We propose VL-DUN, a principled framework for joint All-in-One Medical Image Restoration and Segmentation (AiOMIRS) that bridges the gap between low-level signal recovery and high-level semantic understanding. While standard pipelines treat these tasks in isolation, our core insight is that they are fundamentally synergistic: restoration provides clean anatomical structures to improve segmentation, while semantic priors regularize the restoration process. VL-DUN resolves the sub-optimality of sequential processing through two primary innovations. (1) We formulate AiOMIRS as a unified optimization problem, deriving an interpretable joint unfolding mechanism where restoration and segmentation are mathematically coupled for mutual refinement. (2) We introduce a frequency-aware Mamba mechanism to capture long-range dependencies for global segmentation while preserving the high-frequency textures necessary for restoration. This allows for efficient global context modeling with linear complexity, effectively mitigating the spectral bias of standard architectures. As a pioneering work in the AiOMIRS task, VL-DUN establishes a new state-of-the-art across multi-modal benchmarks, improving PSNR by 0.92 dB and the Dice coefficient by 9.76\%. Our results demonstrate that joint collaborative learning offers a superior, more robust solution for complex clinical workflows compared to isolated task processing. The codes are provided in https://github.com/cipi666/VLDUN.
Stroke continues to be a major global cause of disability and death, but recent advancements are reshaping its management. In 2025, research has highlighted the promising role of uric acid as a cerebroprotective agent in acute ischemic stroke, with encouraging preclinical and early human data. Ultrasound-enhanced thrombolysis, or sonothrombolysis, is emerging as an innovative technique to improve clot breakdown safely. Rehabilitation is also evolving with virtual reality technologies and assistive devices like the Sixth Finger, which enhance recovery and daily functioning. On the preventive front, retinal vascular imaging is proving valuable in predicting stroke risk non-invasively, while simple lifestyle habits, including routine flossing, have shown significant protective effects. Additionally, growing evidence links environmental factors, such as microplastic accumulation, to cerebrovascular disease, opening new avenues for research and public health measures. Together, these advances reflect a shift toward more personalized, integrated, and preventive stroke care, offering hope for improved patient outcomes and reduced global burden.
History of medicine. Medical expeditions, General works
Medical image analysis often faces significant challenges due to limited expert-annotated data, hindering both model generalization and clinical adoption. We propose an expert-guided explainable few-shot learning framework that integrates radiologist-provided regions of interest (ROIs) into model training to simultaneously enhance classification performance and interpretability. Leveraging Grad-CAM for spatial attention supervision, we introduce an explanation loss based on Dice similarity to align model attention with diagnostically relevant regions during training. This explanation loss is jointly optimized with a standard prototypical network objective, encouraging the model to focus on clinically meaningful features even under limited data conditions. We evaluate our framework on two distinct datasets: BraTS (MRI) and VinDr-CXR (Chest X-ray), achieving significant accuracy improvements from 77.09% to 83.61% on BraTS and from 54.33% to 73.29% on VinDr-CXR compared to non-guided models. Grad-CAM visualizations further confirm that expert-guided training consistently aligns attention with diagnostic regions, improving both predictive reliability and clinical trustworthiness. Our findings demonstrate the effectiveness of incorporating expert-guided attention supervision to bridge the gap between performance and interpretability in few-shot medical image diagnosis.
