Skip to main content

Medicine & Health

463 items

  1. arXiv

    ProSMA-UNet replaces U-Net skip gating with an ℓ1 proximal sparse gate, reporting best results across 2D and 3D medical segmentation benchmarks and about a 19% F1 gain on 3D colon.

    The work proposes ProSMA-UNet, which recasts skip connections in U-shaped medical segmentation networks as a decoder-conditioned sparse feature selection problem: it builds a multi-scale encoder-decoder compatibility field with lightweight depthwise dilated convolutions, applies an ℓ1 proximal operator with learnable per-channel thresholds to yield a closed-form soft-thresholding gate, and adds decoder-conditioned channel gating driven by global decoder context, reporting best results on three 2D benchmarks (BUSI, GlaS, Kvasir-SEG) and two 3D benchmarks (Spleen and Colon from the Medical Segmentation Decathlon), with roughly a 19% relative F1 gain over the strongest baseline on Colon.
  2. Research Square

    Life Whisperer AI blastocyst assessment predicted implantation across 340 frozen embryo transfer cycles with AUC 0.91, but concordance with PGT-A was only κ=0.257

    This retrospective cohort study analyzed 340 frozen embryo transfer cycles at Indira IVF Fertility Centre, Delhi, India, between January 2022 and December 2024, assessing Day 5 blastocysts with both conventional Gardner morphological grading and Life Whisperer™ AI-based viability scoring, with implantation success determined by serum β-hCG positivity; 237 of 340 embryos (69.7%) implanted successfully, AI viability scores showed independent predictive performance (implantation rising from 53.5% in low viability to 74.2% in high viability, with an area under the ROC curve of 0.91), while AI-derived genetic prediction showed only fair concordance with PGT-A (Cohen's κ = 0.257).
  3. arXiv

    DCD raises compressed 3D MRI segmentation mDice from 63.60% to 68.51% on BraTS 2024 and to 73.95% on ISLES 2022 while cutting parameters from 101.9M to 6.4M

    The authors propose Detail Consistent Distillation (DCD), which applies a 3D discrete wavelet transform to teacher and student encoder features at every stage during training and aligns only the directional detail subband D (excluding the low-frequency approximation A and the most noise-prone extreme high-frequency band S) after inverse-wavelet reconstruction in the spatial domain, raising the mDice of a 4x channel-reduced student from 63.60% to 68.51% on BraTS 2024 and from 70.21% to 73.95% on ISLES 2022 with no inference-time overhead.
  4. 发表出处待核验

    When three LDL-C equations disagree at thresholds, accuracy falls to 48%-61%, and an interpretable calibration model raises classification accuracy by 19-25 percentage points

    Using direct LDL-C as the reference standard across 10,799 All of Us lipid panels, this study classified panels as Agree or Disagree at the 70, 100, and 130 mg/dL thresholds for three LDL-C estimation equations (Friedewald, Sampson/NIH, Martin-Hopkins), finding accuracy of 92%-96% when equations agreed (86%-92% of panels) versus 48%-61% when they disagreed (8%-14%); it then introduced an interpretable regime-aware calibration model with a mean absolute error of 8.98 mg/dL, matching the best machine learning ensemble (9.01 mg/dL; 95% CI for the difference, -0.35 to 0.29 mg/dL), which in 14,549 external MIMIC-IV panels outperformed the best-performing individual equation at each threshold by 3.5-9.0 percentage points and the majority vote by 18.5-25.
  5. Mendeley Data

    Shank3-deficient rats show a sign-inverted accumbal dopamine response during pouncing, and closed-loop optogenetic VTA-NAc stimulation persistently lengthens social play

    Using nine-camera volumetric imaging, Social-Seq behavioral syllable parsing, and GRAB-DA3m fiber photometry in PND 35-85 wild-type and Shank3+/- rats during same-sex dyadic interaction, this study characterized nucleus accumbens dopamine dynamics, finding that wild-type males show dopamine surges during proactive play such as pouncing and pinning while forced submission suppresses dopamine, wild-type females show increases during evasion and rearing but not contact-heavy play, Shank3 mutants show blunted responses during sniffing and chasing and a sign-inverted dopamine response during pouncing, a multi-agent reinforcement learning model parameterized with empirical dopamine amplitudes reproduced the mutant phenotype, and closed-loop optogenetic stimulation of VTA-NAc established causal s
  6. Nature Communications

