AI-Based Image Quality Assessment in CT
Author(s): Lars Edenbrandt, Elin Tragardh, and Johannes Ulen
Medical imaging, especially computed tomography (CT), is becoming increasingly important in research studies and clinical trials and adequate image quality is essential for reliable results. The aim of this study was to develop an artificial intelligence (AI)-based method for quality assessment of CT studies, both regarding the parts of the body included (i.e. head, chest, abdomen, pelvis), and other image features (i.e. presence of hip prosthesis, intravenous contrast and oral contrast).
Approach: 1, 000 CT studies from eight different publicly available CT databases were retrospectively included. The full dataset was randomly divided into a training (n = 500), a validation/tuning (n = 250), and a testing set (n = 250). All studies were manually classified by an imaging specialist. A deep neural network network was then trained to directly classify the 7 different properties of the image.
Results: The classification results on the 250 test CT studies showed accuracy for the anatomical regions and presence of hip prosthesis in the interval 98.4% to 100.0%. The accuracy for intravenous contrast was 89.6% and for oral contrast 82.4%.
Conclusions: We have shown that it is feasible to develop an AI-based method to automatically perform a quality assessment regarding if correct body parts are included in CT scans, with a very high accuracy.