As a crucial component of Traditional Chinese Medicine (TCM) knowledge system, TCM processing (paozhi) is deeply influenced by traditional Chinese medical culture and philosophical thought, embodying both scientific and humanistic attributes. During the Republic of China era, the chaos in the processing of TCM attracted widespread attention and became a trigger for intense debate in the Chinese and Western medical circles. Under the dissemination of the "scientization of TCM" ideology and practices, conflicting perspectives emerged regarding how to reform flawed processing methods. Some scholars advocated for the extraction of active ingredients, criticizing TCM processing as outdated and potentially harmful to medicinal efficacy. Conversely, most scholars in the Chinese medical community emphasized preserving TCM processing but called for necessary reforms. This debate reflected the complex tension of TCM processing during the scientization of TCM in the Republic of China era: a tension between the need to establish scientific standards and the imperative to maintain cultural identity.
Yi Jiao Angelina Tian, Michael Dunn, Silke Schicktanz
et al.
Abstract Background The parallel growth of population ageing and international migration have introduced a unique population of transnational caregivers in elder care. Particularly for only children who face conflicting obligations and reduced caregiving resources, smart home devices could be technical tools to care for older parents from a distance. Research towards the use of these technologies has unearthed ethical issues such as privacy, autonomy, stigma and beneficence, but has not been fully explored in distance care. In this paper, we explore the ethical issues expressed by a group of only children towards integrating assistive, monitoring, and robotic technologies in their transnational care plans. Methods Purposive snowball sampling was used for the recruitment of 26 distance caregivers aged between 28 and 45, who were their parent’s only children. They lived in Europe for at least 5 years, with at least one parent residing in the home country. In semi-structured interviews, participants discussed the ethical issues of wearable devices, ambient and visual remote monitoring technologies, as well as the possible use of one assistive robot in the context of distance caregiving for older parents. We used the applied thematic analysis methodology to analyze the data. Results We highlight two ethical considerations. First, participants saw the need for maximizing good outcomes in caring for their older parents and fulfilling their responsibilities to ensure their health and safety, balanced against the respect for the parents’ autonomy, dignity, and privacy. Second, they weighed the benefits and harms of technologies at a distance to provide companionship and support against the intrinsic value placed on care received from one’s only child. Conclusions Discussions to involve technologies in elder care at a distance prompted complex decision-making processes to balance, weigh, and rationalize their ethical concerns as foreseen by the caregivers. The importance of maximizing the health and safety of older parents came at an unavoidable cost of the respect to autonomy, privacy, and dignity. Participants valued their own emotional connection and relationship to their parents, which they prioritized above the instrumental value of technological support. We further discuss our findings within the ethics of care theory and concepts within transnational care literature to make sense of the broader ethical implications of this empirical study.
Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance. However, most explanation methods rely on post-hoc attribution, approximating the decision-making process of already trained black-box models. These methods are often sensitive, unreliable, and fail to reflect true model reasoning, limiting their trustworthiness in critical applications. In this work, we introduce SoftCAM, a straightforward yet effective approach that makes standard CNN architectures inherently interpretable. By removing the global average pooling layer and replacing the fully connected classification layer with a convolution-based class evidence layer, SoftCAM preserves spatial information and produces explicit class activation maps that form the basis of the model's predictions. Evaluated on three medical datasets, SoftCAM maintains classification performance while significantly improving both the qualitative and quantitative explanation compared to existing post-hoc methods. Our results demonstrate that CNNs can be inherently interpretable without compromising performance, advancing the development of self-explainable deep learning for high-stakes decision-making. The code is available at https://github.com/kdjoumessi/SoftCAM
Abstract Background Confidentiality is one of the central preconditions for clinical ethics support (CES). CES cases which generate moral questions for CES staff concerning (breaching) confidentiality of what has been discussed during CES can cause moral challenges. Currently, there seems to be no clear policy or guidance regarding how CES staff can or should deal with these moral challenges related to (not) breaching confidentiality within CES. Moral case deliberation is a specific kind of CES. Method Based on experiences and research into MCD facilitators’ needs for ethics support in this regard, we jointly developed an ethics support tool for MCD facilitators: the Confidentiality Compass. This paper describes the iterative developmental process, including our theoretical viewpoints and reflections on characteristics of CES tools in general. Results The content and goals of the ethics support tool, which contains four elements, is described. Part A is about providing information on the concept of confidentiality in MCD, part B is a moral compass with reflective questions, part C focuses on courses of action for careful handling of moral challenges related to confidentiality. Part D contains general lessons, best practices and tips for dealing with confidentiality in future cases. Conclusions This paper concludes with providing some lessons-learned related to developing ethics support tools and some reflections on issues of quality and normativity of ethics support tools.
