Personal radiation protective equipment (PRPE) play a critical role in minimising occupational exposure to ionising radiation in medical imaging, nuclear medicine, interventional procedures and related fields. Over time, repeated use, mechanical stress, and improper handling can degrade their protective performance, making regular inspection essential to ensure continued radiation safety. This study aimed to compare the performance of multiple imaging modalities in evaluating the integrity and lead equivalence of PRPE, to identify the most accurate and practical methods for quality assurance programmes. Over a four-year period, 1063 PRPE items from 20 manufacturers were evaluated. Each item underwent visual and tactile inspection, followed by imaging using radiography, fluoroscopy, computed tomography (CT), and a dedicated PRPE testing system (FLOWD 8020). Lead equivalence was determined by comparison with certified reference lead foils using both x-ray quality assurance dosimeter and image-based methods. Integrity was categorised on a four-level scale according to defect size and location, and attenuation performance was assessed relative to manufacturers' nominal specifications. Of all PRPE items tested, 88.8% were defect-free, while 11.2% showed cracks or tears cracks or tears of varying extent. Lead equivalence results revealed that 74.3% met specifications within ±5%, 13.8% deviated by 5%-10%, and 11.9% by more than 10%. All imaging modalities demonstrated comparable accuracy, though the dedicated screening system offered clear advantages in workflow efficiency, full-apron coverage, automated reporting, and low stray dose (<0.3μSv h-1at 1 m). Routine PRPE inspection is essential for maintaining occupational radiation safety. Standardised testing protocols and inspection intervals are recommended to ensure consistent and traceable quality assurance practices across institutions.

Acute ischemic stroke is a leading cause of morbidity and mortality requiring timely intervention. Mechanical thrombectomy is an increasingly prevalent technique for removal of the clot burden in patients with acute ischemic stroke with a targetable vessel, enabling treatment within 24 hours of symptom onset. In the post-mechanical thrombectomy period, patients must be monitored closely for complications and in preparation for secondary prevention therapy. Patients typically undergo serial follow-up imaging examinations with multiple modalities, including newer techniques such as dual-energy CT. The radiologist should be aware of the expected findings in the post-mechanical thrombectomy period, such as contrast material staining, and be able to distinguish these from complications. Post-mechanical thrombectomy complications can arise anywhere along the instrumentation path, involving both intracranial and extracranial findings. A conceptual understanding of the clinical implications of various complications is presented to help radiologists appropriately contextualize their findings at follow-up imaging. ©RSNA, 2025 Supplemental material is available for this article.

Pediatric diaphyseal femur fractures are a fairly common fracture type for which all trained orthopaedic surgeons should develop a treatment framework. Treatment goals are to restore an acceptable limb length, alignment, and rotation. Nuances exist regarding acceptable tolerances depending on the age and remaining growth of the patient. Various treatment modalities exist, including flexible nailing, plate fixation, and rigid nail fixation, each with its own advantages, disadvantages, and limitations. Proper identification of key patient factors and fracture type is important for optimal decision making regarding fixation modality. Flexible nailing is typically reserved for patients age 5 to 11 years with stable fracture patterns and who weigh less than 100 lb. Plate fixation, typically via a submuscular application, is typically indicated in patients with unstable fractures and can be a reasonable choice for patients older than 5 years with no weight limitation. Rigid nail fixation, specifically antegrade nailing via a lateral-entry starting point, can be indicated in patients older than 11 years with any fracture pattern. Understanding how each fracture and patient factor affects healing can help the savvy surgeon choose which fixation modality to use when the clinical situation inevitably falls in the gray zones shared by multiple modalities.

Neuro-cortical signatures of attention in uni- and multi-sensory audio-visual processing in children.

Antibody-based targeted protein degradation: Mechanisms, challenges and future directions.

Impact of interoception and multisensory integration on functional and physical activities in aging.

Modality-AGnostic image Cascade (MAGIC) for multi-modality cardiac substructure segmentation.

