HOPPR 扩展医学影像 AI 产品线，推出全身肌骨 X 射线叙述模型

HOPPR® FS MSK Whole-Body Narrative Model generates draft report findings from up to three X-ray views per study, with customization and integration available through HOPPR Forward Deployed Services

• Vision-language foundation model that drafts the findings section of a musculoskeletal (MSK) radiograph report from up to three views per study
• Trained across the musculoskeletal system, including the spine, thorax and chest wall, upper extremity, and pelvis and lower extremity
• Available through HOPPR® Forward Deployed Services, which customizes and integrates the model for organizations' data and workflows
• Beta release for evaluation; not FDA cleared and not intended for diagnostic use

, /PRNewswire/ -- HOPPR, a company transforming how AI is developed for medical imaging, today announced the beta release of the HOPPR® FS MSK Whole-Body Narrative Model, a vision-language foundation model that generates draft findings text for musculoskeletal (MSK) radiographs. The model processes up to three views per study and provides a software component for developers building radiology reporting and image-based workflow applications. Through HOPPR® Forward Deployed Services (FDS), HOPPR works with organizations to evaluate, customize, and integrate the model within their workflow.

MSK radiography spans the body, from the cervical spine to the toes. The FS MSK Model was trained across the musculoskeletal system – including the spine, thorax and chest wall, upper extremity, and pelvis and lower extremity – giving developers one starting point for report drafting across anatomical regions.

HOPPR trained the model on approximately 674,000 proprietary outpatient MSK studies, with the dataset balanced across body parts. The model focuses on describing abnormalities rather than normal anatomy. HOPPR evaluates the model against 26 MSK finding categories, including fracture, degenerative joint and spine changes, alignment, soft tissue, bone quality and lesions, and hardware.

"Organizations shouldn't need a separate AI model for every bone and joint. Musculoskeletal imaging spans the whole body, and a single model trained across it gives developers a far stronger foundation to build on," said Khan Siddiqui, MD, co-founder and CEO of HOPPR. "The FS MSK Model offers one whole-body model for generating draft findings text, and our Forward Deployed Services team works with each customer to adapt it to their data and workflows."

The FDS team brings together HOPPR machine learning scientists, software engineers, data scientists, and clinical experts who work alongside each organization. For the FS MSK Model, that work includes customizing the model with the customer's own data, designing the labeling workflows that support it, integrating the model into existing systems, and supporting validation testing in the customer's environment. HOPPR's secure infrastructure is HITRUST e1 certified and SOC 2 Type II attested, and operates under a Quality Management System.

The model name, "FS," honors Dr. Florence Ada Stoney (1870-1932), widely credited as the first woman radiologist in the United Kingdom. Stoney established an X-ray department at the Elizabeth Garrett Anderson Hospital for Women in 1902 and later led the X-ray department at Fulham Military Hospital during World War I.

"Dr. Stoney practiced radiology when the field was young and few doors were open to women," said Roger Boodoo, MD, Medical Director of AI at HOPPR. "Naming this model in her honor recognizes the people who helped build the discipline our work depends on."

The FS MSK Whole-Body Narrative Model is a software component, not a medical device.

To learn more about the FS MSK Whole-Body Narrative Model and Forward Deployed Services, click here.

About HOPPR
HOPPR, founded in 2019, brings together clinical radiology, AI development, and healthcare commercialization expertise to advance transparent and scalable AI for medical imaging. The HOPPR® AI Foundry is a secure development platform designed for building, validating, and hosting AI models for medical imaging, with curated datasets, traceable development workflows, and secure infrastructure aligned with SOC 2 Type II, HITRUST e1, HIPAA, and quality management and regulatory standards. Learn more at hoppr.ai.

Beta Software Disclaimer: This software is provided for evaluation and feedback purposes only. It is a pre-release product and should not be used in products, services, or workflows intended for commercial distribution or operational deployment. HOPPR provides foundation models as software components, not as medical devices. This model is not cleared or approved by the U.S. FDA and is not intended for diagnostic use. Partners are responsible for validating model performance in the final product and obtaining any applicable regulatory marketing authorizations.

SOURCE HOPPR