Current medical image segmentation relies on the region-based (Dice, F1-score) and boundary-based (Hausdorff distance, surface distance) metrics as the de-facto standard. While these metrics are widely used, they lack a unified interpretation, particularly regarding volume agreement. Clinicians often lack clear benchmarks to gauge the "goodness" of segmentation results based on these metrics. Recognizing the clinical relevance of volumetry, we utilize relative volume prediction error (vpe) to directly assess the accuracy of volume predictions derived from segmentation tasks. Our work integrates theoretical analysis and empirical validation across diverse datasets. We delve into the often-ambiguous relationship between segmentation quality (measured by Dice) and volumetric accuracy in clinical practice. Our findings highlight the critical role of incorporating volumetric prediction accuracy into segmentation evaluation. This approach empowers clinicians with a more nuanced understanding of segmentation performance, ultimately improving the interpretation and utility of these metrics in real-world healthcare settings.
Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional layer with the local receptive field, which makes it difficult to learn global shape information from the limited information provided by scribble annotations. To address this issue, this paper proposes a new CNN-Transformer hybrid solution for scribble-supervised medical image segmentation called ScribFormer. The proposed ScribFormer model has a triple-branch structure, i.e., the hybrid of a CNN branch, a Transformer branch, and an attention-guided class activation map (ACAM) branch. Specifically, the CNN branch collaborates with the Transformer branch to fuse the local features learned from CNN with the global representations obtained from Transformer, which can effectively overcome limitations of existing scribble-supervised segmentation methods. Furthermore, the ACAM branch assists in unifying the shallow convolution features and the deep convolution features to improve model's performance further. Extensive experiments on two public datasets and one private dataset show that our ScribFormer has superior performance over the state-of-the-art scribble-supervised segmentation methods, and achieves even better results than the fully-supervised segmentation methods. The code is released at https://github.com/HUANGLIZI/ScribFormer.
Partially-supervised multi-organ medical image segmentation aims to develop a unified semantic segmentation model by utilizing multiple partially-labeled datasets, with each dataset providing labels for a single class of organs. However, the limited availability of labeled foreground organs and the absence of supervision to distinguish unlabeled foreground organs from the background pose a significant challenge, which leads to a distribution mismatch between labeled and unlabeled pixels. Although existing pseudo-labeling methods can be employed to learn from both labeled and unlabeled pixels, they are prone to performance degradation in this task, as they rely on the assumption that labeled and unlabeled pixels have the same distribution. In this paper, to address the problem of distribution mismatch, we propose a labeled-to-unlabeled distribution alignment (LTUDA) framework that aligns feature distributions and enhances discriminative capability. Specifically, we introduce a cross-set data augmentation strategy, which performs region-level mixing between labeled and unlabeled organs to reduce distribution discrepancy and enrich the training set. Besides, we propose a prototype-based distribution alignment method that implicitly reduces intra-class variation and increases the separation between the unlabeled foreground and background. This can be achieved by encouraging consistency between the outputs of two prototype classifiers and a linear classifier. Extensive experimental results on the AbdomenCT-1K dataset and a union of four benchmark datasets (including LiTS, MSD-Spleen, KiTS, and NIH82) demonstrate that our method outperforms the state-of-the-art partially-supervised methods by a considerable margin, and even surpasses the fully-supervised methods. The source code is publicly available at https://github.com/xjiangmed/LTUDA.
Este artigo parte de uma questão central na Bioética Global de Van Rensselaer Potter: como aplicá-la à realidade concreta? Hipotenizamos que uma possibilidade de resposta poderia ser vislumbrada convergindo os seus elementos centrais com o caminho hermenêutico percorrido pelo autor a partir de seu “lugar de fala”. Metodologicamente, adotamos uma investigação crítico-analítica da sua obra. Discutimos que para além da originalidade da proposta, ela requer um novo olhar e um outro agir, envolve um caminho pragmático, ousado, uma linguagem própria e uma metodologia sui generis que precisa ser adequadamente compreendida. Concluímos que a obra de Potter, como ele próprio parece sugerir, não encerra em si um sistema bioético pronto e acabado, mas antes disso, um método para o construir, a partir do qual é possível a sua aplicação.
