This week's articles in Diagnostic Reading include: advice for innovators in radiology; a study on radiologist performance with AIO windows; NPPs rarely render diagnostic imaging services; some radiologists don't participate in certification programs; and can AI fool a radiologist? Radiologists are in an exciting pioneering field. The possibilities for innovation within the field are near limitless. This article provides information and advice about product development, resources and processes for radiology entrepreneurs. How do you fight HAIs in NICU and ICU? I'd like to include your best practices in my upcoming blog.

We develop an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists. Our algorithm, CheXNet, is a 121-layer convolutional neural network trained on ChestX-ray14, currently the largest publicly available chest X-ray dataset, containing over 100,000 frontal-view X-ray images with 14 diseases. Four practicing academic radiologists annotate a test set, on which we compare the performance of CheXNet to that of radiologists. We find that CheXNet exceeds average radiologist performance on the F1 metric. We extend CheXNet to detect all 14 diseases in ChestX-ray14 and achieve state of the art results on all 14 diseases.