共找到 20 条结果
Machine unlearning aims to remove private or sensitive data from a pre-trained model while preserving the model's robustness. Despite recent advances, this technique has not been explored in medical image classification. This work evaluates the SalUn unlearning model by conducting experiments on the PathMNIST, OrganAMNIST, and BloodMNIST datasets. We also analyse the impact of data augmentation on the quality of unlearning. Results show that SalUn achieves performance close to full retraining, indicating an efficient solution for use in medical applications.
The pharmacopeia used by physicians and lay people in medieval Europe has largely been dismissed as placebo or superstition. While we now recognise that some of the materia medica used by medieval physicians could have had useful biological properties, research in this area is limited by the labour-intensive process of searching and interpreting historical medical texts. Here, we demonstrate the potential power of turning medieval medical texts into contextualised electronic databases amenable to exploration by algorithm. We use established methodologies from network science to reveal statistically significant patterns in ingredient selection and usage in a key text, the fifteenth-century Lylye of Medicynes, focusing on remedies to treat symptoms of microbial infection. We discuss the potential that these patterns reflect rational medical decisions. In providing a worked example of data-driven textual analysis, we demonstrate the potential of this approach to encourage interdisciplinary collaboration and to shine a new light on the ethnopharmacology of historical medical texts.
Type 2 diabetes patients in China face many significant challenges in patient-provider communication and self management In light of this, this work designed,implemented,and evaluated an AI-driven, personalized, multi-functional mobile app system named T2MD Health. The appintegrates real-time patient- provider conversation transcription,medical terminology interpretation, daily health tracking, and adata-driven feedback loop. We conducted qualitative interviewswith 40 participants to study key user needs before systemdevelopment and a mixed- method controlled experiment with 60participants after to evaluate the effectiveness and usability ofthe app. Evaluation results showed that the app was effective inimproving patient-provider communication efficiency, patientunderstanding and knowledge retention,and patient selfmanagement, Patient feedback also revealed that the app has thepotential to address the urban-rural gap in the access to medica!consultation services to some extent, Findings ofthis study couldinform future studies that seek to utilize mobile apps andartificial intelligence to support patients with chronic diseases.
Large language models (LLMs) have demonstrated exceptional capabilities in general domains, yet their application in highly specialized and culturally-rich fields like Traditional Chinese Medicine (TCM) requires rigorous and nuanced evaluation. Building upon prior foundational work such as TCM-3CEval, which highlighted systemic knowledge gaps and the importance of cultural-contextual alignment, we introduce TCM-5CEval, a more granular and comprehensive benchmark. TCM-5CEval is designed to assess LLMs across five critical dimensions: (1) Core Knowledge (TCM-Exam), (2) Classical Literacy (TCM-LitQA), (3) Clinical Decision-making (TCM-MRCD), (4) Chinese Materia Medica (TCM-CMM), and (5) Clinical Non-pharmacological Therapy (TCM-ClinNPT). We conducted a thorough evaluation of fifteen prominent LLMs, revealing significant performance disparities and identifying top-performing models like deepseek\_r1 and gemini\_2\_5\_pro. Our findings show that while models exhibit proficiency in recalling foundational knowledge, they struggle with the interpretative complexities of classical texts. Critically, permutation-based consistency testing reveals widespread fragilities in model inference. All
Thyroid scintigraphy is vital for diagnosing thyroid disorders, yet deep learning (DL) models in this domain often struggle with limited, imbalanced datasets. This study investigates the impact of three data augmentation strategies including Stable Diffusion (SD), Flow Matching (FM), and Conventional Augmentation (CA), on enhancing DL-based classification of disease. Anterior thyroid scintigraphy images from 2,954 patients across nine medical centers were classified into four categories: Diffuse Goiter (DG), Nodular Goiter (NG), Normal (NL), and Thyroiditis (TI). Data augmentation was performed using CA as well as various SD and FM models, creating 18 distinct scenarios. Each augmented dataset was used to train a ResNet18 DL-classifier. Model performance was assessed using class-wise and average precision, recall, F1-score, AUC, and image fidelity metrics (FID and KID). FM-based methods demonstrated top-tier performance, with the Original dataset combined with FM (O+FM) configuration achieving the highest micro, macro, and weighted F1-scores (0.78, 0.77, 0.78) and AUC values (0.95, 0.93, 0.94). While the O+FM+CA model also yielded excellent, balanced results, O+FM was statistically
In cases when it is desirable to transport medication through blood vessels, especially when dealing with brain cancer being confronted with the narrow arteries in the brain, the blood-brain barrier makes the medical treatment difficult. There is a need of expanding the diameters of the arteries in order to facilitate the transport of medicaments. Recent research has pointed to various ways to improve this situation; in particular, the use ultrasound acting on microbubbles in the blood stream has turned out to be a promising option. Here, a different possibility of enlarging the diameters of arteries is discussed, namely to exploit the electrostrictive pressure produced by internal strong, ultrashort and repetitive laser pulses. Each pulse will at first give rise to inward directed optical forces, and once the pulse terminates there will be a hydrodynamical bouncing flow in the outward radial direction giving an outward impulse to the vessel wall. In the absence of friction a symmetric oscillation picture emerges. Clearly, a supply of repetitive pulses will be needed (at parametric resonance) to make the effect appreciable. The effect has to our knowledge not been discussed before.