Medical philosophy. Medical ethics, Business ethics
Despite recent progress in enhancing the privacy of federated learning (FL) via differential privacy (DP), the trade-off of DP between privacy protection and performance is still underexplored for real-world medical scenario. In this paper, we propose to optimize the trade-off under the context of client-level DP, which focuses on privacy during communications. However, FL for medical imaging involves typically much fewer participants (hospitals) than other domains (e.g., mobile devices), thus ensuring clients be differentially private is much more challenging. To tackle this problem, we propose an adaptive intermediary strategy to improve performance without harming privacy. Specifically, we theoretically find splitting clients into sub-clients, which serve as intermediaries between hospitals and the server, can mitigate the noises introduced by DP without harming privacy. Our proposed approach is empirically evaluated on both classification and segmentation tasks using two public datasets, and its effectiveness is demonstrated with significant performance improvements and comprehensive analytical studies. Code is available at: https://github.com/med-air/Client-DP-FL.
Recently, the diffusion model has emerged as a superior generative model that can produce high quality and realistic images. However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images. For instance, errors in image translation may distort, shift, or even remove structures and tumors, leading to incorrect diagnosis and inadequate treatments. Training and conditioning diffusion models using paired source and target images with matching anatomy can help. However, such paired data are very difficult and costly to obtain, and may also reduce the robustness of the developed model to out-of-distribution testing data. We propose a frequency-guided diffusion model (FGDM) that employs frequency-domain filters to guide the diffusion model for structure-preserving image translation. Based on its design, FGDM allows zero-shot learning, as it can be trained solely on the data from the target domain, and used directly for source-to-target domain translation without any exposure to the source-domain data during training. We evaluated it on three cone-beam CT (CBCT)-to-CT translation tasks for different anatomical sites, and a cross-institutional MR imaging translation task. FGDM outperformed the state-of-the-art methods (GAN-based, VAE-based, and diffusion-based) in metrics of Frechet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM), showing its significant advantages in zero-shot medical image translation.
Hussain Ahmad Madni, Rao Muhammad Umer, Gian Luca Foresti
Federated Learning (FL) is an evolving machine learning method in which multiple clients participate in collaborative learning without sharing their data with each other and the central server. In real-world applications such as hospitals and industries, FL counters the challenges of data heterogeneity and model heterogeneity as an inevitable part of the collaborative training. More specifically, different organizations, such as hospitals, have their own private data and customized models for local training. To the best of our knowledge, the existing methods do not effectively address both problems of model heterogeneity and data heterogeneity in FL. In this paper, we exploit the data and model heterogeneity simultaneously, and propose a method, MDH-FL (Exploiting Model and Data Heterogeneity in FL) to solve such problems to enhance the efficiency of the global model in FL. We use knowledge distillation and a symmetric loss to minimize the heterogeneity and its impact on the model performance. Knowledge distillation is used to solve the problem of model heterogeneity, and symmetric loss tackles with the data and label heterogeneity. We evaluate our method on the medical datasets to conform the real-world scenario of hospitals, and compare with the existing methods. The experimental results demonstrate the superiority of the proposed approach over the other existing methods.
This study addresses the challenges of confounding effects and interpretability in artificial-intelligence-based medical image analysis. Whereas existing literature often resolves confounding by removing confounder-related information from latent representations, this strategy risks affecting image reconstruction quality in generative models, thus limiting their applicability in feature visualization. To tackle this, we propose a different strategy that retains confounder-related information in latent representations while finding an alternative confounder-free representation of the image data. Our approach views the latent space of an autoencoder as a vector space, where imaging-related variables, such as the learning target (t) and confounder (c), have a vector capturing their variability. The confounding problem is addressed by searching a confounder-free vector which is orthogonal to the confounder-related vector but maximally collinear to the target-related vector. To achieve this, we introduce a novel correlation-based loss that not only performs vector searching in the latent space, but also encourages the encoder to generate latent representations linearly correlated with the variables. Subsequently, we interpret the confounder-free representation by sampling and reconstructing images along the confounder-free vector. The efficacy and flexibility of our proposed method are demonstrated across three applications, accommodating multiple confounders and utilizing diverse image modalities. Results affirm the method's effectiveness in reducing confounder influences, preventing wrong or misleading associations, and offering a unique visual interpretation for in-depth investigations by clinical and epidemiological researchers. The code is released in the following GitLab repository: https://gitlab.com/radiology/compopbio/ai_based_association_analysis}
AbstractThe dominant model for bioethical inquiry taught in medical schools is that of principlism. The heritage of this methodology can be traced to the Enlightenment project of generating a universalizable justification for normative morality arising from within the individual, rational agent. This project has been criticized by Alasdair MacIntyre who suggests that its failure has resulted in a fragmented and incoherent contemporary ethical framework characterized by fundamental intractability in moral debate. This incoherence implicates principlist conceptions of bioethics. Medical ethics as practiced, though, is partially in keeping with teleological alternatives to principlism. Nonetheless, the hegemony of principlism threatens to harm the practice of good medicine whenever it is used to provide justification for the sanction or prohibition of practices, despite not being equipped to grant moral authority to such justifications. An example of this failure and its resulting harm is expressed in the growing obsolescence of living donor liver transplantation.