Due to its high energy and deep tissue penetration, X-ray is an ideal stimulus source for diagnosis and therapy. In the field of cancer treatment, by reasonably designing and using systems with X-ray responsiveness, it is possible to improve treatment methods or combine multiple treatment modalities, thereby improving treatment effectiveness and reducing side effects. This review aims to summarize the research progress of X-ray responsiveness in the field of cancer treatment in recent years. Specifically, it introduces the promotion of X-ray responsive radiosensitizers on X-ray radiation therapy itself, as well as the combination of radiotherapy and other cancer therapies mediated by X-ray responsive therapeutic systems, which mainly includes the combination of radiotherapy and photodynamic therapy through X-ray responsive scintillators and the combination of radiotherapy and chemotherapy through X-ray responsive drug delivery systems.

Sensory signals from multiple modalities presented close in time are often integrated, building a coherent and meaningful multisensory perceptual world. A better understanding of our perception requires characterization of how the nervous system detects and encodes unisensory cues in time. There are very few studies that have focused on the development and individual variabilities in temporal aspects of unisensory signal processing in neurotypical populations across modalities. Using a temporal order judgment (TOJ) task, this study explored individual differences in the temporal processing of unisensory (auditory, tactile, and visual) stimuli in neurotypical children and young adults. We examined whether the precision of unisensory temporal processing and perceptual synchrony for unisensory stimuli can be influenced by participants' age, cognition, and sensory responsiveness profiles. Performance in each of the unisensory TOJ tasks, measured in temporal order judgment threshold (JND) and reaction time (RT), showed significant improvement with age. On the other hand, perceptual synchrony, measured in Point of Subjective Simultaneity (PSS), remained stable with age across modalities. Although cognitive abilities and sensory responsiveness patterns could not predict the individual variability in unisensory temporal precision or perceptual synchrony for this group of subjects, results from this study show a developmental trajectory of unisensory temporal sensitivity from childhood to young adulthood.

MEMOL: Mixture of experts for multimodal learning through multi-head attention to predict drug toxicity.

Early-onset psychosis presents diagnostic challenges due to overlapping clinical presentations and complex comorbidities, typically requiring specialized tertiary care with extensive neuroimaging, neuropsychometric testing, and multidisciplinary evaluation. This case-control study investigated whether machine learning could integrate multiple diagnostic modalities to create an objective diagnostic framework for early-onset psychosis. We recruited 45 patients with early-onset psychosis and 34 healthy controls from a tertiary referral centre. Participants underwent comprehensive assessment including serum protein biomarker analysis (brain-derived neurotrophic factor, proBDNF, p75 neurotrophin receptor, S100B), neuropsychometric testing (Iowa Gambling Task, Simple Response Time, Zabor Verbal Task), and demographic evaluation. Four machine learning algorithms (logistic regression, support vector machine, random forest, XGBoost) were trained on five feature combinations using nested cross-validation with hyperparameter optimization. XGBoost demonstrated superior performance, achieving optimal classification with the complete multimodal dataset (accuracy: 0.91 ± 0.08, precision: 0.92 ± 0.08, area under curve: 0.97 ± 0.04). Feature importance analysis revealed cognitive measures, particularly Zabor Verbal Task errors and response time parameters, as most discriminative, with brain-derived neurotrophic factor pathway components showing highest biomarker importance. Machine learning effectively integrated neuropsychometric and protein biomarker data for high-accuracy early-onset psychosis classification, with multimodal approaches outperforming single-domain assessments.

