Explore the vast range of titles available.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology. Pretrained using over 100,000 diagnostic histopathological slides across 20 major tissue types, a self-supervised model is shown to outperform existing baselines across various clinically relevant computational pathology tasks.

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature ( n  = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here, the authors present the largest FL study to-date to generate an automatic tumor boundary detector for glioblastoma.

Several studies underscore the potential of deep learning in identifying complex patterns, leading to diagnostic and prognostic biomarkers. Identifying sufficiently large and diverse datasets, required for training, is a significant challenge in medicine and can rarely be found in individual institutions. Multi-institutional collaborations based on centrally-shared patient data face privacy and ownership challenges. Federated learning is a novel paradigm for data-private multi-institutional collaborations, where model-learning leverages all available data without sharing data between institutions, by distributing the model-training to the data-owners and aggregating their results. We show that federated learning among 10 institutions results in models reaching 99% of the model quality achieved with centralized data, and evaluate generalizability on data from institutions outside the federation. We further investigate the effects of data distribution across collaborating institutions on model quality and learning patterns, indicating that increased access to data through data private multi-institutional collaborations can benefit model quality more than the errors introduced by the collaborative method. Finally, we compare with other collaborative-learning approaches demonstrating the superiority of federated learning, and discuss practical implementation considerations. Clinical adoption of federated learning is expected to lead to models trained on datasets of unprecedented size, hence have a catalytic impact towards precision/personalized medicine.

Wearable electronics with great breathability enable a comfortable wearing experience and facilitate continuous biosignal monitoring over extended periods 1 – 3 . However, current research on permeable electronics is predominantly at the stage of electrode and substrate development, which is far behind practical applications with comprehensive integration with diverse electronic components (for example, circuitry, electronics, encapsulation) 4 – 8 . Achieving permeability and multifunctionality in a singular, integrated wearable electronic system remains a formidable challenge. Here we present a general strategy for integrated moisture-permeable wearable electronics based on three-dimensional liquid diode (3D LD) configurations. By constructing spatially heterogeneous wettability, the 3D LD unidirectionally self-pumps the sweat from the skin to the outlet at a maximum flow rate of 11.6 ml cm −2  min −1 , 4,000 times greater than the physiological sweat rate during exercise, presenting exceptional skin-friendliness, user comfort and stable signal-reading behaviour even under sweating conditions. A detachable design incorporating a replaceable vapour/sweat-discharging substrate enables the reuse of soft circuitry/electronics, increasing its sustainability and cost-effectiveness. We demonstrated this fundamental technology in both advanced skin-integrated electronics and textile-integrated electronics, highlighting its potential for scalable, user-friendly wearable devices. Incorporation of a ‘liquid diode’ into a wearable electronic platform enhances comfort and stability by shunting away sweat as it accumulates.

Continuous monitoring of arterial blood pressure (BP) outside of a clinical setting is crucial for preventing and diagnosing hypertension related diseases. However, current continuous BP monitoring instruments suffer from either bulky systems or poor user-device interfacial performance, hampering their applications in continuous BP monitoring. Here, we report a thin, soft, miniaturized system (TSMS) that combines a conformal piezoelectric sensor array, an active pressure adaptation unit, a signal processing module, and an advanced machine learning method, to allow real wearable, continuous wireless monitoring of ambulatory artery BP. By optimizing the materials selection, control/sampling strategy, and system integration, the TSMS exhibits improved interfacial performance while maintaining Grade A level measurement accuracy. Initial trials on 87 volunteers and clinical tracking of two hypertension individuals prove the capability of the TSMS as a reliable BP measurement product, and its feasibility and practical usability in precise BP control and personalized diagnosis schemes development. Continuous monitoring of arterial blood pressure is limited by bulky connecting systems and poor interfacial contact. Here, Li et al. report a wearable thin, soft, miniaturized system that integrates sensing, active pressure adaptation, and signal processing for improved performance and accuracy.

The artificial intelligence revolution has been spurred forward by the availability of large-scale datasets. In contrast, the paucity of large-scale medical datasets hinders the application of machine learning in healthcare. The lack of publicly available multi-centric and diverse datasets mainly stems from confidentiality and privacy concerns around sharing medical data. To demonstrate a feasible path forward in medical image imaging, we conduct a case study of applying a differentially private federated learning framework for analysis of histopathology images, the largest and perhaps most complex medical images. We study the effects of IID and non-IID distributions along with the number of healthcare providers, i.e., hospitals and clinics, and the individual dataset sizes, using The Cancer Genome Atlas (TCGA) dataset, a public repository, to simulate a distributed environment. We empirically compare the performance of private, distributed training to conventional training and demonstrate that distributed training can achieve similar performance with strong privacy guarantees. We also study the effect of different source domains for histopathology images by evaluating the performance using external validation. Our work indicates that differentially private federated learning is a viable and reliable framework for the collaborative development of machine learning models in medical image analysis.

