Deep Diagnosis' core technology is about diagnosing pneumonia from the lung X-Ray images of patients using self laid convolutional neural network and transfer learning.
Deep Diagnosis' InceptionV3 based transfer learning model structure
The model we featured in, consists of 48 layers, having more than 20 Million parameters and has been trained on 6000 images.
An example likelihood map image generated by the Deep Learning Algorithms
The model takes a chest X-ray image as input and outputs the probability of each thoracic disease along with a likelihood map of pathologies.