Hasil untuk "Medical legislation"

Vangelis Kostoulas, Arthur Guijt, Ellen M. Kerkhof et al.

Brachytherapy involves bringing a radioactive source near tumor tissue using implanted needles. Image-guided brachytherapy planning requires amongst others, the reconstruction of the needles. Manually annotating these needles on patient images can be a challenging and time-consuming task for medical professionals. For automatic needle reconstruction, a two-stage pipeline is commonly adopted, comprising a segmentation stage followed by a post-processing stage. While deep learning models are effective for segmentation, their results often contain errors. No currently existing post-processing technique is robust to all possible segmentation errors. We therefore propose adaptations to existing post-processing techniques mainly aimed at dealing with segmentation errors and thereby improving the reconstruction accuracy. Experiments on a prostate cancer dataset, based on MRI scans annotated by medical professionals, demonstrate that our proposed adaptations can help to effectively manage segmentation errors, with the best adapted post-processing technique achieving median needle-tip and needle-bottom point localization errors of $1.07$ (IQR $\pm 1.04$) mm and $0.43$ (IQR $\pm 0.46$) mm, respectively, and median shaft error of $0.75$ (IQR $\pm 0.69$) mm with 0 false positive and 0 false negative needles on a test set of 261 needles.

Jordi de la Torre

Objective: To develop and evaluate a scalable methodology for harmonizing inconsistent units in large-scale clinical datasets, addressing a key barrier to data interoperability. Materials and Methods: We designed a novel unit harmonization system combining BM25, sentence embeddings, Bayesian optimization, and a bidirectional transformer based binary classifier for retrieving and matching laboratory test entries. The system was evaluated using the Optum Clinformatics Datamart dataset (7.5 billion entries). We implemented a multi-stage pipeline: filtering, identification, harmonization proposal generation, automated re-ranking, and manual validation. Performance was assessed using Mean Reciprocal Rank (MRR) and other standard information retrieval metrics. Results: Our hybrid retrieval approach combining BM25 and sentence embeddings (MRR: 0.8833) significantly outperformed both lexical-only (MRR: 0.7985) and embedding-only (MRR: 0.5277) approaches. The transformer-based reranker further improved performance (absolute MRR improvement: 0.10), bringing the final system MRR to 0.9833. The system achieved 83.39\% precision at rank 1 and 94.66\% recall at rank 5. Discussion: The hybrid architecture effectively leverages the complementary strengths of lexical and semantic approaches. The reranker addresses cases where initial retrieval components make errors due to complex semantic relationships in medical terminology. Conclusion: Our framework provides an efficient, scalable solution for unit harmonization in clinical datasets, reducing manual effort while improving accuracy. Once harmonized, data can be reused seamlessly in different analyses, ensuring consistency across healthcare systems and enabling more reliable multi-institutional studies and meta-analyses.

Andrea Moglia, Matteo Leccardi, Matteo Cavicchioli et al.

Following the successful paradigm shift of large language models, leveraging pre-training on a massive corpus of data and fine-tuning on different downstream tasks, generalist models have made their foray into computer vision. The introduction of Segment Anything Model (SAM) set a milestone on segmentation of natural images, inspiring the design of a multitude of architectures for medical image segmentation. In this survey we offer a comprehensive and in-depth investigation on generalist models for medical image segmentation. We start with an introduction on the fundamentals concepts underpinning their development. Then, we provide a taxonomy on the different declinations of SAM in terms of zero-shot, few-shot, fine-tuning, adapters, on the recent SAM 2, on other innovative models trained on images alone, and others trained on both text and images. We thoroughly analyze their performances at the level of both primary research and best-in-literature, followed by a rigorous comparison with the state-of-the-art task-specific models. We emphasize the need to address challenges in terms of compliance with regulatory frameworks, privacy and security laws, budget, and trustworthy artificial intelligence (AI). Finally, we share our perspective on future directions concerning synthetic data, early fusion, lessons learnt from generalist models in natural language processing, agentic AI and physical AI, and clinical translation.

Qiang Li, Heyu Ma, Chengcheng Liu et al.

