❌

Normal view

Received — 24 November 2025 ⏭ Favourites

Health care Experiences of Educated Young Adults With Blindness in the Digital Age: Qualitative Study

✇Journal of Medical Internet Research
By: Junling Zhao · Can Su · Xiji Zhu · Cong Cai · Wei Liu · Xiaochen Ma
22 November 2025 at 04:45
Background: The rapid advancement of digital health technologies (DHTs) offers substantial potential for improving healthcare access, yet it simultaneously risks exacerbating existing inequities for marginalized populations. Previous research on the digital divide has often treated individuals with blindness as a homogenous group, primarily focusing on barriers related to digital access and skills. However, less is known about the nuanced experiences of specific subgroups, such as educated and digitally literate young adults. This study focuses on this demographic to understand how their advanced digital capabilities interact with systemic and infrastructural barriers in healthcare. Objective: This qualitative study aimed to explore the lived healthcare experiences of educated young adults with blindness in China, specifically identifying how DHTs simultaneously contribute to their empowerment and exclusion. Methods: Eligible participants were educated young adults with blindness in China (aged 18-30 years, Mandarin speakers, smartphone users, and holding or pursuing higher education). A total of 12 semi-structured interviews were conducted in Mandarin during September 2024. All interviews were audio-recorded and transcribed verbatim. An inductive thematic analysis was employed to interpret the data and identify key themes. Results: Participants’ experiences highlighted an “empowered but excluded” dynamic. Seven key themes emerged, categorized into empowerment and exclusion. Empowerment themes included: (1) digital platforms empowering self-management and healthcare access, where DHTs enabled independent appointment booking and access to comprehensive health information; and (2) digital platforms empowering for finding medical visit companions, facilitating the discovery of companions for physical and emotional support. Exclusion themes comprised: (3) inaccessible online appointment systems, due to non-inclusive designs; (4) inaccessible healthcare environments and information formats, stemming from non-accessible self-service machines and written materials; (5) lack of provider competencies in respecting patient autonomy, as providers often assumed digital incompetence; (6) data privacy and security concerns, heightened by increased digitalization and reliance on assistive tools; and (7) challenges related to the quality and consistency of online companion support, highlighting the limitations of platform-based assistance. Conclusions: Our findings reveal an “empowered but excluded” dynamic: the potential for digital empowerment and enhanced independence is often curtailed by systematic barriers. Addressing this necessitates a multifaceted approach: enhancing technological accessibility through robust standards adherence and inclusive co-design processes; improving healthcare provider competencies in patient-centered care via targeted training; and empowering educated young blind adults by building their capacity for self-determination to achieve equitable healthcare access.

Impact of Digital Interventions on the Treatment Burden of Patients With Chronic Conditions: Systematic Review

✇Journal of Medical Internet Research
By: Manria Polus · Pantea Keikhosrokiani · Olli Korhonen · Woubshet Behutiye · Minna Isomursu
22 November 2025 at 02:00
Background: Digital interventions can provide cost-effective, quality health care for patients with chronic conditions. Patients with chronic conditions often are burdened by a substantial load of adhering to a treatment regimen and suffer from impacts on their function and well-being. This treatment burden has consequences for treatment adherence and disease outcomes. Digital interventions have the potential to alleviate the burden, but they also may cause new challenges and an increased workload for the patient. Previous reviews have examined digital interventions or treatment burden separately, but there is a lack of systematic reviews on the intersection of digital interventions, treatment burden, and chronic conditions. Objective: This systematic review aimed to evaluate the evidence of how digital interventions impact the treatment burden experienced by people with chronic conditions, and to assess the quality of this evidence. Methods: We searched databases PubMed, Scopus, Web of Science, ACM, PubMed Central, and CINAHL for articles published between January 1, 2013, and June 17, 2025. We included studies that had key topics related to chronic conditions, treatment burden, and digital interventions. A total of 2 reviewers independently screened the articles in 2 stages, extracted data on study design, participant characteristics, intervention type, and treatment burden outcomes from included articles, and assessed their quality using the Critical Appraisal tools from the Joanna Briggs Institute. A convergent integrated approach was used for data synthesis and integration, where quantitative data were converted into qualitative data, and the qualitative and quantitative evidence were analyzed and categorized together. Results: We included 46 relevant studies in total. We categorized the interventions into 4 types: Telehealth, informational resources, self-management tools, and facilitated tools. The results of this study indicate that digital interventions mostly support patients with chronic conditions with their treatment burden, with minor concerns of increasing treatment burden. The main benefits are support with self-management, informational support, and easier ways to contact health care professionals. The main concerns were accessibility issues, time-consuming tools, and causing fear and anxiety. Conclusions: Our findings demonstrate how treatment burden is a relevant concept for future digital health care research and practice. Digital interventions can help patients with their treatment burden by supporting self-management, improving access to health care, improving patients’ experience, and addressing relevant concerns. More research is needed about conditions with low or medium initial treatment burden.