Granulomatous cheilitis (GC) is a rare, idiopathic, inflammatory disorder which usually affects young adults. It is characterized by persistent, cosmetically disturbing and persistent idiopathic lip swelling. Multiple treatment modalities have been suggested. In spite of the treatment used, recurrence of the disease is very common. We reported an intractable and recurrent case of GC characterized by a large swelling of upper lip. The diagnosis is confirmed with a combination of history, clinical examination, radiographical and histopathological evaluation. This patient was treated with modified treatment protocol with a combination of intralesional steroids, prednisolone, systemic metronidazole, and doxycycline and maintenance drug therapy with approximately no signs of relapse at twelve months’ follow-up. In conclusion, the mentioned therapeutic protocol proved a success in the treatment this an intractable case of GC with a long follow up period with no relapse. More clinical trials and case control trials are needed for enhancing our understanding of this disease for evaluating the efficacy of the various treatments and establishing a universally accepted protocol for management of GC.

Score fusion is a technique that combines the matching scores from multiple biometric modalities for an authentication system. Biometric modalities are unique physical or behavioral characteristics that can be used to identify individuals. Biometric authentication systems use these modalities to verify or identify individuals. Score fusion can improve the performance of biometric authentication systems by exploiting the complementary strengths of different modalities and reducing the impact of noise and outliers from individual modalities. This paper proposes a new score fusion method based on the Sine Cosine Algorithm (SCA). SCA is a meta-heuristic optimization algorithm used in various optimization problems. The proposed method extracts features from multiple biometric sources and then computes intra/inter scores for each modality. The proposed method then normalizes the scores for a given user using different biometric modalities. Then, the mean, maximum, minimum, median, summation, and Tanh are used to aggregate the scores from different biometric modalities. The role of the SCA is to find the optimal parameters to fuse the normalized scores. We evaluated our methods on the CASIA-V3-Internal iris dataset and the AT&T (ORL) face database. The proposed method outperforms existing optimization-based methods under identical experimental conditions and achieves an Equal Error Rate (EER) of 1.003% when fusing left iris, right iris, and face. This represents an improvement of up to 85.89% over unimodal baselines. These findings validate SCA’s effectiveness for adaptive score fusion in multimodal biometric systems.

Prediction of soil properties at different depth levels and scales requires the use of multimodal datasets to represent the characteristics of the SCORPAN factors within the digital soil mapping (DSM) technique. With spectral variables representing the dynamic nature of soil property estimation, evaluating their efficiency can enhance the applicability of the models for further standardization. The current study aimed to compare the utility of different spectral modalities (i.e., Sentinel 1A, Sentinel 2A, Landsat 8, and PRISMA) for digital soil mapping of soil infiltration rates (cmh-1) and textural classes in the Thiruparankundram block of Madurai district. Further, the utility of the spectral subsets, both independently and in combination with other SCORPAN variables, was studied to perceive the efficiency of the framework and to determine the integration potential of spatial variables from multiple modalities. A total of 224 soil observations were derived from the legacy soil maps using a stratified random sampling procedure. The extracted soil and the covariate information were then subjected to the random forest algorithm for the mapping process. To mitigate the redundancy effect of the PRISMA spectral variables, supervised band selection techniques-viz., Recursive Feature Elimination (RFE), Boruta, Variable Selection Using Random Forest (VSURF), and Genetic Algorithm (GA)-were utilized to derive the optimal bands for the prediction process. The efficiency of the models trained for each subset was determined using data partitioning and repeated k-fold cross-validation techniques (10 folds; 10 repetitions) with several validation metrics opted for continuous and categorical variables. Among the spectral subsets utilized, the PRISMA bands selected through embedded selection methods (Boruta and VSURF) and the Landsat 8 spectral datasets under both validation strategies had the highest efficiency in predicting the soil infiltration and textural classes, respectively. Further, the variable importance measure determined for both continuous and categorical predictions through the permutation feature importance (PFI) indicated that Physiography, Geomorphology, Land Use and Land Cover, Multiresolution Ridge Top Flatness (MRRTF), and Multiresolution Valley Bottom Flatness (MRVB), among others, made the highest contribution towards the entire modelling process.

