By accelerating the first stage of spatial omics data analysis, a new artificial intelligence model developed at Children’s Hospital of Philadelphia provides detailed information on how a disease develops and progresses at the cellular level, and can advance accurate diagnoses and targeted treatments.
CHOP’s open source AI tool is now available in a public repository for non-commercial use, the hospital says.
WHY IT IS IMPORTANT
Pediatric researchers have developed a deep learning-enhanced biomedical imaging model, called CelloType, to accelerate the identification and classification of cells in tissue images. They then tested biomedical imaging AI across a wide range of complex diseases, including cancer and chronic kidney disease.
CelloType is programmed to improve the accuracy of cell detection, segmentation and classification, CHOP said, and is effective in handling large-scale tasks such as natural language processing and image analysis.
Although CHOP’s model requires training for segmentation and classification tasks, it can learn patterns and make predictions or classifications faster than previous approaches.
The researchers compared CelloType’s performance to that of models that segment multiplexed tissue images, including Mesmer and Cellpose2, and detailed the results of the National Institutes of Cancer-funded research in Natural methods.
“Unlike the traditional two-step approach of segmentation followed by classification, CelloType adopts a multi-task learning strategy that integrates these tasks, simultaneously improving the performance of both,” they said in their report. report.
Some cell types are either large or irregularly shaped, presenting challenges for conventional segmentation methods. CelloType, which leverages transformer-based deep learning and automates high-dimensional data analysis, better captures complex relationships and context in tissue samples, they said.
CelloType uses AI to accurately describe objects in an image.
Kai Tan, lead author of the study and professor in CHOP’s Department of Pediatrics, said in a statement that “the approach could redefine how we understand complex tissues at the cellular level, paving the way for transformative advances in the field of health care”.
THE BIGGEST TREND
According to CHOP, there is a pressing need in spatial omics – a field that combines genomics, transcriptomics or proteomics with spatial information to map the location of different molecules in cells of complex tissues – for more sophisticated computational tools to data analysis.
Recent advances have led to the analysis of intact tissues at the cellular level, providing unprecedented insights into the link between cellular architecture and functionality of various tissues and organs.
Using AI to improve understanding of biomedical images can not only help clinicians treat patients, but can also improve patient access to advanced imaging and even predict diseases like cancer. Health systems are therefore adopting AI imaging tools.
As Norwegian and Danish researchers use mammogram images in national breast cancer screening programs to help predict diagnoses, Stamford Health’s Heart & Vascular Institute announced in October that its patients would automatically receive a screening for coronary heart disease during any non-contrast chest scan. and when their future risk indicators are high.
“This tool improves our ability to detect early signs of cardiovascular disease and ensures that patients receive the follow-up care they need to avoid serious health problems,” said Dr. David Hsi, chief of cardiology and co-director of the institute, in a press release. statement.
A chief medical officer and professor of pediatrics said he believes that with AI and machine learning, healthcare providers can turn the tide for patients fighting complex illnesses.
“Personalized genetic and epigenetic information can help tailor many drugs to specific patients and specific diseases. All of these omics involve enormous amounts of data that information technology can now analyze in exquisite detail and which can be functionally evaluated using artificial intelligence and machine learning. algorithms,” said Dr. William Hay Jr., chief medical officer at Astarte Medical, a precision medicine company. Healthcare IT News last year.
ON THE FILE
“We are just beginning to unlock the potential of this technology,” Tan said in a statement.
Andrea Fox is the editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.