The automated detection of Intervertebral disc (IVD) herniation in animal MRI may facilitate veterinary diagnosis, yet it is rarely studied due to the lack of training data and the challenges from inter-breed variations. Here, we constructed a dog spinal cord MRI dataset with bounding box annotations of herniated discs, and conducted experiments using a number of well-known deep learning models. We demonstrated that automated detection of animal IVD herniation was feasible and in general two-stage detection models such as Faster R-CNN outperformed one-stage models.
This abstract and the presentation materials are available to members only; a login is required.