We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding, focusing on detection, localization, and counting of findings in medical images. Our objective is to evaluate whether instruction-tuned VLMs can simultaneously improve these tasks, with the goal of enhancing diagnostic accuracy and efficiency. Using MedMultiPoints, a multimodal dataset with annotations from endoscopy (polyps and instruments) and microscopy (sperm cells), we reformulate each task into instruction-based prompts suitable for vision-language reasoning. We fine-tune Qwen2.5-VL-7B-Instruct using Low-Rank Adaptation (LoRA) across multiple task combinations. Results show that multi-task training improves robustness and accuracy. For example, it reduces the Count Mean Absolute Error (MAE) and increases Matching Accuracy in the Counting + Pointing task. However, trade-offs emerge, such as more zero-case point predictions, indicating reduced reliability in edge cases despite overall performance gains. Our study highlights the potential of adapting general-purpose VLMs to specialized medical tasks via prompt-driven fine-tuning. This approach mirrors clinical workflows, where radiologists simultaneously localize, count, and describe findings - demonstrating how VLMs can learn composite diagnostic reasoning patterns. The model produces interpretable, structured outputs, offering a promising step toward explainable and versatile medical AI. Code, model weights, and scripts will be released for reproducibility at https://github.com/simula/PointDetectCount.
Heyuan Huang, Alexandra DeLucia, Vijay Murari Tiyyala
et al.
While Large Language Models (LLMs) can generate fluent and convincing responses, they are not necessarily correct. This is especially apparent in the popular decompose-then-verify factuality evaluation pipeline, where LLMs evaluate generations by decomposing the generations into individual, valid claims. Factuality evaluation is especially important for medical answers, since incorrect medical information could seriously harm the patient. However, existing factuality systems are a poor match for the medical domain, as they are typically only evaluated on objective, entity-centric, formulaic texts such as biographies and historical topics. This differs from condition-dependent, conversational, hypothetical, sentence-structure diverse, and subjective medical answers, which makes decomposition into valid facts challenging. We propose MedScore, a new pipeline to decompose medical answers into condition-aware valid facts and verify against in-domain corpora. Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts. The resulting factuality score substantially varies by decomposition method, verification corpus, and used backbone LLM, highlighting the importance of customizing each step for reliable factuality evaluation by using our generalizable and modularized pipeline for domain adaptation.
Medical Referring Image Segmentation (MRIS) involves segmenting target regions in medical images based on natural language descriptions. While achieving promising results, recent approaches usually involve complex design of multimodal fusion or multi-stage decoders. In this work, we propose NTP-MRISeg, a novel framework that reformulates MRIS as an autoregressive next-token prediction task over a unified multimodal sequence of tokenized image, text, and mask representations. This formulation streamlines model design by eliminating the need for modality-specific fusion and external segmentation models, supports a unified architecture for end-to-end training. It also enables the use of pretrained tokenizers from emerging large-scale multimodal models, enhancing generalization and adaptability. More importantly, to address challenges under this formulation-such as exposure bias, long-tail token distributions, and fine-grained lesion edges-we propose three novel strategies: (1) a Next-k Token Prediction (NkTP) scheme to reduce cumulative prediction errors, (2) Token-level Contrastive Learning (TCL) to enhance boundary sensitivity and mitigate long-tail distribution effects, and (3) a memory-based Hard Error Token (HET) optimization strategy that emphasizes difficult tokens during training. Extensive experiments on the QaTa-COV19 and MosMedData+ datasets demonstrate that NTP-MRISeg achieves new state-of-the-art performance, offering a streamlined and effective alternative to traditional MRIS pipelines.
Lemar Abdi, Francisco Caetano, Amaan Valiuddin
et al.
In medical imaging, unsupervised out-of-distribution (OOD) detection offers an attractive approach for identifying pathological cases with extremely low incidence rates. In contrast to supervised methods, OOD-based approaches function without labels and are inherently robust to data imbalances. Current generative approaches often rely on likelihood estimation or reconstruction error, but these methods can be computationally expensive, unreliable, and require retraining if the inlier data changes. These limitations hinder their ability to distinguish nominal from anomalous inputs efficiently, consistently, and robustly. We propose a reconstruction-free OOD detection method that leverages the forward diffusion trajectories of a Stein score-based denoising diffusion model (SBDDM). By capturing trajectory curvature via the estimated Stein score, our approach enables accurate anomaly scoring with only five diffusion steps. A single SBDDM pre-trained on a large, semantically aligned medical dataset generalizes effectively across multiple Near-OOD and Far-OOD benchmarks, achieving state-of-the-art performance while drastically reducing computational cost during inference. Compared to existing methods, SBDDM achieves a relative improvement of up to 10.43% and 18.10% for Near-OOD and Far-OOD detection, making it a practical building block for real-time, reliable computer-aided diagnosis.
