qXR can detect abnormal findings on a chest X-ray. It can be used to separate normal from abnormal X-rays, for pre-read assistance, or as a radiology audit tool. qXR includes patented algorithms that can detect a total of 29 findings on the chest X-ray.
qXR is a chest X-ray screening tool built with deep learning. It classifies chest X-rays as normal or abnormal, identifies the abnormal findings, and highlights them on the X-ray.
The CE certified algorithms have been trained and tested using a growing database (over 3.6 Million) of X-rays from diverse sources.
qXR can detect upto 29 different findings on chest X-rays. Irrespective of CR/DR scans or PA/AP views, qXR can aid in detecting multiple findings with the lungs, pleura, heart, bones and the diaphragm.
The algorithms generate contours for lung and pleural abnormalities for quick and easy interpretation. Integrated with multiple PACS providers globally, qXR outputs are pushed back in under a minute for each scan.
qXR can generate free text reports that can be pushed back as Structured DICOM reports for immediate adoption in the workflow.
Currently, qXR uses globally compliant templates which can be tailored based on hospital requirements. Each scan analysed by qXR can also display a sidebar for all the findings presented in a dichotomized fashion.
qXR can detect and localize multiple findings in a Chest X-ray including detection of multiple findings with the lungs, pleura, heart, bones and the diaphragm.
With qXR v3.0, the analytical capabilites of the algorithms go a step further. Individual finding specific abnormalities detect and localise the lesion in the lungs and then quantify the affected lesion in comparison to the entire lung volume seen on the chest X-ray.
qXR can also analyse multiple scans from the same patient sequentially and create a progression report to detect changes in lesions over time.
We were impressed with the seamless set-up of the algorithm allowing us to test it with very little effort and get immediate results. Also we realized how easy the algorithms quantification methods make it to follow up with a patients’ improvement or deterioration.
CIO, Grupo Empresarial Angeles.
First published online on July 2018,the study has been updated to include validation of 10 different findings on the Qure 100k test set and an additional algorithm accuracy comparison against a 3 radiologist majority on 2000 scans.Read the paper on arXiv
Independent evaluation at Mass General Hospital, Boston, USA on 874 Chest X-rays for 4 different findings. qXR Algorithms were found to outperform Radiologists with different years of experience against Ground Truth set by Thoracic Radiologists and were able to quantify change over timeRead the paper on PLOS ONE
Drop us a line at firstname.lastname@example.org to know how we can set up qXR in your imaging workflow.