Medicine & Health

466 items

arXiv Sep 24, 2026
The work proposes a zero-shot 3D CT super-resolution framework: it first trains a diffusion model on abundant 2D X-ray data and uses DDNM/DDNM+ to upsample low-resolution CT projections into high-resolution projection priors, then applies a new Negative Alpha Blending Gaussian Splatting (NAB-GS) that models positive and negative Gaussian densities to learn the signed residual between diffusion-generated HR projections and upsampled LR projections for HR volume reconstruction; on the two public datasets UHRCT and MELA it achieves higher PSNR and SSIM than trilinear, cubic, NeRF, and CuNeRF zero-shot methods, is competitive with the supervised ArSSR, runs in about 15 minutes per volume, and two domain experts judged the 4× results to have clinical potential while 8× still needs improvement.
The work proposes a zero-shot 3D CT super-resolution framework: it first trains a diffusion model on abundant 2D X-ray data and uses DDNM/DDNM+ to upsample low-resolution CT projections into high-resolution projection priors, then applies a new Negative Alpha Blending Gaussian Splatting (NAB-GS) that models positive and negative Gaussian densities to learn the signed residual between diffusion-generated HR projections and upsampled LR projections for HR volume reconstruction; on the two public datasets UHRCT and MELA it achieves higher PSNR and SSIM than trilinear, cubic, NeRF, and CuNeRF zero-shot methods, is competitive with the supervised ArSSR, runs in about 15 minutes per volume, and two domain experts judged the 4× results to have clinical potential while 8× still needs improvement.
A zero-shot CT super-resolution framework that generates 2D projections with an X-ray diffusion prior and learns signed residuals via negative-density 3D Gaussians, outperforming CuNeRF in PSNR/SSIM on UHRCT and MELA
The work proposes a zero-shot 3D CT super-resolution framework: it first trains a diffusion model on abundant 2D X-ray data and uses DDNM/DDNM+ to upsample low-resolution CT projections into high-resolution projection priors, then applies a new Negative Alpha Blending Gaussian Splatting (NAB-GS) that models positive and negative Gaussian densities to learn the signed residual between diffusion-generated HR projections and upsampled LR projections for HR volume reconstruction; on the two public datasets UHRCT and MELA it achieves higher PSNR and SSIM than trilinear, cubic, NeRF, and CuNeRF zero-shot methods, is competitive with the supervised ArSSR, runs in about 15 minutes per volume, and two domain experts judged the 4× results to have clinical potential while 8× still needs improvement.
The work proposes a zero-shot 3D CT super-resolution framework: it first trains a diffusion model on abundant 2D X-ray data and uses DDNM/DDNM+ to upsample low-resolution CT projections into high-resolution projection priors, then applies a new Negative Alpha Blending Gaussian Splatting (NAB-GS) that models positive and negative Gaussian densities to learn the signed residual between diffusion-generated HR projections and upsampled LR projections for HR volume reconstruction; on the two public datasets UHRCT and MELA it achieves higher PSNR and SSIM than trilinear, cubic, NeRF, and CuNeRF zero-shot methods, is competitive with the supervised ArSSR, runs in about 15 minutes per volume, and two domain experts judged the 4× results to have clinical potential while 8× still needs improvement.
arXiv Sep 24, 2026
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
SRMA-Mamba lifts cirrhotic liver MRI segmentation to 92.95% mDSC on T1W and 86.25% on T2W in CirrMRI600+ while cutting compute
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
arXiv Sep 24, 2026
The work proposes TG-OT, a fully automatic CCTA-IVUS registration framework: lightweight CNNs first predict calcifications, bifurcations, and lumen radii on the topological (θ, z) cylinder (with the IVUS network additionally detecting guidewire artifacts), and the frozen detectors are then integrated directly into a differentiable registration pipeline that optimizes centerline warping parameters driven by an unbalanced Sinkhorn optimal transport loss on the cylindrical geometry plus a Dice term, complemented by a lumen radius matching term; on N=47 paired CCTA-IVUS cases from the IMPACT study at Erasmus University Medical Center in a 5-fold cross-validation setup, it reaches longitudinal Dicectl=0.99, rotational Sc=0.96, and lumen DiceL=0.