Abstract Introduction Dementia diseases, especially Alzheimer’s disease (AD), are of considerable importance in terms of social policy and health economics. Moreover, against the background of the current Karlsruhe judgement on the legalisation of assisted suicide, there are also questions to be asked about medical humanities in AD. Methodology Relevant literature on complementary forms of therapy and prognosis was included and discussed. Results Creative sociotherapeutic approaches (art, music, dance) and validating psychotherapeutic approaches show promise for suitability and efficiency in the treatment of dementia, but in some cases still need to be scientifically tested. Biomarker-based early diagnosis of dementia diseases is increasingly becoming a subject of debate against the background of the Karlsruhe ruling. Discussion Needs-oriented and resource-enhancing approaches can make a significant contribution to improving the quality of life of people with dementia. The discussion on the issue of “assisted suicide” should include questions of the dignity and value of a life with dementia. Outlook The integrative dementia therapy model can be complemented by a religion- and spirituality-based approach. Appropriate forms of psychotherapy should be scientifically evaluated.
Marlen Ibeth Chaverra Castellar, Jhon Henry Osorio Castaño
El propósito del presente artículo es identificar los conocimientos sobre la Voluntad Anticipada (VA) en enfermeros que laboran en servicios de oncología. Para ello, se utilizó como metodología un estudio observacional con intención analítica que midió el nivel de conocimiento a través de un cuestionario autodiligenciado. En él participaron 50 enfermeros, seleccionados por muestreo no probabilístico. Así, se analizaron las variables cualitativas con distribuciones de frecuencia, y las cuantitativas con estadística descriptiva y análisis bivariado. El nivel de conocimiento se categorizó así: 0 a 10 puntos (nivel bajo), 11 a 20 puntos (nivel medio), 21 a 30 puntos (nivel alto). Los resultados de la investigación arrojaron como dato que, para un grupo donde el 86 % eran mujeres, con promedio de edad de 37 años, el promedio de años de experiencia como enfermeros fue de 11.5 años. Por otra parte, el promedio de años de experiencia en el área de oncología fue de 6.2 años. De los que hacían parte de este último promedio, el 48 % tenían diplomado en oncología y el 46 % especialización. El 70 % de los participantes tenía un conocimiento medio, el 26 % un conocimiento alto, y el 4 %un nivel bajo. Cabe mencionar que solo el nivel de formación de postgrado se relacionó de manera significativa con el nivel de conocimientos. Como conclusión, se encontró que los profesionales en enfermería poseen un nivel de conocimiento medio sobre la legislación que aborda las voluntades anticipadas en Colombia y esto está relacionado con el nivel de formación.
İslam dinini yeterince tanımayan çevreler, onu sadece Allah inancı, ahiret inancı ve ibadetlerden ibaret görürler. Hatta Kur’an-ı Kerim’deki ayetlerin büyük kısmının ibadet ve dualardan oluştuğunu zannederler. Oysa bu konuyla ilgili ayet sayısı iki yüz civarındadır. İslam dini inanç sistemi, sosyal yaşama dair temel ilkeleri ve evrensel ahlak anlayışıyla tam teşekküllü bir dindir. O, kişiyle Allah arası ilişkileri düzenlediği gibi kişiler arası ilişkileri de düzenler. İslam dini insanın sağlıklı, mutlu, müreffeh bir hayat sürebilmesi için gerekli temel unsurları sunmuştur. Bu unsurların başında sağlıklı bir yaşam gelmektedir. Zira akıl ve beden sağlığı yerinde olmayan insanlar, İslam’ın gereklerini hakkıyla yapamazlar. İnsan yaşamının en önemli konularından biri olan sağlığın insanlık tarihi boyunca herkesi çok yakından ilgilendirdiği bilinen bir gerçektir. Bu yüzden, tüm tarih sürecinde tıp ilmi kadar ilgi duyulan başka bir ilim dalı olmamıştır. Yüce Allah’ın insanlığa gönderdiği peygamberler de en az diğer insanlar kadar kendilerinin ve çevrelerindekilerin sağlıklarıyla ilgilenmişlerdir. Sağlığın korunması ve hastalıkların tedavisiyle ilgili temel bilgiler Kur’an ve sünnette göze çapmaktadır. Hz. Peygamberden nakledilen söz ve uygulamalar derlenmiş ve “Tıbbu’n-Nebî; Peygamber’in tıbbı” veya “et-Tıbbu’n-Nebevî; Nebevi tıp” olarak adlandırılmıştır. Hazreti Peygamber’in yaşadığı dönemde Arabistan’da meşhur tabipler