Full Waveform Inversion (FWI) is a promising technique for achieving high-resolution imaging in medical ultrasound. However, conventional FWI methods suffer from issues related to computational efficiency, dependence on initial models, and the inability to quantify uncertainty. This study aims to enhance inversion performance and provide a reliable method for uncertainty quantification in medical FWI imaging. This study integrates the Stein Variational Gradient Descent (SVGD) algorithm into the FWI framework by deriving the posterior gradient for probabilistic inversion. To evaluate the proposed method, numerical experiments are conducted on synthetic datasets, including a breast tissue model with realistic anatomical structure. Imaging accuracy and uncertainty quantification are assessed to compare the performance of SVGD-based FWI with conventional FWI and Stochastic Variational Inference (SVI) methods. Markov Chain Monte Carlo (MCMC) is implemented as a benchmark to evaluate the quality of uncertainty estimates. For synthetic data, the SVGD-based FWI framework yields more precise estimates in the region of interest (ROI) and demonstrates faster convergence compared to the conventional FWI. For the anatomically realistic breast tissue simulation, SVGD produces a maximum relative error of 1.10\% and a mean relative error of 0.09\% in the ROI. The estimated uncertainty is spatially consistent, with most values below 0.01 and a mean of approximately 0.003. Compared to SVI, SVGD provides improved structural resolution and stronger agreement with the MCMC benchmark, indicating more reliable uncertainty quantification. The SVGD-based FWI method improves inversion quality, enhances uncertainty quantification. These findings indicate that probabilistic inversion is a promising tool for addressing the limitations of traditional FWI methods in ultrasonic imaging of medical tissues.

Saurabh Koju, Saurav Bastola, Prashant Shrestha et al.

Realistic and interactive surgical simulation has the potential to facilitate crucial applications, such as medical professional training and autonomous surgical agent training. In the natural visual domain, world models have enabled action-controlled data generation, demonstrating the potential to train autonomous agents in interactive simulated environments when large-scale real data acquisition is infeasible. However, such works in the surgical domain have been limited to simplified computer simulations, and lack realism. Furthermore, existing literature in world models has predominantly dealt with action-labeled data, limiting their applicability to real-world surgical data, where obtaining action annotation is prohibitively expensive. Inspired by the recent success of Genie in leveraging unlabeled video game data to infer latent actions and enable action-controlled data generation, we propose the first surgical vision world model. The proposed model can generate action-controllable surgical data and the architecture design is verified with extensive experiments on the unlabeled SurgToolLoc-2022 dataset. Codes and implementation details are available at https://github.com/bhattarailab/Surgical-Vision-World-Model

Miriam Fuerst-Wilmes, Vanessa Respondek, Michael Schramm et al.

Due to their biological properties, bacteriophages represent a regulatory specialty and, at the same time, a challenge with regard to medicinal product approval. Established European guidelines on pharmaceutical quality, preclinical development, and clinical development are only partially applicable. The growing threat posed by infections with multidrug-resistant bacteria has not only boosted the development of bacteriophages for the treatment of bacterial infections in recent years but has also led to substantial progress in adapting regulatory requirements. In 2024, harmonized quality criteria for phage therapy medicinal products and active substances were implemented for the first time in the European Pharmacopoeia. Future European pharmaceutical legislation and recent national acts such as the German Medical Research Act are intended to enable exemptions that address the specific characteristics of phage therapeutics and open new regulatory pathways. Increasing amounts of data on clinical use of phage therapeutics are being published; however, the anticipated breakthrough in the form of a demonstration of efficacy in randomized controlled clinical trials has not yet been achieved. Growing experience with innovative phage preparations has been utilized to adjust regulatory requirements. On the path to approval of a defined phage therapy medicinal product, the evidence-based demonstration of efficacy and safety in randomized controlled clinical trials is the next and decisive step.

Atharvan Dogra, Krishna Pillutla, Ameet Deshpande et al.

