Lightweight Combinational Machine Learning Algorithm for Sorting Canine Torso Radiographs
This addresses the lack of automation in veterinary radiology, though it is incremental as it builds on existing CNN architectures.
The paper tackled the problem of automating the sorting of canine torso radiographs by view and anatomy, achieving a lightweight algorithm that is lighter than SqueezeNet while maintaining higher accuracy than AlexNet, ResNet, DenseNet, and SqueezeNet.
The veterinary field lacks automation in contrast to the tremendous technological advances made in the human medical field. Implementation of machine learning technology can shorten any step of the automation process. This paper explores these core concepts and starts with automation in sorting radiographs for canines by view and anatomy. This is achieved by developing a new lightweight algorithm inspired by AlexNet, Inception, and SqueezeNet. The proposed module proves to be lighter than SqueezeNet while maintaining accuracy higher than that of AlexNet, ResNet, DenseNet, and SqueezeNet.