The rapid increase in the number of Computed Tomography (CT) scan examinations has created an urgent need for automated tools, such as organ segmentation, anomaly classification, and report generation, to assist radiologists with their growing workload. Multi-label classification of Three-Dimensional (3D) CT scans is a challenging task due to the volumetric nature of the data and the variety of anomalies to be detected. Existing deep learning methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies effectively, while Vision Transformers require extensive pre-training, posing challenges for practical use. Additionally, these existing methods do not explicitly model the radiologist's navigational behavior while scrolling through CT scan slices, which requires both global context understanding and local detail awareness. In this study, we present CT-Scroll, a novel global-local attention model specifically designed to emulate the scrolling behavior of radiologists during the analysis of 3D CT scans. Our approach is evaluated on two public datasets, demonstrating its efficacy through comprehensive experiments and an ablation study that highlights the contribution of each model component.

Early detection of cervical cancer is crucial for improving patient outcomes and reducing mortality by identifying precancerous lesions as soon as possible. As a result, the use of pap smear screening has significantly increased, leading to a growing demand for automated tools that can assist cytologists managing their rising workload. To address this, the Pap Smear Cell Classification Challenge (PS3C) has been organized in association with ISBI in 2025. This project aims to promote the development of automated tools for pap smear images classification. The analyzed images are grouped into four categories: healthy, unhealthy, both, and rubbish images which are considered as unsuitable for diagnosis. In this work, we propose a two-stage ensemble approach: first, a neural network determines whether an image is rubbish or not. If not, a second neural network classifies the image as containing a healthy cell, an unhealthy cell, or both.

Current interstitial techniques of tumor ablation face challenges that ultrasound technologies could meet. The ablation radius and directionality of the ultrasound beam could improve the efficiency and precision. Here, a 9gauge MR-compatible dual-mode ultrasound catheter prototype was experimentally evaluated for Ultrasound Imageguided High Intensity Focused Ultrasound (USgHIFU) conformal ablations. The prototype consisted of 64 piezocomposite linear array elements and was driven by an open research programmable dual-mode ultrasound platform. After verifying the US-image guidance capabilities of the prototype, the HIFU output performances (dynamic focusing and HIFU intensities) were quantitatively characterized, together with the associated 3D HIFU-induced thermal heating in tissue phantoms (using MR thermometry). Finally, the ability to produce robustly HIFU-induced thermal ablations in in-vitro liver was studied experimentally and compared to numerical modeling. Investigations of several HIFU dynamic focusing allowed overcoming the challenges of miniaturizing the device: mono-focal focusing maximized deep energy deposition, while multi-focal strategies eliminated grating lobes. The linear-array design of the prototype made it possible to produce interstitial ultrasound images of tissue and tumor mimics in situ. Multi-focal pressure fields were generated without grating lobes and transducer surface intensities reached up to Isapa =14 W$\bullet$cm -2 . Seventeen elementary thermal ablations were performed in vitro. Rotation of the catheter proved the directionality of ablation, sparing non-targeted tissue. This experimental proof of concept demonstrates the feasibility of treating volumes comparable to those of primary solid tumors with a miniaturized USgHIFU catheter whose dimensions are close to those of tools traditionally used in interventional radiology, while offering new functionalities.

Fully supervised deep models have shown promising performance for many medical segmentation tasks. Still, the deployment of these tools in clinics is limited by the very timeconsuming collection of manually expert-annotated data. Moreover, most of the state-ofthe-art models have been trained and validated on moderately homogeneous datasets. It is known that deep learning methods are often greatly degraded by domain or label shifts and are yet to be built in such a way as to be robust to unseen data or label distributions. In the clinical setting, this problematic is particularly relevant as the deployment institutions may have different scanners or acquisition protocols than those from which the data has been collected to train the model. In this work, we propose to address these two challenges on the detection of clinically significant prostate cancer (csPCa) from bi-parametric MRI. We evaluate the method proposed by (Kervadec et al., 2018), which introduces a size constaint loss to produce fine semantic cancer lesions segmentations from weak circle scribbles annotations. Performance of the model is based on two public (PI-CAI and Prostate158) and one private databases. First, we show that the model achieves on-par performance with strong fully supervised baseline models, both on in-distribution validation data and unseen test images. Second, we observe a performance decrease for both fully supervised and weakly supervised models when tested on unseen data domains. This confirms the crucial need for efficient domain adaptation methods if deep learning models are aimed to be deployed in a clinical environment. Finally, we show that ensemble predictions from multiple trainings increase generalization performance.