The Islamic Maghreb, encompassing modern-day North African countries, was a vast land. It had a rich history of medical practice. Since the beginning of the arrival of Islam in the Maghreb lands, the medical profession was common and the healers who came to this land with the Islamic armies called “fuqaha al-badan” (lit. “body jurists”), practiced the profession of medicine. The Bani Aghelab Muslim rulers pioneered hospital establishments in the Islamic Maghreb, founding the Damneh Qairwan. After them, the Touloni and Akhshidi rulers and others continued the tradition of building hospitals by building Damneh in Tripoli, Fes, Sousse, and Safaqas in today’s eastern Tunisia. Ibn Tulun also founded Atiq Hospital and Al-Asfal Hospital in Fostat, Egypt. The Muslim rulers stationed great doctors, such as Yohanna bin Maswayh, Ishaq bin Imran Israeli, Ain bin Ain, Ahmad bin Jazzar, Muhammad Jabali, Saeed bin Noufal, and Muhammad bin Abdulrahman Masri in these hospitals.This article employs a descriptive-analytical approach to examine the role and contributions of Muslims in advancing medical knowledge, institutions, and hospitals within the Islamic Maghreb. The primary research question explores the extent of Muslim influence in this development. The findings of the study show that medicine in the Islamic Maghreb was predominantly experimental from the Muslims’ arrival until the third century of Hijri. However, between the third and fourth centuries of Hijri, in the light of the efforts of doctors, medical knowledge evolved into a science-based practice. This contributed to significant improvements in medical care, facilities, and services, as hospitals expanded and became increasingly effective.
Medicine, History of medicine. Medical expeditions
Menghan Yu, Sourabh Kulhare, Courosh Mehanian
et al.
Acquiring large quantities of data and annotations is known to be effective for developing high-performing deep learning models, but is difficult and expensive to do in the healthcare context. Adding synthetic training data using generative models offers a low-cost method to deal effectively with the data scarcity challenge, and can also address data imbalance and patient privacy issues. In this study, we propose a comprehensive framework that fits seamlessly into model development workflows for medical image analysis. We demonstrate, with datasets of varying size, (i) the benefits of generative models as a data augmentation method; (ii) how adversarial methods can protect patient privacy via data substitution; (iii) novel performance metrics for these use cases by testing models on real holdout data. We show that training with both synthetic and real data outperforms training with real data alone, and that models trained solely with synthetic data approach their real-only counterparts. Code is available at https://github.com/Global-Health-Labs/US-DCGAN.
Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang
Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of "understanding" human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures-locality and compositionality-within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at https://github.com/JLiangLab/Eden.
The history of medicine has been continuously devaluated in medical education but its importance should not be ignored as for other medical humanities. The educational value of the history of medicine could be summarized as follows ; it allows the students 1) to understand the humane aspect of medicine by telling them how medicine has dealt with human health-disease phenomena in each era of the human history. 2) to improve the professionalism by recognizing that medicine is a profession with a long tradition that dates back to the Hippocratic era 3) to improve current medical practice by understanding the limitations and uncertainties of medicine. 4) to understanding the historical changes of the disease phenomena 5) to develop the basic competence of learned intellectual. 6) to integrate the tradition of their own institutions with themselves.
Max-Heinrich Laves, Malte Tölle, Alexander Schlaefer
et al.