The work proposes TG-OT, a fully automatic CCTA-IVUS registration framework: lightweight CNNs first predict calcifications, bifurcations, and lumen radii on the topological (θ, z) cylinder (with the IVUS network additionally detecting guidewire artifacts), and the frozen detectors are then integrated directly into a differentiable registration pipeline that optimizes centerline warping parameters driven by an unbalanced Sinkhorn optimal transport loss on the cylindrical geometry plus a Dice term, complemented by a lumen radius matching term; on N=47 paired CCTA-IVUS cases from the IMPACT study at Erasmus University Medical Center in a 5-fold cross-validation setup, it reaches longitudinal Dicectl=0.99, rotational Sc=0.96, and lumen DiceL=0.
TG-OT matches features on a topological cylinder via unbalanced optimal transport, achieving fully automatic segmentation-free CCTA-IVUS registration on 47 paired cases (Dicectl=0.99, Sc=0.96, DiceL=0.69)
The work proposes TG-OT, a fully automatic CCTA-IVUS registration framework: lightweight CNNs first predict calcifications, bifurcations, and lumen radii on the topological (θ, z) cylinder (with the IVUS network additionally detecting guidewire artifacts), and the frozen detectors are then integrated directly into a differentiable registration pipeline that optimizes centerline warping parameters driven by an unbalanced Sinkhorn optimal transport loss on the cylindrical geometry plus a Dice term, complemented by a lumen radius matching term; on N=47 paired CCTA-IVUS cases from the IMPACT study at Erasmus University Medical Center in a 5-fold cross-validation setup, it reaches longitudinal Dicectl=0.99, rotational Sc=0.96, and lumen DiceL=0.
The work proposes TG-OT, a fully automatic CCTA-IVUS registration framework: lightweight CNNs first predict calcifications, bifurcations, and lumen radii on the topological (θ, z) cylinder (with the IVUS network additionally detecting guidewire artifacts), and the frozen detectors are then integrated directly into a differentiable registration pipeline that optimizes centerline warping parameters driven by an unbalanced Sinkhorn optimal transport loss on the cylindrical geometry plus a Dice term, complemented by a lumen radius matching term; on N=47 paired CCTA-IVUS cases from the IMPACT study at Erasmus University Medical Center in a 5-fold cross-validation setup, it reaches longitudinal Dicectl=0.99, rotational Sc=0.96, and lumen DiceL=0.
arXiv Sep 24, 2026
The work introduces an exemplar-free continual learning framework for whole-slide-image-to-report generation: it builds a compact domain footprint per domain in a frozen patch-embedding space (a k-means codebook, a slide-level code histogram bank, patch-count statistics, and a report-style prototype), uses it to synthesize pseudo-WSIs whose pseudo-reports come from an immediate teacher snapshot for generative replay, and conditions the language model through a style prefix; across multiple public continual learning benchmarks the approach outperforms exemplar-free and limited-buffer rehearsal baselines and supports domain-agnostic inference without explicit domain identifiers.
The work introduces an exemplar-free continual learning framework for whole-slide-image-to-report generation: it builds a compact domain footprint per domain in a frozen patch-embedding space (a k-means codebook, a slide-level code histogram bank, patch-count statistics, and a report-style prototype), uses it to synthesize pseudo-WSIs whose pseudo-reports come from an immediate teacher snapshot for generative replay, and conditions the language model through a style prefix; across multiple public continual learning benchmarks the approach outperforms exemplar-free and limited-buffer rehearsal baselines and supports domain-agnostic inference without explicit domain identifiers.
Compact domain footprints in a frozen embedding space enable generative replay for continual pathology report generation without storing slides or patch exemplars, outperforming exemplar-free and limited-buffer rehearsal baselines on multiple public continual learning benchmarks
The work introduces an exemplar-free continual learning framework for whole-slide-image-to-report generation: it builds a compact domain footprint per domain in a frozen patch-embedding space (a k-means codebook, a slide-level code histogram bank, patch-count statistics, and a report-style prototype), uses it to synthesize pseudo-WSIs whose pseudo-reports come from an immediate teacher snapshot for generative replay, and conditions the language model through a style prefix; across multiple public continual learning benchmarks the approach outperforms exemplar-free and limited-buffer rehearsal baselines and supports domain-agnostic inference without explicit domain identifiers.
