Lung cancer screening using low-dose CT scans is the most effective form of imaging for identifying early-stage cancer. American College of Radiology (ACR) guidelines specify that the CTD Ivol for lung cancer screening in average-sized patients (170 cm, 70 kg, BMI of 24.1 kg/m2) should be ≤3 mGy, while National Comprehensive Cancer Care Network (NCCN) guidelines suggest an effective dose of ≤3 mSv for patients with BMI ≤30 kg/m2 and ≤5 mSv for patients with BMI >30 kg/m2. Even when following these guidelines, the cumulative effects of repeated radiation exposure may cause irreversible damage, especially for high-risk patients. Studies have found that patient size and orientation, CT scan protocols, and image reconstruction parameters can all affect patient dose exposure. While Iterative Reconstruction (IR) is commonly used to assist in lowering dose, over-application of IR does introduce image characteristics which compromise quality. New AI-powered image processing tools such as PixelShine® can consistently support imaging at dose levels as low as <1mSv, which is 75% lower than the 3 mSv recommendations set forth by the ACR. This can be achieved without sacrificing diagnostic image quality – creating a breakthrough for lung screening programs.
Pediatric radiology teams strive to do everything possible to minimize dose exposure to children during a CT exam. However, even when deploying the latest scanner technologies in combination with dose-optimized protocols there is a limit to the level that dose can be reduced before the images become too noisy. This becomes particularly challenging with very small children, pediatric cancer patients and children with high Body Mass Index (BMI). PixelShine is a new image processing tool that uses Deep Learning methods to significantly reduce CT image noise, which expands the definition of the lowest possible dose, and has the potential to transform the As Low As Reasonably Attainable (ALARA) paradigm in pediatric CT imaging.
What if you could improve the quality and efficiency of your existing CTs without incurring the high cost associated with purchasing a new scanner? Using Deep Learning Reconstruction (DLR) technology PixelShine can automatically enhance and harmonize the image quality of studies acquired by any CT scanner at the lowest possible dose –extending the life of older scanners and deferring costly and disruptive replacement projects. This is an exceptional opportunity as Covid-19 impacts the traditional revenue stream of any hospital.