AI Case Study
Capitol Health improves accuracy of diagnosis from scans, X-rays etc using deep learning
Capitol Health, a diagnostic imaging services provider, has partnered with Enlitic to develop a deep learning system to assess the condition of patient and thus improve outcomes. Capitol Health is building a database mapping the entire human body. Some of the projects include automating detection of lung cancer nodules from chest CT images, extremity (e.g. wrist) bone fractures etc. Diagnosis is upto 50% more accurate than trained radiologists.
Healthcare Providers And Services
When a patient arrives, there are multiple sources of information available which are currently not integrated, by integrating all sources and analyzing data quicker and comparing with historical data, patient condition and severity can be predicted leading to better care.
Enlitic uses data from patient’s history, symptoms, lab tests, and medical images to detect condition accurately.
How Enlitic's technology is used in radiology:
Lung cancer: Kills 80-90 percent of all patients diagnosed in late-stages; this is one of the hardest cancers to detect in medical images. If caught early, survival is nearly 10 times more likely.
For the first time ever, Enlitic adapted deep learning to automatically detect lung cancer nodules in chest CT images 50 percent more accurately than an expert panel of thoracic radiologists. The reduction of false negatives and the ability to detect early-stage nodules saves lives. The simultaneous reduction of false positives leads to fewer unnecessary and often costly biopsies, and less patient anxiety.
Enlitic benchmarked its performance against the publicly available, NIH-funded Lung Image Database Consortium data set, demonstrating its commitment to transparency.
Bone fractures: Enlitic has also achieved recent breakthroughs in detection of extremity (e.g. wrist) bone fractures, which are very common yet extremely difficult for radiologists to reliably detect. Errors can lead to improper bone healing, resulting in a lifetime of alignment issues.
These fractures are often represented only by 4x4 pixels in a 4,000x4,000-pixel X-ray image, pushing the limits of computer vision technology.
In detection of fractures, Enlitic achieved 0.97 AUC (the most common measure of predictive modeling accuracy), more than 3 times better than the 0.85 AUC achieved by leading radiologists and many times better than the 0.71 AUC achieved by traditional computer vision approaches.
Enlitic was able to support analysis of thousands of image studies in a fraction of the time needed for a human to analyze a single study.
R And D
Capitol Health is a leading provider of diagnostic imaging services to the Australian healthcare market.
The company claims it can:
* Detect lung cancer nodules in chest CT images 50% more accurately than thoracic radiologists facilitating precise early stage detection
* In fracture detection, Enlitic achieved 0.97 AUC, more than 3 times better than the 0.85 AUC achieved by leading radiologists
All radiology modalities (Ultrasound, CT, MRI, PET, X-Ray) and EHR