vardı. Hz. Peygamber onlarla iletişimde bulunmuştur. Hâris b. Kelede es-Sakafi ve Ebû Rimse et-Teymî o tabiplerin en meşhurlarındandır. Hz. Peygamber, her vesileyle hastalandıkları zaman arkadaşlarına tedavi olmalarını tavsiye etmiş, bu konuda tereddüt yaşayanları uyarmıştır. O, hastalıkların Allah’tan geldiğini ve Allah’ın her hastalığın şifasını yeryüzüne indirdiğini vurgulamıştır. Hatta bazı hastalıklar konusunda kendisinin de özel tavsiyeleri olmuştur. Hz. Peygamber’in vefatından sonra İslam topraklarının genişlemesi ve Müslümanların farklı kültürlerle tanışması vesilesiyle tıp ilminde birçok gelişmeler olmuştur. Farklı milletlere ait tıp kitaplarının Arapçaya çevrilmesi, farklı milletten gelen tabiplerin Müslüman beldelerinde hizmet etmesi ve küçük çaplı tıp okullarının açılması Emevîler döneminde gerçekleşmiştir. Abbâsî devleti döneminde, özellikle de Halife Hârûn Reşit’in gayretleriyle batı kaynaklı birçok tıp kitabı Arapçaya çevrildi. Bu süreçte hastane kurma faaliyetleri hızlandı. Bu dönemde birçok tıp medresesi ve binlerce hastane kuruldu. Sağlık ve tıp alanındaki gelişmeler Selçuklu ve Osmanlı dönemlerinde devam etti. Bimarhane, Bîmâristan, Mâristân, Darüşşifa, Şifâiyye, Dâru’t-tıb, Dâru’s-sıhha, Dâru’l-âfiye Tımarhane gibi isimlerle hizmet veren hastanelerle tıp medreseleri genişledi. Bu alanda birçok eser yazıldı. Tanzimat sonrası Osmanlı devletinde sağlık ve tıp hizmetleri alanında batı tarzı modern tıp eğitimine ve hastahane yapılanmasına geçildi. Günümüze kadar hizmet veren Bezmi Alem Valide Sultan Gureba vakıf hastanesi, Haydarpaşa Numune Hastanesi, Gülhane Askeri Tıp Akademisi, İstanbul Şişli Hamidiye Etfal Hastanesi gibi hastane ve tıp fakülteleri kuruldu. Bu çalışmamızda, İslam dininin sağlık ve tıp ile olan alakasını, İslam tarihi sürecinde bu alandaki gelişmeleri ve İslam hukuku tıp ilişkisini sunmaya çalışacağız.
Since the WHO’s “Influenza Pandemic Preparedness Plan” in 1999, pandemic preparedness plans at the international and national level have been constantly adapted with the common goal to respond early to outbreaks, identify risks, and outline promising interventions for pandemic containment. Two years into the COVID-19 pandemic, public health experts have started to reflect on the extent to which previous preparations have been helpful as well as on the gaps in pandemic preparedness planning. In the present commentary, we advocate for the inclusion of social and ethical factors in future pandemic planning—factors that have been insufficiently considered so far, although social determinants of infection risk and infectious disease severity contribute to aggravated social inequalities in health.
Riccardo Taiello, Melek Önen, Francesco Capano
et al.
Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame. Current approaches to image registration are generally based on the assumption that the content of the images is usually accessible in clear form, from which the spatial transformation is subsequently estimated. This common assumption may not be met in practical applications, since the sensitive nature of medical images may ultimately require their analysis under privacy constraints, preventing to openly share the image content.In this work, we formulate the problem of image registration under a privacy preserving regime, where images are assumed to be confidential and cannot be disclosed in clear. We derive our privacy preserving image registration framework by extending classical registration paradigms to account for advanced cryptographic tools, such as secure multi-party computation and homomorphic encryption, that enable the execution of operations without leaking the underlying data. To overcome the problem of performance and scalability of cryptographic tools in high dimensions, we propose several techniques to optimize the image registration operations by using gradient approximations, and by revisiting the use of homomorphic encryption trough packing, to allow the efficient encryption and multiplication of large matrices. We demonstrate our privacy preserving framework in linear and non-linear registration problems, evaluating its accuracy and scalability with respect to standard, non-private counterparts. Our results show that privacy preserving image registration is feasible and can be adopted in sensitive medical imaging applications.