Sina Khajehabdollahi, Gautier Hamon, Marko Cvjetko
et al.
Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional exploration methods like Novelty Search (NS) expand locally by mutating known novel solutions but often plateau when local novelty is exhausted, failing to reach distant, unexplored regions. We introduce Expedition and Expansion (E&E), a hybrid strategy where exploration alternates between local novelty-driven expansions and goal-directed expeditions. During expeditions, E&E leverages a Vision-Language Model (VLM) to generate linguistic goals--descriptions of interesting but hypothetical patterns that drive exploration toward uncharted regions. By operating in semantic spaces that align with human perception, E&E both evaluates novelty and generates goals in conceptually meaningful ways, enhancing the interpretability and relevance of discovered behaviors. Tested on Flow Lenia, a continuous CA known for its rich, emergent behaviors, E&E consistently uncovers more diverse solutions than existing exploration methods. A genealogical analysis further reveals that solutions originating from expeditions disproportionately influence long-term exploration, unlocking new behavioral niches that serve as stepping stones for subsequent search. These findings highlight E&E's capacity to break through local novelty boundaries and explore behavioral landscapes in human-aligned, interpretable ways, offering a promising template for open-ended exploration in artificial life and beyond.
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.
In this paper, we introduce InMD-X, a collection of multiple large language models specifically designed to cater to the unique characteristics and demands of Internal Medicine Doctors (IMD). InMD-X represents a groundbreaking development in natural language processing, offering a suite of language models fine-tuned for various aspects of the internal medicine field. These models encompass a wide range of medical sub-specialties, enabling IMDs to perform more efficient and accurate research, diagnosis, and documentation. InMD-X's versatility and adaptability make it a valuable tool for improving the healthcare industry, enhancing communication between healthcare professionals, and advancing medical research. Each model within InMD-X is meticulously tailored to address specific challenges faced by IMDs, ensuring the highest level of precision and comprehensiveness in clinical text analysis and decision support. This paper provides an overview of the design, development, and evaluation of InMD-X, showcasing its potential to revolutionize the way internal medicine practitioners interact with medical data and information. We present results from extensive testing, demonstrating the effectiveness and practical utility of InMD-X in real-world medical scenarios.
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.
Large language models (LLMs), such as ChatGPT, have received substantial attention due to their capabilities for understanding and generating human language. While there has been a burgeoning trend in research focusing on the employment of LLMs in supporting different medical tasks (e.g., enhancing clinical diagnostics and providing medical education), a review of these efforts, particularly their development, practical applications, and outcomes in medicine, remains scarce. Therefore, this review aims to provide a detailed overview of the development and deployment of LLMs in medicine, including the challenges and opportunities they face. In terms of development, we provide a detailed introduction to the principles of existing medical LLMs, including their basic model structures, number of parameters, and sources and scales of data used for model development. It serves as a guide for practitioners in developing medical LLMs tailored to their specific needs. In terms of deployment, we offer a comparison of the performance of different LLMs across various medical tasks, and further compare them with state-of-the-art lightweight models, aiming to provide an understanding of the advantages and limitations of LLMs in medicine. Overall, in this review, we address the following questions: 1) What are the practices for developing medical LLMs 2) How to measure the medical task performance of LLMs in a medical setting? 3) How have medical LLMs been employed in real-world practice? 4) What challenges arise from the use of medical LLMs? and 5) How to more effectively develop and deploy medical LLMs? By answering these questions, this review aims to provide insights into the opportunities for LLMs in medicine and serve as a practical resource. We also maintain a regularly updated list of practical guides on medical LLMs at https://github.com/AI-in-Health/MedLLMsPracticalGuide
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.
Resumo O artigo investiga o projeto de estudo científico da criança idealizado por Maria Lacerda de Moura entre 1908 e 1921. O recorte contempla a trajetória da professora na cidade de Barbacena, lugar em que pensou, escreveu e difundiu seus ideais sobre a psicologia experimental. Dentre as fontes mobilizadas, destacam-se o requerimento enviado pela professora à Secretaria do Interior do Estado de Minas Gerais, solicitando autorização para realizar experiências científicas nas escolas de Barbacena, e os pareceres gerados em resposta ao seu pedido. Além da identificação dos testes, também foi possível verificar a resistência do governo ao projeto, revelando diferentes relações de poder no contexto da inserção da psicologia experimental na educação.
