Hasil untuk "Medical legislation"

Binesh Sadanandan, Vahid Behzadan

Consistency under paraphrase, the property that semantically equivalent prompts yield identical predictions, is increasingly used as a proxy for reliability when deploying medical vision-language models (VLMs). We show this proxy is fundamentally flawed: a model can achieve perfect consistency by relying on text patterns rather than the input image. We introduce a four-quadrant per-sample safety taxonomy that jointly evaluates consistency (stable predictions across paraphrased prompts) and image reliance (predictions that change when the image is removed). Samples are classified as Ideal (consistent and image-reliant), Fragile (inconsistent but image-reliant), Dangerous (consistent but not image-reliant), or Worst (inconsistent and not image-reliant). Evaluating five medical VLM configurations across two chest X-ray datasets (MIMIC-CXR, PadChest), we find that LoRA fine-tuning dramatically reduces flip rates but shifts a majority of samples into the Dangerous quadrant: LLaVA-Rad Base achieves a 1.5% flip rate on PadChest while 98.5% of its samples are Dangerous. Critically, Dangerous samples exhibit high accuracy (up to 99.6%) and low entropy, making them invisible to standard confidence-based screening. We observe a negative correlation between flip rate and Dangerous fraction (r = -0.89, n=10) and recommend that deployment evaluations always pair consistency checks with a text-only baseline: a single additional forward pass that exposes the false reliability trap.

Chenxin Yuan, Shoupeng Chen, Haojiang Ye et al.

Accurate segmentation of 3D medical scans is crucial for clinical diagnostics and treatment planning, yet existing methods often fail to achieve both high accuracy and computational efficiency across diverse anatomies and imaging modalities. To address these challenges, we propose GCNV-Net, a novel 3D medical segmentation framework that integrates a Tri-directional Dynamic Nonvoid Voxel Transformer (3DNVT), a Geometrical Cross-Attention module (GCA), and Nonvoid Voxelization. The 3DNVT dynamically partitions relevant voxels along the three orthogonal anatomical planes, namely the transverse, sagittal, and coronal planes, enabling effective modeling of complex 3D spatial dependencies. The GCA mechanism explicitly incorporates geometric positional information during multi-scale feature fusion, significantly enhancing fine-grained anatomical segmentation accuracy. Meanwhile, Nonvoid Voxelization processes only informative regions, greatly reducing redundant computation without compromising segmentation quality, and achieves a 56.13% reduction in FLOPs and a 68.49% reduction in inference latency compared to conventional voxelization. We evaluate GCNV-Net on multiple widely used benchmarks: BraTS2021, ACDC, MSD Prostate, MSD Pancreas, and AMOS2022. Our method achieves state-of-the-art segmentation performance across all datasets, outperforming the best existing methods by 0.65% on Dice, 0.63% on IoU, 1% on NSD, and relatively 14.5% on HD95. All results demonstrate that GCNV-Net effectively balances accuracy and efficiency, and its robustness across diverse organs, disease conditions, and imaging modalities highlights strong potential for clinical deployment.

Joshua Hatherley

Artificial intelligence (AI) is expected to revolutionize the practice of medicine. Recent advancements in the field of deep learning have demonstrated success in a variety of clinical tasks: detecting diabetic retinopathy from images, predicting hospital readmissions, aiding in the discovery of new drugs, etc. AI's progress in medicine, however, has led to concerns regarding the potential effects of this technology upon relationships of trust in clinical practice. In this paper, I will argue that there is merit to these concerns, since AI systems can be relied upon, and are capable of reliability, but cannot be trusted, and are not capable of trustworthiness. Insofar as patients are required to rely upon AI systems for their medical decision-making, there is potential for this to produce a deficit of trust in relationships in clinical practice.

Bailiang Jian, Jiazhen Pan, Rohit Jena et al.

