Imagen AI: Democratizing Access To World-Class Imaging

Imagen’s proprietary FDA-cleared AI detection and diagnosis software is helping us to provide world-class image interpretation services directly in primary care settings.

Contact Sales

Real-World Impact

At Imagen, AI is not an academic exercise. Our software is being used in real practices today, helping real patients. Imagen is at the forefront of the AI revolution in healthcare, putting the latest deep learning techniques into actual clinical use.

Better Outcomes
Patient Experience
Reduced Costs
Clinician Experience

Imagen’s FDA-Cleared AI Software

  • OsteoDetect

    OsteoDetect is the first ever FDA-cleared software device for Radiological Computer Aided Diagnosis/Detection (CAD). It uses AI to help detect and localize distal radius fractures – the most commonly misdiagnosed musculoskeletal injury. In a clinical study, the average clinician experienced a relative reduction in misinterpretation rate of 47% when aided by the software.

  • FractureDetect

    Missed fractures on X-rays are the most common diagnostic errors within emergency departments. FractureDetect helps eliminate these errors by detecting hard-to-spot fractures  throughout the musculoskeletal system and across multiple X-ray views. Clinicians in a clinical study showed a 45% relative reduction in missed fractures when assisted by FractureDetect.

  • ChestCAD

    Chest-CAD detects, categorizes, and localizes suspicious regions on chest X-rays, and was shown in a clinical study to reduce diagnostic errors by 40%. The underlying AI model was trained on a massive proprietary data set, with labels comprehensively encompassing all abnormalities that can be screened for on a chest X-ray – making this model the first-ever general abnormality detector for radiology.

Imagen’s proprietary, FDA-cleared software helps physicians detect and diagnose findings more comprehensively and document findings more automatically.

Placing Patient Safety First

At Imagen, all of our technology development is done in the service of our guiding star: improving patient outcomes and placing patient needs first. To that end, intellectual integrity and scientific rigor are at the core of everything we do. We engage actively with regulators to make sure our products are safe and effective. Imagen received the first-ever FDA clearance for Computer-Aided Detection and Diagnosis (CADe/x) software for radiology, supported by extensive clinical data.

Our FDA-cleared AI products have been validated through large-scale clinical trials. In fact, we’ve gone far above and beyond what’s required: our trials are among the largest of their kind.

Read about some of our groundbreaking, peer-reviewed research:

A Multi-Disciplinary Philosophy

Imagen is uniquely positioned as a vertically-integrated organization that both develops AI software in-house and operates it through our clinical services. We directly control the deployment and monitoring of our models, and work closely with the clinicians who are actually using them. These tight feedback loops enable us to continuously improve our machine learning techniques and observe how they work in the real world.

Our AI is developed by an interdisciplinary team including machine learning experts, clinical researchers, and physicians. We work with a wide array of healthcare practitioners, and they are intimately involved in every aspect of our development process.

Imagen develops AI software in-house

Scaling The World’s Best Clinical Expertise

Our AI models are trained to incorporate the human expertise of some of the world’s best diagnosticians. We’ve partnered with top medical institutions, including several leading research hospitals, to design our devices. Through these partnerships, we’ve curated some of the industry’s largest and highest-quality medical imaging datasets.

Want to help us apply state-of-the-art machine learning techniques to make high-quality healthcare accessible to everyone? Join us.

Open Positions

In this work, we tested whether Imagen’s FDA cleared software for detecting fractures (FractureDetect) in musculoskeletal radiographs would improve clinicians’ accuracy at diagnosing fractures. Clinicians were more accurate at diagnosing fractures when assisted by the deep learning system (p < 0.01). Clinicians with limited training in musculoskeletal image interpretation had a 61% relative reduction in missed fractures for X-rays from Medicare-aged patients when assisted by the deep learning system. Reducing the number of missed fractures may allow for improved patient care and increased patient mobility.

In this work, we present a 46 year-old male with chest pain referred for chest X-ray, and initial interpretation reported no abnormality within the patient's lungs. Retrospective analysis of the initial chest radiograph was performed with Chest-CAD, Imagen’s FDA cleared software that analyzes chest radiograph studies using artificial intelligence. The software highlighted a region of the left lung as suspicious. Additional information provided by artificial intelligence software holds promise to prevent missed detection of lung cancer on chest radiographs.

In this work, we developed a deep-learning system for detecting fractures across the musculoskeletal system. In a multi-site study, the deep-learning system accurately identified fractures throughout the adult musculoskeletal system. The results were used, in part, to support FDA clearance of Imagen’s software (FractureDetect) to assist clinicians in detecting fractures for a selected subset of the anatomic regions reported in this paper.

In this work, we developed a deep neural network to detect and localize fractures in wrist radiographs. We then ran a controlled experiment with clinicians to evaluate their ability to detect fractures with and without the assistance of the deep learning model. The average clinician had a 47% relative reduction in misinterpretation rate assisted by the deep learning model. The significant improvements in diagnostic accuracy show that deep learning methods can substantially enhance patient care.