{"results":[{"id":"doaj_10.1177/26323524251338859","title":"Medical assistance in dying in Canada: A review of regulatory practice standards and guidance documents for physicians","authors":[{"name":"Eliana Close"},{"name":"Mona Gupta"},{"name":"Jocelyn Downie"},{"name":"Ben P. White"}],"abstract":"Background: Medical assistance in dying (“MAiD”) became legal across Canada in 2016, and in Québec in 2015. Provincial/territorial regulatory bodies play a critical role in MAiD as they can issue binding requirements on health practitioners. Law and regulatory standards are the “twin pillars” of MAiD regulation, yet the content of MAiD practice standards for physicians is unstudied. Design: This article analysed MAiD guidance for physicians from Canadian medical regulators (often called the “College of Physicians and Surgeons”), using a qualitative descriptive approach, informed by regulatory space theory. Methods: We identified MAiD-specific regulatory documents (practice standards and related documents) using web-based searches and follow-up inquiries. We analysed the documents using qualitative descriptive analysis and the Framework Method, facilitated by NVivo. The analysis focused on identifying areas where regulators issued guidance beyond the law. Results: We identified 15 regulatory documents from 11 of the 13 provinces and territories. We determined that these documents primarily outline the law without detailed guidance on how to apply it. We identified eight areas for which regulators provided guidance that went beyond the MAiD-specific legislation, most relating to core aspects of medical practice, such as competency, documentation, and patient-centred care. The rights and obligations of conscientious objectors were a predominant focus in all documents. The documents largely lacked guidance about the meaning of terms in the legislation. There was also variation in standards between provinces and territories; the documents focused on similar topics but varied in their policy choices. Physicians in each province/territory are therefore subject to differing expectations (to some extent). Conclusion: This study highlights a gap in guidance on the meaning of legal terms in the Criminal Code MAiD provisions and highlights interprovincial/territorial variability in MAiD practice standards and guidance for physicians. The study demonstrates the risks of fragmentation inherent in polycentric regulation, which can be challenging for physicians to navigate.","source":"DOAJ","year":2025,"language":"","subjects":["Medicine (General)"],"doi":"10.1177/26323524251338859","url":"https://doi.org/10.1177/26323524251338859","is_open_access":true,"published_at":"","score":69},{"id":"doaj_doi.org/10.5377/rcfh.v11i1.21379","title":"Potencialidades y limitaciones de la aplicación de la reconstrucción cráneo-facial en la investigación forense","authors":[{"name":"Gustavo Faúndez Salinas"}],"abstract":"La evidencia en una investigación forense, exige el desarrollo y la aplicación de un análisis crítico de las imágenes, así como el estudio de su circulación y transformación.\r\nEste trabajo plantea la necesidad de contextualizar el desarrollo histórico de la reconstrucción cráneo-facial, en el marco de las técnicas biométricas y de identificación facial y evaluar las posibilidades y limitaciones, que trae consigo su aplicación forense.\r\nSe propone una puesta en contexto de las aplicaciones más recientes de la antropometría, así como la realización de un análisis de fortalezas, oportunidades, debilidades y amenazas, con el fin de alcanzar claridad, respecto de las condiciones en que resulta pertinente utilizarla y cuáles son profesionales forenses idóneos, a quienes solicitar su aplicación.\r\nFinalmente, se concluye que, con el objeto de sacar el máximo provecho del empleo de la reconstrucción cráneo-facial forense, es necesario tener claros sus límites, contar con un perfil de los profesionales idóneos y moderar las expectativas respecto de sus alcances.","source":"DOAJ","year":2025,"language":"","subjects":["Criminal law and procedure","Medical legislation","Public aspects of medicine","Social pathology. Social and public welfare. Criminology"],"doi":"doi.org/10.5377/rcfh.v11i1.21379","url":"https://www.camjol.info/index.php/RCFH/article/view/21379","is_open_access":true,"published_at":"","score":69},{"id":"doaj_10.1080/02673843.2025.2470204","title":"Beliefs and attitudes of young towards cannabis legislation and associated factors: a cross-sectional study in Morocco","authors":[{"name":"Fatima Zahra Ramdani"},{"name":"Mohamed Merzouki"},{"name":"Laila Lahlou"},{"name":"Jalal Doufik"},{"name":"Khalid Mouhadi"},{"name":"Saliha Hamri"},{"name":"Khadija Akebour"},{"name":"Said Boujraf"},{"name":"Ismail Rammouz"}],"abstract":"In Morocco, the legislation of cannabis marks a significant political shift that warrants thorough analysis. This study aims to identify the attitudes of young Moroccans towards the new cannabis regulations and their perceptions of its future consequences. A questionnaire was administered to a sample of 4040 participants, including high school and university students in southern Morocco. The results revealed that females were significantly more likely to be opposed to medical cannabis use (MCU) compared to males and believed more strongly that the law would discourage users from abstaining. Additionally, females were significantly more likely to be against the recreational use of cannabis (RCU). In contrast, tobacco smokers, cannabis users, and participants with depression were more favourable towards