Medical image registration drives quantitative analysis across organs, modalities, and patient populations. Recent deep learning methods often combine low-level "trend-driven" computational blocks from computer vision, such as large-kernel CNNs, Transformers, and state-space models, with high-level registration-specific designs like motion pyramids, correlation layers, and iterative refinement. Yet, their relative contributions remain unclear and entangled. This raises a central question: should future advances in registration focus on importing generic architectural trends or on refining domain-specific design principles? Through a modular framework spanning brain, lung, cardiac, and abdominal registration, we systematically disentangle the influence of these two paradigms. Our evaluation reveals that low-level "trend-driven" computational blocks offer only marginal or inconsistent gains, while high-level registration-specific designs consistently deliver more accurate, smoother, and more robust deformations. These domain priors significantly elevate the performance of a standard U-Net baseline, far more than variants incorporating "trend-driven" blocks, achieving an average relative improvement of $\sim3\%$. All models and experiments are released within a transparent, modular benchmark that enables plug-and-play comparison for new architectures and registration tasks (https://github.com/BailiangJ/rethink-reg). This dynamic and extensible platform establishes a common ground for reproducible and fair evaluation, inviting the community to isolate genuine methodological contributions from domain priors. Our findings advocate a shift in research emphasis: from following architectural trends to embracing domain-specific design principles as the true drivers of progress in learning-based medical image registration.

Orhan Demirci, Bulent Yilmaz

This paper introduces Tree-NET, a novel framework for medical image segmentation that leverages bottleneck feature supervision to enhance both segmentation accuracy and computational efficiency. While previous studies have employed bottleneck feature supervision, their applications have largely been limited to the training phase, offering no computational benefits during training or evaluation. To the best of our knowledge, this study is the first to propose a framework that incorporates two additional training phases for segmentation models, utilizing bottleneck features at both input and output stages. This approach significantly improves computational performance by reducing input and output dimensions with a negligible addition to parameter count, without compromising accuracy. Tree-NET features a three-layer architecture comprising Encoder-Net and Decoder-Net, which are autoencoders designed to compress input and label data, respectively, and Bridge-Net, a segmentation framework that supervises the bottleneck features. By focusing on dense, compressed representations, Tree-NET enhances operational efficiency and can be seamlessly integrated into existing segmentation models without altering their internal structures or increasing model size. We evaluate Tree-NET on two critical segmentation tasks -- skin lesion and polyp segmentation -- using various backbone models, including U-NET variants and Polyp-PVT. Experimental results demonstrate that Tree-NET reduces FLOPs by a factor of 4 to 13 and decreases memory usage, while achieving comparable or superior accuracy compared to the original architectures. These findings underscore Tree-NET's potential as a robust and efficient solution for medical image segmentation.

Marvellous Eyube, Courage Enuesueke, Marvellous Alimikhena

Biocompatibility is a critical factor in the application of nanomaterials in medical fields, as these materials must interact safely and effectively with biological systems to be viable for therapeutic and diagnostic use. This article investigates the biocompatibility of nanomaterials, focusing on their interactions with biological cells, tissues, and the immune system. Key properties such as surface chemistry, size, shape, and material composition are examined, as they significantly influence the biological response. The article explores the role of nanomaterials in medical applications, including drug delivery, diagnostic imaging, and tissue engineering, while discussing the challenges involved in enhancing their biocompatibility. A case study on the CaO-CaP binary system is presented, showcasing the use of calcium oxide (CaO) and calcium phosphate (CaP) nanoparticles in bone tissue engineering. This system is widely investigated for its ability to mimic the mineral content of bone and promote osteogenesis, highlighting both its therapeutic potential and challenges in ensuring safe biocompatibility in clinical settings. The article concludes by reviewing strategies to optimize the biocompatibility of nanomaterials and discussing future directions for research in advancing their applications in medical treatments.

André Bastos Lopes Ferreira, Larissa Bezerra Cuervo, Thárick Hernani dos Santos Ferreira Mafra et al.

