IoT Technologies for HealthCare. 6th EAI International Conference, HealthyIoT 2019, Braga, Portugal, December 4–6, 2019, Proceedings

Research Article

Assisting Radiologists in X-Ray Diagnostics

  • @INPROCEEDINGS{10.1007/978-3-030-42029-1_8,
        author={Cristian Avramescu and Bercean Bogdan and Stefan Iarca and Andrei Tenescu and Sebastian Fuicu},
        title={Assisting Radiologists in X-Ray Diagnostics},
        proceedings={IoT Technologies for HealthCare. 6th EAI International Conference, HealthyIoT 2019, Braga, Portugal, December 4--6, 2019, Proceedings},
        proceedings_a={HEALTHYIOT},
        year={2020},
        month={6},
        keywords={Radiology Deep Learning X-ray Segmentation Bone GAN},
        doi={10.1007/978-3-030-42029-1_8}
    }
    
  • Cristian Avramescu
    Bercean Bogdan
    Stefan Iarca
    Andrei Tenescu
    Sebastian Fuicu
    Year: 2020
    Assisting Radiologists in X-Ray Diagnostics
    HEALTHYIOT
    Springer
    DOI: 10.1007/978-3-030-42029-1_8
Cristian Avramescu1, Bercean Bogdan1, Stefan Iarca1,*, Andrei Tenescu1, Sebastian Fuicu1,*
  • 1: Politehnica University of Timisoara
*Contact email: stefan.iarca@student.upt.ro, sebastian.fuicu@cs.upt.ro

Abstract

Studies have shown that radiologists working together with Computer Aided Diagnostic software have increased accuracy. Automated screening software can be used to prioritize X-Rays coming in for diagnosis. We developed a suite of machine learning algorithms that aim to improve radiologist performance. It provides suggested diagnostics, a heatmap showing pathological areas and a bone subtracted version of the image which helps radiologists to identify fractures. We test different configurations for our diagnosis model, training it on both normal and enhanced images, using one or two branches. Our experiments show that adding enhanced inputs (lung segmented and bone subtracted versions of the input) increases the performance of our algorithm, which in turn increases the performance of the radiologist user. This shows that preprocessing the images before input increases model performance. More research is needed to find other preprocessing techniques, to refine existing ones, and to determine the optimal number and type of input X-Rays.