MCU legislation. Further studies on young people’s perceptions of cannabis and its effects remain crucial for public health and prevention policy-makers.","source":"DOAJ","year":2025,"language":"","subjects":["Special aspects of education","The family. Marriage. Woman"],"doi":"10.1080/02673843.2025.2470204","url":"https://www.tandfonline.com/doi/10.1080/02673843.2025.2470204","is_open_access":true,"published_at":"","score":69},{"id":"doaj_10.12014/j.issn.1002-0772.2025.17.12","title":"Dilemma and Legal Risk of Subrogation of Informed Consent Rights in Cancer Patients","authors":[{"name":"Qingqing HUANG"}],"abstract":"Civil Code of the People's Republic of China stipulates that when a patient \"cannot or should not\" be informed of their medical condition, such information should instead be disclosed to close relatives. But in practice, the surrogate exercise of cancer patients' right to informed consent by family members has shown signs of expansion and abuse, seriously infringing upon patients' personal rights and dignity. There is a pressing need to regulate the legal interpretation of the \"cannot or should not\" clause through legislation, judicial interpretations, and guiding case law. The scope of protective medical measures must be narrowly defined, and medical institutions should be granted limited discretionary authority when fulfilling their duty of disclosure. Additionally, a statutory procedure or third-party evaluation mechanism should be established to assess a patient's capacity for medical decision-making. These measures would reduce the legal risk of subrogation of informed consent and better safeguard the rights and interests of patients.","source":"DOAJ","year":2025,"language":"","subjects":["Medical philosophy. Medical ethics"],"doi":"10.12014/j.issn.1002-0772.2025.17.12","url":"https://yizhe.dmu.edu.cn/article/doi/10.12014/j.issn.1002-0772.2025.17.12","is_open_access":true,"published_at":"","score":69},{"id":"doaj_10.33102/mjsl.vol12no3.616","title":"PENGGUNAAN SARUNG TELUR MENTADAK DALAM PERUBATAN TRADISIONAL CINA MENURUT PERSPEKTIF FIQH KEPENGGUNAAN","authors":[{"name":"Zubair Amir Nur Rashid"},{"name":"Nur Mardia Mazri"}],"abstract":"\nConsumer jurisprudence is a branch of the broad jurisprudential debate covering the utilization and use of all natural resources and their contents. Traditional Chinese Medicine as an alternative medicine uses natural resources as a source of medicine. The Mantidis Ootheca in Traditional Chinese Medicine is a substance that comes out through a special accessory gland on the abdomen of the mantis mother and then produces a foamy and hardened structure like polystyrene. It is believed to have various benefits including treating cloudy urine, kidney health, helping in treating Benign Prostatic Hyperplasia (BPH) and others. However, there is an issue involving the status of the Mantidis Ootheca from the perspective of Islamic law since the egg case is produced from the liquid that comes out through the mantis stomach. The focus of this paper was to clarify the Islamic legislation regarding the use of Mantidis Ootheca in the manufacture of pharmaceutical products from the standpoint of the consumer jurisprudence discussion. The researcher utilized a qualitative method by referring to books of fiqh and usul fiqh to find out the law of using Mantidis Ootheca in products and the liquid flowing from its stomach in medicine. This study emphasize on analyzing the application of rukhsah and istihalah in medicine in unraveling the problem of treatment using Mantidis Ootheca. Standards from halal authorities such as the Department Standards of Malaysia are also reviewed for pharmaceutical manufacturing rules including the requirement of safety assessment. Meanwhile, the researcher also consulted scientific studies to know the benefits, uses and side effects of Mantidis Ootheca in the medical field. According to the study's findings, the use Mantidis Ootheca in medicine is not halal since they are tainted with impurities (najāsah). The egg case that come from mantis are considered disgusting, according to scholars, and should not be eaten. Still, its use in pharmaceuticals needs to be evaluated from the perspective of medical jurisprudence by looking at its level of need in the field. Until now, its use is not reached to an emergency demand as there are still alternative treatments for the related diseases. Frequently it has been consumed as a health supplement rather than the primary component in medications. It also does not meet the safety standards determined by the jurists and according to the MS 2424: 2019 ruling based on current research showing that there is no comprehensive report on toxicity aspects and adverse side effects to users. The study of the pharmaceutical industry should continue to be pioneered by Muslims to ensure the use of halal ingredients in medicine.