included the ease, efficiency, and affordability to obtain pharmacogenetic test results from reused sequencing data, stakeholders' positive attitudes about patient impacts of a pharmacogenetic passport, and that patient control of their health data is provided.

CONCLUSION: When considering the implementation of a pharmacogenetic passport, strategies can be developed to diminish barriers and strengthen facilitators. It is important to focus on data infrastructure, (visibility of) guidelines, clear division of tasks, and pharmacogenetic education.

PMID:40396487 | DOI:10.1080/14622416.2025.2504862

Microbiol Spectr. 2025 May 21:e0281124. doi: 10.1128/spectrum.02811-24. Online ahead of print.

ABSTRACT

Pseudomonas aeruginosa is an opportunistic human pathogen that can also infect mammals, invertebrates, and plants. Protease IV (PIV) is a secreted protease shown to be important in mammalian cornea, lung, and wound models of infection. It also contributes to P. aeruginosa virulence in many invertebrate models. Previous studies have shown that the expression of the gene encoding PIV is higher at 25°C than at 37°C. Thus, we hypothesized that piv would be more important for P. aeruginosa virulence at 25°C than at 37°C. To test this, we first demonstrated that more PIV is secreted by P. aeruginosa PAO1 cells grown at 25°C than at 37°C. We then determined the survival of larvae of the greater wax moth Galleria mellonella infected by PAO1 and an isogenic Δpiv mutant at both 25°C and 37°C. We found no significant difference in virulence between PAO1 and Δpiv at either 25°C or 37°C, although both strains were more virulent at 37°C than 25°C as measured by a decrease in median survival time. P. aeruginosa possesses an arsenal of virulence factors besides PIV, and thus loss of this single virulence factor may not result in attenuation in the highly susceptible G. mellonella larvae.IMPORTANCEPathogenesis of the important opportunistic pathogen Pseudomonas aeruginosa is often investigated using model organisms. Larvae of the greater wax moth, Galleria mellonella, are a popular non-mammalian model organism for P. aeruginosa infections that have been used to study highly attenuated mutants and characterize their defects in virulence. Our study shows that small differences in the virulence of P. aeruginosa, such as those caused by deleting the gene encoding a single virulence factor, may not be detectable in the G. mellonella model of infection. This is an important finding for researchers considering the choice of model organisms for virulence studies.

PMID:40396793 | DOI:10.1128/spectrum.02811-24

Pediatr Pulmonol. 2025 May;60(5):e71140. doi: 10.1002/ppul.71140.

NO ABSTRACT

PMID:40396441 | DOI:10.1002/ppul.71140

Pediatr Pulmonol. 2025 May;60(5):e71134. doi: 10.1002/ppul.71134.

ABSTRACT

OBJECTIVES: This study aims to study the healthcare (HC) costs associated with cystic fibrosis (CF) in children diagnosed prenatally (ANT), through newborn screening (NBS), after birth due to meconium ileus (MI), or later based on symptoms (LS). Additionally, it seeks to clinically characterize children with CF (chCF) with different trajectories of HC costs.

STUDY DESIGN: A retrospective observational study was conducted on data from the French CF Registry (FCFR) and the French National Claims Database (SNDS) linked from 2006 to 2021. HC costs related to CF diagnosis circumstances were estimated per year of life among chCF up to age 10. Group-based trajectory modeling was performed to identify subgroups with similar cost trajectories.

RESULTS: Between 2006 and 2011, data from 1065 chCF were recorded in the FCFR. Nine hundred seventy-three (91.4%) were matched with SNDS, and 779 (73.1%) had at least 10 years of follow-up. During the first year, HC costs of chCF diagnosed with NBS were lower than for those diagnosed with MI and ANT (all p < 0.05). However, by the tenth year HC were no longer different between groups. Three groups with different cost trajectories were identified. Groups with the highest costs had a lower lung function at 6 and 10 years and the lowest weight and height z-scores at 2 and 10 years (all p < 0.05).

CONCLUSION: NBS is associated with the lowest HC costs during the first year of life.

