Hasil untuk "Medical legislation"

Anas Zafar, Leema Krishna Murali, Ashish Vashist

Recent work shows that text-only reinforcement learning with verifiable rewards (RLVR) can match or outperform image-text RLVR on multimodal medical VQA benchmarks, suggesting current evaluation protocols may fail to measure causal visual dependence. We introduce a counterfactual evaluation framework using real, blank, and shuffled images across four medical VQA benchmarks: PathVQA, PMC-VQA, SLAKE, and VQA-RAD. Beyond accuracy, we measure Visual Reliance Score (VRS), Image Sensitivity (IS), and introduce Hallucinated Visual Reasoning Rate (HVRR) to detect cases where models generate visual claims despite producing image-invariant answers. Our findings reveal that RLVR improves accuracy while degrading visual grounding: text-only RLVR achieves negative VRS on PathVQA (-0.09), performing better with mismatched images, while image-text RLVR reduces image sensitivity to 39.8% overall despite improving accuracy. On VQA-RAD, both variants achieve 63% accuracy through different mechanisms: text-only RLVR retains 81% performance with blank images, while image-text RLVR shows only 29% image sensitivity. Models generate visual claims in 68-74% of responses, yet 38-43% are ungrounded (HVRR). These findings demonstrate that accuracy-only rewards enable shortcut exploitation, and progress requires grounding-aware evaluation protocols and training objectives that explicitly enforce visual dependence.

Shahad Fadhil Bunyan, Attia Suleiman Khalifa

Medical tourism, including in the fields of prosthetic and maxillofacial dentistry, is a rapidly developing segment of the global healthcare industry. With the development of new technologies, such as 3D printing and dental implants, increasing numbers of patients are traveling abroad for dental treatment. This study demonstrates the complex legal consequences of medical errors in prosthetic dental treatment and clarifies the subtleties of professional fault according to the principles of law, and highlights the dual ergonomic and aesthetic aspects of prosthetic dentistry that differentiate it from direct therapeutic interventions and complicate both demonstration of harm and attribution of responsibility. It addresses the principles of private international law governing conflicts of law, and clarifies how the applicable law is determined when dentist and patient are from different countries, or when treatment has occurred abroad. It also provides a comparison of international regulations and legislation protecting patient rights, such the Oviedo Convention and the World Health Organization Declaration, and exposes the lack, in national laws, of any specific rules governing dental medical liability. The study concludes by stressing the need to increase dentists' understanding of the law, create new ways, such as mediation and arbitration, to settle disputes, and create a unified, global legal framework for medical responsibility in prosthetic dentistry.

Simon Chesterman

"Fake news" is an old problem. In recent years, however, increasing usage of social media as a source of information, the spread of unverified medical advice during the Covid-19 pandemic, and the rise of generative artificial intelligence have seen a rush of legislative proposals seeking to minimize or mitigate the impact of false information spread online. Drawing on a novel dataset of statutes and other instruments, this article analyses changing perceptions about the potential harms caused by misinformation, disinformation, and "mal-information". The turn to legislation began in countries that were less free, in terms of civil liberties, and poorer, as measured by GDP per capita. Internet penetration does not seem to have been a driving factor. The focus of such laws is most frequently on national security broadly construed, though 2020 saw a spike in laws addressing public health. Unsurprisingly, governments with fewer legal constraints on government action have generally adopted more robust positions in dealing with false information. Despite early reservations, however, growth in such laws is now steepest in Western states. Though there are diverse views on the appropriate response to false information online, the need for legislation of some kind appears now to be global. The question is no longer whether to regulate "lawful but awful" speech online, but how.

Patrícia de Paula Queiroz Bonato, Carla Aparecida Arena Ventura, Claudio do Prado Amaral et al.