Clinical validation of a three-marker methylation panel to detect CIN3+ in vaginal self-samples in the Dutch population-based screening programme

✇Most Recent Articles: Clinical Epigenetics
By: Jolien de Waard · Arkajyoti Bhattacharya · Martine T. de Boer · Bettien M. van Hemel · Martha D. Esajas · Karin M. Vermeulen · Geertruida H. de Bock · Ed Schuuring and G. Bea A. Wisman
23 November 2025 at 08:00
The use of vaginal self-sampling for cervical cancer screening is promising and increasing. However, triage cytology cannot be performed on vaginal self-sampling material after a high-risk human papilloma viru...
Received — 21 November 2025 ⏭ Favourites

Accelerating Local AI on Consumer GPUs: A Hardware-Aware Dynamic Strategy for YOLOv10s

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mahmudul Islam Masum · Miad Islam
20 November 2025 at 13:00
arXiv:2509.07928v2 Announce Type: replace-cross Abstract: As local AI grows in popularity, there is a critical gap between the benchmark performance of object detectors and their practical viability on consumer-grade hardware. While models like YOLOv10s promise real-time speeds, these metrics are typically achieved on high-power, desktop-class GPUs. This paper reveals that on resource-constrained systems, such as laptops with RTX 4060 GPUs, performance is not compute-bound but is instead dominated by system-level bottlenecks, as illustrated by a simple bottleneck test. To overcome this hardware-level constraint, we introduce a Two-Pass Adaptive Inference algorithm, a model-independent approach that requires no architectural changes. This study mainly focuses on adaptive inference strategies and undertakes a comparative analysis of architectural early-exit and resolution-adaptive routing, highlighting their respective trade-offs within a unified evaluation framework. The system uses a fast, low-resolution pass and only escalates to a high-resolution model pass when detection confidence is low. On a 5000-image COCO dataset, our method achieves a 1.85x speedup over a PyTorch Early-Exit baseline, with a modest mAP loss of 5.51%. This work provides a practical and reproducible blueprint for deploying high-performance, real-time AI on consumer-grade devices by shifting the focus from pure model optimization to hardware-aware inference strategies that maximize throughput.

Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sebasti\'an Andr\'es Cajas Ord\'o\~nez · Luis Fernando Torres Torres · Mackenzie J. Meni · Carlos Andr\'es Duran Paredes · Eric Arazo · Cristian Bosch · Ricardo Simon Carbajo · Yuan Lai · Leo Anthony Celi
20 November 2025 at 13:00
arXiv:2511.11743v2 Announce Type: replace-cross Abstract: Deploying deep neural networks on resource-constrained devices faces two critical challenges: maintaining accuracy under aggressive quantization while ensuring predictable inference latency. We present a curiosity-driven quantized Mixture-of-Experts framework that addresses both through Bayesian epistemic uncertainty-based routing across heterogeneous experts (BitNet ternary, 1-16 bit BitLinear, post-training quantization). Evaluated on audio classification benchmarks (ESC-50, Quinn, UrbanSound8K), our 4-bit quantization maintains 99.9 percent of 16-bit accuracy (0.858 vs 0.859 F1) with 4x compression and 41 percent energy savings versus 8-bit. Crucially, curiosity-driven routing reduces MoE latency variance by 82 percent (p = 0.008, Levene's test) from 230 ms to 29 ms standard deviation, enabling stable inference for battery-constrained devices. Statistical analysis confirms 4-bit/8-bit achieve practical equivalence with full precision (p > 0.05), while MoE architectures introduce 11 percent latency overhead (p