Este artigo propõe uma metodologia empírico-legislativa baseada em técnicas de web scraping e inteligência artificial, com os objetivos específicos de descrever o método proposto, aplicá-lo na pesquisa de normas municipais relacionadas à regulação da saúde digital no Brasil e avaliá-lo, tendo em vista vieses, lacunas e limitações encontrados em sua aplicação. A pesquisa partiu de uma análise exploratória em cinco capitais brasileiras, cujos repositórios normativos foram selecionados por critérios de acessibilidade e padronização. Por meio de raspagem automatizada de dados e classificação de textos jurídicos com um modelo de linguagem, foi possível identificar normas pertinentes ao tema e categorizá-las em cinco áreas principais: governança, privacidade e proteção de dados pessoais, telessaúde, pesquisa e dispositivos médicos. Os resultados indicam que as normas relacionadas à saúde digital ainda são uma pequena fração do total normativo municipal, majoritariamente na forma de decretos do Poder Executivo, mas têm crescido significativamente em número, nos últimos anos, especialmente após a promulgação da Lei Geral de Proteção de Dados e durante a pandemia da covid-19. Apesar das limitações, como a falta de padronização dos repositórios e a exclusão de certas normas infralegais, a metodologia apresentou-se eficiente e escalável, possibilitando análises mais profundas sobre padrões e lacunas regulatórias. O estudo conclui que ferramentas automatizadas têm potencial para amplificar a capacidade de análise no campo jurídico, favorecendo o conhecimento empírico indispensável para orientar políticas públicas em saúde digital, tema estratégico para o futuro regulatório no Brasil.

Andrew Hoopes, Neel Dey, Victor Ion Butoi et al.

We present VoxelPrompt, an end-to-end image analysis agent that tackles free-form radiological tasks. Given any number of volumetric medical images and a natural language prompt, VoxelPrompt integrates a language model that generates executable code to invoke a jointly-trained, adaptable vision network. This code further carries out analytical steps to address practical quantitative aims, such as measuring the growth of a tumor across visits. The pipelines generated by VoxelPrompt automate analyses that currently require practitioners to painstakingly combine multiple specialized vision and statistical tools. We evaluate VoxelPrompt using diverse neuroimaging tasks and show that it can delineate hundreds of anatomical and pathological features, measure complex morphological properties, and perform open-language analysis of lesion characteristics. VoxelPrompt performs these objectives with an accuracy similar to that of specialist single-task models for image analysis, while facilitating a broad range of compositional biomedical workflows.

Daniel Duenias, Brennan Nichyporuk, Tal Arbel et al.

The integration of diverse clinical modalities such as medical imaging and the tabular data extracted from patients' Electronic Health Records (EHRs) is a crucial aspect of modern healthcare. Integrative analysis of multiple sources can provide a comprehensive understanding of the clinical condition of a patient, improving diagnosis and treatment decision. Deep Neural Networks (DNNs) consistently demonstrate outstanding performance in a wide range of multimodal tasks in the medical domain. However, the complex endeavor of effectively merging medical imaging with clinical, demographic and genetic information represented as numerical tabular data remains a highly active and ongoing research pursuit. We present a novel framework based on hypernetworks to fuse clinical imaging and tabular data by conditioning the image processing on the EHR's values and measurements. This approach aims to leverage the complementary information present in these modalities to enhance the accuracy of various medical applications. We demonstrate the strength and generality of our method on two different brain Magnetic Resonance Imaging (MRI) analysis tasks, namely, brain age prediction conditioned by subject's sex and multi-class Alzheimer's Disease (AD) classification conditioned by tabular data. We show that our framework outperforms both single-modality models and state-of-the-art MRI tabular data fusion methods. A link to our code can be found at https://github.com/daniel4725/HyperFusion

Yuetan Chu, Yilan Zhang, Zhongyi Han et al.