PMID:40396435 | DOI:10.1002/ppul.71134

Adv Sci (Weinh). 2025 May 21:e2416958. doi: 10.1002/advs.202416958. Online ahead of print.

ABSTRACT

Accurate characterization of cellular states is the foundation for precise prediction of drug sensitivity in cancer cell lines, which in turn is fundamental to realizing precision oncology. However, current deep learning approaches have limitations in characterizing cellular states. They rely solely on isolated genetic markers, overlooking the complex regulatory networks and cellular mechanisms that underlie drug responses. To address this limitation, this work proposes DeepCCDS, a Deep learning framework for Cancer Cell Drug Sensitivity prediction through Characterizing Cancer Driver Signals. DeepCCDS incorporates a prior knowledge network to characterize cancer driver signals, building upon the self-supervised neural network framework. The signals can reflect key mechanisms influencing cancer cell development and drug response, enhancing the model's predictive performance and interpretability. DeepCCDS has demonstrated superior performance in predicting drug sensitivity compared to previous state-of-the-art approaches across multiple datasets. Benefiting from integrating prior knowledge, DeepCCDS exhibits powerful feature representation capabilities and interpretability. Based on these feature representations, we have identified embedding features that could potentially be used for drug screening in new indications. Further, this work demonstrates the applicability of DeepCCDS on solid tumor samples from The Cancer Genome Atlas. This work believes integrating DeepCCDS into clinical decision-making processes can potentially improve the selection of personalized treatment strategies for cancer patients.

PMID:40397390 | DOI:10.1002/advs.202416958

Mol Divers. 2025 May 21. doi: 10.1007/s11030-025-11171-0. Online ahead of print.

ABSTRACT

11β-Hydroxysteroid dehydrogenase type 1 (11β-HSD1) has been shown to play an important role in the treatment of impaired glucose tolerance, insulin resistance, dyslipidemia, and obesity and is a promising drug target. In this study, we built a gated recurrent unit (GRU)-based recurrent neural network using 1,854,484 (processed) drug-like molecules from ChEMBL and the US patent database and successfully built a molecular generative model of 11βHSD1 inhibitors by using the known 11β-HSD1 inhibitors that have undergone transfer learning, our constructed GRU model was able to accurately capture drug-like molecules evaluated using traditional machine model-related syntax, and transfer learning can also easily generate potential 11β-HSD1 inhibitors. By combining Lipinski's and absorption, distribution, metabolism, excretion, and toxicity (ADME/T) analyses to filter nonconforming molecules and stepwise screening through molecular docking and molecular dynamics simulation, we finally obtained 5 potential compounds. We found that compound 02 is identical to a previously published inhibitor of 11β-HSD1. We selected compounds 02 and 05 with the lowest binding free energy for in vitro activity validation and found that compound 02 possessed inhibitory activity but was not as potent as the control. In conclusion, our study provides new ideas and methods for the development of new drugs and the discovery of new 11β-HSD1 inhibitors.

PMID:40397334 | DOI:10.1007/s11030-025-11171-0

Insights Imaging. 2025 May 21;16(1):109. doi: 10.1186/s13244-025-01983-x.

ABSTRACT

PURPOSE: We developed an artificial intelligence system (AIS) using multi-view multi-level convolutional neural networks for breast cancer detection, diagnosis, and BI-RADS categorization support in mammography.

METHODS: Twenty-four thousand eight hundred sixty-six breasts from 12,433 Asian women between August 2012 and December 2018 were enrolled. The study consisted of three parts: (1) evaluation of AIS performance in malignancy diagnosis; (2) stratified analysis of BI-RADS 3-4 subgroups with AIS; and (3) reassessment of BI-RADS 0 breasts with AIS assistance. We further evaluate AIS by conducting a counterbalance-designed AI-assisted study, where ten radiologists read 1302 cases with/without AIS assistance. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and F1 score were measured.

