AI tool can analyse complex cancer images rapidly – offering potential to personalise treatment
Peer-Reviewed Publication
This month, we’re focusing on artificial intelligence (AI), a topic that continues to capture attention everywhere. Here, you’ll find the latest research news, insights, and discoveries shaping how AI is being developed and used across the world.
Updates every hour. Last Updated: 9-May-2026 15:15 ET (9-May-2026 19:15 GMT/UTC)
Complex digital images of tissue samples that can take an experienced pathologist up to 20 minutes to annotate could be analysed in just one minute using a new AI tool developed by researchers at the University of Cambridge. SMMILe, a machine learning algorithm, is able not only to correctly detect the presence of cancer cells on slides taken from biopsies and surgical sections, but it can predict where the tumour lesions are located and even the proportion of regions with different levels of aggressiveness.
Low-dimensional (LD) halide perovskites have attracted considerable attention due to their distinctive structures and exceptional optoelectronic properties, including high absorption coefficients, extended charge carrier diffusion lengths, suppressed non-radiative recombination rates, and intense photoluminescence. A key advantage of LD perovskites is the tunability of their optical and electronic properties through the precise optimization of their structural arrangements and dimensionality. This review systematically examines recent progress in the synthesis and optoelectronic characterizations of LD perovskites, focusing on their structural, optical, and photophysical properties that underpin their versatility in diverse applications. The review further summarizes advancements in LD perovskite-based devices, including resistive memory, artificial synapses, photodetectors, light-emitting diodes, and solar cells. Finally, the challenges associated with stability, scalability, and integration, as well as future prospects, are discussed, emphasizing the potential of LD perovskites to drive breakthroughs in device efficiency and industrial applicability.
Researchers from the SNI network have discovered a novel way to fuse lipid vesicles at neutral pH. By harnessing a fragment of the diphtheria toxin, the team achieved vesicle membrane fusion without the need for pre-treatment or harsh conditions. Their work, recently published in Communications Chemistry, opens the door to new applications in lab-on-a-chip technologies, biosensors, and artificial cell prototypes.
Researchers have developed a graph-based expert system that improves the accuracy and prediction stability of automated bank reconciliation. By modelling historical transactional data as a network graph, the system can learn complex one-to-many matching scenarios that existing tools often fail to predict correctly. The findings point to more reliable automation for high-risk domains such as finance and accounting.