This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.
The purpose was to investigate the spatial heterogeneity of prostate-specific membrane antigen (PSMA) positron emission tomography (PET) uptake within parotid glands. We aim to quantify patterns in well-defined regions to facilitate further investigations. Furthermore, we investigate whether uptake is correlated with computed tomography (CT) texture features. Parotid glands from [18F]DCFPyL PSMA PET/CT images of 30 prostate cancer patients were analyzed. Thresholding was used to define high-uptake regions, and uptake statistics were computed within various divisions. Spearman's rank correlation coefficient was calculated between PSMA PET uptake and the Grey Level Run Length Matrix (GLRLM) using a long and short run length emphasis (GLRLML and GLRLMS) in subregions of parotid glands. PSMA PET uptake was significantly higher (p < 0.001) in lateral/posterior regions of the glands than anterior/medial regions. Maximum uptake was found in the lateral half of parotid glands in 50 out of 60 glands. The difference in SUV between parotid halves is greatest when parotids are divided by a plane separating the anterior/medial and posterior/lateral halves symmetrically. PSMA PET uptake was s
To fulfill needs in oncological research a new Micromegas detector has been developed to follow radiolabelled drugs in living organisms at the single cell level. This article describes the proof-of-concept of such a detector and compares its ability to detect and assess sub-becquerel \tritium~activities with a commercial $β$-imager
In this paper, we address the challenges of automatic metadata annotation in the domain of Galleries, Libraries, Archives, and Museums (GLAMs) by introducing a novel dataset, EUFCC340K, collected from the Europeana portal. Comprising over 340,000 images, the EUFCC340K dataset is organized across multiple facets: Materials, Object Types, Disciplines, and Subjects, following a hierarchical structure based on the Art & Architecture Thesaurus (AAT). We developed several baseline models, incorporating multiple heads on a ConvNeXT backbone for multi-label image tagging on these facets, and fine-tuning a CLIP model with our image text pairs. Our experiments to evaluate model robustness and generalization capabilities in two different test scenarios demonstrate the utility of the dataset in improving multi-label classification tools that have the potential to alleviate cataloging tasks in the cultural heritage sector.
Purpose: To develop a machine learning-based, 3D dose prediction methodology for Gamma Knife (GK) radiosurgery. The methodology accounts for cases involving targets of any number, size, and shape. Methods: Data from 322 GK treatment plans was modified by isolating and cropping the contoured MRI and clinical dose distributions based on tumor location, then scaling the resulting tumor spaces to a standard size. An accompanying 3D tensor was created for each instance to account for tumor size. The modified dataset for 272 patients was used to train both a generative adversarial network (GAN-GK) and a 3D U-Net model (U-Net-GK). Unmodified data was used to train equivalent baseline models. All models were used to predict the dose distribution of 50 out-of-sample patients. Prediction accuracy was evaluated using gamma, with criteria of 4%/2mm, 3%/3mm, 3%/1mm and 1%/1mm. Prediction quality was assessed using coverage, selectivity, and conformity indices. Results: The predictions resulting from GAN-GK and U-Net-GK were similar to their clinical counterparts, with average gamma (4%/2mm) passing rates of 84.9 and 83.1, respectively. In contrast, the gamma passing rate of baseline models were
Maternal health remains a pervasive challenge in developing and underdeveloped countries. Inadequate access to basic antenatal Ultrasound (US) examinations, limited resources such as primary health services and infrastructure, and lack of skilled healthcare professionals are the major concerns. To improve the quality of maternal care, robot-assisted antenatal US systems with teleoperable and autonomous capabilities were introduced. However, the existing teleoperation systems rely on standard video stream-based approaches that are constrained by limited immersion and scene awareness. Also, there is no prior work on autonomous antenatal robotic US systems that automate standardized scanning protocols. To that end, this paper introduces a novel Virtual Reality (VR) platform for robotic antenatal ultrasound, which enables sonologists to control a robotic arm over a wired network. The effectiveness of the system is enhanced by providing a reconstructed 3D view of the environment and immersing the user in a VR space. Also, the system facilitates a better understanding of the anatomical surfaces to perform pragmatic scans using 3D models. Further, the proposed robotic system also has auto
Background: Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation. Purpose: investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation. Methods: CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A ``Baseline'' generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline. Results: The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE)=106$\pm$20.7 HU (mean$\pmσ$). Performance on FLAIR significantly improved for the
Thyrotoxicosis (TT) is associated with an increase in both total and cardiovascu-lar mortality. One of the main thyrotoxicosis risks is Atrial Fibrillation (AF). Right AF predicts help medical personal prescribe the correct medicaments and correct surgical or radioiodine therapy. The main goal of this study is creating a method for practical treatment and diagnostic AF. This study proposes a new method for assessing the risk of occurrence atrial fibrillation for patients with TT. This method considers both the features of the complication and the specifics of the chronic disease. A model is created based on case histories of patients with thyrotoxicosis. We used Machine Learning methods for creating several models. Each model has advantages and disadvantages depending on the diagnostic and medical purposes. The resulting models show high results in the different metrics of the prediction of AF. These models interpreted and simple for use. Therefore, models can be used as part of the support and decision-making system (DSS) by medical specialists in the treatment and diagnostic of AF.