We explore the ability of large language models (LLMs) to engage in subtle deception through strategically phrasing and intentionally manipulating information. This harmful behavior can be hard to detect, unlike blatant lying or unintentional hallucination. We build a simple testbed mimicking a legislative environment where a corporate \textit{lobbyist} module is proposing amendments to bills that benefit a specific company while evading identification of this benefactor. We use real-world legislative bills matched with potentially affected companies to ground these interactions. Our results show that LLM lobbyists can draft subtle phrasing to avoid such identification by strong LLM-based detectors. Further optimization of the phrasing using LLM-based re-planning and re-sampling increases deception rates by up to 40 percentage points. Our human evaluations to verify the quality of deceptive generations and their retention of self-serving intent show significant coherence with our automated metrics and also help in identifying certain strategies of deceptive phrasing. This study highlights the risk of LLMs' capabilities for strategic phrasing through seemingly neutral language to attain self-serving goals. This calls for future research to uncover and protect against such subtle deception.

A. S. Lunev, K. A. Petrosova, K. E. Ternovskaya et al.

SCIENTIFIC RELEVANCE. Owing to specific aspects of their development and use, radiopharmaceuticals require separate rules and regulations for preclinical studies. However, current legislation and regulations on the organisation and conduct of preclinical studies of radiopharmaceuticals contain a number of contradictions and need improvement.AIM. This review aimed to analyse the rules and regulations governing preclinical studies of radiopharmaceuticals in the Russian Federation and abroad.DISCUSSION. The regulatory requirements for preclinical studies of radiopharmaceuticals that are conducted by specialised institutions in Russia and abroad have several shortcomings and inconsistencies. Laboratories working with animals and open sources of ionising radiation should prioritise regulations related to radiation safety. Radiation safety requirements should be in line with the sanitary standards and practical guidelines used in preclinical studies. This review covers the specific aspects of conducting preclinical studies of therapeutic and diagnostic radiopharmaceuticals. According to the review results, international guidelines for preclinical studies of radiopharmaceuticals focus on systematising the applicable requirements and aim at providing a consistent approach to preclinical studies to reduce the conduct of studies that are not informative for a specific radiopharmaceutical product.CONCLUSIONS. Radiation safety requirements should be harmonised with international guidelines. Methodological recommendations and local regulations should be developed and approved to facilitate the resolution of regulatory issues related to the organisation and conduct of preclinical studies of radiopharmaceuticals. Many medical, social, technical, and administrative issues need addressing at the inter-institutional and/or national level.

Yongyi Shi, Wenjun Xia, Chuang Niu et al.

Deep learning methods have impacted almost every research field, demonstrating notable successes in medical imaging tasks such as denoising and super-resolution. However, the prerequisite for deep learning is data at scale, but data sharing is expensive yet at risk of privacy leakage. As cutting-edge AI generative models, diffusion models have now become dominant because of their rigorous foundation and unprecedented outcomes. Here we propose a latent diffusion approach for data synthesis without compromising patient privacy. In our exemplary case studies, we develop a latent diffusion model to generate medical CT, MRI and PET images using publicly available datasets. We demonstrate that state-of-the-art deep learning-based denoising/super-resolution networks can be trained on our synthetic data to achieve image quality equivalent to what the same network can achieve after being trained on the original data (the p values well exceeding the threshold of 0.05). In our advanced diffusion model, we specifically embed a safeguard mechanism to protect patient privacy effectively and efficiently. Consequently, every synthetic image is guaranteed to be different by a pre-specified threshold from the closest counterpart in the original patient dataset. Our approach allows privacy-proof public sharing of diverse big datasets for development of deep models, potentially enabling federated learning at the level of input data instead of local network weights.

Geoffroy Oudoumanessah, Carole Lartizien, Michel Dojat et al.

Anomaly detection in medical imaging is a challenging task in contexts where abnormalities are not annotated. This problem can be addressed through unsupervised anomaly detection (UAD) methods, which identify features that do not match with a reference model of normal profiles. Artificial neural networks have been extensively used for UAD but they do not generally achieve an optimal trade-o$\hookleftarrow$ between accuracy and computational demand. As an alternative, we investigate mixtures of probability distributions whose versatility has been widely recognized for a variety of data and tasks, while not requiring excessive design e$\hookleftarrow$ort or tuning. Their expressivity makes them good candidates to account for complex multivariate reference models. Their much smaller number of parameters makes them more amenable to interpretation and e cient learning. However, standard estimation procedures, such as the Expectation-Maximization algorithm, do not scale well to large data volumes as they require high memory usage. To address this issue, we propose to incrementally compute inferential quantities. This online approach is illustrated on the challenging detection of subtle abnormalities in MR brain scans for the follow-up of newly diagnosed Parkinsonian patients. The identified structural abnormalities are consistent with the disease progression, as accounted by the Hoehn and Yahr scale.