We present Posterior Temperature Optimized Bayesian Inverse Models (POTOBIM), an unsupervised Bayesian approach to inverse problems in medical imaging using mean-field variational inference with a fully tempered posterior. Bayesian methods exhibit useful properties for approaching inverse tasks, such as tomographic reconstruction or image denoising. A suitable prior distribution introduces regularization, which is needed to solve the ill-posed problem and reduces overfitting the data. In practice, however, this often results in a suboptimal posterior temperature, and the full potential of the Bayesian approach is not being exploited. In POTOBIM, we optimize both the parameters of the prior distribution and the posterior temperature with respect to reconstruction accuracy using Bayesian optimization with Gaussian process regression. Our method is extensively evaluated on four different inverse tasks on a variety of modalities with images from public data sets and we demonstrate that an optimized posterior temperature outperforms both non-Bayesian and Bayesian approaches without temperature optimization. The use of an optimized prior distribution and posterior temperature leads to improved accuracy and uncertainty estimation and we show that it is sufficient to find these hyperparameters per task domain. Well-tempered posteriors yield calibrated uncertainty, which increases the reliability in the predictions. Our source code is publicly available at github.com/Cardio-AI/mfvi-dip-mia.
Segmenting medical images is critical to facilitating both patient diagnoses and quantitative research. A major limiting factor is the lack of labeled data, as obtaining expert annotations for each new set of imaging data and task can be labor intensive and inconsistent among annotators. We present CUTS, an unsupervised deep learning framework for medical image segmentation. CUTS operates in two stages. For each image, it produces an embedding map via intra-image contrastive learning and local patch reconstruction. Then, these embeddings are partitioned at dynamic granularity levels that correspond to the data topology. CUTS yields a series of coarse-to-fine-grained segmentations that highlight features at various granularities. We applied CUTS to retinal fundus images and two types of brain MRI images to delineate structures and patterns at different scales. When evaluated against predefined anatomical masks, CUTS improved the dice coefficient and Hausdorff distance by at least 10% compared to existing unsupervised methods. Finally, CUTS showed performance on par with Segment Anything Models (SAM, MedSAM, SAM-Med2D) pre-trained on gigantic labeled datasets.
Зародження психіатричної допомоги на Буковині можна поділити
на два етапи: перший етап - донауковий, другий етап - науковий або
нозологічний. Під час донаукового періоду надання допомоги особам з
ментальними порушеннями відбувалося при монастирях. Їх розцінювали
як одержимих, тобто осіб з бісами. На теренах сучасної Чернівецької
області знаходилося декілька таких монастирів, де могли отримати
допомогу пацієнти з психічними розладами. З моменту проголошення
Буковини коронним краєм австро-угорської імперії, надання
психіатричної допомоги змінилося. Зародилася психіатрична служба та
розуміння, що таке психічний розлад. Відбувся перехід до наукового
тлумачення та підходу надання психіатричної допомоги.
Метою статті було висвітлення становлення психіатричної служби
на Буковині, трансформація підходу надання допомоги хворим з
психічними розладами, від містики до сучасної моделі. Наукова новизна
полягає у аналізі історії психіатрії на Буковині від минулого до
сьогодення та висвітлення основних історичних моментів, що дали
поштовх до формування справжньої нейронауки. Методологічні засади
дослідження: хронологічний та порівняльно-історичний підхід,
системний міждисциплінарний аналіз. Висновки. Історія виникнення
психіатричної служби на Буковині зазнавала злетів та падінь, що
відповідали умовам часу. Трансформація ментальної служби змінювалася
від світогляду та рівня розвитку тогочасної науки. Можна спостерігати
зміни від містифікації до становлення психіатрії, як справжньої сучасної
нейронауки з доказовою базою та гуманним ставленням до пацієнтів.
History of medicine. Medical expeditions, Social Sciences
Weimin Zhou, Sayantan Bhadra, Frank J. Brooks
et al.