A instituição do Programa Nacional de Qualidade de Vida para Profissionais de Segurança Pública, em 2018, no contexto da criação do Sistema Único de Segurança Pública, estabeleceu como objetivo a atenção psicossocial e de saúde no trabalho para os profissionais que atuam na segurança pública. O contexto da pandemia da covid-19 reforçou a importância de estudos e cuidados voltados à saúde em prisões, que são historicamente suscetíveis às doenças infecciosas. O presente trabalho objetivou reunir e sintetizar as publicações a respeito da assistência à saúde de policiais penais durante a pandemia da covid-19 no Brasil, identificando as iniciativas que foram desenvolvidas nesse contexto para preservar a saúde desses profissionais. Trata-se de uma revisão de escopo, com abordagem qualitativa de dados, que foi complementada por pesquisa documental na plataforma eletrônica do Departamento Penitenciário Nacional. A análise dos dados permitiu identificar que, no Brasil, houve um baixo número de pesquisas acerca da saúde de policiais penais, durante o período de pandemia em análise e que, diante dos comprovados riscos a que essa categoria profissional está submetida, é imprescindível o cumprimento do disposto na Portaria n. 483/2021, a respeito da realização de pesquisas na área para identificar o perfil sociodemográfico e as condições de saúde física e mental dos policiais penais. Mostra-se urgente a promoção de uma cultura de saúde em prisões que abranja os profissionais que ali trabalham. Tal cultura deveria começar por uma revisão da lógica do encarceramento massivo e pela instituição de políticas públicas de prevenção, promoção e educação em saúde para policiais penais e demais profissionais que trabalham em prisões.

Loany Alvarado Sorto

Justificación: Pese a que el país cuenta con normativa jurídica que en teoría permite contrarrestar adecuadamente el problema de la violencia contra la mujer, en la práctica esto no siempre es posible debido a limitantes operativas. Objetivo: Reflexionar sobre la urgente necesidad que tiene el Estado de Honduras de priorizar a través de su institucionalidad el problema de la violencia contra la mujer, que ha alcanzado proporciones alarmantes. Conclusión: La alarmante situación de violencia que viven las mujeres hondureñas requiere que de manera urgente se implementen políticas públicas eficaces, en materia de violencia basada en género para lograr reducir las cifras impactantes que afectan a la población en general, pero a las mujeres en particular afectando su desarrollo humano.

Anna Reithmeir, Veronika Spieker, Vasiliki Sideri-Lampretsa et al.

Image registration is fundamental in medical imaging applications, such as disease progression analysis or radiation therapy planning. The primary objective of image registration is to precisely capture the deformation between two or more images, typically achieved by minimizing an optimization problem. Due to its inherent ill-posedness, regularization is a key component in driving the solution toward anatomically meaningful deformations. A wide range of regularization methods has been proposed for both conventional and deep learning-based registration. However, the appropriate application of regularization techniques often depends on the specific registration problem, and no one-fits-all method exists. Despite its importance, regularization is often overlooked or addressed with default approaches, assuming existing methods are sufficient. A comprehensive and structured review remains missing. This review addresses this gap by introducing a novel taxonomy that systematically categorizes the diverse range of proposed regularization methods. It highlights the emerging field of learned regularization, which leverages data-driven techniques to automatically derive deformation properties from the data. Moreover, this review examines the transfer of regularization methods from conventional to learning-based registration, identifies open challenges, and outlines future research directions. By emphasizing the critical role of regularization in image registration, we hope to inspire the research community to reconsider regularization strategies in modern registration algorithms and to explore this rapidly evolving field further.

Shahabedin Nabavi, Kian Anvari Hamedani, Mohsen Ebrahimi Moghaddam et al.

Background: Image classification can be considered one of the key pillars of medical image analysis. Deep learning (DL) faces challenges that prevent its practical applications despite the remarkable improvement in medical image classification. The data distribution differences can lead to a drop in the efficiency of DL, known as the domain shift problem. Besides, requiring bulk annotated data for model training, the large size of models, and the privacy-preserving of patients are other challenges of using DL in medical image classification. This study presents a strategy that can address the mentioned issues simultaneously. Method: The proposed domain adaptive model based on knowledge distillation can classify images by receiving limited annotated data of different distributions. The designed multiple teachers-meticulous student model trains a student network that tries to solve the challenges by receiving the parameters of several teacher networks. The proposed model was evaluated using six available datasets of different distributions by defining the respiratory motion artefact detection task. Results: The results of extensive experiments using several datasets show the superiority of the proposed model in addressing the domain shift problem and lack of access to bulk annotated data. Besides, the privacy preservation of patients by receiving only the teacher network parameters instead of the original data and consolidating the knowledge of several DL models into a model with almost similar performance are other advantages of the proposed model. Conclusions: The proposed model can pave the way for practical clinical applications of deep classification methods by achieving the mentioned objectives simultaneously.

