New AI-based method for tissue analysis improves understanding of disease pathology
By the LabMedica editorial team in Spanish
Updated on June 18, 2024
Scientists at Brown University (Providence, RI, USA) and the University of Michigan (Ann Arbor, MI, USA) have created an innovative computational technique to examine complex tissue data, potentially revolutionizing our understanding of diseases and their treatment. The method, known as integrative and reference-informed tissue segmentation (IRIS), uses machine learning and artificial intelligence to provide biomedical researchers with precise information about tissue development, disease pathology, and tumor structure. IRIS employs spatially resolved transcriptomics (SRT) data and incorporates single-cell RNA sequencing data as a reference. This approach allows for the simultaneous examination of multiple layers of tissue and accurately identifies different regions with exceptional computational speed and precision. Unlike traditional methods that provide data averaged across tissue samples, SRT offers a much more detailed view, locating thousands of specific points within a single tissue section.
Handling vast and complex data sets has always posed significant challenges, IRIS addresses them by using algorithms to examine the data, segmenting various functional domains, such as tumor areas, and shedding light on cellular interactions and progression dynamics. of the illness. Unlike existing methods, IRIS directly maps the cellular composition of tissues and delineates biologically meaningful spatial domains, improving understanding of the cellular activities that drive tissue functions. IRIS developers tested it on six SRT data sets, evaluating its effectiveness compared to other spatial domain analysis methods. As SRT technologies gain traction and become more widely used, the creators of IRIS anticipate that it will contribute to identifying new clinical intervention points or pharmaceutical targets, thereby improving personalized treatment strategies and ultimately improving health outcomes. from the patients.
Image: New AI-powered statistical method has the potential to improve tissue and disease research (photo courtesy of 123RF)
“IRIS’s computational approach pioneers a new avenue for biologists to delve into the intricate architecture of complex tissues, offering unparalleled opportunities to explore the dynamic processes that shape tissue structure during development and disease progression.” “said Xiang Zhou, professor of biostatistics at the University of Michigan School of Public Health. “By characterizing refined tissue structures and elucidating their alterations during pathological states, IRIS has the potential to reveal mechanistic insights crucial to understanding and combating various diseases.” The researchers’ findings were published in the journal Nature Methods on June 6, 2024.
Related links:
Brown University
University of Michigan
