A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information in mammograms and pinpoints with high accuracy the individual risk of metastasis in the armpit. A newly completed study shows that the model indicates that just over 40 per cent of today’s axillary surgery procedures could be avoided.

Lower back pain is the most common musculoskeletal issue in the U.S. and a top cause of global disability. To tackle this, researchers have developed a groundbreaking AI-powered system that automates patient-specific lumbar spine modeling. By merging deep learning with biomechanical simulation, the new method slashes model prep time by nearly 98% – from more than 24 hours to just 30 minutes – while preserving clinical accuracy. This innovation enables faster, more consistent diagnoses and personalized treatment planning.

A study published in the Journal of Bioresources and Bioproducts explores hydrothermal aging of Moso bamboo (Phyllostachys edulis). Researchers subjected bamboo to controlled temperature–humidity cycles and analyzed its physical, chemical, and mechanical changes. Findings show that moisture-driven degradation causes dimensional instability, discoloration, and strength loss. Using Random Forest modeling, the team achieved highly accurate predictions of bamboo’s service life. The work provides new data-driven approaches for managing bamboo quality during storage and supports its role as a sustainable alternative to plastics.

Inspired by insect hearing, we present a compact, chip-based system for superior acoustic perception. A dual-soliton microcomb drives over 100 parallel opto-acousitc sensors, achieving extreme sensitivity, pinpointing sound sources within centimeters, and identifying targets in real-time. This all-in-one photonic microsystem providing biomimetic robots with advanced, out-of-lab hearing for next-generation acoustic intelligence and scalable sensor networks.