CABI has launched a new course, Primer on Evidence Synthesis, as part of its free suite of learning resources alongside the Evidence Synthesis Skills Framework. This short course allows people to quickly gain an understanding of the complex world of evidence synthesis, and provides a strong introduction to key terminology and important principles. As well as addressing what evidence synthesis is, the course also explores why it matters for decision making in the agricultural sector.

A new study shows that AI is revolutionizing colon cancer diagnosis, making detection easier, faster, less invasive, and more accurate. The research, based on a meta-analysis of studies published between 2020 and 2024, highlights how AI has been applied to colon cancer screening and analysis. Findings reveal significant gains in diagnostic precision, particularly in polyp detection during colonoscopies and in histopathological assessments, where deep learning models frequently outperform traditional methods.

Recently, addressing the inherent timescale mismatch challenge between fast and slow responses in optoelectronic sensors, a collaborative team from Suzhou Institute of Nano-Tech and Nano-Bionics (SINANO), Chinese Academy of Sciences (Yukun ZHAO, Shulong LU, Min JIANG), Fudan University (Lifeng BIAN), and Suzhou University of Science and Technology (Jianya ZHANG) has proposed an innovative monolithic integration scheme. By combining surface defect introduction and local contact interface design with a gallium nitride (GaN) nanowire lift-off technique that eliminates the interference from the underlying silicon substrate, the team integrates fast and slow responses into a single device. This results in a transparent bifunctional device capable of self-driven detection and neural synaptic integration, with omnidirectional (360°) detection capability. As a photodetector, the device demonstrates the millisecond-level response speeds, while it exhibits the second- to minute-level relaxation time as an artificial synapse, achieving an over 1000-fold contrast in response dynamics. The device has been validated in the intelligent perception systems for humanoid robots successfully, advancing the development of multifunctional monolithic optoelectronic devices and providing a solid foundation for further research in related fields.

 

The work entitled "A dual-mode transparent device for 360° quasi-omnidirectional self-driven photodetection and efficient ultralow-power neuromorphic computing" was published in Light: Science & Applications.

- Developed the world's first multimodal brain signal-based model capable of learning without simultaneous EEG and fNIRS measurements. - Self-learning from data of hundreds of individuals... Introducing a new era of multimodal brain signal analysis AI by achieving high accuracy with minimal labels.