Yunlu Yan, Lei Zhu, Yuexiang Li et al.

Improving the fairness of federated learning (FL) benefits healthy and sustainable collaboration, especially for medical applications. However, existing fair FL methods ignore the specific characteristics of medical FL applications, i.e., domain shift among the datasets from different hospitals. In this work, we propose Fed-LWR to improve performance fairness from the perspective of feature shift, a key issue influencing the performance of medical FL systems caused by domain shift. Specifically, we dynamically perceive the bias of the global model across all hospitals by estimating the layer-wise difference in feature representations between local and global models. To minimize global divergence, we assign higher weights to hospitals with larger differences. The estimated client weights help us to re-aggregate the local models per layer to obtain a fairer global model. We evaluate our method on two widely used federated medical image segmentation benchmarks. The results demonstrate that our method achieves better and fairer performance compared with several state-of-the-art fair FL methods.

Yucheng Lu, Dovile Juodelyte, Jonathan D. Victor et al.

In this paper, we use spectral analysis to investigate transfer learning and study model sensitivity to frequency shortcuts in medical imaging. By analyzing the power spectrum density of both pre-trained and fine-tuned model gradients, as well as artificially generated frequency shortcuts, we observe notable differences in learning priorities between models pre-trained on natural vs medical images, which generally persist during fine-tuning. We find that when a model's learning priority aligns with the power spectrum density of an artifact, it results in overfitting to that artifact. Based on these observations, we show that source data editing can alter the model's resistance to shortcut learning.

SungKyung Lee, Jong Hyuk Lee

Ever since relevant bioengineering technologies have sufficiently matured to the platformizable commercialization stage, a slew of money has flocked to the cell and gene therapy market over the last few years, resulting in an abundance of clinical studies in the field. Newer modalities have brought up a string of regulatory and legislative tasks, such as developing guidelines and legislative rules to systematically regulate newer pharmaceutical products. Accordingly, another layer of legislation and guidelines tailored for cell and gene therapies has been introduced and is expected to evolve on par with technological progress. Furthermore, authorities have shifted to pricing and reimbursement policies that can share risks for cost and outcome among stakeholders altogether, such as developers and the government, while expanding the accessibility of patients to innovative cell and gene therapies. This review attempts to capture the salient regulatory features of the cell and gene therapy market in the context of South Korea and the European Union and points out where two sovereign entities currently stand on each policy element and how each tackles regulatory challenges. We can observe the converging trend where regulatory, pricing and reimbursement rules of adjoining countries in the supranational union or member countries of a consortium are getting more aligned. Evidently, concerted efforts to share regulatory science knowledge and embrace reference pricing have played their parts. The authors argue that policy priorities should be placed on initiatives to harmonize with other medical authorities to better the rights of patients and clear out the uncertainties of developers, ultimately to share and advance regulatory science and layout forward-looking policies at opportune times.

Germano André Doederlein Schwartz, Renata Almeida da Costa, Matteo Finco

A pandemia de covid-19 representou um grande desafio para a diferenciação dos sistemas sociais. O Brasil foi a segunda nação do mundo em número de vítimas, e a influência das decisões tomadas dentro de diferentes esferas sociais (em particular saúde, ciência, direito e mídia de massa) tenderam, no país, a afetar as demais de maneria imprópria. O propósito do presente estudo foi apresentar, com base nas teorias dos sistemas sociais de Luhmann, os perigos dessa desdiferenciação para a sociedade e, também, para o indivíduo. A metodologia consistiu na pesquisa bibliográfica. O estudo concluiu que a preservação da função de cada um dos sistemas citados é essencial para a preservação de suas respectivas autonomias e da saúde coletiva e individual em solo brasileiro.