D. Hudson Smith, John Paul Lineberger, George H. Baker

Many medical ultrasound video recognition tasks involve identifying key anatomical features regardless of when they appear in the video suggesting that modeling such tasks may not benefit from temporal features. Correspondingly, model architectures that exclude temporal features may have better sample efficiency. We propose a novel multi-head attention architecture that incorporates these hypotheses as inductive priors to achieve better sample efficiency on common ultrasound tasks. We compare the performance of our architecture to an efficient 3D CNN video recognition model in two settings: one where we expect not to require temporal features and one where we do. In the former setting, our model outperforms the 3D CNN - especially when we artificially limit the training data. In the latter, the outcome reverses. These results suggest that expressive time-independent models may be more effective than state-of-the-art video recognition models for some common ultrasound tasks in the low-data regime.

Lindy Willmott, Casey Haining, Ben White

Australians living in regional and remote communities face several barriers when accessing high quality health care. Voluntary assisted dying (VAD), a new and sensitive end-of-life option, presents a new challenge for residents living in these communities. Western Australia (WA) is the second Australian state to implement VAD laws and, to date, is the jurisdiction with the greatest need to address access inequities in regional and remote communities due to its vast area. This article identifies and explores initiatives introduced by the WA Government to address regional and remote access inequities in each of the two stages of the reform process: the stage of the reform process leading up to passing the law ('law-making stage'), and the stage of the reform process after the law was passed and prior to it commencing operation ('implementation stage'). The analysis reveals that several initiatives were implemented during each of the law-making and implementation stages of reform. Initiatives introduced in the law-making stage through inclusion in the legislation itself included dedicated guiding principles promoting equality of access for regional and remote residents, broadened qualification requirements for medical practitioners who can participate in VAD, allowing nurse practitioner administration, and mandating that statistics relating to regional and remote access are recorded and reported. Other initiatives dedicated to facilitating regional and remote access were not specifically provided for by legislation but were introduced during the implementation stage of the reform process. These include the establishment of a Statewide Care Navigator Service that administers a Regional Access Support Scheme and ensuring that the Statewide Pharmacy Service is accessible to regional and remote residents. Other initiatives intended to facilitate regional and remote access were provided for in legislation but given further content during the implementation stage. These include an access standard (contents determined by the CEO during implementation) and telehealth (supporting guidance around lawful use issued by the WA Government during implementation). This policy report reveals that WA took a considered and targeted focus to address regional and remote access in both the law-making and implementation stages of reform. Given VAD in WA is still in the early stages of its operation, it is too soon to determine how effective these initiatives have been in promoting regional and remote access to VAD in WA. Careful evaluation of these initiatives will be crucial to monitor their effectiveness and to assess whether additional measures are needed. Reflecting on the WA experience will also be valuable for other states as they legalise VAD and develop (and adapt) their own access initiatives.

Zhaonian Zhang, Richard Jiang, Danny Crookes et al.

In recent years, there are various methods of estimating Biological Age (BA) have been developed. Especially with the development of machine learning (ML), there are more and more types of BA predictions, and the accuracy has been greatly improved. The models for the estimation of BA play an important role in monitoring healthy aging, and could provide new tools to detect health status in the general population and give warnings to sub-healthy people. We will mainly review three age prediction methods by using ML. They are based on blood biomarkers, facial images, and structural neuroimaging features. For now, the model using blood biomarkers is the simplest, most direct, and most accurate method. The face image method is affected by various aspects such as race, environment, etc., the prediction accuracy is not very good, which cannot make a great contribution to the medical field. In summary, we are here to track the way forward in the era of big data for us and other potential general populations and show ways to leverage the vast amounts of data available today.