RESULTS: The AIS yielded AUC values of 0.995, 0.933, and 0.947 for malignancy diagnosis in the validation set, testing set 1, and testing set 2, respectively. Within BI-RADS 3-4 subgroups with pathological results, AIS downgraded 83.1% of false-positives into benign groups, and upgraded 54.1% of false-negatives into malignant groups. AIS also successfully assisted radiologists in identifying 7 out of 43 malignancies initially diagnosed with BI-RADS 0, with a specificity of 96.7%. In the counterbalance-designed AI-assisted study, the average AUC across ten readers significantly improved with AIS assistance (p = 0.001).

CONCLUSION: AIS can accurately detect and diagnose breast cancer on mammography and further serve as a supportive tool for BI-RADS categorization.

CRITICAL RELEVANCE STATEMENT: An AI risk assessment tool employing deep learning algorithms was developed and validated for enhancing breast cancer diagnosis from mammograms, to improve risk stratification accuracy, particularly in patients with dense breasts, and serve as a decision support aid for radiologists.

KEY POINTS: The false positive and negative rates of mammography diagnosis remain high. The AIS can yield a high AUC for malignancy diagnosis. The AIS is important in stratifying BI-RADS categorization.

PMID:40397242 | DOI:10.1186/s13244-025-01983-x

Neuroradiology. 2025 May 21. doi: 10.1007/s00234-025-03657-3. Online ahead of print.

ABSTRACT

BACKGROUND: Predicting hematoma progression in traumatic brain injury (TBI) is crucial for timely interventions and effective clinical management, as unchecked hematoma growth can lead to rapid neurological deterioration, increased intracranial pressure, and poor patient outcomes. Accurate risk assessment enables proactive therapeutic strategies, minimizing secondary brain damage and improving survival rates.

METHODS: This study evaluated to assess the performance of artificial intelligence (AI) algorithms, including machine learning (ML) and deep learning (DL), in forecasting risk of hematoma progression. Comprehensive searches across Embase, Scopus, Web of Science and PubMed identified relevant studies, with data extracted on algorithm metrics such as sensitivity, specificity, and area under the curve (AUC).

RESULTS: 1,240 studies screened, five out of them met the inclusion criteria, evaluating various AI models. The meta-analysis revealed a pooled sensitivity and specificity was 0.76 [95% CI: 0.67-0.83], 0.84 [95% CI: 0.78-0.89], positive and negative likelihood ratio was 4.82 [95% CI: 3.51-6.61] 0.29 [95% CI: 0.21-0.39], diagnostic score was 2.82 [95% CI: 2.33-3.32], diagnostic odds ratio was16.85 [95% CI: 10.29-27.59] and an AUC of 0.88 [95% CI: 0.85-0.90]. Among the evaluated algorithms, XGBoost has the best predictive performance with an accuracy of 91%. Integrating radiomics and clinical features in these models considerably improved the predictive outcomes.

CONCLUSION: The current results demonstrated the potential of AI-based models to improve hematoma progression prediction for TBI patients, thereby supporting more effective clinical decision-making. Further research should aim to standardize datasets and diversify patient populations to improve model applicability and reliability.

PMID:40397134 | DOI:10.1007/s00234-025-03657-3

Technol Cancer Res Treat. 2025 Jan-Dec;24:15330338251344198. doi: 10.1177/15330338251344198. Epub 2025 May 21.