This article sets its investigative goal on determining the medical knowledge of medieval physicians from 1347-8 to 1351 concerning the causes of plague. As the plague killed a third of Europe’s population, the contemporary witness at the time perceived God as the sender of this plague to punish the human society. However, physicians separated the religious and cultural explanation for the cause of this plague and instead seek the answer to this question elsewhere. Developing on traditional medical knowledges, physicians classified the possible range of the plague’s causes into two areas: universal cause and individual/particular causes. In addition, they also sought to explain the causes by employing the traditional miasma-humoral theory. Unlike the previous ones, however, the plague during 1347-8 to 1351 killed the patients indiscriminately and also incredibly viciously. This phenomenon could not be explained by merely using the traditional medical knowledge and this idiosyncrasy led the physicians employ the poison theory to explain the causes of plague more pragmatically.
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.
Explainable artificial intelligence (XAI) is essential for enabling clinical users to get informed decision support from AI and comply with evidence-based medical practice. Applying XAI in clinical settings requires proper evaluation criteria to ensure the explanation technique is both technically sound and clinically useful, but specific support is lacking to achieve this goal. To bridge the research gap, we propose the Clinical XAI Guidelines that consist of five criteria a clinical XAI needs to be optimized for. The guidelines recommend choosing an explanation form based on Guideline 1 (G1) Understandability and G2 Clinical relevance. For the chosen explanation form, its specific XAI technique should be optimized for G3 Truthfulness, G4 Informative plausibility, and G5 Computational efficiency. Following the guidelines, we conducted a systematic evaluation on a novel problem of multi-modal medical image explanation with two clinical tasks, and proposed new evaluation metrics accordingly. Sixteen commonly-used heatmap XAI techniques were evaluated and found to be insufficient for clinical use due to their failure in G3 and G4. Our evaluation demonstrated the use of Clinical XAI Guidelines to support the design and evaluation of clinically viable XAI.
Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman
Visual Question Answering (VQA) models take an image and a natural-language question as input and infer the answer to the question. Recently, VQA systems in medical imaging have gained popularity thanks to potential advantages such as patient engagement and second opinions for clinicians. While most research efforts have been focused on improving architectures and overcoming data-related limitations, answer consistency has been overlooked even though it plays a critical role in establishing trustworthy models. In this work, we propose a novel loss function and corresponding training procedure that allows the inclusion of relations between questions into the training process. Specifically, we consider the case where implications between perception and reasoning questions are known a-priori. To show the benefits of our approach, we evaluate it on the clinically relevant task of Diabetic Macular Edema (DME) staging from fundus imaging. Our experiments show that our method outperforms state-of-the-art baselines, not only by improving model consistency, but also in terms of overall model accuracy. Our code and data are available at https://github.com/sergiotasconmorales/consistency_vqa.
Olha DENYSENKO, Liliia HULEI, Maryna HAIEVSKA
et al.
The article summarizes the results of
scientific activities of the Dermatovenereology Department of Bukovinian
State Medical University for 75 years of its existence. The authors consider
the main scientific achievements of the department in the historical aspect
and and over the past 10 years. Research methods: the chronological,
historical and and system analysis method. Scientific novelty. For the first
time, the directions of the scientific work of the department staff in the
historical aspect and the main scientific achievements over the past 10 years
are comprehensively highlighted. Conclusions. It is shown that the priority
directions of the department scientific work at different historical stages of
its existence were scientific research devoted to solving the actual problems
of the dermatovenereological morbidity in the region and the country
overall - studying aspects of etiopathogenesis and improving the
diagnostics and treatment of dermatomycoses, tuberculosis, psoriasis,
allergic diseases, lupus erythematosus, acne, rosacea, syphilitic infection.
The development of the new improved schemes of diagnostics and
treatment of the chronic dermatoses and their implementation into the
medical practice, the defence of PhD and doctoral dissertations, helding the
scientific conferences, participation with reports at the international forums,
the issued monographs, numerous scientific publications, patents, etc. were
the results of scientific work, as well as the implemention of the research
results into the pedagogical process of the department, which assist in
increasing the efficiency of the future medical professionals training at
different levels.