Abstract Ovarian leiomyoma is an extremely rare benign tumor often diagnosed incidentally due to its nonspecific clinical and radiologic features. We present the case of a 48-year-old woman with progressive lower abdominal pain, distention, and genitourinary complaints. Imaging revealed a large complex adnexal mass with both solid and cystic components, seen on ultrasound, CT, and MRI, raising suspicion for a neoplastic process. Despite the use of multiple imaging modalities, definitive diagnosis required histopathological confirmation following surgical resection, which revealed an ovarian leiomyoma with cystic and myxoid degenerative changes. This case underscores the importance of considering ovarian leiomyoma in the differential diagnosis of adnexal masses and highlights the complementary roles of imaging and histopathology in achieving an accurate diagnosis and guiding appropriate management.

Abstract Cross-domain artistic style conversion is a challenging task that requires integrating multiple modalities. Leveraging advanced Generative Adversarial Networks (GAN) architectures, this research aims to improve cross-domain style transfer by integrating multimodal fusion techniques. The objective is to develop an Intelligent Whale Optimized Time Series GAN (IWO-TSGAN) model for high-quality cross-domain artistic style conversion. The model aims to merge different modalities effectively to achieve accurate and coherent artistic transformations while preserving content and style consistency. Multimodal data was collected, comprising high-resolution images of artwork styles, textual descriptions, and audio narrations. Image preprocessing involved resizing for consistency. Text data underwent tokenization to convert descriptions into structured formats for input. Audio data was normalized to ensure uniformity across samples, enabling better fusion across different modalities for style conversion. Feature-level fusion is performed at the intermediate layer level, where extracted features from image, text, and audio modalities are combined. A novel technique inspired by the IWO Algorithm was used to fine-tune the GAN’s performance in cross-domain artistic style conversion. Using Python, the model achieved impressive results in cross-domain style conversion. Metrics such as SSIM (0.890), FID, and PSNR above 25dB, were used to evaluate image quality, showing a significant improvement over traditional models in handling multimodal fusion. The proposed IWO-TSGAN model successfully enhances cross-domain artistic style conversion by integrating multimodal data sources. The results demonstrate significant improvements in transfer quality, offering promising applications in digital art creation, multimedia content generation, and interactive media.

Multi-modal conversation emotion recognition (MCER) aims to recognize and track the speaker's emotional state using text, speech, and visual information. Compared with traditional single-utterance multi-modal emotion recognition or single-modal conversation emotion recognition, MCER is more challenging. It requires modeling complex emotional interactions and learning consistent and complementary semantics across multiple modalities. Although many deep learning-based approaches have been proposed for MCER, there is still a lack of systematic reviews summarizing existing modeling methods. Therefore, a timely and comprehensive overview of MCER's recent advances in deep learning is of great significance. In this survey, we provide a comprehensive overview of MCER modeling methods and roughly divide MCER methods into four categories, i.e., context-free modeling, sequential context modeling, speaker-differentiated modeling, and speaker-relationship modeling. Unlike conventional taxonomies based on modality combinations or task-stage decomposition, our framework focuses on how models structurally capture conversational dynamics, speaker roles, and emotional dependencies. In addition, we further discuss MCER's publicly available popular datasets, multi-modal feature extraction methods, application areas, existing challenges, and future development directions. We hope this review provides valuable insights into the current state of MCER research and inspires the development of more effective models.