ABSTRACT

IntroductionThis study aims to evaluate auto-segmentation results using deep learning-based auto-segmentation models on different online CT imaging modalities in image-guided radiotherapy.MethodsPhantom studies were first performed to benchmark image quality. Daily CT images for sixty patients were retrospectively retrieved from fan-beam kilovoltage CT (kVCT), kV cone-beam CT (kV-CBCT), and megavoltage CT (MVCT) scans. For each imaging modality, half of the patients received CT scans in the pelvic region, while the other half in the thoracic region. Deep learning auto-segmentation models using a convolutional neural network algorithm were used to generate organs-at-risk contours. Quantitative metrics were calculated to compare auto-segmentation results with manual contours.ResultsThe auto-segmentation contours on kVCT images showed statistically significant difference in Dice similarity coefficient (DSC), Jaccard similarity coefficient, sensitivity index, inclusiveness index, and the 95th percentile Hausdorff distance, compared to those on kV-CBCT and MVCT images for most major organs. In the pelvic region, the largest difference in DSC was observed for the bowel volume with an average DSC of 0.84 ± 0.05, 0.35 ± 0.23, and 0.48 ± 0.27 for kVCT, kV-CBCT, and MVCT images, respectively (p-value < 0.05); in the thoracic region, the largest difference in DSC was found for the esophagus with an average DSC of 0.63 ± 0.16, 0.18 ± 0.13, and 0.22 ± 0.08 for kVCT, kV-CBCT, and MVCT images, respectively (p-value < 0.05).ConclusionDeep learning-based auto-segmentation models showed better agreement with manual contouring when using kVCT images compared to kV-CBCT or MVCT images. However, manual correction remains necessary after auto-segmentation with all imaging modalities, particularly for organs with limited contrast from surrounding tissues. These findings underscore the potential and limits in applying deep learning-based auto-segmentation models for adaptive radiotherapy.

PMID:40397131 | DOI:10.1177/15330338251344198

Eur Radiol. 2025 May 21. doi: 10.1007/s00330-025-11674-2. Online ahead of print.

ABSTRACT

OBJECTIVES: To perform a systematic review on the impact of deep learning (DL)-based triage for reducing diagnostic delays and improving patient outcomes in peer-reviewed and pre-print publications.

MATERIALS AND METHODS: A search was conducted of primary research studies focused on DL-based worklist optimization for diagnostic imaging triage published on multiple databases from January 2018 until July 2024. Extracted data included study design, dataset characteristics, workflow metrics including report turnaround time and time-to-treatment, and patient outcome differences. Further analysis between clinical settings and integration modality was investigated using nonparametric statistics. Risk of bias was assessed with the risk of bias in non-randomized studies-of interventions (ROBINS-I) checklist.

RESULTS: A total of 38 studies from 20 publications, involving 138,423 images, were analyzed. Workflow interventions concerned pulmonary embolism (n = 8), stroke (n = 3), intracranial hemorrhage (n = 12), and chest conditions (n = 15). Patients in the post DL-triage group had shorter median report turnaround times: a mean difference of 12.3 min (IQR: -25.7, -7.6) for pulmonary embolism, 20.5 min (IQR: -32.1, -9.3) for stroke, 4.3 min (IQR: -8.6, 1.3) for intracranial hemorrhage and 29.7 min (IQR: -2947.7, -18.3) for chest diseases. Sub-group analysis revealed that reductions varied per clinical environment and relative prevalence rates but were the highest when algorithms actively stratified and reordered the radiological worklist, with reductions of -43.7% in report turnaround time compared to -7.6% from widget-based systems (p < 0.01).

CONCLUSION: DL-based triage systems had comparable report turnaround time improvements, especially in outpatient and high-prevalence settings, suggesting that AI-based triage holds promise in alleviating radiology workloads.

KEY POINTS: Question Can DL-based triage address lengthening imaging report turnaround times and improve patient outcomes across distinct clinical environments? Findings DL-based triage improved report turnaround time across disease groups, with higher reductions reported in high-prevalence or lower acuity settings. Clinical relevance DL-based workflow prioritization is a reliable tool for reducing diagnostic imaging delay for time-sensitive disease across clinical settings. However, further research and reliable metrics are needed to provide specific recommendations with regards to false-negative examinations and multi-condition prioritization.