Foundation models have recently attracted significant attention for their impressive generalizability across diverse downstream tasks. However, these models are demonstrated to exhibit great limitations in representing high-frequency components and fine-grained details. In many medical imaging tasks, the precise representation of such information is crucial due to the inherently intricate anatomical structures, sub-visual features, and complex boundaries involved. Consequently, the limited representation of prevalent foundation models can result in significant performance degradation or even failure in these tasks. To address these challenges, we propose a novel pretraining strategy, named Frequency-advanced Representation Autoencoder (Frepa). Through high-frequency masking and low-frequency perturbation combined with adversarial learning, Frepa encourages the encoder to effectively represent and preserve high-frequency components in the image embeddings. Additionally, we introduce an innovative histogram-equalized image masking strategy, extending the Masked Autoencoder approach beyond ViT to other architectures such as Swin Transformer and convolutional networks. We develop Frepa across nine medical modalities and validate it on 32 downstream tasks for both 2D images and 3D volume data. Without fine-tuning, Frepa can outperform other self-supervised pretraining methods and, in some cases, even surpasses task-specific trained models. This improvement is particularly significant for tasks involving fine-grained details, such as achieving up to a +15% increase in DSC for retina vessel segmentation and a +7% increase in IoU for lung nodule detection. Further experiments quantitatively reveal that Frepa enables superior high-frequency representations and preservation in the embeddings, underscoring its potential for developing more generalized and universal medical image foundation models.

Ron Keuth, Lasse Hansen, Maren Balks et al.

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently introduced Segment Anything Model (SAM) enables prompt-based segmentation and offers zero-shot generalization to unfamiliar objects. In our work, we leverage SAM's abstract object understanding for medical image segmentation to provide pseudo labels for semi-supervised learning, thereby mitigating the need for extensive annotated training data. Our approach refines initial segmentations that are derived from a limited amount of annotated data (comprising up to 43 cases) by extracting bounding boxes and seed points as prompts forwarded to SAM. Thus, it enables the generation of dense segmentation masks as pseudo labels for unlabelled data. The results show that training with our pseudo labels yields an improvement in Dice score from $74.29\,\%$ to $84.17\,\%$ and from $66.63\,\%$ to $74.87\,\%$ for the segmentation of bones of the paediatric wrist and teeth in dental radiographs, respectively. As a result, our method outperforms intensity-based post-processing methods, state-of-the-art supervised learning for segmentation (nnU-Net), and the semi-supervised mean teacher approach. Our Code is available on GitHub.

Melissa A. Theurich, Monika Ziebart, Frances Strobl

Abstract Bottles and teats are ubiquitously used for feeding infants and young children. Yet there are limited empirical studies on the scope of infant feeding bottles, their attributes, or their marketing claims. We report the first comprehensive survey on infant feeding bottles and teats in Germany. We aimed to explore the extent of bottles and teats available in Germany, describe their physical attributes and analyze their marketing claims. A cross‐sectional survey of German bottle and teat manufacturer websites was conducted between June and November 2022. Product attributes are presented with descriptive statistics and photographs. Marketing claims are summarized in a descriptive content analysis. We identified 41 brands encompassing 447 unique products (226 bottles, 221 teats). The majority of bottles were plastic (147, 65%) or glass (64, 28%), and the majority of teats were silicone (188, 85%). Most brands (38, 93%) promoted products using one or more inappropriate marketing claims, including equivalency to breastfeeding (29, 73%), idealization through technical or medical descriptions (23, 58%), claims on disease prevention (31, 78%), references to naturalness (29, 73%), infant autonomy (10, 25%), and endorsements from parents (10, 25%) or health professionals (11, 28%). The majority of bottles and teats available in Germany appear to be marketed inappropriately and hold the potential to undermine public health recommendations on infant and young child feeding. Therefore, we recommend Germany strengthens legislation on the marketing of bottles and teats in accordance with the International Code of Marketing of Breastmilk Substitutes.

Josiane Garcia, Anna Cecília Dias Maciel Carneiro, Sheila Soares Silva et al.

Background: Blood transfusion is an effective therapeutic practice. However, even adopting all procedures for transfusion safety, there are risks, one of which is immediate adverse reactions. The aim of this study was, by active search, to evaluate the occurrence of immediate adverse reactions estimating the occurrence rate within the first 24 h. Methods: An exploratory, descriptive, prospective study with quantitative analysis was carried out of patients undergoing surgery who received blood component transfusions during hospitalization from October 2018 to August 2019. Data on blood component request forms were collected from the transfusion agency by reviewing medical records and interviewing the patient or family members. Descriptive statistics and the chi-square test were used to analyze the association of demographic variables with the presence or absence of transfusion reactions. Results: A total of 1042 blood component units were transfused in 393 transfusions performed on 184 patients. The main transfused blood component was packed red blood cells. Seventeen reactions were identified in the medical records, using the active search method, none of which had been reported. The transfusion reaction rate was 16.3 occurrences per 1000 transfused units, while the notification rate for the 9389 blood component units transfused by the transfusion agency in the study period was 3.83/1000. There was no statistically significant association between the occurrences or not of transfusion reactions and demographic variables. Conclusion: Through the active search method, it was possible to observe the underreporting of adverse reactions, showing inadequate compliance with current legislation, which is essential to minimize errors and increase transfusion safety.