Patients with end stage kidney disease undergoing hemodialysis (HD) experience high rates of hospitalizations and mortality, partly due to the incomplete removal of some toxic uremic molecules. To improve outcomes, multiple modalities of kidney replacement therapy have been developed, including high-flux HD and on-line hemodiafiltration (HDF). Notably, on-line high-volume HDF (HV-HDF) has demonstrated mortality benefits over high-flux HD in some randomized trials. This retrospective cohort study evaluated hospitalization outcomes among in-center dialysis patients treated with HV-HDF and high-flux HD at Fresenius Medical Care NephroCare centers across Europe, the Middle East, and Africa between January 2019 and December 2022. Data were extracted from the European Clinical Database. The primary outcome was all-cause hospitalization; secondary outcomes included cause-specific hospitalizations. Negative binomial regression was used to estimate incidence rate ratio (IRR) for hospital outcomes, incorporating inverse probability of treatment weighting (IPTW) to adjust for baseline differences between treatment groups. A total of 71,669 patients were included, with 45% receiving HD and 55% receiving HDF. During the follow-up period, patients in the HDF group underwent a total of 12,741,453 HDF treatments, with a mean convection volume of 25.8L. Compared to HD, treatment with HDF was associated with a lower incidence of both hospital admissions (adjusted IRR, 0.80; 95% confidence interval [CI], 0.79-0.82) and days spent in the hospital (adjusted IRR, 0.80; 95% CI, 0.78-0.82). These reductions were consistent across subgroups analyzed and across most major causes of hospitalization, including cardiovascular disease, infections, and fluid-related complications. In this large, real-world cohort spanning multiple regions and dialysis centers, HV-HDF was associated with significantly lower rates of both hospital admissions and days spent in the hospital compared to treatment with high-flux HD. These findings suggest that HV-HDF may have the potential to reduce morbidity in patients with ESKD.

Introduction: Giant cell tumor of bone typically arises from the epiphysis of long bones; involvement of the distal tibia is a relative rarity, especially in adolescents. While this tumor is benign, GCTB may behave quite aggressively with recurrence or even pulmonary metastasis. The case below describes the natural history of a distal tibial GCTB that was complicated by recurrence and lung metastasis, detailing the use of multiple modalities of management. Case presentation: A 17-year-old female patient presented with an eight-month history of progressive swelling and pain in the left ankle. Imaging showed an expansile lytic lesion in the distal tibia; biopsy confirmed GCTB. She then underwent wide excision with reconstruction using a fibular graft and talofibular arthrodesis. Two years later, during surveillance imaging, pulmonary nodules consistent with metastasis were shown; she was thus treated with monthly intravenous zoledronic acid, 4 mg for six months. In 2019, a local recurrence was detected and treated with curettage and augmentation with bone cement. On follow-up in 2021, the patient had no pain, was fully ambulatory, and was without further recurrence or metastatic progression. Discussion: Distal tibial GCTB has a high tendency for recurrence despite adequate resection due to the poor soft-tissue cover surrounding it. Though pulmonary metastasis is rare, the case indicates the importance of long-term thoracic surveillance. Zoledronic acid in this case contributed to the radiological stabilization of metastatic lesions and thus appears as a possible adjunct in recurrent or metastatic GCTB. Conclusion: This case illustrates the indolent course of the distal tibial GCTB and represents an example of tailored multi-modality treatment with extended follow-up. Zoledronic acid may offer effective disease stabilization to a highly selected patient population at high risk. Keywords: Giant cell tumor, progression, recurrence, distal tibia, fibular graft, arthrodesis

Hair cells are the sensory receptors of the auditory and vestibular systems in the inner ears of all vertebrates. Hair cells also serve to detect water flow in the lateral line system in amphibians and fish. The zebrafish lateral line serves as a well-established model for investigating hair cell development and function, including research on genetic mutations associated with deafness and environmental factors that cause hair cell damage. Rheotaxis, the ability to orient and swim in response to water flow, is a behavior mediated by multiple sensory modalities, including the lateral line organ. In this protocol, we describe a rheotaxis assay in which station holding behavior, which employs positive rheotaxis to maintain position in oncoming water flow, serves as a sensitive measure of lateral line function in larval zebrafish. This assay provides a valuable tool for researchers assessing the functional consequences of genetic or environmental disruptions of the lateral line system.Key features• Describes the method developed by Newton et al. [1] to assess lateral line function in larval zebrafish.• Provides instructions on building the micro flume apparatus with updated information from the WashU Neurotech Hub.• Uses DeepLabCut to track fish and SimBA to classify rheotaxis to compare lateral line–mediated behaviors in large cohorts of larval zebrafish.