The work introduces an exemplar-free continual learning framework for whole-slide-image-to-report generation: it builds a compact domain footprint per domain in a frozen patch-embedding space (a k-means codebook, a slide-level code histogram bank, patch-count statistics, and a report-style prototype), uses it to synthesize pseudo-WSIs whose pseudo-reports come from an immediate teacher snapshot for generative replay, and conditions the language model through a style prefix; across multiple public continual learning benchmarks the approach outperforms exemplar-free and limited-buffer rehearsal baselines and supports domain-agnostic inference without explicit domain identifiers.
arXiv Sep 24, 2026
The work proposes Dino U-Net: a frozen DINOv3 foundation backbone as encoder, combined with a dual-branch DINO Adapter and a Fidelity-Aware Projection Module (FAPM), which outperforms seven baseline methods on seven public medical image datasets spanning endoscopy, ultrasound, microscopy, MRI, fundus and CMR modalities, and shows performance improving as the backbone scales from S to 7B.
The work proposes Dino U-Net: a frozen DINOv3 foundation backbone as encoder, combined with a dual-branch DINO Adapter and a Fidelity-Aware Projection Module (FAPM), which outperforms seven baseline methods on seven public medical image datasets spanning endoscopy, ultrasound, microscopy, MRI, fundus and CMR modalities, and shows performance improving as the backbone scales from S to 7B.
Dino U-Net, a frozen DINOv3 encoder with FAPM projection, reaches top segmentation across seven medical imaging datasets, with the 7B variant averaging 76.43% Dice
The work proposes Dino U-Net: a frozen DINOv3 foundation backbone as encoder, combined with a dual-branch DINO Adapter and a Fidelity-Aware Projection Module (FAPM), which outperforms seven baseline methods on seven public medical image datasets spanning endoscopy, ultrasound, microscopy, MRI, fundus and CMR modalities, and shows performance improving as the backbone scales from S to 7B.
The work proposes Dino U-Net: a frozen DINOv3 foundation backbone as encoder, combined with a dual-branch DINO Adapter and a Fidelity-Aware Projection Module (FAPM), which outperforms seven baseline methods on seven public medical image datasets spanning endoscopy, ultrasound, microscopy, MRI, fundus and CMR modalities, and shows performance improving as the backbone scales from S to 7B.
Nature News Sep 24, 2026
A genome-wide association study of 27,885 people using GLP1 receptor agonists identified a missense variant in GLP1R associated with weight-loss efficacy (about 0.76 kg additional weight loss per effect allele), plus GLP1R and GIPR signals for nausea and vomiting (the GIPR association restricted to tirzepatide users), and used these to build combined genetic and non-genetic models that stratify patients by efficacy and side-effect risk in held-out electronic health record data.
A genome-wide association study of 27,885 people using GLP1 receptor agonists identified a missense variant in GLP1R associated with weight-loss efficacy (about 0.76 kg additional weight loss per effect allele), plus GLP1R and GIPR signals for nausea and vomiting (the GIPR association restricted to tirzepatide users), and used these to build combined genetic and non-genetic models that stratify patients by efficacy and side-effect risk in held-out electronic health record data.
A 23andMe genome-wide study of 27,885 people links GLP1R and GIPR variants to GLP-1 weight-loss response and nausea or vomiting risk
A genome-wide association study of 27,885 people using GLP1 receptor agonists identified a missense variant in GLP1R associated with weight-loss efficacy (about 0.76 kg additional weight loss per effect allele), plus GLP1R and GIPR signals for nausea and vomiting (the GIPR association restricted to tirzepatide users), and used these to build combined genetic and non-genetic models that stratify patients by efficacy and side-effect risk in held-out electronic health record data.
A genome-wide association study of 27,885 people using GLP1 receptor agonists identified a missense variant in GLP1R associated with weight-loss efficacy (about 0.76 kg additional weight loss per effect allele), plus GLP1R and GIPR signals for nausea and vomiting (the GIPR association restricted to tirzepatide users), and used these to build combined genetic and non-genetic models that stratify patients by efficacy and side-effect risk in held-out electronic health record data.
OpenAI Sep 23, 2026
This work co-created MentalHealthBench, an open benchmark built with more than 80 licensed mental health experts from 22 countries, using privacy-preserving techniques to generate synthetic mental health conversations that span non-acute, high-acuity, and emergency situations and four user personas (adults, teens aged 13-17, caregivers, and clinicians), with experts writing rubric criteria weighted from -10 to +10 (each conversation reviewed by at least three experts, retaining only criteria agreed by at least two and not contradicted by a third) and an automated grader, GPT-5.