Purpose: To objectively assess new medical imaging technologies via computer-simulations, it is important to account for the variability in the ensemble of objects to be imaged. This source of variability can be described by stochastic object models (SOMs). It is generally desirable to establish SOMs from experimental imaging measurements acquired by use of a well-characterized imaging system, but this task has remained challenging. Approach: A generative adversarial network (GAN)-based method that employs AmbientGANs with modern progressive or multiresolution training approaches is proposed. AmbientGANs established using the proposed training procedure are systematically validated in a controlled way using computer-simulated magnetic resonance imaging (MRI) data corresponding to a stylized imaging system. Emulated single-coil experimental MRI data are also employed to demonstrate the methods under less stylized conditions. Results: The proposed AmbientGAN method can generate clean images when the imaging measurements are contaminated by measurement noise. When the imaging measurement data are incomplete, the proposed AmbientGAN can reliably learn the distribution of the measurement components of the objects. Conclusions: Both visual examinations and quantitative analyses, including task-specific validations using the Hotelling observer, demonstrated that the proposed AmbientGAN method holds promise to establish realistic SOMs from imaging measurements.
Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system is then encoded by a fully convolutional network (FCN)-based context feedback system. The encoded feature space of the FCN is then integrated back into the forward system's feed-forward learning process. Using the FCN-based context feedback loop allows the forward system to learn and extract more high-level image features and fix previous mistakes, thereby improving prediction accuracy over time. Experimental results, performed on four different clinical datasets, demonstrate our method's potential application for single and multi-structure medical image segmentation by outperforming the state of the art methods. With the feedback loop, deep learning methods can now produce results that are both anatomically plausible and robust to low contrast images. Therefore, formulating image segmentation as a recurrent framework of two interconnected networks via context feedback loop can be a potential method for robust and efficient medical image analysis.
In the article the titles of Olga
Kobylyanska's small prose through the prism of a cognitive-
pragmatic aspect are described. As a first representative of a work
the title is of great importance, because it carries encoded informa-
tion, adjusts the reader to the theme, idea and rhyme of the work,
creates a background for his perception. The relevance of the artic-
le is determined by the need of further in-depth study of Olga Ko-
bylyanskaya idiostyle in order to form a cognitive-pragmatic conc-
eption of the writer's artistic discourse. The novelty of scientific
exploration is conditioned by the fact that the titles of Olga
Kobylyanska's works of small prose, written at the turn of the 19th
- 20th centuries, have not yet been the subject of analysis. The
purpose of the article is to analyze the titles – ordinary signs of
Olga Kobylyanska's works.
Research methods. In the article as the main general scientific
methods of analysis and synthesis are used, as well as linguistic –
method of linguistic observation, descriptive and structural methods.
Conclusions. Among the names of Olga Kobylyanskaya's small
prose works there are three types of titles: ordinary signs, complicated
signs, figurative signs. Usually, the name of a work depends on the type
of information presented in it, on the form in which the author wanted to
express a particular opinion – explicitly or implicitly. Among the
names of the works – the usual signs we highlight a group motivat-
ed by the social origin of the main characters: "The Beggar", "The
Aristocrat", "The Villein". Some titles of the works indicate the
time and place of action, thus implementing the idea of chronotope:
"In St. Ivan", "Time", "Bank rusticalnyi". We distinguish a series
of works in which the titles indicate the object of lyric hero admira-
ration: "Roses", "What I loved", "Poets".
History of medicine. Medical expeditions, Social Sciences
The strict security requirements placed on medical records by various privacy regulations become major obstacles in the age of big data. To ensure efficient machine learning as a service schemes while protecting data confidentiality, in this work, we propose blind UNET (BUNET), a secure protocol that implements privacy-preserving medical image segmentation based on the UNET architecture. In BUNET, we efficiently utilize cryptographic primitives such as homomorphic encryption and garbled circuits (GC) to design a complete secure protocol for the UNET neural architecture. In addition, we perform extensive architectural search in reducing the computational bottleneck of GC-based secure activation protocols with high-dimensional input data. In the experiment, we thoroughly examine the parameter space of our protocol, and show that we can achieve up to 14x inference time reduction compared to the-state-of-the-art secure inference technique on a baseline architecture with negligible accuracy degradation.