Ines Elisa Ulrich, Christian Boehm, Andrea Zunino et al.

An alternative approach to ultrasound computed tomography (USCT) for medical imaging is proposed, with the intent to (i) shorten acquisition time for devices with a large number of emitters, (ii) eliminate the calibration step, and (iii) suppress instrument noise. Inspired by seismic ambient field interferometry, the method rests on the active excitation of diffuse ultrasonic wavefields and the extraction of deterministic travel time information by inter-station correlation. To reduce stochastic errors and accelerate convergence, ensemble interferograms are obtained by phase-weighted stacking of observed and computed correlograms, generated with identical realizations of random sources. Mimicking a breast imaging setup, the accuracy of the travel time measurements as a function of the number of emitters and random realizations can be assessed both analytically and with spectral-element simulations for realistic breast phantoms. The results warrant tomographic reconstructions with straight- or bent-ray approaches, where the effect of inherent stochastic fluctuations can be made significantly smaller than the effect of subjective choices on regularisation. This work constitutes a first conceptual study and a necessary prelude to future implementations.

Shaymaa Al-kubaisy, Ban Khalaf, Evan Khaleef

One of the most problematic health issues nowadays is the prevalence of nosocomial diseases which is one of the most important health problems in the world and till now there are no series solutions. There are several types of nosocomial infection such as; Infections of the bloodstream caused by a central line (CLABSI), Infections of the Urinary Tract Caused by Catheters (CAUTI), Infections at the Site of Surgery (SSI), and Pneumonia linked with Ventilators (VAP). All these types caused by one or more type of biological agent such as bacteria, viruses and fungi. Uncontrolled use of drugs and disregard for health preventative techniques will result in significant health troubles, such as an increase in antibiotic resistance, which the medical community views as a major concern. The most urgent problem facing the medical profession at the moment is the existence of bacteria with genetic traits that allow them to resist antibiotics. It is now necessary to utilize extra antibiotics or a combination of antibiotics to treat many straightforward illnesses that could previously be treated with simple antibiotics. To lessen the harmful repercussions that might arise in the future from failing to pay attention to this problem, several efforts and activities must be done to restrict the spread of nosocomial diseases. Also, should awareness the people to avoid using antibiotics unless absolutely essential. On the other hand, it would be advisable to pass legislation requiring a prescription from a licensed medical expert before any prescriptions may be filled at a pharmacy or drug store.

Abhinav K. Jha, Kyle J. Myers, Nancy A. Obuchowski et al.

Artificial intelligence (AI)-based methods are showing promise in multiple medical-imaging applications. Thus, there is substantial interest in clinical translation of these methods, requiring in turn, that they be evaluated rigorously. In this paper, our goal is to lay out a framework for objective task-based evaluation of AI methods. We will also provide a list of tools available in the literature to conduct this evaluation. Further, we outline the important role of physicians in conducting these evaluation studies. The examples in this paper will be proposed in the context of PET with a focus on neural-network-based methods. However, the framework is also applicable to evaluate other medical-imaging modalities and other types of AI methods.

Carolina Luque, Juan Sosa

This paper applies Bayesian methodologies to characterize the legislative behavior of the Colombian Senate during the period 2010-2014. The analysis is carried out through the plenary roll call votes of this legislative chamber. In addition, parliamentary electoral behavior is operationalized by implementing the one-dimensional standard Bayesian ideal point estimator via the Markov chain Monte Carlo algorithms. The results contribute mainly to two points: political space dimensionality and the identification of pivot legislators. The pattern revealed by the estimated ideal points suggests a latent non-ideological trait (opposition - non-opposition) underlying the vote of deputies in the Senate. Thus, in addition to providing empirical evidence for a better understanding of legislative policy in Colombia during the period under analysis, this work also offers methodological and theoretical tools to guide the analysis of roll call vote data in contexts of unbalanced parliaments (as opposed to the U.S. parliament), taking the particular case of the Colombian Senate as a reference.

Sho Ozaki, Shizuo Kaji, Kanabu Nawa et al.