\n\n\n \n\n\nAbstrak\n\n\nFiqh kepenggunaan merupakan suatu cabang daripada perbahasan ilmu fiqh yang luas meliputi pemanfaatan dan penggunaan segala sumber alam dan seisinya. Perubatan Tradisional Cina sebagai suatu perubatan alternatif banyak mengambil sumber alam semula jadi sebagai sumber perubatan. Sarung telur mentadak atau Mantidis Ootheca dalam Perubatan Tradisional Cina ialah suatu bahan yang keluar melalui kelenjar aksesori khas pada perut ibu mantis seterusnya menghasilkan sebuah struktur berbuih dan mengeras seperti polisterin. Ianya dipercayai mempunyai pelbagai khasiat antaranya merawat air kencing yang keruh, kesihatan ginjal, membantu dalam merawat Benign Prostatic Hyperplasia (BPH) dan lain-lain. Namun, timbul isu melibatkan status sarung telur tersebut dari perspektif hukum Islam memandangkan sarung telur itu terhasil daripada cecair yang keluar melalui perut serangga. Kertas ini ditulis bertujuan menjelaskan hukum penggunaan sarung telur mentadak dalam perubatan menurut perspektif perbahasan fiqh kepenggunaan. Pengkaji menggunakan kaedah kualitatif dengan menjadikan kitab-kitab fiqh, usul fiqh dan fatwa-fatwa di Malaysia sebagai rujukan bagi mengetahui hukum penggunaan mentadak dan cecair yang keluar dari perut mentadak dalam perubatan. Kajian ini juga menumpukan analisis terhadap aplikasi konsep darurat dan istihalah dalam perubatan dalam merungkai permasalahan rawatan menggunakan sarung telur mentadak. Piawaian badan halal berautoriti seperti Jabatan Standard Malaysia turut diteliti untuk mengetahui peraturan dalam penghasilan produk farmaseutikal termasuk aspek penilaian keselamatan yang perlu dipatuhi. Selain itu, pengkaji turut merujuk kajian-kajian saintifik untuk mengetahui khasiat, kegunaan serta kesan sampingan telur mentadak dalam bidang perubatan. Hasil kajian mendapati penggunaan telur mentadak adalah tidak halal kerana mengandungi unsur najis. Telur yang keluar daripada serangga dianggap suatu yang menjijikkan menurut pandangan ulama serta tidak boleh dimakan. Walau bagaimanapun, penggunaannya dalam perubatan perlu dinilai dari perspektif fiqh perubatan dengan melihat tahap keperluannya dalam bidang tersebut. Sehingga kini, penggunaannya tidak mencapai tahap darurat kerana masih terdapat rawatan alternatif bagi penyakit-penyakit yang berkaitan. Malah penggunaan Mantidis Ootheca dalam farmaseutikal hanya melibatkan unsur tambahan yang membantu aspek kesihatan dan bukannya sebagai ramuan utama dalam penghasilan sesuatu ubat-ubatan.  Ia juga tidak menepati piawaian keselamatan yang digariskan oleh fuqaha dan ketetapan MS 2424:2019 berdasarkan kajian semasa yang menunjukkan tiada laporan yang tuntas mengenai aspek toksikologi dan kesan sampingan berbahaya kepada pengguna. Kajian terhadap industri farmaseutikal ini sewajarnya terus dipelopori oleh umat Islam bagi memastikan penggunaan bahan yang halal dalam perubatan.\n","source":"DOAJ","year":2024,"language":"","subjects":["Islamic law","Law"],"doi":"10.33102/mjsl.vol12no3.616","url":"https://mjsl.usim.edu.my/index.php/jurnalmjsl/article/view/616","is_open_access":true,"published_at":"","score":68},{"id":"arxiv_2412.01496","title":"Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets","authors":[{"name":"Nicholas Konz"},{"name":"Richard Osuala"},{"name":"Preeti Verma"},{"name":"Yuwen Chen"},{"name":"Hanxue Gu"},{"name":"Haoyu Dong"},{"name":"Yaqian Chen"},{"name":"Andrew Marshall"},{"name":"Lidia Garrucho"},{"name":"Kaisar Kushibar"},{"name":"Daniel M. Lang"},{"name":"Gene S. Kim"},{"name":"Lars J. Grimm"},{"name":"John M. Lewin"},{"name":"James S. Duncan"},{"name":"Julia A. Schnabel"},{"name":"Oliver Diaz"},{"name":"Karim Lekadir"},{"name":"Maciej A. Mazurowski"}],"abstract":"Determining whether two sets of images belong to the same or different distributions or domains is a crucial task in modern medical image analysis and deep learning; for example, to evaluate the output quality of image generative models. Currently, metrics used for this task either rely on the (potentially biased) choice of some downstream task, such as segmentation, or adopt task-independent perceptual metrics (e.g., Fréchet Inception Distance/FID) from natural imaging, which we show insufficiently capture anatomical features. To this end, we introduce a new perceptual metric tailored for medical images, FRD (Fréchet Radiomic Distance), which utilizes standardized, clinically meaningful, and interpretable image features. We show that FRD is superior to other image distribution metrics for a range of medical imaging applications, including out-of-domain (OOD) detection, the evaluation of image-to-image translation (by correlating more with downstream task performance as well as anatomical consistency and realism), and the evaluation of unconditional image generation. Moreover, FRD offers additional benefits such as stability and computational efficiency at low sample sizes, sensitivity to image corruptions and adversarial attacks, feature interpretability, and correlation with radiologist-perceived image quality. Additionally, we address key gaps in the literature by presenting an extensive framework for the multifaceted evaluation of image similarity metrics in medical imaging -- including the first large-scale comparative study of generative models for medical image translation -- and release an accessible codebase to facilitate future research. Our results are supported by thorough experiments spanning a variety of datasets, modalities, and downstream tasks, highlighting the broad potential of FRD for medical image analysis.","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV","cs.LG","eess.IV","stat.ML"],"doi":"10.1016/j.media.2026.103943","url":"https://arxiv.org/abs/2412.01496","pdf_url":"https://arxiv.org/pdf/2412.01496","is_open_access":true,"published_at":"2024-12-02T13:49:14Z","score":68},{"id":"arxiv_2407.03548","title":"HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation","authors":[{"name":"Tao Chen"},{"name":"Chenhui Wang"},{"name":"Zhihao Chen"},{"name":"Yiming Lei"},{"name":"Hongming Shan"}],"abstract":"Medical image segmentation has been significantly advanced with the rapid development of deep learning (DL) techniques. Existing DL-based segmentation models are typically discriminative; i.e., they aim to