Background: Chiari-like malformation (CM) is a complex malformation of the skull and cranial cervical vertebrae potentially resulting in pain and secondary syringomyelia (SM). CM associated pain can be challenging to diagnose [35]. We propose a machine learning approach to characterize morphological changes in dogs that may/may not be apparent to human observers. This data driven approach can remove potential bias (or blindness) that may be produced by a hypothesis driven expert observer approach.

Hypothesis/Objectives: Using a novel machine learning approach to understand neuromorphological change and to identify image-based biomarkers in dogs with CM associated pain (CM-P) and symptomatic SM (SM-S), with the aim of deepening the understanding on these disorders. Animals: 32 client owned Cavalier King Charles Spaniels (CKCS) (11 controls, 10 CM-P, 11 SM-S)

Methods: Retrospective study using T2W midsagittal DICOM anonymized images which were mapped to a images of a average clinically normal CKCS reference using Demons image registration. Key deformation features were automatically selected from the resulting deformation maps. A kernelized Support Vector Machine was used for classifying characteristic localized changes in morphology.

Results: Candidate biomarkers were identified with receiver operating characteristic (ROC) curves with area under the curve (AUC) of 0.78 (sensitivity = 82%; specificity = 69%) for the CM-P biomarkers collectively, and an AUC of 0.82 (sensitivity = 93%; specificity = 67%) for the SM biomarkers collectively.

Conclusions and clinical importance: Machine learning techniques can assist CM/SM diagnosis and understand abnormal morphology location with the potential to be applied to a variety of breeds and conformational diseases.