A data-efficient strategy for building high-performing medical foundation models
Related Articles
An Integrative lifecycle design approach based on carbon intensity for renewable-battery-consumer energy systems
Driven by sustainable development goals and carbon neutrality worldwide, demands for both renewable energy and storage systems are constantly increasing. However, the lack of an appropriate approach without considering renewable intermittence and demand stochasticity will lead to capacity oversizing or undersizing. In this study, an optimal design approach is proposed for integrated photovoltaic-battery-consumer energy systems in the form of a m2-kWp-kWh relationship in both centralized and distributed formats. Superiorities of the proposed matching degree approach are compared with the traditional uniformity approach, in photovoltaic capacity, battery capacity, net present value and lifecycle carbon intensity. Results showed that the proposed method is superior to the traditional approach with higher net present value and lower carbon intensity. Furthermore, the proposed method can be scaled and applied to guide the design of photovoltaic-battery-consumer energy systems in different climate zones, promoting sustainable development and carbon neutrality globally.
Evolutionary optimization of model merging recipes
Large language models (LLMs) have become increasingly capable, but their development often requires substantial computational resources. Although model merging has emerged as a cost-effective promising approach for creating new models by combining existing ones, it currently relies on human intuition and domain knowledge, limiting its potential. Here we propose an evolutionary approach that overcomes this limitation by automatically discovering effective combinations of diverse open-source models, harnessing their collective intelligence without requiring extensive additional training data or compute. Our approach operates in both parameter space and data flow space, allowing optimization beyond just the weights of the individual models. This approach even facilitates cross-domain merging, generating models such as a Japanese LLM with math reasoning capabilities. Surprisingly, our Japanese math LLM achieved state-of-the-art performance on a variety of established Japanese LLM benchmarks, even surpassing models with substantially more parameters, despite not being explicitly trained for such tasks. Furthermore, a culturally aware Japanese vision–language model generated through our approach demonstrates its effectiveness in describing Japanese culture-specific content, outperforming previous Japanese vision–language models. This work not only contributes new state-of-the-art models back to the open-source community but also introduces a new paradigm for automated model composition, paving the way for exploring alternative, efficient approaches to foundation model development.
Air, surface, and wastewater surveillance of SARS-CoV-2; a multimodal evaluation of COVID-19 detection in a built environment
Environmental surveillance of infectious organisms holds tremendous promise to reduce human-to-human transmission in indoor spaces through early detection.
Segment Anything for Microscopy
Accurate segmentation of objects in microscopy images remains a bottleneck for many researchers despite the number of tools developed for this purpose. Here, we present Segment Anything for Microscopy (μSAM), a tool for segmentation and tracking in multidimensional microscopy data. It is based on Segment Anything, a vision foundation model for image segmentation. We extend it by fine-tuning generalist models for light and electron microscopy that clearly improve segmentation quality for a wide range of imaging conditions. We also implement interactive and automatic segmentation in a napari plugin that can speed up diverse segmentation tasks and provides a unified solution for microscopy annotation across different microscopy modalities. Our work constitutes the application of vision foundation models in microscopy, laying the groundwork for solving image analysis tasks in this domain with a small set of powerful deep learning models.
Distributed training of foundation models for ophthalmic diagnosis
Vision impairment affects nearly 2.2 billion people globally, and nearly half of these cases could be prevented with early diagnosis and intervention—underscoring the urgent need for reliable and scalable detection methods for conditions like diabetic retinopathy and age-related macular degeneration. Here we propose a distributed deep learning framework that integrates self-supervised and domain-adaptive federated learning to enhance the detection of eye diseases from optical coherence tomography images. We employed a self-supervised, mask-based pre-training strategy to develop a robust foundation encoder. This encoder was trained on seven optical coherence tomography datasets, and we compared its performance under local, centralized, and federated learning settings. Our results show that self-supervised methods—both centralized and federated—improved the area under the curve by at least 10% compared to local models. Additionally, incorporating domain adaptation into the federated learning framework further boosted performance and generalization across different populations and imaging conditions. This approach supports collaborative model development without data sharing, providing a scalable, privacy-preserving solution for effective retinal disease screening and diagnosis in diverse clinical settings.
Responses