Weijia Feng, Lingting Zhu, Lequan Yu

The Segment Anything Model (SAM) has demonstrated remarkable capabilities of scaled-up segmentation models, enabling zero-shot generalization across a variety of domains. By leveraging large-scale foundational models as pre-trained models, it is a natural progression to fine-tune SAM for specific domains to further enhance performances. However, the adoption of foundational models in the medical domain presents a challenge due to the difficulty and expense of labeling sufficient data for adaptation within hospital systems. In this paper, we introduce an efficient and practical approach for fine-tuning SAM using a limited number of exemplars, making it suitable for such scenarios. Our approach combines two established techniques from the literature: an exemplar-guided synthesis module and the widely recognized Low-Rank Adaptation (LoRA) fine-tuning strategy, serving as data-level and model-level attempts respectively. Interestingly, our empirical findings suggest that SAM can be effectively aligned within the medical domain even with few labeled data. We validate our approach through experiments on brain tumor segmentation (BraTS) and multi-organ CT segmentation (Synapse). The comprehensive results underscore the feasibility and effectiveness of such an approach, paving the way for the practical application of SAM in the medical domain.

Hao Du, Qihua Dong, Yan Xu et al.

Medical image segmentation is almost the most important pre-processing procedure in computer-aided diagnosis but is also a very challenging task due to the complex shapes of segments and various artifacts caused by medical imaging, (i.e., low-contrast tissues, and non-homogenous textures). In this paper, we propose a simple yet effective segmentation framework that incorporates the geometric prior and contrastive similarity into the weakly-supervised segmentation framework in a loss-based fashion. The proposed geometric prior built on point cloud provides meticulous geometry to the weakly-supervised segmentation proposal, which serves as better supervision than the inherent property of the bounding-box annotation (i.e., height and width). Furthermore, we propose contrastive similarity to encourage organ pixels to gather around in the contrastive embedding space, which helps better distinguish low-contrast tissues. The proposed contrastive embedding space can make up for the poor representation of the conventionally-used gray space. Extensive experiments are conducted to verify the effectiveness and the robustness of the proposed weakly-supervised segmentation framework. The proposed framework is superior to state-of-the-art weakly-supervised methods on the following publicly accessible datasets: LiTS 2017 Challenge, KiTS 2021 Challenge, and LPBA40. We also dissect our method and evaluate the performance of each component.

M Brotherton

Various human rights issues arise from the intersection of adolescent motherhood and HIV. While health rights may be the most obvious means by which to address such issues through policy development and legislative means, the right to health is not the only human right that may provide recourse or relief in this regard. This article considers an unexplored avenue of approaching such issues through reliance on the right to enjoy the benefits of scientific progress. The International Covenant on Economic, Social and Cultural Rights provides for the ‘right to science’ in article 15(1)(b) and more recently, as elaborated on in General Comment no. 25 of 2020. This article considers how this right can be relied upon to address issues pertaining to adolescent motherhood and HIV. Precedent from a Venezuelan Supreme Court decision is considered, as well as the normative content of the right to enjoy the benefits of scientific progress. This may be another legal means by which to hold states accountable for the health of young mothers and their children, especially as new practices, medicines and treatments emerge regarding HIV.