PMID:40397031 | DOI:10.1007/s00330-025-11674-2

Radiol Artif Intell. 2025 May 21:e240586. doi: 10.1148/ryai.240586. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a deep learning segmentation model that can segment abdominal organs on CT and MR images with high accuracy and generalization ability. Materials and Methods In this study, an extended nnU-Net model was trained for abdominal organ segmentation. A domain randomization method in both the image and feature space was developed to improve the generalization ability under cross-site and cross-modality settings on public prostate MRI and abdominal CT and MRI datasets. The prostate MRI dataset contains data from multiple health care institutions with domain shifts. The abdominal CT and MRI dataset is structured for cross-modality evaluation, training on one modality (eg, MRI) and testing on the other (eg, CT). This domain randomization method was then used to train a segmentation model with enhanced generalization ability on the abdominal multiorgan segmentation challenge (AMOS) dataset to improve abdominal CT and MR multiorgan segmentation, and the model was compared with two commonly used segmentation algorithms (TotalSegmentator and MRSegmentator). Model performance was evaluated using the Dice similarity coefficient (DSC). Results The proposed domain randomization method showed improved generalization ability on the cross-site and cross-modality datasets compared with the state-of-the-art methods. The segmentation model using this method outperformed two other publicly available segmentation models on data from unseen test domains (Average DSC: 0.88 versus 0.79; P < .001 and 0.88 versus 0.76; P < .001). Conclusion The combination of image and feature domain randomizations improved the accuracy and generalization ability of deep learning-based abdominal segmentation on CT and MR images. © RSNA, 2025.

PMID:40396895 | DOI:10.1148/ryai.240586

Eur J Orthod. 2025 Apr 8;47(3):cjaf025. doi: 10.1093/ejo/cjaf025.

ABSTRACT

BACKGROUND: Dental crowding is a primary concern in orthodontic treatment and significantly impacts therapy choices. Accurate quantification of crowding requires time-intensive cast- or scan-based measurements. The aim was to develop an automated deep-learning model capable of assessing anterior crowding and calculating the Little Irregularity Index using single occlusal intra-oral photographs.

METHODS: A dataset of 125 untreated individuals (100 from Zurich, Switzerland, and 25 from Nijmegen, the Netherlands) comprised of annotated intra-oral scans and corresponding intra-oral photographs were used to train a dedicated convolutional neural network (CNN). The CNN was modeled to detect teeth boundaries, contact points and contact point displacements on photographs. The model's performance to determine anterior crowding and the Little Irregularity Index score was compared to consensus measurements based on intra-oral scans in terms of intra-class correlation (ICC) and mean absolute difference (MAD).

RESULTS: The model correlated well with the consensus measurement, and proved to be reliable (ICC = 0.900) and accurate (MAD = 0.36 mm) for anterior crowding assessment and Little Irregularity Index alike (ICC = 0.930; MAD = 0.74 mm).

LIMITATION: The model was not trained on cases with interdental spacing, and its reliability for cases with crowding severity outside the tested sample has not been established.

CONCLUSION: The presented CNN-based model was able to quantify the crowding in the anterior segment of the lower dental arch and score the Little Irregularity Index from a single intra-oral photograph with a satisfactory reliability and accuracy. Application of this model may lead to more efficient and convenient orthodontic diagnostics.

PMID:40396639 | DOI:10.1093/ejo/cjaf025

Curr Opin Neurol. 2025 May 22. doi: 10.1097/WCO.0000000000001383. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: This review explores the use of brain age estimation from MRI scans as a biomarker of brain health. With disorders like Alzheimer's and Parkinson's increasing globally, there is an urgent need for early detection tools that can identify at-risk individuals before cognitive symptoms emerge. Brain age offers a noninvasive, quantitative measure of neurobiological ageing, with applications in early diagnosis, disease monitoring, and personalized medicine.

RECENT FINDINGS: Studies show that individuals with Alzheimer's, mild cognitive impairment (MCI), and Parkinson's have older brain ages than their chronological age. Longitudinal research indicates that brain-predicted age difference (brain-PAD) rises with disease progression and often precedes cognitive decline. Advances in deep learning and multimodal imaging have improved the accuracy and interpretability of brain age predictions. Moreover, socioeconomic disparities and environmental factors significantly affect brain aging, highlighting the need for inclusive models.

SUMMARY: Brain age estimation is a promising biomarker for identify future risk of neurodegenerative disease, monitoring progression, and helping prognosis. Challenges like implementation of standardization, demographic biases, and interpretability remain. Future research should integrate brain age with biomarkers and multimodal imaging to enhance early diagnosis and intervention strategies.

PMID:40396549 | DOI:10.1097/WCO.0000000000001383