This work co-created MentalHealthBench, an open benchmark built with more than 80 licensed mental health experts from 22 countries, using privacy-preserving techniques to generate synthetic mental health conversations that span non-acute, high-acuity, and emergency situations and four user personas (adults, teens aged 13-17, caregivers, and clinicians), with experts writing rubric criteria weighted from -10 to +10 (each conversation reviewed by at least three experts, retaining only criteria agreed by at least two and not contradicted by a third) and an automated grader, GPT-5.
MentalHealthBench: An Open Benchmark for Realistic Mental Health Conversations
This work co-created MentalHealthBench, an open benchmark built with more than 80 licensed mental health experts from 22 countries, using privacy-preserving techniques to generate synthetic mental health conversations that span non-acute, high-acuity, and emergency situations and four user personas (adults, teens aged 13-17, caregivers, and clinicians), with experts writing rubric criteria weighted from -10 to +10 (each conversation reviewed by at least three experts, retaining only criteria agreed by at least two and not contradicted by a third) and an automated grader, GPT-5.
This work co-created MentalHealthBench, an open benchmark built with more than 80 licensed mental health experts from 22 countries, using privacy-preserving techniques to generate synthetic mental health conversations that span non-acute, high-acuity, and emergency situations and four user personas (adults, teens aged 13-17, caregivers, and clinicians), with experts writing rubric criteria weighted from -10 to +10 (each conversation reviewed by at least three experts, retaining only criteria agreed by at least two and not contradicted by a third) and an automated grader, GPT-5.
arXiv Sep 23, 2026
This survey organizes and analyzes the literature on large language models in mental health around a central thesis: their role is evolving through three increasingly sophisticated phases—Phase I as passive Information Tools and Pattern Recognizers for assessment and risk detection, Phase II as Empathetic Conversationalists for in-the-moment, stateless interactions, and Phase III as Longitudinal, Personalized Companions implemented as stateful cognitive agents—while systematically reviewing the core technologies, agent architectures (Profile, Memory, Reasoning, Planning, Tool Use), datasets, and benchmarks that underpin this trajectory, arguing the field is shifting from one-shot help to long-term companionship.
This survey organizes and analyzes the literature on large language models in mental health around a central thesis: their role is evolving through three increasingly sophisticated phases—Phase I as passive Information Tools and Pattern Recognizers for assessment and risk detection, Phase II as Empathetic Conversationalists for in-the-moment, stateless interactions, and Phase III as Longitudinal, Personalized Companions implemented as stateful cognitive agents—while systematically reviewing the core technologies, agent architectures (Profile, Memory, Reasoning, Planning, Tool Use), datasets, and benchmarks that underpin this trajectory, arguing the field is shifting from one-shot help to long-term companionship.
From Pattern Recognizers to Personalized Companions: A Three-Phase Evolutionary Framework for LLMs in Mental Health
This survey organizes and analyzes the literature on large language models in mental health around a central thesis: their role is evolving through three increasingly sophisticated phases—Phase I as passive Information Tools and Pattern Recognizers for assessment and risk detection, Phase II as Empathetic Conversationalists for in-the-moment, stateless interactions, and Phase III as Longitudinal, Personalized Companions implemented as stateful cognitive agents—while systematically reviewing the core technologies, agent architectures (Profile, Memory, Reasoning, Planning, Tool Use), datasets, and benchmarks that underpin this trajectory, arguing the field is shifting from one-shot help to long-term companionship.
This survey organizes and analyzes the literature on large language models in mental health around a central thesis: their role is evolving through three increasingly sophisticated phases—Phase I as passive Information Tools and Pattern Recognizers for assessment and risk detection, Phase II as Empathetic Conversationalists for in-the-moment, stateless interactions, and Phase III as Longitudinal, Personalized Companions implemented as stateful cognitive agents—while systematically reviewing the core technologies, agent architectures (Profile, Memory, Reasoning, Planning, Tool Use), datasets, and benchmarks that underpin this trajectory, arguing the field is shifting from one-shot help to long-term companionship.
Nature News Sep 23, 2026
A single-nucleus RNA-sequencing atlas of the human dorsolateral prefrontal cortex built from nearly 1,500 donors and more than 6.3 million nuclei, together with the companion statistical tool Dreamlet, characterizes cell-type-specific transcriptional changes across eight brain disorders, reports shared cross-disease signatures, cell-composition shifts along Alzheimer's disease progression, and marked up-regulation of PTPRG in microglia.
