Chest radiography is one of the most performed radiological examinations. Engineered on deep neural networks, ChestGuard detects and localizes the presence of abnormal radiological signs on a frontal chest radiography.
What’s new: Engineered on deep neural networks, Topazium implemented a platform which detects and localizes the presence of abnormal radiological signs indicative of clinical conditions on a frontal chest radiography (chest X-ray).
Key insights: Our system accurately identifies and localizes key radiological findings in chest X-rays of patients faster than current clinical practice.
How it works: Chest X-ray images belonging to patients with a suspected clinical condition are uploaded into Topazium’s platform. It outputs the probability of abnormal radiological signs along with a heatmap localizing the suspected regions.
Results: The system can detect images with evidential radiological signs of disease, whilst correctly categorizing those deemed as “negative”. Accuracies are comparable to expert radiologists; however, it does it faster.
Why it matters: Chest X-ray is one of the most performed diagnostic examinations. Assisted chest radiograph interpretation could provide substantial benefit in many medical settings. At the level of practicing radiologists, it can reduce time to diagnosis as well as fatigue-based diagnostic error. It can also increase access to medical imaging expertise in areas of the world where access to skilled radiologists is limited.
HOW TO RUN THE EXPERIMENT
Access: available through a dedicated app and/or via an API.
Image upload: Upload your image by clicking the “Browse” button. The system can work with any type of image format (jpeg, tiff, png).
Running your experiment: Expected run time for each image: less than 45 seconds
Output: A similarity score that represents the probability (in %) of the image to be classified as normal or abnormal. In this last case, the system will mark with a heatmap the region in the uploaded image that it considers abnormal.