Flow-guided Localization (FGL) enables the identification of spatial regions within the human body that contain an event of diagnostic interest. FGL does that by leveraging the passive movement of energy-constrained nanodevices circulating through the bloodstream. Existing FGL solutions rely on graph models with fixed topologies or handcrafted features, which limit their adaptability to anatomical variability and hinder scalability. In this work, we explore the use of Set Transformer architectures to address these limitations. Our formulation treats nanodevices' circulation time reports as unordered sets, enabling permutation-invariant, variable-length input processing without relying on spatial priors. To improve robustness under data scarcity and class imbalance, we integrate synthetic data generation via deep generative models, including CGAN, WGAN, WGAN-GP, and CVAE. These models are trained to replicate realistic circulation time distributions conditioned on vascular region labels, and are used to augment the training data. Our results show that the Set Transformer achieves comparable classification accuracy compared to Graph Neural Networks (GNN) baselines, while simultaneously providing by-design improved generalization to anatomical variability. The findings highlight the potential of permutation-invariant models and synthetic augmentation for robust and scalable nanoscale localization.

By 2030, rapid technological advancements are expected to reshape humanity, unlocking abilities once confined to science fiction--from superhuman strength to enhanced senses. Robotic exoskeletons may soon allow people to lift heavy objects with ease, while AI-powered wearables, such as smart glasses and earbuds, could provide real-time information and immersive augmented reality experiences. Healthcare may be revolutionized by microscopic nanobots capable of repairing tissue and fighting disease from within the bloodstream, potentially extending human lifespans. Developers are also working on contact lenses with infrared vision and devices that allow users to "feel" digital objects, paving the way for entirely new ways to experience the world. Tech pioneers like former Google engineer Ray Kurzweil believe these innovations are early steps toward the merging of humans and machines, with brain-computer interfaces offering direct access to digital intelligence.

Recent discoveries have suggested that the promising avenue of using circulating tumor DNA (ctDNA) levels in blood samples provides reasonable accuracy for cancer monitoring, with extremely low burden on the patient's side. It is known that the presence of ctDNA can result from various mechanisms leading to DNA release from cells, such as apoptosis, necrosis or active secretion. One key idea in recent cancer monitoring studies is that monitoring the dynamics of ctDNA levels might be sufficient for early multi-cancer detection. This interesting idea has been turned into commercial products, e.g. in the company named GRAIL. In the present work, we propose to explore the use of Signature theory for detecting aggressive cancer tumors based on the analysis of blood samples. Our approach combines tools from continuous time Markov modelling for the dynamics of ctDNA levels in the blood, with Signature theory for building efficient testing procedures. Signature theory is a topic of growing interest in the Machine Learning community (see Chevyrev2016 and Fermanian2021), which is now recognised as a powerful feature extraction tool for irregularly sampled signals. The method proposed in the present paper is shown to correctly address the challenging problem of overcoming the inherent data scarsity due to the extremely small number of blood samples per patient. The relevance of our approach is illustrated with extensive numerical experiments that confirm the efficiency of the proposed pipeline.

Flow-guided localization using in-body nanodevices in the bloodstream is expected to be beneficial for early disease detection, continuous monitoring of biological conditions, and targeted treatment. The nanodevices face size and power constraints that produce erroneous raw data for localization purposes. On-body anchors receive this data, and use it to derive the locations of diagnostic events of interest. Different Machine Learning (ML) approaches have been recently proposed for this task, yet they are currently restricted to a reference bloodstream of a resting patient. As such, they are unable to deal with the physical diversity of patients' bloodstreams and cannot provide continuous monitoring due to changes in individual patient's activities. Toward addressing these issues for the current State-of-the-Art (SotA) flow-guided localization approach based on Graph Neural Networks (GNNs), we propose a pipeline for GNN adaptation based on individual physiological indicators including height, weight, and heart rate. Our results indicate that the proposed adaptions are beneficial in reconciling the individual differences between bloodstreams and activities.