In recent years, deep-learning-based image processing has emerged as a valuable tool for medical imaging owing to its high performance. However, the quality of deep-learning-based methods heavily relies on the amount of training data; the high cost of acquiring a large dataset is a limitation to their utilization in medical fields. Herein, based on deep learning, we developed a computed tomography (CT) modality conversion method requiring only a few unsupervised images. The proposed method is based on CycleGAN with several extensions tailored for CT images, which aims at preserving the structure in the processed images and reducing the amount of training data. This method was applied to realize the conversion of megavoltage computed tomography (MVCT) to kilovoltage computed tomography (kVCT) images. Training was conducted using several datasets acquired from patients with head and neck cancer. The size of the datasets ranged from 16 slices (two patients) to 2745 slices (137 patients) for MVCT and 2824 slices (98 patients) for kVCT. The required size of the training data was found to be as small as a few hundred slices. By statistical and visual evaluations, the quality improvement and structure preservation of the MVCT images converted by the proposed model were investigated. As a clinical benefit, it was observed by medical doctors that the converted images enhanced the precision of contouring. We developed an MVCT to kVCT conversion model based on deep learning, which can be trained using only a few hundred unpaired images. The stability of the model against changes in data size was demonstrated. This study promotes the reliable use of deep learning in clinical medicine by partially answering commonly asked questions, such as "Is our data sufficient?" and "How much data should we acquire?"

Khomyakova Margarita, Bagretsov Dmitry

The text of this article emphasizes that the history of transplantation as an independent medical industry originated in the Union of Soviet Socialist Republics, the first successful operation to transplant human organs and tissues was performed there by the surgeon Yuri Voronoy. Today Russia is one of the world-leading powers where human organ and tissue transplant operations are performed. Among all the subjects of Russia where transplant operations are carried out, Sverdlovsk region occupies a special place: doctors in this region conduct successful operations on organ and tissue transplantation and make discoveries that are significant for Russian transplantology. The study of Russian laws and regulations regulating relations in the field of transplantology conducted by authors, as well as an analysis of the scientific literature showed that relations in the field of transplantology are not fully regulated by Russian legislation, including criminal law. On the territory of Sverdlovsk region in particular, as well as on the territory of Sverdlovsk region as a whole, it is possible, for example, to carry out transactions for the sale and purchase of human organs and tissues with impunity, if such transactions are not related to causing harm to the life and health of the victim. These deals are illegal, but not punishable. As the analysis of the practice carried out in the framework of this study has shown, the inhabitants of Sverdlovsk region suffered from the imperfection of the norms of Russian legislation regulating relations in the field of transplantology. While the residents of Sverdlovsk region are suffering from illegal transplantation, one cannot speak of the sustainable development of this region. The authors of the study, in order to combat illegal transplantation in Sverdlovsk region, propose that the regional authorities strengthen measures to improve the general legal literacy of the population, introduce a register of citizens' opinions on the posthumous transplantation of their organs and tissues, and introduce mandatory registration of transactions made in Sverdlovsk region, a subject of which are human organs and tissues.

E. Brücken, S. Bharthuar, M. Emzir et al.

We present the current status of our project of developing a photon counting detector for medical imaging. An example motivation lays in producing a monitoring and dosimetry device for boron neutron capture therapy, currently not commercially available. Our approach combines in-house developed detectors based on cadmium telluride or thick silicon with readout chip technology developed for particle physics experiments at CERN. Here we describe the manufacturing process of our sensors as well as the processing steps for the assembly of first prototypes. The prototypes use currently the PSI46digV2.1-r readout chip. The accompanying readout electronics chain that was used for first measurements will also be discussed. Finally we present an advanced algorithm developed by us for image reconstruction using such photon counting detectors with focus on boron neutron capture therapy. This work is conducted within a consortium of Finnish research groups from Helsinki Institute of Physics, Aalto University, Lappeenranta-Lahti University of Technology LUT and Radiation and Nuclear Safety Authority (STUK) under the RADDESS program of Academy of Finland. Keywords: Solid state detectors, X-ray detectors, Gamma detectors, Neutron detectors, Instrumentation for hadron therapy, Medical-image reconstruction methods and algorithms.