Pan-cancer prevalence, risk, and clinical and demographic characteristics of Lynch Syndrome-associated variants in BioBank Japan

✇(Multiomics OR Omics) AND (Pancreatic)
By: Keijiro Mizukami · Yoshiaki Usui · Yusuke Iwasaki · Kouya Shiraishi · Makoto Hirata · Yoichiro Kamatani · Mikiko Endo · Satoshi Takahashi · Yoshiki Mochizuki · Mitusyo Yamaguchi · Takashi Kohno · Koichi Matsuda · Kokichi Sugano · Teruhiko Yoshida · Hidewaki Nakagawa · Chikashi Terao · Yuriko N Koyanagi · Keitaro Matsuo · Yoshinori Murakami · Amanda B Spurdle · Yukihide Momozawa
19 November 2025 at 19:00

Commun Med (Lond). 2025 Nov 13. doi: 10.1038/s43856-025-01231-9. Online ahead of print.

ABSTRACT

BACKGROUND: Although germline testing for DNA mismatch repair (MMR) genes is routinely performed, clinical guidelines highlight evidence gaps due to limited populations and biases. We examined germline pathogenic variants of MMR genes (MLH1, MSH2, MSH6, and PMS2) in 112,927 unselected individuals from BioBank Japan.

METHODS: We analyzed 74,085 cancer patients with 23 cancer types and 38,842 controls matched by sex, age, and hospital area from BioBank Japan, collected between April 2003 and March 2018. Germline pathogenic variants in the coding regions and 2 bp flanking intronic sequences of MMR genes were identified using a multiplex PCR-based target sequencing method. We examined associations with cancer types and demographic characterization of the pathogenic variants, comparing findings to existing clinical guidelines.

RESULTS: Here we show 228 pathogenic variants identified in MMR genes, with pathogenic MSH6 variants most frequently observed in endometrial cancer and 12 other significant associations. Twelve other significant associations are noted across a broad range of odds ratios, whereas pancreatic cancer exhibits no such association. Pathogenic variant carriers are diagnosed up to 12.4 years earlier than non-carriers, and colorectal and gastric cancers are diagnosed up to 16.4 years later than indicated by the guidelines. Higher carrier frequencies are observed in patients with both colorectal and endometrial cancers (24.8%) and in those with endometrial cancer and a family history of endometrial (26.0%) or colorectal (16.1%) cancers.

CONCLUSIONS: This study provides critical insights for clinical guidelines on the associations between cancer types, age at diagnosis, and carrier frequency.

PMID:41258140 | DOI:10.1038/s43856-025-01231-9

Latent plasticity of the human pancreas across development, health, and disease

✇(Multiomics OR Omics) AND (Pancreatic)
By: Elisabetta Mereu · Diego Balboa · Johannes Liebig · Aitor Gonzalez-Herrero · Anna Martinez-Casals · Mariya Mardamshina · Fanny Mollandin · Felix Schicktanz · Luca Tosti · Valerie Vandenbempt · Dana Avrahami · Edgar Bernardo · Frida Björklund · Robert Lorenz Chua · Marten Engelse · Javier García-Hurtado · Nathalie Groen · Maaike Hanegraaf · Pablo Iañez · Katharina Jechow · Björn Konukiewitz · Christian Lawerenz · Domenica Marchese · Mauro J Muraro · Silvia Pellegrini · Valeria Sordi · Alexander Sudy · Ulrike Taron · Foo Wei Ten · Timo Trefzer · Sven Twardziok · Maarten van Agen · Françoise Carlotti · Eelco de Koning · Jorge Ferrer · Benjamin Glaser · Holger Heyn · Emma Lundberg · Lorenzo Piemonti · Katja Steiger · Alexander van Oudenaarden · Wilko Weichert · Christian Conrad · Roland Eils
19 November 2025 at 19:00

bioRxiv [Preprint]. 2025 Oct 3:2025.10.01.679230. doi: 10.1101/2025.10.01.679230.