learn a mapping from the input image to segmentation masks. However, these discriminative methods neglect the underlying data distribution and intrinsic class characteristics, suffering from unstable feature space. In this work, we propose to complement discriminative segmentation methods with the knowledge of underlying data distribution from generative models. To that end, we propose a novel hybrid diffusion framework for medical image segmentation, termed HiDiff, which can synergize the strengths of existing discriminative segmentation models and new generative diffusion models. HiDiff comprises two key components: discriminative segmentor and diffusion refiner. First, we utilize any conventional trained segmentation models as discriminative segmentor, which can provide a segmentation mask prior for diffusion refiner. Second, we propose a novel binary Bernoulli diffusion model (BBDM) as the diffusion refiner, which can effectively, efficiently, and interactively refine the segmentation mask by modeling the underlying data distribution. Third, we train the segmentor and BBDM in an alternate-collaborative manner to mutually boost each other. Extensive experimental results on abdomen organ, brain tumor, polyps, and retinal vessels segmentation datasets, covering four widely-used modalities, demonstrate the superior performance of HiDiff over existing medical segmentation algorithms, including the state-of-the-art transformer- and diffusion-based ones. In addition, HiDiff excels at segmenting small objects and generalizing to new datasets. Source codes are made available at https://github.com/takimailto/HiDiff.","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV"],"doi":"10.1109/TMI.2024.3424471","url":"https://arxiv.org/abs/2407.03548","pdf_url":"https://arxiv.org/pdf/2407.03548","is_open_access":true,"published_at":"2024-07-03T23:59:09Z","score":68},{"id":"arxiv_2406.17608","title":"Test-time generative augmentation for medical image segmentation","authors":[{"name":"Xiao Ma"},{"name":"Yuhui Tao"},{"name":"Zetian Zhang"},{"name":"Yuhan Zhang"},{"name":"Xi Wang"},{"name":"Sheng Zhang"},{"name":"Zexuan Ji"},{"name":"Yizhe Zhang"},{"name":"Qiang Chen"},{"name":"Guang Yang"}],"abstract":"Medical image segmentation is critical for clinical diagnosis, treatment planning, and monitoring, yet segmentation models often struggle with uncertainties stemming from occlusions, ambiguous boundaries, and variations in imaging devices. Traditional test-time augmentation (TTA) techniques typically rely on predefined geometric and photometric transformations, limiting their adaptability and effectiveness in complex medical scenarios. In this study, we introduced Test-Time Generative Augmentation (TTGA), a novel augmentation strategy specifically tailored for medical image segmentation at inference time. Different from conventional augmentation strategies that suffer from excessive randomness or limited flexibility, TTGA leverages a domain-fine-tuned generative model to produce contextually relevant and diverse augmentations tailored to the characteristics of each test image. Built upon diffusion model inversion, a masked null-text inversion method is proposed to enable region-specific augmentations during sampling. Furthermore, a dual denoising pathway is designed to balance precise identity preservation with controlled variability. We demonstrate the efficacy of our TTGA through extensive experiments across three distinct segmentation tasks spanning nine datasets. Our results consistently demonstrate that TTGA not only improves segmentation accuracy (with DSC gains ranging from 0.1% to 2.3% over the baseline) but also offers pixel-wise error estimation (with DSC gains ranging from 1.1% to 29.0% over the baseline). The source code and demonstration are available at: https://github.com/maxiao0234/TTGA.","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV"],"doi":"10.1016/j.media.2025.103902","url":"https://arxiv.org/abs/2406.17608","pdf_url":"https://arxiv.org/pdf/2406.17608","is_open_access":true,"published_at":"2024-06-25T14:53:01Z","score":68},{"id":"arxiv_2408.08070","title":"MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation","authors":[{"name":"Fenghe Tang"},{"name":"Bingkun Nian"},{"name":"Yingtai Li"},{"name":"Zihang Jiang"},{"name":"Jie Yang"},{"name":"Wei Liu"},{"name":"S. Kevin Zhou"}],"abstract":"Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba's potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://github.com/FengheTan9/MambaMIM.","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV"],"doi":"10.1016/j.media.2025.103606","url":"https://arxiv.org/abs/2408.08070","pdf_url":"https://arxiv.org/pdf/2408.08070","is_open_access":true,"published_at":"2024-08-15T10:35:26Z","score":68},{"id":"doaj_10.3205/mibe000250","title":"Wissenschaftsausbildung im Medizinstudium: Das Oldenburger Datenanalyseprojekt als Umsetzungsbeispiel [Lessons learned]","authors":[{"name":"Timmer, Antje"},{"name":"Neuser, Johanna"},{"name":"Uslar, Verena"},{"name":"Kappen, Sanny"},{"name":"Seipp, Alexander"},{"name":"Tiles-Sar, Natalia"},{"name":"de Sordi, Dominik"},{"name":"Beckhaus, Julia"},{"name":"Otto-Sobotka, Fabian"}],"abstract":"Introduction: According to the Master Plan 2020, science education will play a critical role in future medical curricula. Science modules have already been implemented at many locations. Other medical faculties will follow in the next few years, as legislation is expected to make recommendations of the national competence-based learning objectives curriculum for medicine (NKLM) mandatory. This article aims to present an implementation example from epidemiology and biometry as a contribution to the didactic discussions within the data sciences in medicine. Project description: We report on our experiences with a data analysis project for second-year medical students, which has been compulsory at the Faculty of Medicine and Health Sciences since 2019. The project is intended to train the scientific skills required from the subjects of epidemiology and biometry for student research projects. Emphasis is placed on responsible data handling, transparency, and reproducibility. For example, the writing of a statistical analysis plan is required prior to data access. Improved standardization of materials, optional use of the English language, and digital support will be implemented to help manage the project when student numbers increase. Discussion: The experience from five years is very positive, although a formal evaluation of the learning success is still pending. Current challenges concern staffing, additional time and supervision requirements for those students who do statistical programming with R, and improved integration into the medical curriculum.","source":"DOAJ","year":2023,"language":"","subjects":["Computer applications to medicine. Medical informatics","Infectious and parasitic diseases"],"doi":"10.3205/mibe000250","url":"http://www.egms.de/static/en/journals/mibe/2023-19/mibe000250.shtml","is_open_access":true,"published_at":"","score":67},{"id":"arxiv_2304.10517","title":"Segment Anything Model for Medical Image Analysis: an Experimental Study","authors":[{"name":"Maciej A. Mazurowski"},{"name":"Haoyu Dong"},{"name":"Hanxue Gu"},{"name":"Jichen Yang"},{"name":"Nicholas Konz"},{"name":"Yixin Zhang"}],"abstract":"Training segmentation models for medical images continues to be challenging due to the limited availability of data annotations. Segment Anything Model (SAM) is a foundation model that is intended to segment user-defined objects of interest in an interactive manner. While the performance on natural images is impressive, medical image domains pose their own set of challenges. Here, we perform an extensive evaluation of SAM's ability to segment medical images on a collection of 19 medical imaging datasets from various modalities and anatomies. We report the following findings: (1) SAM's performance based on single prompts highly varies depending on the dataset and the task, from IoU=0.1135 for spine MRI to IoU=0.8650 for hip X-ray. (2) Segmentation performance appears to be better for well-circumscribed objects with prompts with less ambiguity and poorer in various other scenarios such as the segmentation of brain tumors. (3) SAM performs notably better with box prompts than with point prompts. (4) SAM outperforms similar methods RITM, SimpleClick, and FocalClick in almost all single-point prompt settings. (5) When multiple-point prompts are provided iteratively, SAM's performance generally improves only slightly while other methods' performance improves to the level that surpasses SAM's point-based performance. We also provide several illustrations for SAM's performance on all tested datasets, iterative segmentation, and SAM's behavior given prompt ambiguity. We conclude that SAM shows impressive zero-shot segmentation performance for certain medical imaging datasets, but moderate to poor performance for others. SAM has the potential to make a significant impact in automated medical image segmentation in medical imaging, but appropriate care needs to be applied when using it.","source":"arXiv","year":2023,"language":"en","subjects":["cs.CV","cs.AI","cs.LG"],"doi":"10.1016/j.media.2023.102918","url":"https://arxiv.org/abs/2304.10517","pdf_url":"https://arxiv.org/pdf/2304.10517","is_open_access":true,"published_at":"2023-04-20T17:50:18Z","score":67},{"id":"arxiv_2311.02115","title":"Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging","authors":[{"name":"Emma A. M. Stanley"},{"name":"Raissa Souza"},{"name":"Anthony Winder"},{"name":"Vedant Gulve"},{"name":"Kimberly Amador"},{"name":"Matthias Wilms"},{"name":"Nils D. Forkert"}],"abstract":"Artificial intelligence (AI) models trained using medical images for clinical tasks often exhibit bias in the form of disparities in performance between subgroups. Since not all sources of biases in real-world medical imaging data are easily identifiable, it is challenging to comprehensively assess how those biases are encoded in models, and how capable bias mitigation methods are at ameliorating performance disparities. In this article, we introduce a novel analysis framework for systematically and objectively investigating the impact of biases in medical images on AI models. We developed and tested this framework for conducting controlled in silico trials to assess bias in medical imaging AI using a tool for generating synthetic magnetic resonance images with known disease effects and sources of bias. The feasibility is showcased by using three counterfactual bias scenarios to measure the impact of simulated bias effects on a convolutional neural network (CNN) classifier and the efficacy of three bias mitigation strategies. The analysis revealed that the simulated biases resulted in expected subgroup performance disparities when the CNN was trained on the synthetic datasets. Moreover, reweighing was identified as the most successful bias mitigation strategy for this setup, and we demonstrated how explainable AI methods can aid in investigating the manifestation of bias in the model using this framework. Developing fair AI