Advancements in nanotechnology and material science are paving the way toward nanoscale devices that combine sensing, computing, data and energy storage, and wireless communication. In precision medicine, these nanodevices show promise for disease diagnostics, treatment, and monitoring from within the patients' bloodstreams. Assigning the location of a sensed biological event with the event itself, which is the main proposition of flow-guided in-body nanoscale localization, would be immensely beneficial from the perspective of precision medicine. The nanoscale nature of the nanodevices and the challenging environment that the bloodstream represents, result in current flow-guided localization approaches being constrained in their communication and energy-related capabilities. The communication and energy constraints of the nanodevices result in different features of raw data for flow-guided localization, in turn affecting its performance. An analytical modeling of the effects of imperfect communication and constrained energy causing intermittent operation of the nanodevices on the raw data produced by the nanodevices would be beneficial. Hence, we propose an analytical model of raw data for flow-guided localization, where the raw data is modeled as a function of communication and energy-related capabilities of the nanodevice. We evaluate the model by comparing its output with the one obtained through the utilization of a simulator for objective evaluation of flow-guided localization, featuring comparably higher level of realism. Our results across a number of scenarios and heterogeneous performance metrics indicate high similarity between the model and simulator-generated raw datasets.

Nanodevices with Terahertz (THz)-based wireless communication capabilities are providing a primer for flow-guided localization within the human bloodstreams. Such localization is allowing for assigning the locations of sensed events with the events themselves, providing benefits in precision medicine along the lines of early and precise diagnostics, and reduced costs and invasiveness. Flow-guided localization is still in a rudimentary phase, with only a handful of works targeting the problem. Nonetheless, the performance assessments of the proposed solutions are already carried out in a non-standardized way, usually along a single performance metric, and ignoring various aspects that are relevant at such a scale (e.g., nanodevices' limited energy) and for such a challenging environment (e.g., extreme attenuation of in-body THz propagation). As such, these assessments feature low levels of realism and cannot be compared in an objective way. Toward addressing this issue, we account for the environmental and scale-related peculiarities of the scenario and assess the performance of two state-of-the-art flow-guided localization approaches along a set of heterogeneous performance metrics such as the accuracy and reliability of localization.

A novel artificial intelligence blood testing technology developed and used by Johns Hopkins Kimmel Cancer Center researchers to successfully detect lung cancer in a 2021 study has now detected more than 80% of liver cancers in a new study of 724 people. The blood test, called DELFI (DNA evaluation of fragments for early interception) detects fragmentation changes among DNA from cancer cells shed into the bloodstream, known as cell-free DNA (cfDNA). In the most recent study, investigators used the DELFI technology on blood plasma samples obtained from 724 individuals in the U.S., the European Union (E.U.) and Hong Kong to detect hepatocellular cancer (HCC), a type of liver cancer. The researchers believe this is the first genome-wide fragmentation analysis independently validated in two high-risk populations and across different racial and ethnic groups with different causes associated with their liver cancers. Their findings were reported Nov. 18 in Cancer Discovery and at the American Association for Cancer Research Special Conference: Precision Prevention, Early Detection, and Interception of Cancer.

What if there was a magical robot that could cure any disease? Everyone knows there's no one machine that could do that. But maybe a swarm made up of tens of thousands of tiny autonomous micro-bots could? That's the premise laid out by proponents of nanobot medical technology. In science fiction, the big idea usually involves creating tiny metal robots via some sort of magic-adjacent miniaturization technology.

With 2021 behind us, we're going down memory lane to highlight biotech innovations that shaped the year--with impact that will likely reverberate for many years to come. Covid-19 dominated the news, but science didn't stand still. CRISPR spun off variations with breathtaking speed, expanding into a hefty toolbox packed with powerhouse gene editors far more efficient, reliable, and safer than their predecessors. CRISPRoff, for example, hijacks epigenetic processes to reversibly turn genes on and off--all without actually snipping or damaging the gene itself. Prime editing, the nip-tuck of DNA editing that only snips--rather than fully cutting--DNA received an upgrade to precisely edit up to 10,000 DNA letters in a variety of cells.

A new eye test that uses artificial intelligence AI to study retina scans can predict age-related macular degeneration (AMD) three years before symptoms start. The first part of the'pioneering' test, developed by researchers at University College London, is called DARC. DARC involves injecting dye into a person's bloodstream to illuminate'stressed' endothelial cells in the retina, so they appear bright white under a fluorescent camera. These'stressed' retinal cells could lead to abnormalities and later leaking blood vessels – causing AMD, which can severely compromise the central field of vision. The second part of the test uses an AI algorithm, trained to detect whether the highlighted white spots are around the macula – which indicates high AMD risk.