ABSTRACT

The pancreas plays a central role in major human diseases, yet our understanding of its cellular diversity and plasticity remains incomplete. Here, we present a single-cell multiomics atlas of the human pancreas, profiling over four million cells and nuclei from 57 donors across fetal development, adult homeostasis, and type 2 diabetes (T2D). Integrating sc/snRNA-seq, snATAC-seq, VASA-seq, spatial transcriptomics (Xenium), and multiplexed proteomics (CODEX), we resolve gene expression, chromatin accessibility, and spatial organization at high resolution. We identify transcriptionally plastic centroacinar-like cells (pCACs) in adults with fetal-like features, delineate endocrine and exocrine lineage trajectories during development, and uncover HNF1A-defined beta cell epigenetic states. In T2D, we observe shifts in beta cell subtypes and altered regulatory programs. Glucose perturbation of healthy islets reveals cell-type-specific adaptation and stress responses. This atlas provides a foundational framework to understand pancreas biology and the role of cellular plasticity in regeneration and disease.

PMID:41256699 | PMC:PMC12622017 | DOI:10.1101/2025.10.01.679230

SMMILe enables accurate spatial quantification in digital pathology using multiple-instance learning

✇Nature Cancer
By: Zeyu Gao · Anyu Mao · Yuxing Dong · Hannah Clayton · Jialun Wu · Jiashuai Liu · ChunBao Wang · Kai He · Tieliang Gong · Chen Li · Mireia Crispin-Ortuzar
19 November 2025 at 08:00

Nature Cancer, Published online: 19 November 2025; doi:10.1038/s43018-025-01060-8

Gao et al. present SMMILe, a multiple-instance learning-based tool that leverages whole-slide images for accurate spatial quantification without compromising on classification performance, and show it outperforms state-of-the-art methods.
Received — 19 November 2025 ⏭ Favourites

Foundation Models in Medical Imaging: A Review and Outlook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Vivien van Veldhuizen · Vanessa Botha · Chunyao Lu · Melis Erdal Cesur · Kevin Groot Lipman · Edwin D. de Jong · Hugo Horlings · Cl\'arisa I. Sanchez · Cees G. M. Snoek · Lodewyk Wessels · Ritse Mann · Eric Marcus · Jonas Teuwen
19 November 2025 at 13:00
arXiv:2506.09095v4 Announce Type: replace-cross Abstract: Foundation models (FMs) are changing the way medical images are analyzed by learning from large collections of unlabeled data. Instead of relying on manually annotated examples, FMs are pre-trained to learn general-purpose visual features that can later be adapted to specific clinical tasks with little additional supervision. In this review, we examine how FMs are being developed and applied in pathology, radiology, and ophthalmology, drawing on evidence from over 150 studies. We explain the core components of FM pipelines, including model architectures, self-supervised learning methods, and strategies for downstream adaptation. We also review how FMs are being used in each imaging domain and compare design choices across applications. Finally, we discuss key challenges and open questions to guide future research.

Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images

✇npj Digital Medicine
By: Xiu Su · Qinghua Mao · Zhongze Wu · Xi Lin · Shan You · Yue Liao · Chang Xu
18 November 2025 at 08:00

npj Digital Medicine, Published online: 18 November 2025; doi:10.1038/s41746-025-02042-x

Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images
Received — 18 November 2025 ⏭ Favourites

CLINB: A Climate Intelligence Benchmark for Foundational Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Michelle Chen Huebscher · Katharine Mach · Aleksandar Stani\'c · Markus Leippold · Ben Gaiarin · Zeke Hausfather · Elisa Rawat · Erich Fischer · Massimiliano Ciaramita · Joeri Rogelj · Christian Buck · Lierni Sestorain Saralegui · Reto Knutti
18 November 2025 at 13:00
arXiv:2511.11597v1 Announce Type: new Abstract: Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended, grounded, multimodal question answering tasks with clear requirements for knowledge quality and evidential support. CLINB relies on a dataset of real users' questions and evaluation rubrics curated by leading climate scientists. We implement and validate a model-based evaluation process and evaluate several frontier models. Our findings reveal a critical dichotomy. Frontier models demonstrate remarkable knowledge synthesis capabilities, often exhibiting PhD-level understanding and presentation quality. They outperform "hybrid" answers curated by domain experts assisted by weaker models. However, this performance is countered by failures in grounding. The quality of evidence varies, with substantial hallucination rates for references and images. We argue that bridging this gap between knowledge synthesis and verifiable attribution is essential for the deployment of AI in scientific workflows and that reliable, interpretable benchmarks like CLINB are needed to progress towards building trustworthy AI systems.