Andrea Patricia Valenzuela Toledo, Katerin Arias Ortega

El estudio expone una revisión del estado del arte sobre la concepción de salud desde las perspectivas indígena y occidental. Los materiales y métodos utilizados se circunscriben a un diseño cualitativo de tipo exploratorio y de carácter descriptivo, en el que, a través de una revisión de 51 artículos científicos, se problematiza acerca del objeto de estudio. Los resultados dan cuenta de la existencia de tensiones epistemológicas sobre la concepción de salud desde las perspectivas indígena y occidental. Concluimos que estas problemáticas han traído consigo un aumento en las desigualdades en la salud respecto al acceso a esta, según ubicación geográfica y territorial de la población indígena. Asimismo, discutimos sobre cómo la atención de salud en territorios indígenas se distingue por ser ofrecida con un carácter monocultural, aumentando la marginalización de la persona indígena. Sostenemos que es imperioso abordar las desigualdades de salud en el contexto indígena, tanto en el acceso a esta como en las formas de atención a los usuarios, desde una perspectiva intercultural.

V. Shapovalov, L. Butko, V. Shapovalov

The study is dedicated to legislative, normative, legal, and regulatory changes in the medical and educational sphere of activity, which occurred as a result of quarantine and introduction of restrictive anti-epidemic measures in order to prevent the spread of acute respiratory disease COVID-19 in Ukraine. It was noted that the changes in the legislation of Ukraine have significantly affected the medical and educational sphere of activity (doctors, pharmacists, teachers, students, listeners). The main prohibitions and permits in the work of specialists in medicine and education were given. The necessity of further studying the experience in the leading countries of the world on vaccination of different segments of the population is substantiated.

Ziyuan Zhao, Fangcheng Zhou, Kaixin Xu et al.

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the expert-driven and time-consuming nature of pixel-level annotations in clinical practices, and (ii) failure to generalize from one domain to another, especially when the target domain is a different modality with severe domain shifts. Recent unsupervised domain adaptation~(UDA) techniques leverage abundant labeled source data together with unlabeled target data to reduce the domain gap, but these methods degrade significantly with limited source annotations. In this study, we address this underexplored UDA problem, investigating a challenging but valuable realistic scenario, where the source domain not only exhibits domain shift~w.r.t. the target domain but also suffers from label scarcity. In this regard, we propose a novel and generic framework called ``Label-Efficient Unsupervised Domain Adaptation"~(LE-UDA). In LE-UDA, we construct self-ensembling consistency for knowledge transfer between both domains, as well as a self-ensembling adversarial learning module to achieve better feature alignment for UDA. To assess the effectiveness of our method, we conduct extensive experiments on two different tasks for cross-modality segmentation between MRI and CT images. Experimental results demonstrate that the proposed LE-UDA can efficiently leverage limited source labels to improve cross-domain segmentation performance, outperforming state-of-the-art UDA approaches in the literature. Code is available at: https://github.com/jacobzhaoziyuan/LE-UDA.

Caitlin E. Kennedy, Ping Teresa Yeh, Jack Byrne et al.

Self-administration of quality gender-affirming hormones is one approach to expanding access to hormone therapy for individuals seeking secondary sex characteristics more aligned with their gender identity or expression and can be empowering when provided within safe, supportive health systems. To inform World Health Organization guidelines on self-care interventions, we systematically reviewed the evidence for self-administration compared to health worker-administration of gender-affirming hormones. We conducted a comprehensive search for peer-reviewed articles and conference abstracts that addressed effectiveness, values and preferences, and cost considerations. Data were extracted in duplicate using standardised forms. Of 3792 unique references, five values and preferences articles were included; no studies met the criteria for the effectiveness or cost reviews. All values and preferences studies focused on self-administration of unprescribed hormones, not prescribed hormones within a supportive health system. Four studies from the U.S. (N = 2), Brazil (N = 1), and the U.K. (N = 1) found that individuals seeking gender-affirming hormone therapy may self-manage due to challenges finding knowledgeable and non-stigmatising health workers, lack of access to appropriate services, exclusion, and discomfort with health workers, cost, and desire for a faster transition. One study from Thailand found health worker perspectives were shaped by restrictive legislation, few transgender-specific services or guidelines, inappropriate communication with health workers, and medical knowledge gaps. There is limited literature on self-administration of gender-affirming hormone therapy. Principles of gender equality and human rights in the delivery of quality gender-affirming hormones are critical to expand access to this important intervention and reduce discrimination based on gender identity.