Radiotherapy is part of the treatment of over 50% of cancer patients. Its efficacy is limited by the radiotoxicity to the healthy tissue. FLASH-RT is based on the biological effect that ultra-high dose rates (UHDR) and very short treatment times strongly reduce normal tissue toxicity, while preserving the anti-tumoral effect. Despite many positive preclinical results, the translation of FLASH-RT to the clinic is hampered by the lack of accurate dosimetry for UHDR beams. To date radiochromic film is commonly used for dose assessment but has the drawback of lengthy and cumbersome read out procedures. In this work, we investigate the equivalence of a 2D OSL system to radiochromic film dosimetry in terms of dose rate independency. The comparison of both systems was done using the ElectronFlash linac. We investigated the dose rate dependence by variation of the 1) modality, 2) pulse repetition frequency, 3) pulse length and 4) source to surface distance. Additionally, we compared the 2D characteristics by field size measurements. The OSL calibration showed transferable between conventional and UHDR modality. Both systems are equally independent of average dose rate, pulse length and ins
A estereoscopia eh uma tecnica que permite a observacao de imagens tridimensionais, mas estah sempre associada com o uso de algum equipamento especial para visualizacao, como oculos bicolores ou polarizados. Para o uso em aplicacoes medicas o emprego de tais equipamentos pode inviabilizar sua utilizacao durante procedimentos cirurgicos, por exemplo. Neste trabalho apresentamos um novo tipo de estereoscopio que utiliza uma tela holografica para geracao de imagens tridimensionais sem o uso de qualquer equipamento adicional. Apresentamos a descricao do equipamento utilizado e resultados das imagens visualizadas.
In many practical tasks it is needed to estimate an effect of treatment on individual level. For example, in medicine it is essential to determine the patients that would benefit from a certain medicament. In marketing, knowing the persons that are likely to buy a new product would reduce the amount of spam. In this chapter, we review the methods to estimate an individual treatment effect from a randomized trial, i.e., an experiment when a part of individuals receives a new treatment, while the others do not. Finally, it is shown that new efficient methods are needed in this domain.
Antianemic medicament Ascofer and ferrous gluconate, its basic iron bearing ingredient, were studied with the use of Mossbauer spectroscopy. Room temperature spectra gave a clear evidence that two phases of iron were present viz. ferrous (Fe2+) as a major one with a contribution of 85+-5%, and ferric (Fe3+) whose contribution was found to be 15+-5%. However, the actual values of the contributions of the two kind of the iron ions in Ascofer depend on sample's age: the abundance of Fe2+ ions increases with time by 10% after 51 months, while that of Fe3+ decreases by the same amount. This means that an internal reduction of Fe3+ ions takes place. Ferrous ions were shown to occupy at least two different sites. In Ascofer, the relative abundance of the two sites does not depend on the age of sample, while in the gluconate the population of site 1 increases and that of site 2 decreases with the age of the sample.
We discuss MET, a learning-based algorithm proposed for perceiving a patient's level of engagement during telehealth sessions. We leverage latent vectors corresponding to Affective and Cognitive features frequently used in psychology literature to understand a person's level of engagement in a semi-supervised GAN-based framework. We showcase the efficacy of this method from the perspective of mental health and more specifically how this can be leveraged for a better understanding of patient engagement during telemental health sessions. To further the development of similar technologies that can be useful for telehealth, we also plan to release a dataset MEDICA containing 1299 video clips, each 3 seconds long and show experiments on the same. Our framework reports a 40% improvement in RMSE (Root Mean Squared Error) over state-of-the-art methods for engagement estimation. In our real-world tests, we also observed positive correlations between the working alliance inventory scores reported by psychotherapists. This indicates the potential of the proposed model to present patient engagement estimations that aligns well with the engagement measures used by psychotherapists.