Tornar a resultats destacats 2024

AI Spots Cancer cells, Stem cells and Viral Infected cells at Nanoscale Precision

Cosma, Maria Pia (CRG)

Life & Medical Sciences

We have developed an artificial intelligence AI algorithm called AINU – AI of the nucleus- which can differentiate stem cells and cancer cells from normal cells, as well as detect the very early stages of viral infection inside cells. The images are obtained with a special microscopy technique called STORM, which creates a picture that captures many finer details than what regular microscopes can see. The high-definition snapshots reveal structures at nanoscale resolution. AINU detects and analyses these tiny chromatin structures inside cells at the molecular level. We trained the model by feeding it with nanoscale-resolution images of the nucleus of many different types of cells in different states. The model learned to recognize specific patterns in cells by analysing how nuclear components are distributed and arranged in three-dimensional space. Our method in the future might pave the way for improved diagnostic techniques and new monitoring strategies for disease.

Many biological features driving cellular heterogeneity are still widely unknown due to a lack of technical capabilities. We have developed an artificial intelligence tool called AINU that addresses this issue. AINU can identify nuclear features characteristic of different cellular states, pinpointing the key aspects that need further study. In the image, nuclear features are highlighted using a magnifying glass, symbolizing AINU. In the background, a network connects different cells, illustrating how AINU, a Convolutional Neural Network, identifies and analyzes the differences between them. Credit for the drawing: Carlotta Viana, PhD student at CRG, Barcelona


REFERÈNCIA

Carnevali D, Zhong LM, González-Almela E, Viana C, Rotkevich M, Wang AP, Franco-Barranco D, Gonzalez-Marfil A, Neguembor MV, Castells-Garcia A, Arganda-Carreras I & Cosma MP 2024, 'A deep learning method that identifies cellular heterogeneity using nanoscale nuclear features', Nature machine intelligence, 6 - 9.