End to End AI System for Surgical Gesture Sequence Recognition and Clinical Outcome Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xi Li · Nicholas Matsumoto · Ujjwal Pasupulety · Atharva Deo · Cherine Yang · Jay Moran · Miguel E. Hernandez · Peter Wager · Jasmine Lin · Jeanine Kim · Alvin C. Goh · Christian Wagner · Geoffrey A. Sonn · Andrew J. Hung
18 November 2025 at 13:00
arXiv:2511.11899v1 Announce Type: new Abstract: Fine-grained analysis of intraoperative behavior and its impact on patient outcomes remain a longstanding challenge. We present Frame-to-Outcome (F2O), an end-to-end system that translates tissue dissection videos into gesture sequences and uncovers patterns associated with postoperative outcomes. Leveraging transformer-based spatial and temporal modeling and frame-wise classification, F2O robustly detects consecutive short (~2 seconds) gestures in the nerve-sparing step of robot-assisted radical prostatectomy (AUC: 0.80 frame-level; 0.81 video-level). F2O-derived features (gesture frequency, duration, and transitions) predicted postoperative outcomes with accuracy comparable to human annotations (0.79 vs. 0.75; overlapping 95% CI). Across 25 shared features, effect size directions were concordant with small differences (~ 0.07), and strong correlation (r = 0.96, p

UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI

✇cs.AI, q-bio.NC updates on arXiv.org
By: Darvin Yi · Teng Liu · Mattie Terzolo · Lance Hasson · Ayan Sinh · Pablo Mendes · Andrew Rabinovich
18 November 2025 at 13:00
arXiv:2511.12306v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly undertake digital work, reliable frameworks are needed to evaluate their real-world competence, adaptability, and capacity for human collaboration. Existing benchmarks remain largely static, synthetic, or domain-limited, providing limited insight into how agents perform in dynamic, economically meaningful environments. We introduce UpBench, a dynamically evolving benchmark grounded in real jobs drawn from the global Upwork labor marketplace. Each task corresponds to a verified client transaction, anchoring evaluation in genuine work activity and financial outcomes. UpBench employs a rubric-based evaluation framework, in which expert freelancers decompose each job into detailed, verifiable acceptance criteria and assess AI submissions with per-criterion feedback. This structure enables fine-grained analysis of model strengths, weaknesses, and instruction-following fidelity beyond binary pass/fail metrics. Human expertise is integrated throughout the data pipeline (from job curation and rubric construction to evaluation) ensuring fidelity to real professional standards and supporting research on human-AI collaboration. By regularly refreshing tasks to reflect the evolving nature of online work, UpBench provides a scalable, human-centered foundation for evaluating agentic systems in authentic labor-market contexts, offering a path toward a collaborative framework, where AI amplifies human capability through partnership rather than replacement.

Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dylan M. Asmar · Mykel J. Kochenderfer
18 November 2025 at 13:00
arXiv:2511.12378v1 Announce Type: new Abstract: Autonomous agents operating in sequential decision-making tasks under uncertainty can benefit from external action suggestions, which provide valuable guidance but inherently vary in reliability. Existing methods for incorporating such advice typically assume static and known suggester quality parameters, limiting practical deployment. We introduce a framework that dynamically learns and adapts to varying suggester reliability in partially observable environments. First, we integrate suggester quality directly into the agent's belief representation, enabling agents to infer and adjust their reliance on suggestions through Bayesian inference over suggester types. Second, we introduce an explicit ``ask'' action allowing agents to strategically request suggestions at critical moments, balancing informational gains against acquisition costs. Experimental evaluation demonstrates robust performance across varying suggester qualities, adaptation to changing reliability, and strategic management of suggestion requests. This work provides a foundation for adaptive human-agent collaboration by addressing suggestion uncertainty in uncertain environments.

