Skip to main content
Search

Inserm

12 related articles

Subscribe to updates
  1. H&E slides skip spatial transcriptomics: ALHENA distills cell and neighborhood similarity, reaching 0.341 patient-level signature correlation

    ALHENA distills spatial transcriptomic information into a routine H&E encoder that reads only images at inference. Rather than regressing individual genes, it trains the H&E representation to match the sample-to-sample similarity structure of two frozen transcriptomic models at cell and neighborhood scales. Across 110 cancer-type and signature combinations in TCGA, mean Spearman correlation was 0.341 versus 0.161 for unadapted UNI2-h; on the Thunder pathology benchmark the median change was −0.004.

  2. bioRxiv

    A snapshot can rank a mouse's age: within-session ordering hits 65%, and mice that look older are frailer with 14% higher death hazard

    A laboratory mouse's age can be read from an ordinary photograph, but what transfers is relative age rather than absolute age. Across 2,846 photographs of 1,292 mice from seven facilities, a frozen DINOv2 vision model with ridge regression predicted age; on unseen facilities the median absolute error was 138 days, yet within a session the older of two mice was ranked older in 65% of pairs, rising above 95% for age gaps over 500 days. Mice predicted older than their age were frailer, with each 100 days of photographic age gap linked to 0.12 SD more frailty and a 14% higher hazard of death.

  3. medRxiv

    Is a new gene link actually new? PESTO sorts 940 associations into four evidence tiers and calls 7% novel

    Rare-variant studies now yield more significant gene-phenotype associations than teams can place against prior evidence, and that placement has become the tighter bottleneck. PESTO combines large language model literature curation with structured Open Targets genetic evidence in one agentic pipeline that assigns Novel, Hypothesized, Existing or Established with supporting citations. Across 940 unique associations from two rare-variant studies, 7% were called Novel and 21% Hypothesized; 86% of 50 randomly paired negative controls fell into those two tiers.

  4. arXiv

    A CT foundation model built for cancer patients' chest-abdomen-pelvis scans lifts AUC to 0.767 from 0.695

    CAPTOR, a vision-language foundation model pretrained on 25,512 chest-abdomen-pelvis CT-report pairs from cancer-focused exams, outperformed existing CT foundation models in its target setting. Disease classification reached an AUC of 0.767 versus 0.695 for the next-best model on the full chest-abdomen-pelvis subset, and 0.784 versus 0.734 on the oncologic subset. It encodes organ-centered crops of whole exams but makes study-level, not lesion-level, judgments.

  5. AI advice for colorectal liver metastases moves beyond prompting: encoding the surgeon's reasoning lifted overall concordance from 0.444 to 0.626

    Decisions in colorectal liver metastases weigh tumor biology, resectability and future liver remnant, and large language models previously produced recommendations from prompting alone with limited agreement with expert multidisciplinary practice. The METATRON study formalized the evaluation sequence hepatobiliary surgeons follow at tumor boards into a structured workflow and combined it with guideline retrieval, testing 110 synthetic vignettes scored by three independent LLM judges across five dimensions. The workflow-plus-retrieval strategy reached the highest composite score (0.626 versus 0.444 for baseline), yet sensitivity for anatomical resectability remained 40%, insufficient for autonomous clinical use.

  6. bioRxiv

    3D microscopy segmentation stops at voxel masks: Nagini3D writes each cell as a parametric surface and edges past StarDist3D on boundary IoU

    Segmenting cells in 3D fluorescence microscopy has meant choosing between two paths: deep learning is efficient but returns discrete voxel masks, while active surfaces give continuous shape but struggle with multiple objects. Nagini3D joins them, using a 3D U-Net to predict both object locations and spline surface parameters, so each object is one closed smooth parametric surface. On the synthetic CAPS set of non-star-convex objects, the refined Nagini3D+ reaches a mean IoU of 0.859 against StarDist3D's 0.779; on the real BONES set the two are close, but Nagini3D is the fastest tested, at 4.75 seconds on average.

  7. arXiv

    HyperNSDE writes static baselines into a neural SDE drift via a hypernetwork, improving observation-time fidelity on simulated and real clinical data

    The authors propose HyperNSDE, a continuous-time generative model that encodes heterogeneous static covariates with an HI-VAE, maps the static latent representation through a hypernetwork to subject-specific drift parameters driving a latent Neural SDE, and jointly models observation times with a latent-state-dependent intensity process, trained via a deterministic–stochastic path decomposition with a signature-kernel objective; on simulated data and the VELOUR and PPMI cohorts it achieves better observation-time fidelity and several distributional and privacy metrics, while forecasting and correlation performance is mixed and affected by observation-grid regularity and trajectory smoothness.

  8. arXiv

    Splitting prompt dependence into prompt ambiguity and local sensitivity yields two low-correlated metrics that both correlate negatively with gynecological pelvic MRI segmentation quality

    The work introduces the first framework that explicitly disentangles prompt dependence into prompt ambiguity (inter-user variability) and local sensitivity (interaction imprecision): a mixture density network models the image-conditioned distribution of plausible prompts and quantifies ambiguity by the trace of its covariance, while a stability margin captures the minimal perturbation under measurement noise needed to induce a mask change; evaluated on two female pelvic T2-weighted MRI datasets, UT-EndoMRI (81 patients with endometriosis, uterus segmentation) and MOGaMBO (94 patients with locally advanced cervical cancer, bladder segmentation), with MobileSAM and MedSAM, the two metrics correlate significantly and negatively with Dice, correlate little with each other, and conditional samp

  9. arXiv

    IMaX swaps the marginal entropy term of mutual information for a Tsallis α-entropy, lifting accuracy by up to 7.3 points on ESCA and retinal datasets under long-tailed semi-supervised domain generalization

    The work shows that semi-supervised domain generalization methods such as FBCSA and DGWM degrade substantially under long-tailed class distributions, and proposes IMaX: maximizing the mutual information between learned features and latent labels under supervision constraints from labeled samples, while replacing the standard marginal entropy term with a Tsallis α-entropy to relax the class-balance assumption; across two modalities (ESCA histopathology and diabetic retinopathy grading), three SSL frameworks and three SSDG methods, IMaX improves accuracy in all but one setting, with gains up to 7.3 points in the low-label regime (mL=5).

  10. AI-assisted handheld echocardiography for hospital bedside cardiac triage: the prospective OPTIMUST implementation study

    OPTIMUST was a prospective, single-center implementation study in which physicians without formal echocardiography certification completed a structured two-month curriculum and performed focused examinations using Caption AI-enabled handheld ultrasound on cardiology and non-cardiology wards; of 287 attempted examinations, 206 (71.8%) were analyzable, operator assessment correlated with expert review of the same handheld image sets for LVEF (r = 0.84), filling-pressure category agreement gave a quadratic weighted κ of 0.659, physicians reported that handheld findings changed or confirmed management in 93.7% of examinations, and 32.8% underwent comprehensive echocardiography within one month.