History of medicine. Medical expeditions, Social Sciences
Deep learning (DL) models for disease classification or segmentation from medical images are increasingly trained using transfer learning (TL) from unrelated natural world images. However, shortcomings and utility of TL for specialized tasks in the medical imaging domain remain unknown and are based on assumptions that increasing training data will improve performance. We report detailed comparisons, rigorous statistical analysis and comparisons of widely used DL architecture for binary segmentation after TL with ImageNet initialization (TII-models) with supervised learning with only medical images(LMI-models) of macroscopic optical skin cancer, microscopic prostate core biopsy and Computed Tomography (CT) DICOM images. Through visual inspection of TII and LMI model outputs and their Grad-CAM counterparts, our results identify several counter intuitive scenarios where automated segmentation of one tumor by both models or the use of individual segmentation output masks in various combinations from individual models leads to 10% increase in performance. We also report sophisticated ensemble DL strategies for achieving clinical grade medical image segmentation and model explanations under low data regimes. For example; estimating performance, explanations and replicability of LMI and TII models described by us can be used for situations in which sparsity promotes better learning. A free GitHub repository of TII and LMI models, code and more than 10,000 medical images and their Grad-CAM output from this study can be used as starting points for advanced computational medicine and DL research for biomedical discovery and applications.
Долгое время немец-
коязычная литература Буковины не была объектом научных интересов украинских ученых. Причин этому несколько:
во-первых, много буковинских немецкоязычных авторов были вынуждены эмигрировать за границу, а некоторые были
репрессированы и находились в советских трудовых лагерях. Во-вторых, немецкоязычную литературу Буковины рас-
сматривали как колониальное наследие Австро-Венгерской империи, а немецкий язык был вытеснен из ежедневного
использования в связи с новыми политическими и общественными условиями.
Цель статьи – анализ образа матери в лирическом наследии немецкоязычного писателя Буковины Мозеса Розен-
кранца, в частности, в поэтическом сборнике “Буковина. Стихи 1920–1997”. В данной разведке проанализированы
поэзии “Die Mutter”, “Die armen Mütter”, “Pieta auf dem Schlachtfeld”, “Abschied”, которые дают четкое представление
об отношении автора к матери и отражают его в лирической поэзии.
Методы исследования: культурно-исторический, описания, интертекстуальный, биографический.
Выводы. Среди художественных образов в поэтических произведениях Мозеса Розенкранца образ женщины-
матери – один из самых любимых. Мать в его жизни сыграла очень важную роль. Поэтому именно матери посвящено
большое количество стихотворений М. Розенкранца, где он изображает тяжелую и печальную, даже трагическую,
судьбу женщины-матери в современном ему обществе.The German-
language literature of Bukovina was not the subject of interest of
Ukrainian scholars for a long time. There are several reasons for
this: firstly, many Bukovinian German-speaking authors were
forced to emigrate abroad, and some were repressed and spent their
lives in Soviet labor camps. In addition, the German-language
literature of Bukovina was regarded as a colonial heritage of the
Austro-Hungarian Empire, that is why the German language was
forced out from the daily use in connection with the new political
and social conditions. The article is aimed at the image of the
mother in the poetic work of the Bukovinian German-speaking
writer Moses Rosenkranz, in particular, in the collection
“Bukovina. Verses 1920–1997”. The poems “Die Mutter”, “Die
armen Mütter”, “Pieta auf dem Schlachtfeld”, “Abschied” are ana-
lyzed, which give a clear idea of the author’s attitude to his mother
and its reflection in lyrical poetry. To achieve the objectives of the
research, the following methods have been used: biographical,
cultural-historical, descriptive, intertextual, method of peer reading,
etc. The scientific novelty lies in an attempt to analyze the image
of the mother in Moses Rosenkranz’s lyrics on the example of
several poems. Also, the article provides several translations of
poems that were previously published only in German. In the proc-
ess of analysis, we came to the conclusion that the image of the
mother for a Bukovinian poet Moses Rosenkranz is one of the most
beloved ones. His mother played a big role in the life of the author.
That is why a large number of works is devoted to her. The images
of mothers are mostly sad and tragic, and their fates are unlucky, as
the prototypes for them became women, who the writer saw in his
childhood in the Bukovinian villages, during the Second World
War, in a ghetto, in labor camps and emigration. The analyzed
poetry is just a small segment of the artistic production of Moses
Rosenkranz, whose poetic legacy deserves much deeper and more
detailed study in all its thematic variety and multifaceted issues.
History of medicine. Medical expeditions, Social Sciences