Clinical notes plus diagnostic imaging plus AI adds up to a 3D image of a patient's hip.

AI and hip preservation – Boston Children’s Answers

Clinical notes, diagnostic imaging, and AI add up to a 3D image of a patient's hip.
VirtualHip uses artificial intelligence to convert data from clinical notes and X-ray images into a complete view of a patient’s hip. (Illustration: David Chrisom, Boston Children’s)

Orthopedic surgeons and biomedical engineers are trained to approach hip pain in adolescents and young adults from two different angles. Surgeons typically look at conditions such as femoroacetabular impingement (FAI) and hip dysplasia from a clinical perspective. Engineers more often focus on the technology angle.

These two perspectives came together at Boston Children’s Hospital, resulting in a tool that could improve the diagnosis and clinical planning of hip patients worldwide.

Two decades of hip data made accessible through AI

VirtualHip is a software platform that uses artificial intelligence (AI) and 3D imaging to support the diagnosis and treatment of pediatric hip deformities. The idea was born out of conversations between Dr. Ata Kiapour, director of the Boston Children’s Musculoskeletal Informatics Group, and Dr. Young-Jo Kim, director of the Child and Adult Hip Preservation Program, which started in 2017.

“I started shadowing surgeons in the hip preservation team to understand how they worked and how technology could help,” says Kiapour. In doing so, he discovered an unmet clinical need for personalized diagnosis and treatment planning. He also uncovered a largely untapped source of data: images and clinical notes on more than 10,000 hip patients over the past 20 years.

Our goal is to provide detailed information so that surgeons can plan the best treatment for each patient.

The potential of such data is comparable to that of a doctor who has treated thousands of hip deformities and remembers them in detail, says Kiapour. “That doctor can look at a patient’s clinical profile and tell you, ‘We’ve treated patients this way and found that this approach works best.'”

But because historical patient data was not searchable, it was largely inaccessible. To unlock its potential, VirtualHip uses AI to process historical clinical records and match current patients with former patients with similar clinical profiles. These historical and anonymized patient records will provide important information when surgeons diagnose and plan treatments for their current patients. It is an aspect of VirtualHip. The other aspect involves full 3D image analysis.

The combined power of AI and 3D modeling

To diagnose hip deformities, orthopedic surgeons typically rely on a physical exam and diagnostic imaging. While some hip deformities are easily seen on MRIs or CT scans, many are not. Additionally, the impact of certain hip deformities often depends on the position of the hip. In the case of FAI, for example, a hip may only be painful when it is in motion and the bones are rubbing against each other.

The limitations of traditional diagnostic imaging also complicate treatment decisions. Could physiotherapy solve the problem, or does the patient need surgery? If there is an impingement, how much bone needs to be removed for the hip to move freely without pain? In the case of dysplasia, at what angle should the surgeon rotate the acetabulum (hip socket) so that the femoral head fits securely in the socket?

VirtualHip uses MRI or CT imaging to create a 3D model of the hip joint, then uses this model to automatically generate a full set of hip structural measurements. This data, combined with clinical examination information, provides a comprehensive view of the hip and areas of impingement or instability. Surgeons will be able to determine the location and severity of the deformity with a level of precision not possible today.

A 3D image of a hip joint with a color code indicating the degree of hip dysplasia.
A 3D image of hip dysplasia in VirtualHip shows how much of the femoral head is covered (and not covered) by the acetabulum.
A simulated hip impact image.
A 3D image of the hip impact in VirtualHip shows where friction occurs when the hip is in motion.

“Once you have a 3D model, you can have the software simulate the full range of motion,” Kiapour says. “It’s the intricate patterns that aren’t obvious on 2D images.”

Through detailed analysis of hip structure and range of motion, VirtualHip will combine the analysis with comparable historical patient data to provide insight into outcomes associated with various treatment approaches. Such detailed knowledge could help improve the accuracy of hip-sparing procedures, helping surgeons avoid overcorrection or undercorrection. “Our goal is to provide detailed information so surgeons can plan the best treatment for each patient,” says Kiapour.

A unique collaboration and a promising future

Kiapour points out that VirtualHip is not the first platform to analyze hip impingement, but it offers unique capabilities, including the automatic generation of detailed measurements without the need for a technician. It can also assess a patient’s risk of impingement or instability over a wide range of motion and process historical patient data to provide personalized analysis and treatment suggestions.

The ideas that inform the development and refinement of these and other capabilities have come from an ongoing collaboration between Boston Children’s orthopedic surgeons, radiologists and engineers. For five plus years, Kiapour and her team have worked closely with Dr. Kim and Dr. Eduardo Novais from the hip preservation team and Dr. Sarah Bixby from radiology.

We are fortunate to work in an environment where multidisciplinary collaboration is strongly encouraged and where clinicians are eager to participate in translational research.

“Clinicians are the end users of this platform, so it is necessary to keep them informed during development to ensure that the platform will meet their needs,” says Kiapour. Working together, the team has developed a technically sound platform that provides clinically relevant information in a clinician-friendly format. “We are fortunate to work in an environment where multidisciplinary collaboration is strongly encouraged and where clinicians are eager to participate in translational research. »

The combined team continues to develop and validate the prototype so that it can be used in a clinical setting. The ultimate goal is to make VirtualHip available for widespread use in hip treatment centers. The project could also herald a new use of data science in pediatric orthopedic care: using AI to make lessons from historical patient data accessible to surgeons when planning their patients’ care.

Learn more about the Hip Preservation Program for Children and Young Adults and the Musculoskeletal Informatics Group.

#hip #preservation #Boston #Childrens #Answers

Leave a Comment

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