Clinical outcome prediction plays an important role in stroke patient management. From a machine learning point-of-view, one of the main challenges is dealing with heterogeneous data at patient admission, i.e. the image data which are multidimensional and the clinical data which are scalars. In this paper, a multimodal convolutional neural network - long short-term memory (CNN-LSTM) based ensemble model is proposed. For each MR image module, a dedicated network provides preliminary prediction of the clinical outcome using the modified Rankin scale (mRS). The final mRS score is obtained by merging the preliminary probabilities of each module dedicated to a specific type of MR image weighted by the clinical metadata, here age or the National Institutes of Health Stroke Scale (NIHSS). The experimental results demonstrate that the proposed model surpasses the baselines and offers an original way to automatically encode the spatio-temporal context of MR images in a deep learning architecture. The highest AUC (0.77) was achieved for the proposed model with NIHSS.

Contacts between patients, patients and health care workers (HCWs) and among HCWs represent one of the important routes of transmission of hospital-acquired infections (HAI). A detailed description and quantification of contacts in hospitals provides key information for HAIs epidemiology and for the design and validation of control measures. We used wearable sensors to detect close-range interactions ("contacts") between individuals in the geriatric unit of a university hospital. Contact events were measured with a spatial resolution of about 1.5 meters and a temporal resolution of 20 seconds. The study included 46 HCWs and 29 patients and lasted for 4 days and 4 nights. 14037 contacts were recorded. The number and duration of contacts varied between mornings, afternoons and nights, and contact matrices describing the mixing patterns between HCW and patients were built for each time period. Contact patterns were qualitatively similar from one day to the next. 38% of the contacts occurred between pairs of HCWs and 6 HCWs accounted for 42% of all the contacts including at least one patient, suggesting a population of individuals who could potentially act as super-spreaders. Wearable sensors represent a novel tool for the measurement of contact patterns in hospitals. The collected data provides information on important aspects that impact the spreading patterns of infectious diseases, such as the strong heterogeneity of contact numbers and durations across individuals, the variability in the number of contacts during a day, and the fraction of repeated contacts across days. This variability is associated with a marked statistical stability of contact and mixing patterns across days. Our results highlight the need for such measurement efforts in order to correctly inform mathematical models of HAIs and use them to inform the design and evaluation of prevention strategies.

Segmentation of medical images is a fundamental task with numerous applications. While MRI, CT, and PET modalities have significantly benefited from deep learning segmentation techniques, more recent modalities, like functional ultrasound (fUS), have seen limited progress. fUS is a non invasive imaging method that measures changes in cerebral blood volume (CBV) with high spatio-temporal resolution. However, distinguishing arterioles from venules in fUS is challenging due to opposing blood flow directions within the same pixel. Ultrasound localization microscopy (ULM) can enhance resolution by tracking microbubble contrast agents but is invasive, and lacks dynamic CBV quantification. In this paper, we introduce the first deep learning-based segmentation tool for fUS images, capable of differentiating signals from different vascular compartments, based on ULM automatic annotation and enabling dynamic CBV quantification. We evaluate various UNet architectures on fUS images of rat brains, achieving competitive segmentation performance, with 90% accuracy, a 71% F1 score, and an IoU of 0.59, using only 100 temporal frames from a fUS stack. These results are comparable to those from tubular structure segmentation in other imaging modalities. Additionally, models trained on resting-state data generalize well to images captured during visual stimulation, highlighting robustness. This work offers a non-invasive, cost-effective alternative to ULM, enhancing fUS data interpretation and improving understanding of vessel function. Our pipeline shows high linear correlation coefficients between signals from predicted and actual compartments in both cortical and deeperregions, showcasing its ability to accurately capture blood flow dynamics.

With the increasing number of CT scan examinations, there is a need for automated methods such as organ segmentation, anomaly detection and report generation to assist radiologists in managing their increasing workload. Multi-label classification of 3D CT scans remains a critical yet challenging task due to the complex spatial relationships within volumetric data and the variety of observed anomalies. Existing approaches based on 3D convolutional networks have limited abilities to model long-range dependencies while Vision Transformers suffer from high computational costs and often require extensive pre-training on large-scale datasets from the same domain to achieve competitive performance. In this work, we propose an alternative by introducing a new graph-based approach that models CT scans as structured graphs, leveraging axial slice triplets nodes processed through spectral domain convolution to enhance multi-label anomaly classification performance. Our method exhibits strong cross-dataset generalization, and competitive performance while achieving robustness to z-axis translation. An ablation study evaluates the contribution of each proposed component.