models is a considerable challenge given that many and often unknown sources of biases can be present in medical imaging datasets. In this work, we present a novel methodology to objectively study the impact of biases and mitigation strategies on deep learning pipelines, which can support the development of clinical AI that is robust and responsible.","source":"arXiv","year":2023,"language":"en","subjects":["cs.CV","cs.AI","cs.CY","cs.LG"],"doi":"10.1093/jamia/ocae165","url":"https://arxiv.org/abs/2311.02115","pdf_url":"https://arxiv.org/pdf/2311.02115","is_open_access":true,"published_at":"2023-11-03T01:37:28Z","score":67},{"id":"arxiv_2310.15371","title":"Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation","authors":[{"name":"Yongsong Huang"},{"name":"Wanqing Xie"},{"name":"Mingzhen Li"},{"name":"Mingmei Cheng"},{"name":"Jinzhou Wu"},{"name":"Weixiao Wang"},{"name":"Jane You"},{"name":"Xiaofeng Liu"}],"abstract":"Federated learning (FL) enables multiple client medical institutes collaboratively train a deep learning (DL) model with privacy protection. However, the performance of FL can be constrained by the limited availability of labeled data in small institutes and the heterogeneous (i.e., non-i.i.d.) data distribution across institutes. Though data augmentation has been a proven technique to boost the generalization capabilities of conventional centralized DL as a \"free lunch\", its application in FL is largely underexplored. Notably, constrained by costly labeling, 3D medical segmentation generally relies on data augmentation. In this work, we aim to develop a vicinal feature-level data augmentation (VFDA) scheme to efficiently alleviate the local feature shift and facilitate collaborative training for privacy-aware FL segmentation. We take both the inner- and inter-institute divergence into consideration, without the need for cross-institute transfer of raw data or their mixup. Specifically, we exploit the batch-wise feature statistics (e.g., mean and standard deviation) in each institute to abstractly represent the discrepancy of data, and model each feature statistic probabilistically via a Gaussian prototype, with the mean corresponding to the original statistic and the variance quantifying the augmentation scope. From the vicinal risk minimization perspective, novel feature statistics can be drawn from the Gaussian distribution to fulfill augmentation. The variance is explicitly derived by the data bias in each individual institute and the underlying feature statistics characterized by all participating institutes. The added-on VFDA consistently yielded marked improvements over six advanced FL methods on both 3D brain tumor and cardiac segmentation.","source":"arXiv","year":2023,"language":"en","subjects":["eess.IV","cs.AI","cs.CV","cs.LG","physics.med-ph"],"doi":"10.1007/978-3-031-34048-2_28","url":"https://arxiv.org/abs/2310.15371","pdf_url":"https://arxiv.org/pdf/2310.15371","is_open_access":true,"published_at":"2023-10-23T21:14:52Z","score":67},{"id":"arxiv_2306.01022","title":"Introduction of Medical Imaging Modalities","authors":[{"name":"S. K. M Shadekul Islam"},{"name":"MD Abdullah Al Nasim"},{"name":"Ismail Hossain"},{"name":"Md Azim Ullah"},{"name":"Kishor Datta Gupta"},{"name":"Md Monjur Hossain Bhuiyan"}],"abstract":"The diagnosis and treatment of various diseases had been expedited with the help of medical imaging. Different medical imaging modalities, including X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Nuclear Imaging, Ultrasound, Electrical Impedance Tomography (EIT), and Emerging Technologies for in vivo imaging modalities is presented in this chapter, in addition to these modalities, some advanced techniques such as contrast-enhanced MRI, MR approaches for osteoarthritis, Cardiovascular Imaging, and Medical Imaging data mining and search. Despite its important role and potential effectiveness as a diagnostic tool, reading and interpreting medical images by radiologists is often tedious and difficult due to the large heterogeneity of diseases and the limitation of image quality or resolution. Besides the introduction and discussion of the basic principles, typical clinical applications, advantages, and limitations of each modality used in current clinical practice, this chapter also highlights the importance of emerging technologies in medical imaging and the role of data mining and search aiming to support translational clinical research, improve patient care, and increase the efficiency of the healthcare system.","source":"arXiv","year":2023,"language":"en","subjects":["eess.IV","physics.med-ph"],"url":"https://arxiv.org/abs/2306.01022","pdf_url":"https://arxiv.org/pdf/2306.01022","is_open_access":true,"published_at":"2023-06-01T10:18:53Z","score":67},{"id":"arxiv_2401.00314","title":"GAN-GA: A Generative Model based on Genetic Algorithm for Medical Image Generation","authors":[{"name":"M. AbdulRazek"},{"name":"G. Khoriba"},{"name":"M. Belal"}],"abstract":"Medical imaging is an essential tool for diagnosing and treating diseases. However, lacking medical images can lead to inaccurate diagnoses and ineffective treatments. Generative models offer a promising solution for addressing medical image shortage problems due to their ability to generate new data from existing datasets and detect anomalies in this data. Data augmentation with position augmentation methods like scaling, cropping, flipping, padding, rotation, and translation could lead to more overfitting in domains with little data, such as medical image data. This paper proposes the GAN-GA, a generative