Investigators of the Vall d’Hebron Institute of Oncology’s (VHIO) Radiomics Group, led by Raquel Perez-Lopez, have developed SALSA (System for Automatic Liver tumor Segmentation And detection), a fully automated deep learning-driven tool for the precise and completely automated detection and monitoring of liver tumors (hepatocellular carcinoma). Results of this work have been published as an open access article in Cell Reports Medicine.

Researchers have created a comprehensive spatiotemporal atlas of the developing mouse lung, providing unprecedented insights into the molecular and cellular processes that shape this vital organ. The study, published in Science Bulletin, offers a detailed map of gene expression across different stages of lung development, from embryonic day 12.5 (E12.5) to postnatal day 0 (P0).

A new study led by students Adi Shapira and Hodaya Zadok, under the supervision of Prof. Tsachi Ein Dor and Prof. Anat Shoshani of the Baruch Ivcher School of Psychology at Reichman University, explores how the loss of a parent in childhood impacts biological and emotional mechanisms. These changes pave the way for resilience and personal growth through the regulation of the body systems involved in attachment and exploration. Focusing on the long-term effects of childhood parental loss, the study highlights the internal forces that enable people to grow from trauma. It demonstrates that while losing a parent is a painful and life-altering experience, it also presents an opportunity for profound changes in brain structures and emotional mechanisms that can lead to a process of recovery, social connection, and creativity.

A new telemedicine service for personalised breast cancer prevention has launched at preventcancer.co.uk. It allows women aged 30 to 75 across the UK to understand their risk of developing breast cancer and take early action years before NHS screening begins.

As lithium-ion batteries (LIBs) continue to power electric vehicles and energy storage systems, their long-term health remains a critical challenge. A groundbreaking new method combines deep learning with physical modeling to deliver rapid, accurate degradation diagnosis at the electrode level. This innovative approach requires only 11 data points from a charging cycle, achieving reliable predictions in just 2.5 minutes. By simplifying the data needed and eliminating the need for specialized equipment, this technique offers a faster, more accessible solution to battery health monitoring—paving the way for safer, more efficient battery management in large-scale applications.