Multi-agent Self-triage System with Medical Flowcharts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yujia Liu · Sophia Yu · Hongyue Jin · Jessica Wen · Alexander Qian · Terrence Lee · Mattheus Ramsis · Gi Won Choi · Lianhui Qin · Xin Liu · Edward J. Wang
18 November 2025 at 13:00
arXiv:2511.12439v1 Announce Type: new Abstract: Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Classification and Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Andrea Moglia · Elia Clement Nastasio · Luca Mainardi · Pietro Cerveri
18 November 2025 at 13:00
arXiv:2412.15925v1 Announce Type: cross Abstract: Problem: Pancreas radiological imaging is challenging due to the small size, blurred boundaries, and variability of shape and position of the organ among patients. Goal: In this work we present MiniGPT-Pancreas, a Multimodal Large Language Model (MLLM), as an interactive chatbot to support clinicians in pancreas cancer diagnosis by integrating visual and textual information. Methods: MiniGPT-v2, a general-purpose MLLM, was fine-tuned in a cascaded way for pancreas detection, tumor classification, and tumor detection with multimodal prompts combining questions and computed tomography scans from the National Institute of Health (NIH), and Medical Segmentation Decathlon (MSD) datasets. The AbdomenCT-1k dataset was used to detect the liver, spleen, kidney, and pancreas. Results: MiniGPT-Pancreas achieved an Intersection over Union (IoU) of 0.595 and 0.550 for the detection of pancreas on NIH and MSD datasets, respectively. For the pancreas cancer classification task on the MSD dataset, accuracy, precision, and recall were 0.876, 0.874, and 0.878, respectively. When evaluating MiniGPT-Pancreas on the AbdomenCT-1k dataset for multi-organ detection, the IoU was 0.8399 for the liver, 0.722 for the kidney, 0.705 for the spleen, and 0.497 for the pancreas. For the pancreas tumor detection task, the IoU score was 0.168 on the MSD dataset. Conclusions: MiniGPT-Pancreas represents a promising solution to support clinicians in the classification of pancreas images with pancreas tumors. Future research is needed to improve the score on the detection task, especially for pancreas tumors.

MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mohammad Karami · Mohammad Reza Nemati · Aidin Kazemi · Ali Mikaeili Barzili · Hamid Azadegan · Behzad Moshiri
18 November 2025 at 13:00
arXiv:2511.11625v1 Announce Type: cross Abstract: Artificial intelligence (AI) has shown great potential in medical imaging, particularly for brain tumor detection using Magnetic Resonance Imaging (MRI). However, the models remain vulnerable at inference time when they are trained collaboratively through Federated Learning (FL), an approach adopted to protect patient privacy. Adversarial attacks can subtly alter medical scans in ways invisible to the human eye yet powerful enough to mislead AI models, potentially causing serious misdiagnoses. Existing defenses often assume centralized data and struggle to cope with the decentralized and diverse nature of federated medical settings. In this work, we present MedFedPure, a personalized federated learning defense framework designed to protect diagnostic AI models at inference time without compromising privacy or accuracy. MedFedPure combines three key elements: (1) a personalized FL model that adapts to the unique data distribution of each institution; (2) a Masked Autoencoder (MAE) that detects suspicious inputs by exposing hidden perturbations; and (3) an adaptive diffusion-based purification module that selectively cleans only the flagged scans before classification. Together, these steps offer robust protection while preserving the integrity of normal, benign images. We evaluated MedFedPure on the Br35H brain MRI dataset. The results show a significant gain in adversarial robustness, improving performance from 49.50% to 87.33% under strong attacks, while maintaining a high clean accuracy of 97.67%. By operating locally and in real time during diagnosis, our framework provides a practical path to deploying secure, trustworthy, and privacy-preserving AI tools in clinical workflows. Index Terms: cancer, tumor detection, federated learning, masked autoencoder, diffusion, privacy
❌