A single-nucleus RNA-sequencing atlas of the human dorsolateral prefrontal cortex built from nearly 1,500 donors and more than 6.3 million nuclei, together with the companion statistical tool Dreamlet, characterizes cell-type-specific transcriptional changes across eight brain disorders, reports shared cross-disease signatures, cell-composition shifts along Alzheimer's disease progression, and marked up-regulation of PTPRG in microglia.
A Six-Million-Cell Map of Gene Activity in the Human Prefrontal Cortex: How the PsychAD Cohort and Dreamlet Push Brain-Disease Research to Population Scale
A single-nucleus RNA-sequencing atlas of the human dorsolateral prefrontal cortex built from nearly 1,500 donors and more than 6.3 million nuclei, together with the companion statistical tool Dreamlet, characterizes cell-type-specific transcriptional changes across eight brain disorders, reports shared cross-disease signatures, cell-composition shifts along Alzheimer's disease progression, and marked up-regulation of PTPRG in microglia.
A single-nucleus RNA-sequencing atlas of the human dorsolateral prefrontal cortex built from nearly 1,500 donors and more than 6.3 million nuclei, together with the companion statistical tool Dreamlet, characterizes cell-type-specific transcriptional changes across eight brain disorders, reports shared cross-disease signatures, cell-composition shifts along Alzheimer's disease progression, and marked up-regulation of PTPRG in microglia.
Blood Advances Sep 22, 2026
This study retrained a T1-weighted Dixon whole-body MRI deep-learning segmentation pipeline, originally developed on healthy UK Biobank participants, on scans from patients with multiple myeloma to automatically generate 11 image-derived phenotypes of non-diseased tissue (volumes of abdominal subcutaneous adipose tissue, visceral adipose tissue, abdominal skeletal muscle, liver, spleen, both kidneys, both iliopsoas muscles and heart, plus liver relative fat fraction), measured baseline and longitudinal values in a 69-patient prospective observational cohort (iTIMM) undergoing induction therapy and autologous stem cell transplant, and explored associations with progression-free survival, reporting a mean Dice of 0.916 and mean Likert of 4.
This study retrained a T1-weighted Dixon whole-body MRI deep-learning segmentation pipeline, originally developed on healthy UK Biobank participants, on scans from patients with multiple myeloma to automatically generate 11 image-derived phenotypes of non-diseased tissue (volumes of abdominal subcutaneous adipose tissue, visceral adipose tissue, abdominal skeletal muscle, liver, spleen, both kidneys, both iliopsoas muscles and heart, plus liver relative fat fraction), measured baseline and longitudinal values in a 69-patient prospective observational cohort (iTIMM) undergoing induction therapy and autologous stem cell transplant, and explored associations with progression-free survival, reporting a mean Dice of 0.916 and mean Likert of 4.
AI-derived whole-body MRI metrics in multiple myeloma: treatment-related body composition change and its association with outcomes
This study retrained a T1-weighted Dixon whole-body MRI deep-learning segmentation pipeline, originally developed on healthy UK Biobank participants, on scans from patients with multiple myeloma to automatically generate 11 image-derived phenotypes of non-diseased tissue (volumes of abdominal subcutaneous adipose tissue, visceral adipose tissue, abdominal skeletal muscle, liver, spleen, both kidneys, both iliopsoas muscles and heart, plus liver relative fat fraction), measured baseline and longitudinal values in a 69-patient prospective observational cohort (iTIMM) undergoing induction therapy and autologous stem cell transplant, and explored associations with progression-free survival, reporting a mean Dice of 0.916 and mean Likert of 4.
This study retrained a T1-weighted Dixon whole-body MRI deep-learning segmentation pipeline, originally developed on healthy UK Biobank participants, on scans from patients with multiple myeloma to automatically generate 11 image-derived phenotypes of non-diseased tissue (volumes of abdominal subcutaneous adipose tissue, visceral adipose tissue, abdominal skeletal muscle, liver, spleen, both kidneys, both iliopsoas muscles and heart, plus liver relative fat fraction), measured baseline and longitudinal values in a 69-patient prospective observational cohort (iTIMM) undergoing induction therapy and autologous stem cell transplant, and explored associations with progression-free survival, reporting a mean Dice of 0.916 and mean Likert of 4.

Page 21 · showing 10