    SpaCEy links tissue spatial patterns to clinical outcomes with an explainable graph neural network, improving prediction and surfacing spatial markers in lung and breast cancer cohorts

    The authors present SpaCEy (Spatial Clinical Explainability), an explainable graph neural network that builds each tissue sample into a spatial graph via Delaunay triangulation, with nodes as single-cell protein-marker abundances and no predefined cell-type or anatomical-region inputs, learns predictive embeddings with a GNN, and uses a GNNExplainer-style explainer to output edge masks that are aggregated over k-hop neighbourhoods into node importance, thereby localising contiguous outcome-associated spatial regions and key proteins; it predicted progression in a 416-patient lung adenocarcinoma cohort (accuracy 0.68, F1 0.68, AUC 0.62, versus Ali et al. 0.61/0.59/0.57 and SPACE-GM 0.55/0.52/0.
  7. arXiv

    SEER uses skill-evolving image-grounded reasoning to lift worst-case Dice from 79.34 to 95.47 and cut standard deviation to 0.98 in free-text-prompted 3D medical segmentation

    The work proposes SEER, a framework that curates the skill-tagged, image-grounded reasoning-trace dataset SEER-Trace (22,330 multimodal instruction instances from 1,811 cases), extracts anatomical evidence and synthesizes an executable task specification at inference, and uses SEER-Loop to distill high-reward reasoning episodes into reusable skills stored in SEER-Bank, thereby improving accuracy and stability in free-text-promptable 3D medical image segmentation, reporting an 81.94% reduction in performance variance and an 18.60% improvement in worst-case Dice under linguistic perturbations.
  8. arXiv

    NeuroSymb-MRG generates radiology reports via differentiable abductive reasoning and active uncertainty minimization, raising BLEU-1 to 0.602 on IU X-ray and 0.487 on MIMIC-CXR

    The work presents NeuroSymb-MRG, a framework that maps image features to probabilistic clinical concepts, composes multi-hop abductive reasoning chains through a differentiable logic layer (product t-norm AND, probabilistic sum OR, learnable gating α), decodes those chains into roughly 120 clause templates augmented with retrieved evidence and constrained LLM paraphrasing, and drives clinician-in-the-loop review with active sampling based on rule-level predictive entropy (5 MC-dropout passes) plus k-center diversity (k=16 per round); on IU X-ray and MIMIC-CXR it improves BLEU-1 through BLEU-4, ROUGE-L and METEOR over the listed representative baselines, for example IU X-ray BLEU-1 of 0.602 and MIMIC-CXR BLEU-1 of 0.487.
  9. arXiv

    CARE's contrastive multi-agent adjudication lifts zero-shot melanoma-vs-atypical-nevus accuracy from 66.5% to 77.6%, but still trails Gemini-3-Pro on chest X-rays

    In a zero-shot, training-free, tool-free setting, the authors benchmark multimodal LLM agents on two imaging-only proxy tasks (melanoma vs. atypical nevus and pulmonary edema vs. pneumonia) and propose CARE, a multi-agent framework in which two disease-specific agents generate opposing evidence and a third judge adjudicates it against the original image; CARE raises Gemini-3-Flash accuracy from 66.5% to 77.6% (Youden 0.552) on dermoscopy and from 60.2% to 64.6% on chest X-rays, yet remains below Gemini-3-Pro's 70.9% on the chest task and overall below clinical deployment requirements.
  10. arXiv

    UniField merges 64mT-to-3T and 3T-to-7T brain MRI enhancement into one framework, gaining about 1.81 dB PSNR and 9.47% SSIM on average

    The work proposes UniField, a unified multi-modality, multi-task MRI field-strength enhancement framework that consolidates T1, T2, and FLAIR modalities and cross-field tasks such as 64mT-to-3T and 3T-to-7T into a single model, embeds 3D structural priors by operating in the latent space of the pretrained video super-resolution model FlashVSR with LoRA fine-tuning, and introduces a Field-Aware Spectral Rectification Mechanism (FASRM) that adjusts low-, mid-, and high-frequency loss weights according to the physical properties of the source and target fields; it also organizes and publicly releases a paired multi-field MRI dataset from five institutions that is an order of magnitude larger than existing benchmarks, reporting average improvements of about 1.81 dB in PSNR and 9.

Page 14 · showing 10