New tissue atlas aims to help AI understand cancer
How cells are arranged within tissue can reveal as much about disease as the cells themselves. When doctors examine a cancer tumor, for example, they don't just look at which cells are present; they also want to know how those cells are arranged and how they interact with each other. That's because the way cancer cells interact with neighboring immune cells can offer important clues about how a…
A groundbreaking spatial proteomics reference atlas named spora has been created to help artificial intelligence better understand cancer. Spatial proteomics technology captures the arrangement and interaction of cells within tissue by measuring dozens of proteins while preserving their locations. This data reveals crucial information about disease progression and treatment response, but combining it is challenging due to differences in equipment, proteins, and data storage methods.
To address this issue, a collaborative team led by Charlotte Bunne at EPFL developed spora, the world's largest freely available collection of spatial proteomics tissue images and medical data. The atlas includes 13,546 multiplex images from 5,477 patients, covering 14 tissue origins and five imaging technologies, along with paired histopathology images where available.
Creating spora required two years of work from scientists and biomedical experts, as they had to organize thousands of images, standardize protein annotations, match medical information, and identify individual cells. The collection retains links to original studies and their annotations, preserving differences between datasets to help researchers select appropriate data for their questions.
In addition to the atlas, spora provides tools for accessing and analyzing data, developing AI models, and evaluating their performance across different studies. This is essential for examining differences in model performance caused by variations in patients, laboratories, or measurement technologies. While spora currently focuses on cancer research, the team aims to expand it to include more tissues, diseases, and imaging technologies, ultimately translating insights into better predictions of patient disease progression and treatment outcomes.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
