AI-Driven Growth Charts for Muscle Mass

Researchers have created an AI-powered development chart from the biggest pediatric MRI dataset to trace muscle mass in youngsters, enabling extra correct health assessments and potential early intervention for muscle loss.

An evaluation of MRI scans led by Brigham researchers utilizing synthetic intelligence resulted within the manufacturing of a reference development normal and a quick, reproducible technique to measure indicators of lean muscle mass in creating youngsters.

Leveraging synthetic intelligence and the biggest pediatric mind MRI dataset to this point, researchers have now developed a development chart for monitoring muscle mass in rising youngsters. The new examine led by investigators from Brigham and Women’s Hospital, a founding member of the Mass General Brigham healthcare system, discovered that their synthetic intelligence-based device is the primary to supply a standardized, correct, and dependable technique to assess and observe indicators of muscle mass on routine MRI. Their outcomes have been revealed right now (November 9) within the journal Nature Communications.

Introduction to Muscle Mass Tracking

“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,” mentioned senior creator Ben Kann, MD, a radiation oncologist within the Brigham’s Department of Radiation Oncology and Mass General Brigham’s Artificial Intelligence in Medicine Program.

“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.”

The Importance of Lean Muscle Mass

Lean muscle mass in people has been linked to high quality of life, each day purposeful standing, and is an indicator of general health and longevity. Individuals with circumstances corresponding to sarcopenia or low lean muscle mass are liable to dying earlier, or in any other case being susceptible to numerous ailments that may have an effect on their high quality of life.

Historically, there has not been a widespread or sensible technique to observe lean muscle mass, with body mass index (BMI) serving as a default type of measurement. The weak spot in utilizing BMI is that whereas it considers weight, it doesn’t point out how a lot of that weight is muscle.

For a long time, scientists have recognized that the thickness of the temporalis muscle outdoors the cranium is related to lean muscle mass within the body. However, the thickness of this muscle has been troublesome to measure in real-time within the clinic and there was no technique to diagnose regular from irregular thickness. Traditional strategies have usually concerned guide measurements, however these practices are time-consuming and will not be standardized.

Innovative Research and Findings

To deal with this, the analysis staff utilized their deep studying pipeline to MRI scans of sufferers with pediatric mind tumors handled at Boston Children’s Hospital/Dana-Farber Cancer Institute in collaboration with Boston Children’s Radiology Department. The staff analyzed 23,852 regular healthy mind MRIs from people aged 4 by means of 35 to calculate temporalis muscle thickness (iTMT) and develop normal-reference development charts for the muscle. MRI outcomes have been aggregated to create sex-specific iTMT regular development charts with percentiles and ranges. They discovered that iTMT is correct for a variety of sufferers and is corresponding to the evaluation of educated human consultants.

Clinical Applications

“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,” mentioned Kann.

In essence, the brand new technique might be used to evaluate sufferers who’re already receiving routine mind MRIs that observe medical circumstances corresponding to pediatric cancers and neurodegenerative ailments. The staff hopes that the power to watch the temporalis muscle immediately and quantitatively will allow clinicians to rapidly intervene for sufferers who reveal indicators of muscle loss, and thus stop the damaging results of sarcopenia and low muscle mass.

One of the constraints lies within the algorithm’s reliance on scan high quality, and the way a suboptimal decision can have an effect on measurements and the interpretation of outcomes. Another disadvantage is the restricted quantity of MRI datasets accessible outdoors of the United States and Europe that may give an correct world image.

Future Directions

“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,” mentioned Kann. “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: “Automated Temporalis Muscle Quantification and Growth Charts for Children Through Adulthood” by Zapaishchykova, A et al., 9 November 2023, Nature Communications.
DOI: 10.1038/s41467-023-42501-1

Authorship: Brigham-affiliated authors embody Anna Zapaishchykova, Kevin X. Liu, Anurag Saraf, Zezhong Ye, Yashwanth Ravipati, Arnav Jain, Julia Huang, Hasaan Hayat, Jirapat Likitlersuang, Sridhar Vajapeyam, Rishi B. Chopra, Raymond H. Mak, Tabitha M. Cooney, Daphne A. Haas-Kogan, Tina Y. Poussaint, and Hugo J.W.L. Aerts. Additional authors embody Paul Catalano, Viviana Benitez, Ariana M. Familiar, Ali Nabavidazeh, Adam C. Resnick, Sabine Mueller,

Funding: The authors acknowledge monetary help from NIH (HA: NIH-USA U24CA194354, NIH-USA U01CA190234, NIH-USA U01CA209414, and NIH-USA R35CA22052; BHK: NIH-USA Okay08DE030216-01), and the European Union – European Research Council (HA: 866504). KL is funded by the National Institutes of Health Loan Repayment Program L40 CA264321.

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button