Biological systems are non-linear, include unobserved variables and the physical principles that govern their dynamics are partly unknown. This makes the characterization of their behavior very challenging. Notably, their activity occurs on multiple interdependent spatial and temporal scales that require linking mechanisms across scales. To address the challenge of bridging gaps between scales, we leverage partial differential equations (PDE) discovery. PDE discovery suggests meso-scale dynamics characteristics from micro-scale data. In this article, we present our framework combining particle-based simulations and PDE discovery and conduct preliminary experiments to assess equation discovery in controlled settings. We evaluate five state-of-the-art PDE discovery methods on particle-based simulations of calcium diffusion in astrocytes. The performances of the methods are evaluated on both the form of the discovered equation and the forecasted temporal variations of calcium concentration. Our results show that several methods accurately recover the diffusion term, highlighting the potential of PDE discovery for capturing macroscopic dynamics in biological systems from microscopic data.

Intraventricular vector flow mapping (iVFM) seeks to enhance and quantify color Doppler in cardiac imaging. In this study, we propose novel alternatives to the traditional iVFM optimization scheme by utilizing physics-informed neural networks (PINNs) and a physics-guided nnU-Net-based supervised approach. When evaluated on simulated color Doppler images derived from a patient-specific computational fluid dynamics model and in vivo Doppler acquisitions, both approaches demonstrate comparable reconstruction performance to the original iVFM algorithm. The efficiency of PINNs is boosted through dual-stage optimization and pre-optimized weights. On the other hand, the nnU-Net method excels in generalizability and real-time capabilities. Notably, nnU-Net shows superior robustness on sparse and truncated Doppler data while maintaining independence from explicit boundary conditions. Overall, our results highlight the effectiveness of these methods in reconstructing intraventricular vector blood flow. The study also suggests potential applications of PINNs in ultrafast color Doppler imaging and the incorporation of fluid dynamics equations to derive biomarkers for cardiovascular diseases based on blood flow.

This paper describes an original experimental procedure to measure the mechanical interaction between the tongue and teeth and palate during speech production. It consists in using edentulous people as subjects and to insert pressure sensors in the structure of their complete dental prosthesis. Hence, there is no perturbation of the vocal tract cavity due to the sensors themselves. Several duplicates are used with transducers situated at different locations of the complete denture according to palatography's results, in order to carefully analyze the production of specific sounds such as stop consonants.. It is also possible to measure the contact pressure at different locations on the palate for the same sound.

Improving the future of healthcare starts by better understanding the current actual practices in hospital settings. This motivates the objective of discovering typical care pathways from patient data. Revealing typical care pathways can be achieved through clustering. The difficulty in clustering care pathways, represented by sequences of timestamped events, lies in defining a semantically appropriate metric and clustering algorithms. In this article, we adapt two methods developed for time series to the clustering of timed sequences: the drop-DTW metric and the DBA approach for the construction of averaged time sequences. These methods are then applied in clustering algorithms to propose original and sound clustering algorithms for timed sequences. This approach is experimented with and evaluated on synthetic and real-world data.

Neuroblastoma, is a highly heterogeneous pediatric tumour and is responsible for 15% of pediatric cancer-related deaths. The clinical outcomes can vary from spontaneous regression to high metastatic disease. This extracranial tumour arises from a neural crest-derived cell and can harbor different phenotypes. Its heterogeneity may result from variations in differentiation states influenced by genetic and epigenetic factors and individual patient characteristics. This leads downstream to disruption of homeostasis and a metabolic shift in response to the tumour needs. Nutrition can play a key role in influencing various aspects of a tumour behaviour. This review provides an in-depth exploration of the aetiology of neuroblastoma and the different avenues of disease progression, which can be targeted with individualized nutrition intervention strategies to improve the well-being of children and optimize clinical outcomes.