P. Chiara

ABSTRACT This article aims to cast light on how the fast-evolving European cybersecurity regulatory framework would impact the Internet of Things (IoT) domain. The legal analysis investigates whether and to what extent existing and proposed sectoral EU legislation addresses the manifold challenges in securing IoT and its supply chain. It firstly takes into account the Cybersecurity Act, being the most recent and relevant EU legal act covering ICT products and cybersecurity services. Then, EU product legislation is scrutinised. The analysis focuses on the delegated act recently adopted by the Commission under the Radio Equipment Directive (RED), strengthening wireless devices’ cybersecurity, the Medical Devices Regulation, the Proposal for a General Product Safety Regulation and the Proposal for a Machinery Regulation. Lastly, the proposal for a revised Network and Information Systems Directive (NIS2) is assessed in terms of its potential impact on the field of IoT cybersecurity. Against this backdrop, the article concludes by advocating the need for a separate horizontal legislation on cybersecurity for connected products. To avoid fragmentation of the EU's Single Market, a horizontal legal act should be based on the principles of the New Legislative Framework, with ex-ante and ex-post cybersecurity requirements for all IoT sectors and products categories.

J. Downie, U. Schuklenk

The question of whether problems with the social determinants of health that might impact decision-making justify denying eligibility for assisted dying has recently come to the fore in debates about the legalisation of assisted dying. For example, it was central to critiques of the 2021 amendments made to Canada’s assisted dying law. The question of whether changes to a country’s assisted dying legislation lead to descents down slippery slopes has also come to the fore—as it does any time a jurisdiction changes its laws. We explore these two questions through the lens of Canada’s experience both to inform Canada’s ongoing discussions and because other countries will confront the same questions if they contemplate changing their assisted dying law. Canada’s Medical Assistance in Dying (MAiD) law has evolved through a journey from the courts to Parliament, back to the courts, and then back to Parliament. Along this journey the eligibility criteria, the procedural safeguards, and the monitoring regime have changed. In this article, we focus on the eligibility criteria. First, we explain the evolution of the law and what the eligibility criteria were at the various stops along the way. We then explore the ethical justifications for Canada’s new criteria by looking at two elements of the often-corrosive debate. First, we ask whether problems with the social determinants of health that might impact decision-making justify denying eligibility for assisted dying of decisionally capable people with mental illnesses and people with disabilities as their sole underlying medical conditions. Second, we ask whether Canada’s journey supports slippery slope arguments against permitting assisted dying.

Jan Khre

Yawen Wu, Dewen Zeng, Zhepeng Wang et al.

Supervised deep learning needs a large amount of labeled data to achieve high performance. However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective. Federated learning (FL) can help in this regard by learning a shared model while keeping training data local for privacy. Traditional FL requires fully-labeled data for training, which is inconvenient or sometimes infeasible to obtain due to high labeling cost and the requirement of expertise. Contrastive learning (CL), as a self-supervised learning approach, can effectively learn from unlabeled data to pre-train a neural network encoder, followed by fine-tuning for downstream tasks with limited annotations. However, when adopting CL in FL, the limited data diversity on each client makes federated contrastive learning (FCL) ineffective. In this work, we propose an FCL framework for volumetric medical image segmentation with limited annotations. More specifically, we exchange the features in the FCL pre-training process such that diverse contrastive data are provided to each site for effective local CL while keeping raw data private. Based on the exchanged features, global structural matching further leverages the structural similarity to align local features to the remote ones such that a unified feature space can be learned among different sites. Experiments on a cardiac MRI dataset show the proposed framework substantially improves the segmentation performance compared with state-of-the-art techniques.

Raghavendra Selvan, Nikhil Bhagwat, Lasse F. Wolff Anthony et al.