model optimized by embedding a genetic algorithm. The proposed model enhances image fidelity and diversity while preserving distinctive features. The proposed medical image synthesis approach improves the quality and fidelity of medical images, an essential aspect of image interpretation. To evaluate synthesized images: Frechet Inception Distance (FID) is used. The proposed GAN-GA model is tested by generating Acute lymphoblastic leukemia (ALL) medical images, an image dataset, and is the first time to be used in generative models. Our results were compared to those of InfoGAN as a baseline model. The experimental results show that the proposed optimized GAN-GA enhances FID scores by about 6.8\\%, especially in earlier training epochs. The source code and dataset will be available at: https://github.com/Mustafa-AbdulRazek/InfoGAN-GA.","source":"arXiv","year":2023,"language":"en","subjects":["eess.IV","cs.CV","cs.LG","cs.NE"],"doi":"10.3389/978-2-8325-1231-9","url":"https://arxiv.org/abs/2401.00314","pdf_url":"https://arxiv.org/pdf/2401.00314","is_open_access":true,"published_at":"2023-12-30T20:16:45Z","score":67},{"id":"arxiv_2307.15872","title":"Cross-dimensional transfer learning in medical image segmentation with deep learning","authors":[{"name":"Hicham Messaoudi"},{"name":"Ahror Belaid"},{"name":"Douraied Ben Salem"},{"name":"Pierre-Henri Conze"}],"abstract":"Over the last decade, convolutional neural networks have emerged and advanced the state-of-the-art in various image analysis and computer vision applications. The performance of 2D image classification networks is constantly improving and being trained on databases made of millions of natural images. However, progress in medical image analysis has been hindered by limited annotated data and acquisition constraints. These limitations are even more pronounced given the volumetry of medical imaging data. In this paper, we introduce an efficient way to transfer the efficiency of a 2D classification network trained on natural images to 2D, 3D uni- and multi-modal medical image segmentation applications. In this direction, we designed novel architectures based on two key principles: weight transfer by embedding a 2D pre-trained encoder into a higher dimensional U-Net, and dimensional transfer by expanding a 2D segmentation network into a higher dimension one. The proposed networks were tested on benchmarks comprising different modalities: MR, CT, and ultrasound images. Our 2D network ranked first on the CAMUS challenge dedicated to echo-cardiographic data segmentation and surpassed the state-of-the-art. Regarding 2D/3D MR and CT abdominal images from the CHAOS challenge, our approach largely outperformed the other 2D-based methods described in the challenge paper on Dice, RAVD, ASSD, and MSSD scores and ranked third on the online evaluation platform. Our 3D network applied to the BraTS 2022 competition also achieved promising results, reaching an average Dice score of 91.69% (91.22%) for the whole tumor, 83.23% (84.77%) for the tumor core, and 81.75% (83.88%) for enhanced tumor using the approach based on weight (dimensional) transfer. Experimental and qualitative results illustrate the effectiveness of our methods for multi-dimensional medical image segmentation.","source":"arXiv","year":2023,"language":"en","subjects":["eess.IV","cs.CV","cs.LG"],"doi":"10.1016/j.media.2023.102868","url":"https://arxiv.org/abs/2307.15872","pdf_url":"https://arxiv.org/pdf/2307.15872","is_open_access":true,"published_at":"2023-07-29T02:50:38Z","score":67},{"id":"arxiv_2212.08228","title":"SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation","authors":[{"name":"Jee Seok Yoon"},{"name":"Chenghao Zhang"},{"name":"Heung-Il Suk"},{"name":"Jia Guo"},{"name":"Xiaoxiao Li"}],"abstract":"Human organs constantly undergo anatomical changes due to a complex mix of short-term (e.g., heartbeat) and long-term (e.g., aging) factors. Evidently, prior knowledge of these factors will be beneficial when modeling their future state, i.e., via image generation. However, most of the medical image generation tasks only rely on the input from a single image, thus ignoring the sequential dependency even when longitudinal data is available. Sequence-aware deep generative models, where model input is a sequence of ordered and timestamped images, are still underexplored in the medical imaging domain that is featured by several unique challenges: 1) Sequences with various lengths; 2) Missing data or frame, and 3) High dimensionality. To this end, we propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images. Recently, diffusion models have shown promising results in high-fidelity image generation. Our method extends this new technique by introducing a sequence-aware transformer as the conditional module in a diffusion model. The novel design enables learning longitudinal dependency even with missing data during training and allows autoregressive generation of a sequence of images during inference. Our extensive experiments on 3D longitudinal medical images demonstrate the effectiveness of SADM compared with baselines and alternative methods. The code is available at https://github.com/ubc-tea/SADM-Longitudinal-Medical-Image-Generation.","source":"arXiv","year":2022,"language":"en","subjects":["cs.CV","cs.AI","cs.LG"],"doi":"10.1007/978-3-031-34048-2_30","url":"https://arxiv.org/abs/2212.08228","pdf_url":"https://arxiv.org/pdf/2212.08228","is_open_access":true,"published_at":"2022-12-16T01:35:27Z","score":66},{"id":"arxiv_2204.03547","title":"Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imaging","authors":[{"name":"Varun