Osteolytic metastases located in the vertebrae reduce strength and enhance the risk of vertebral fractures. This risk can be predicted by means of validated finite element models, but their reproducibility needs to be assessed. For that purpose, experimental data are requested. The aim of this study was to conduct open-access experiments on vertebrae, with artificial defect representing lytic metastasis and using well-defined boundary conditions. Twelve lumbar vertebral bodies (L1) were prepared by removing the cortical endplates and creating defects that represent lytic metastases, by drilling the cancellous bone. Vertebral bodies were scanned using clinical High Resolution peripherical Quantitative Computed Tomography before and after defect creation for 3D reconstruction. The specimens were then tested under compression loading until failure. Surface Digital Image Correlation was used to assess strain fields on the anterior wall of the vertebral body. These data (biomechanics data and the tomographic images needed to build subject-specific models) are shared with the scientific community in order to assess different vertebral models on the same dataset.

We introduce a particle-based framework inspired by smoothed particle hydrodynamics (SPH) to simulate the dynamics of a continuous field of coupled phase oscillators. This methodology discretizes the spatial domain into particles and employs a smoothing kernel to model non-local interactions, enabling the exploration of how spatial heterogeneities and interaction ranges influence the synchronization and pattern formation of coupled phase oscillators. Notably, we observe the emergence of spatially localized synchronization clusters, providing evidence for spontaneous local synchronization in these systems. This local synchronization refers to the transition from an initially homogeneous state, where no preferred spatial organization exists, to one where structured synchronization patterns emerge due to local interactions. Our results advance the theoretical understanding of spatiotemporal synchronization and demonstrate the utility of SPH-inspired techniques for modeling complex, spatially distributed systems. These findings are particularly relevant to applications where spatial interactions drive collective dynamics, such as in neural systems, ecosystems, power grids, social models, chemical oscillators, and climate systems, as well as in condensed matter and collective phenomena involving synchronization.

IntroductionThe free and cued selective reminding test is used to identify memory deficits in mild cognitive impairment and demented patients. It allows assessing three processes: encoding, storage, and recollection of verbal episodic this http URL investigated the neural correlates of these three memory processes in a large cohort study. The Memento cohort enrolled 2323 outpatients presenting either with subjective cognitive decline or mild cognitive impairment who underwent cognitive, structural MRI and, for a subset, fluorodeoxyglucose--positron emission tomography this http URL was associated with a network including parietal and temporal cortices; storage was mainly associated with entorhinal and parahippocampal regions, bilaterally; retrieval was associated with a widespread network encompassing frontal this http URL neural correlates of episodic memory processes can be assessed in large and standardized cohorts of patients at risk for Alzheimer's disease. Their relation to pathophysiological markers of Alzheimer's disease remains to be studied.

Purpose: Bone metastasis have a major impact on the quality of life of patients and they are diverse in terms of size and location, making their segmentation complex. Manual segmentation is time-consuming, and expert segmentations are subject to operator variability, which makes obtaining accurate and reproducible segmentations of bone metastasis on CT-scans a challenging yet important task to achieve. Materials and Methods: Deep learning methods tackle segmentation tasks efficiently but require large datasets along with expert manual segmentations to generalize on new images. We propose an automated data synthesis pipeline using 3D Denoising Diffusion Probabilistic Models (DDPM) to enchance the segmentation of femoral metastasis from CT-scan volumes of patients. We used 29 existing lesions along with 26 healthy femurs to create new realistic synthetic metastatic images, and trained a DDPM to improve the diversity and realism of the simulated volumes. We also investigated the operator variability on manual segmentation. Results: We created 5675 new volumes, then trained 3D U-Net segmentation models on real and synthetic data to compare segmentation performance, and we evaluated the performance of the models depending on the amount of synthetic data used in training. Conclusion: Our results showed that segmentation models trained with synthetic data outperformed those trained on real volumes only, and that those models perform especially well when considering operator variability.

This paper describes an original experimental procedure to measure mechanical interactions between tongue and teeth during speech production. Using edentulous people as subjects, pressure transducers are inserted in their complete denture duplicate. Physiology is respected during sound and pressure recording as with standard complete denture. Original calibration device is also described in order to know what kind of information can be extracted from the data. The measurements are realized in different experimental conditions in order to remove the auditory and the orosensory feedbacks. Then the first results of the pilot study are presented

We provide a protection system making use of encapsulation, messages communication, interface functions coming from an object oriented model described in previous works. Each user represents himself to the system by the mean of his "USER" object type. The recognition procedure is suitable to every one's needs. Any user's objects and types are labeled with a personal signature, exclusively provided and known by the system. Administrator's rights are restricted to backup procedures. The system verify each messages access, it is robust because partitioned, flexible, suitable and psychologically acceptable.