The increasing energy consumption and carbon footprint of deep learning (DL) due to growing compute requirements has become a cause of concern. In this work, we focus on the carbon footprint of developing DL models for medical image analysis (MIA), where volumetric images of high spatial resolution are handled. In this study, we present and compare the features of four tools from literature to quantify the carbon footprint of DL. Using one of these tools we estimate the carbon footprint of medical image segmentation pipelines. We choose nnU-net as the proxy for a medical image segmentation pipeline and experiment on three common datasets. With our work we hope to inform on the increasing energy costs incurred by MIA. We discuss simple strategies to cut-down the environmental impact that can make model selection and training processes more efficient.

Md Mahfuzur Rahman Siddiquee, Jay Shah, Teresa Wu et al.

Automated anomaly detection from medical images, such as MRIs and X-rays, can significantly reduce human effort in disease diagnosis. Owing to the complexity of modeling anomalies and the high cost of manual annotation by domain experts (e.g., radiologists), a typical technique in the current medical imaging literature has focused on deriving diagnostic models from healthy subjects only, assuming the model will detect the images from patients as outliers. However, in many real-world scenarios, unannotated datasets with a mix of both healthy and diseased individuals are abundant. Therefore, this paper poses the research question of how to improve unsupervised anomaly detection by utilizing (1) an unannotated set of mixed images, in addition to (2) the set of healthy images as being used in the literature. To answer the question, we propose HealthyGAN, a novel one-directional image-to-image translation method, which learns to translate the images from the mixed dataset to only healthy images. Being one-directional, HealthyGAN relaxes the requirement of cycle consistency of existing unpaired image-to-image translation methods, which is unattainable with mixed unannotated data. Once the translation is learned, we generate a difference map for any given image by subtracting its translated output. Regions of significant responses in the difference map correspond to potential anomalies (if any). Our HealthyGAN outperforms the conventional state-of-the-art methods by significant margins on two publicly available datasets: COVID-19 and NIH ChestX-ray14, and one institutional dataset collected from Mayo Clinic. The implementation is publicly available at https://github.com/mahfuzmohammad/HealthyGAN.

Sheng He, Yanfang Feng, P. Ellen Grant et al.

Deep convolutional neural networks (CNNs) have been widely used for medical image segmentation. In most studies, only the output layer is exploited to compute the final segmentation results and the hidden representations of the deep learned features have not been well understood. In this paper, we propose a prototype segmentation (ProtoSeg) method to compute a binary segmentation map based on deep features. We measure the segmentation abilities of the features by computing the Dice between the feature segmentation map and ground-truth, named as the segmentation ability score (SA score for short). The corresponding SA score can quantify the segmentation abilities of deep features in different layers and units to understand the deep neural networks for segmentation. In addition, our method can provide a mean SA score which can give a performance estimation of the output on the test images without ground-truth. Finally, we use the proposed ProtoSeg method to compute the segmentation map directly on input images to further understand the segmentation ability of each input image. Results are presented on segmenting tumors in brain MRI, lesions in skin images, COVID-related abnormality in CT images, prostate segmentation in abdominal MRI, and pancreatic mass segmentation in CT images. Our method can provide new insights for interpreting and explainable AI systems for medical image segmentation. Our code is available on: \url{https://github.com/shengfly/ProtoSeg}.

Christos Papaloukas, Ilias Chalkidis, Konstantinos Athinaios et al.

In this work, we study the task of classifying legal texts written in the Greek language. We introduce and make publicly available a novel dataset based on Greek legislation, consisting of more than 47 thousand official, categorized Greek legislation resources. We experiment with this dataset and evaluate a battery of advanced methods and classifiers, ranging from traditional machine learning and RNN-based methods to state-of-the-art Transformer-based methods. We show that recurrent architectures with domain-specific word embeddings offer improved overall performance while being competitive even to transformer-based models. Finally, we show that cutting-edge multilingual and monolingual transformer-based models brawl on the top of the classifiers' ranking, making us question the necessity of training monolingual transfer learning models as a rule of thumb. To the best of our knowledge, this is the first time the task of Greek legal text classification is considered in an open research project, while also Greek is a language with very limited NLP resources in general.

E. Spatz, H. Krumholz, B. Moulton