Sensitivity is a crucial parameter for flexible pressure sensors and electronic skins. While introducing microstructures (e.g., micro-pyramids) can effectively improve the sensitivity, it in turn leads to a limited pressure-response range due to the poor structural compressibility. Here, we report a strategy of engineering intrafillable microstructures that can significantly boost the sensitivity while simultaneously broadening the pressure responding range. Such intrafillable microstructures feature undercuts and grooves that accommodate deformed surface microstructures, effectively enhancing the structural compressibility and the pressure-response range. The intrafillable iontronic sensor exhibits an unprecedentedly high sensitivity ( S min   >  220 kPa −1 ) over a broad pressure regime (0.08 Pa-360 kPa), and an ultrahigh pressure resolution (18 Pa or 0.0056%) over the full pressure range, together with remarkable mechanical stability. The intrafillable structure is a general design expected to be applied to other types of sensors to achieve a broader pressure-response range and a higher sensitivity. Though flexible pressure sensors are attractive for next-generation applications, limitations in its performance hinder widespread adoption. Here, the authors report an iontronic flexible pressure sensor with graded intrafillable architecture that shows high sensitivity over a broad pressure range.

The potential of monitoring biomarkers in sweat for health-related applications has spurred rapid growth in the field of wearable sweat sensors over the past decade. Some of the key challenges have been addressed, including measuring sweat-secretion rate and collecting sufficient sample volumes for real-time, continuous molecular analysis without intense exercise. However, except for assessment of cystic fibrosis and regional nerve function, the ability to accurately measure analytes of interest and their physiological relevance to health metrics remain to be determined. Although sweat is not a crystal ball into every aspect of human health, we expect sweat measurements to continue making inroads into niche applications involving active sweating, such as hydration monitoring for athletes and physical laborers and later for medical and casual health monitoring of relevant drugs and hormones. A comprehensive look at wearable sweat sensors defines their capabilities.

A tiny soft-bodied robot is described that can be magnetically actuated to swim, climb, roll, walk and jump, while carrying a load. Robots with range Small-scale actuators and robots designed to travel, potentially while carrying cargo, to locations that are inaccessible for their human overlords, tend to struggle to negotiate complex surfaces or terrains. This is pronounced if the miniscule robot has only one style of locomotion, which cannot handle challenges such as slopes, steps or a change in friction. Metin Sitti and colleagues develop a magnetically controlled cuboidal silicone device that exhibits a range of locomotive styles including rolling, crawling, walking, jumping and swimming, which it can switch between depending on the terrain. The device can move from swimming through liquids to transporting itself on a solid surface without physical intervention and can pick up cargo, transport it whilst rolling and deposit it elsewhere. Untethered small-scale (from several millimetres down to a few micrometres in all dimensions) robots that can non-invasively access confined, enclosed spaces may enable applications in microfactories such as the construction of tissue scaffolds by robotic assembly 1 , in bioengineering such as single-cell manipulation and biosensing 2 , and in healthcare 3 , 4 , 5 , 6 such as targeted drug delivery 4 and minimally invasive surgery 3 , 5 . Existing small-scale robots, however, have very limited mobility because they are unable to negotiate obstacles and changes in texture or material in unstructured environments 7 , 8 , 9 , 10 , 11 , 12 , 13 . Of these small-scale robots, soft robots have greater potential to realize high mobility via multimodal locomotion, because such machines have higher degrees of freedom than their rigid counterparts 14 , 15 , 16 . Here we demonstrate magneto-elastic soft millimetre-scale robots that can swim inside and on the surface of liquids, climb liquid menisci, roll and walk on solid surfaces, jump over obstacles, and crawl within narrow tunnels. These robots can transit reversibly between different liquid and solid terrains, as well as switch between locomotive modes. They can additionally execute pick-and-place and cargo-release tasks. We also present theoretical models to explain how the robots move. Like the large-scale robots that can be used to study locomotion 17 , these soft small-scale robots could be used to study soft-bodied locomotion produced by small organisms.

Bioinspired architectures are effective in enhancing the mechanical properties of materials, yet are difficult to construct in metallic systems. The structure-property relationships of bioinspired metallic composites also remain unclear. Here, Mg-Ti composites were fabricated by pressureless infiltrating pure Mg melt into three-dimensional (3-D) printed Ti-6Al-4V scaffolds. The result was composite materials where the constituents are continuous, mutually interpenetrated in 3-D space and exhibit specific spatial arrangements with bioinspired brick-and-mortar, Bouligand, and crossed-lamellar architectures. These architectures promote effective stress transfer, delocalize damage and arrest cracking, thereby bestowing improved strength and ductility than composites with discrete reinforcements. Additionally, they activate a series of extrinsic toughening mechanisms, including crack deflection/twist and uncracked-ligament bridging, which enable crack-tip shielding from the applied stress and lead to “Γ”-shaped rising fracture resistance R-curves. Quantitative relationships were established for the stiffness and strengths of the composites by adapting classical laminate theory to incorporate their architectural characteristics. Bioinspired architectures are desired to achieve improved mechanical properties, but challenging to achieve in metallic systems. Here the authors fabricate a Mg-Ti interpenetrating phase composite with brick-and-mortar, Bouligand, and crossed-lamellar architectures by pressureless infiltrating method.