AVRA: Automatic Visual Ratings of Atrophy from MRI images using Recurrent Convolutional Neural Networks
This work addresses the need for reliable and efficient atrophy assessment in clinical neurology, offering a tool to reduce variability and training requirements, though it is incremental as it applies existing neural network methods to a specific medical imaging task.
The authors tackled the problem of automating visual ratings of brain atrophy from MRI images, which is typically done manually by trained neuroradiologists with imperfect agreement. They developed AVRA, a model based on recurrent convolutional neural networks trained on 2350 ratings, achieving substantial inter-rater agreement with Cohen's weighted kappa values of 0.74/0.72 for MTA, 0.62 for GCA-F, and 0.74 for PA.
Quantifying the degree of atrophy is done clinically by neuroradiologists following established visual rating scales. For these assessments to be reliable the rater requires substantial training and experience, and even then the rating agreement between two radiologists is not perfect. We have developed a model we call AVRA (Automatic Visual Ratings of Atrophy) based on machine learning methods and trained on 2350 visual ratings made by an experienced neuroradiologist. It provides fast and automatic ratings for Scheltens' scale of medial temporal atrophy (MTA), the frontal subscale of Pasquier's Global Cortical Atrophy (GCA-F) scale, and Koedam's scale of Posterior Atrophy (PA). We demonstrate substantial inter-rater agreement between AVRA's and a neuroradiologist ratings with Cohen's weighted kappa values of $κ_w$ = 0.74/0.72 (MTA left/right), $κ_w$ = 0.62 (GCA-F) and $κ_w$ = 0.74 (PA), with an inherent intra-rater agreement of $κ_w$ = 1. We conclude that automatic visual ratings of atrophy can potentially have great clinical and scientific value, and aim to present AVRA as a freely available toolbox.