A. Kelkar"},{"name":"Dimitrios S. Gotsis"},{"name":"Frank J. Brooks"},{"name":"Kyle J. Myers"},{"name":"Prabhat KC"},{"name":"Rongping Zeng"},{"name":"Mark A. Anastasio"}],"abstract":"Modern generative models, such as generative adversarial networks (GANs), hold tremendous promise for several areas of medical imaging, such as unconditional medical image synthesis, image restoration, reconstruction and translation, and optimization of imaging systems. However, procedures for establishing stochastic image models (SIMs) using GANs remain generic and do not address specific issues relevant to medical imaging. In this work, canonical SIMs that simulate realistic vessels in angiography images are employed to evaluate procedures for establishing SIMs using GANs. The GAN-based SIM is compared to the canonical SIM based on its ability to reproduce those statistics that are meaningful to the particular medically realistic SIM considered. It is shown that evaluating GANs using classical metrics and medically relevant metrics may lead to different conclusions about the fidelity of the trained GANs. This work highlights the need for the development of objective metrics for evaluating GANs.","source":"arXiv","year":2022,"language":"en","subjects":["eess.IV","cs.CV","physics.med-ph"],"doi":"10.1117/12.2612893","url":"https://arxiv.org/abs/2204.03547","pdf_url":"https://arxiv.org/pdf/2204.03547","is_open_access":true,"published_at":"2022-04-07T16:19:01Z","score":66},{"id":"doaj_A+aplica%C3%A7%C3%A3o+da+lei+geral+de+prote%C3%A7%C3%A3o+de+dados+na+sa%C3%BAde","title":"A aplicação da lei geral de proteção de dados na saúde","authors":[{"name":"Marcos César Botelho"},{"name":"Elimei Paleari do Amaral Camargo"}],"abstract":"Motivado pela adoção do Regulamento Geral sobre a Proteção de Dados pela União Europeia, o legislador brasileiro aprovou a Lei Geral de Proteção de Dados, expressamente tornando a proteção de dados pessoais um direito fundamental e reconhecendo a existência de uma categoria de dados específica, denominada de dados pessoais sensíveis, cujo conceito abarca os dados relativos à saúde e que recebem tratamento específico desse diploma legal. O objetivo do presente estudo foi analisar como a Lei Geral de Proteção de Dados trata a proteção de dados relativos à saúde. Para tanto, utilizando método dedutivo e análise bibliográfica, o estudo foi dividido em duas partes. Na primeira foi exposto o conceito jurídico de dados trazido pela Lei Geral de Proteção de Dados, bem como a definição legal de dados sensíveis. Na segunda parte discutiu-se como essa lei trata os dados relativos à saúde. De modo geral, conclui-se que, com a entrada em vigor da Lei Geral de Proteção de Dados, profissionais da saúde, clínicas médicas, hospitais e centros de saúde, entre outros, que realizarem tratamento de dados pessoais sensíveis relacionados à saúde deverão adotar medidas para adaptar tais atividades à legislação o mais brevemente possível, a fim de evitar sanções que podem ir desde a aplicação de multas pecuniárias até a proibição do uso de dados pessoais sensíveis.","source":"DOAJ","year":2021,"language":"","subjects":["Law","Law in general. Comparative and uniform law. Jurisprudence","Medical legislation"],"url":"https://www.revistas.usp.br/rdisan/article/view/168023","is_open_access":true,"published_at":"","score":65},{"id":"arxiv_2111.10480","title":"TransMorph: Transformer for unsupervised medical image registration","authors":[{"name":"Junyu Chen"},{"name":"Eric C. Frey"},{"name":"Yufan He"},{"name":"William P. Segars"},{"name":"Ye Li"},{"name":"Yong Du"}],"abstract":"In the last decade, convolutional neural networks (ConvNets) have been a major focus of research in medical image analysis. However, the performances of ConvNets may be limited by a lack of explicit consideration of the long-range spatial relationships in an image. Recently Vision Transformer architectures have been proposed to address the shortcomings of ConvNets and have produced state-of-the-art performances in many medical imaging applications. Transformers may be a strong candidate for image registration because their substantially larger receptive field enables a more precise comprehension of the spatial correspondence between moving and fixed images. Here, we present TransMorph, a hybrid Transformer-ConvNet model for volumetric medical image registration. This paper also presents diffeomorphic and Bayesian variants of TransMorph: the diffeomorphic variants ensure the topology-preserving deformations, and the Bayesian variant produces a well-calibrated registration uncertainty estimate. We extensively validated the proposed models using 3D medical images from three applications: inter-patient and atlas-to-patient brain MRI registration and phantom-to-CT registration. The proposed models are evaluated in comparison to a variety of existing registration methods and Transformer architectures. Qualitative and quantitative results demonstrate that the proposed Transformer-based model leads to a substantial performance improvement over the baseline methods, confirming the effectiveness of Transformers for medical image registration.","source":"arXiv","year":2021,"language":"en","subjects":["eess.IV","cs.AI","cs.CV"],"doi":"10.1016/j.media.2022.102615","url":"https://arxiv.org/abs/2111.10480","pdf_url":"https://arxiv.org/pdf/2111.10480","is_open_access":true,"published_at":"2021-11-19T23:37:39Z","score":65}],"total":3683829,"page":1,"page_size":20,"sources":["DOAJ","arXiv","CrossRef"],"query":"Medical legislation"}