Expanding datasets to improve our automated pneumoconiosis detection model
The Imaging and Computer Vision Group at CSIRO’s Data61 is working on the use of both real and synthetic pneumoconiosis radiographs to train a cascade machine learning model for the automated detection of pneumoconiosis.
Pneumoconiosis is an incurable respiratory disease affecting mine workers that are in contact with inhalable dust from coal, asbestos and silica. Detection of an early stage pneumoconiosis from chest X-rays is difficult and leads to high inter- and intra-reader variability, besides there is only a small number of ILO certified B-readers in Australia.
After developing a deep learning based automated diagnostic tool for pneumoconiosis detection from chest radiographs, with a very promising sensitivity of 93% and accuracy of 90%, we are looking at making our tool more robust and suitable for pre-screening of pneumoconiosis.
The overall architecture of the proposed cascade learning model.
Due to a small incidence of pneumoconiosis in Australia we were able to validate our tool only with a limited number of chest x-rays with pneumoconiosis.
Following being granted additional funding from the Coal Services Health and Safety Trust, we will now collect, nationally and internationally, a set of chest radiographs with different stages of disease and expand our current tool to become a multi-class grading system. Additionally, we will set up a pilot study where our tool will be trialled in a clinical setting alongside human readers.
Our highly skilled team of world class researchers and engineers is open to partnerships and collaborations for research, development, and commercialisation.
For more information contact: Dr Dadong Wang or Yulia Arzhaeva.