Researchers Create Growth Chart from AI-Based Tool to Measure Muscle Mass

Researchers have developed a growth chart to track muscle mass in growing children, according to research conducted by investigators from Brigham and Women’s Hospital. The researchers created an artificial intelligence (AI)-based tool that can track indicators of muscle mass on routine MRIs. The tool was reported to offer a standardized, accurate, and reliable option for children that struggle with low muscle mass.

Image credit: Kamon_saejueng | stock.adobe.com

The press release noted that individuals with conditions that generate low lean muscle mass are at risk for early mortality or other diseases that can interfere with their quality of life. Alternatively, individuals with lean muscle mass have been linked to overall health and longevity. In the past, body mass index (BMI) was the default form to measure lean muscle mass, with few to no additional methods. However, researchers noted that there was a fault in using BMI because it does not define the amount of weight that is muscle. Scientists used other methods to measure the thickness of the muscle, but they were not practical.

“Pediatric cancer patients often struggle with low muscle mass, but there is no standard way to measure this. We were motivated to use artificial intelligence to measure temporalis muscle thickness and create a standardized reference,” said Ben Kann, MD, a radiation oncologist in the Brigham’s Department of Radiation Oncology and Mass General Brigham's Artificial Intelligence in Medicine Program, senior author, in a press release. “Our methodology produced a growth chart that we can use to track muscle thickness within developing children quickly and in real-time. Through this, we can determine whether they are growing within an ideal range.”

To create the AI tool, the researchers studied MRI scans of pediatric patients that were treated for brain tumors at Boston Children’s Hospital/Dana-Farber Cancer Institute, in collaboration with Boston Children’s Radiology Department. The researchers then analyzed 23,852 individuals that were aged 4 to 35 years that had normal, healthy brain MRI scans. This helped the investigators calculate the temporalis muscle thickness (iTMT) to develop a normal-reference growth chart for the muscle.

The press release noted that prior to calculating the iTMT, the researchers were able to create sex-specific iTMT of normal growth charts with ranges and percentiles that could be accurate for a variety of individuals.

“The idea is that these growth charts can be used to determine if a patient’s muscle mass is within a normal range, in a similar way that height and weight growth charts are typically used in the doctor’s office,” said Kann, in a press release.

The press release noted that limitations included the scan quality and how the suboptimal resolution can affect the measurements and the interpretation of results. There is also a limited amount of MRI data sets outside of the United States and Europe, making an accurate global picture difficult.

However, the study authors noted that they hope the growth chart will allow health care providers to quickly aid individuals with signs of muscle loss.

“In the future, we may want to explore if the utility of iTMT will be high enough to justify getting MRIs on a regular basis for more patients,” said Kann, in a press release. “We plan to improve model performance by training it on more challenging and variable cases. Future applications of iTMT could allow us to track and predict morbidity, as well as reveal critical physiologic states in patients that require intervention.”

Reference

AI algorithm developed to measure muscle development, provide growth chart for children. EurekAlert!. News release. November 9, 2023. Accessed November 17, 2023. https://www.eurekalert.org/news-releases/1007222.