Deep transfer learning can be used for the detection of hip joints in pelvis radiographs and the classification of their hip dysplasia status.

Reports of machine learning implementations in veterinary imaging are infrequent but changes in machine learning architecture and access to increased computing power will likely prompt increased interest. This diagnostic accuracy study describes a particular form of machine learning, a deep learning convolution neural network (ConvNet) for hip joint detection and classification of hip dysplasia from ventro-dorsal (VD) pelvis radiographs submitted for hip dysplasia screening. 11,759 pelvis images were available together with their Fédération Cynologique Internationale (FCI) scores.

Breeding schemes for intervertebral disc disease in dachshunds: Is disc calcification score preferable to genotyping of the FGF4 retrogene insertion on CFA12?

Background: Approximately every fifth Dachshund is affected by disc herniation - a painful, hereditary condition which is typically preceded by disc calcification. Therefore, the selection of dogs suitable for breeding can be based on radiographic examination of calcification status. Recently, an insertion of an FGF4 retrogene on CFA12 has been identified and associated with the risk of developing disc herniation in chondrodystrophic breeds and a DNA test is now offered.

Validation of DNA test for hip dysplasia failed in Danish Labrador Retrievers.

Canine hip dysplasia is characterized by poor hip joint conformation and laxity. The disease is a complex trait influenced by both genetics and environment. Diagnosis and quantification of hip dysplasia are performed by radiographic examination of the hip joint and the diagnosis is used for making breeding decisions in many breeds.

Genome wide association study of 40 clinical measurements in eight dog breeds.

The domestic dog represents an ideal model for identifying susceptibility genes, many of which are shared with humans. In this study, we investigated the genetic contribution to individual differences in 40 clinically important measurements by a genome-wide association study (GWAS) in a multinational cohort of 472 healthy dogs from eight breeds. Meta-analysis using the binary effects model after breed-specific GWAS, identified 13 genome-wide significant associations, three of them showed experimental-wide significant associations.

Assessment of Image Quality in Digital Radiographs Submitted for Hip Dysplasia Screening.

Digital radiography is widely seen to be forgiving of poor exposure technique and to provide consistent high quality diagnostic images. Optimal quality images are however not universal; sub-optimal images are encountered. Evaluators on hip dysplasia schemes encounter images from multiple practices produced on equipment from multiple manufacturers.