Jake Ashley Cumber photo

Jake Cumber

Postgraduate Research Student & Research Assistant
Mon-Fri 08:00-11:45 & 13:00-18:00


My research project


Research projects

Start date: September 2021

End date: September 2023

Research projects


J Cumber, C Rusbridge & K Wells (2022) Using AI to Map Mid-sagittal Neuromorphological Changes in Chiari-like Malformation Associated Pain and Syringomyelia in the Cavalier King CharlesSpaniel

Chiari-like Malformation (CM) is a complex developmental condition resulting in neuroparenchyma / skull and craniospinal junction disproportion and is ubiquitous in Cavalier King Charles Spaniels (CKCS). A common consequence of CM is disruption to cerebrospinal fluid flow, precipitating spinal cord fluid cavitation (syringomyelia; SM). An increase in uptake of diagnostic MRI scans has resulted in an increase in the diagnoses of CM-associated pain (CM-P) and SM in CKCS and other brachycephalic toy breeds. This study aims to elucidate head and neck morphological changes associated with CM-P and clinically-relevant SM (SM-S). 

Data from 130 client owned CKCS with diagnostic MRI from one referral centre was used to study the neuromorphological changes linked to CM-Pain and SM using machine learning. The study population comprises 34 control (no clinical signs of CM-P or SM-S), 51 CM-P, 35 SM-S, and 10 CM-P & SM-S. Extracted T2-weighted midsagittal images underwent an initial rigid alignment process, followed by an elastic registration technique (Demon’s deformation) to yield deformation mappings for each subject.

Using machine learning AI, local (9x9 pixel) regions were systematically examined for significant deformations that are distinct for CM-P or SM-S compared to unaffected dogs. Specific morphologies linked to CM-P, and SM-S, were identified using Receiver Operating Characteristic curves to determine Area Under the Curve scores of 0.87 (sensitivity 89%; specificity 76%), and 0.85 (sensitivity 84%; specificity 80%) respectively representing state-of-the-art performance. Principal components analysis of these trait deformations yields further understanding of local discordant morphologies associated with CM-P and SM-S.

Jake Cumber, Mehran Taghipour-Gorjikolaie , Clare Rusbridge, Kevin Wells (2023) Using AI to detect breeding-related brain and airway disorders in pedigree dogs

Covid-19 lockdowns dramatically accelerated demand for companion family animals.  But increased selective breeding of flat-faced dogs has led to a crisis in associated neurological, skeletal, and airway disorders, where canine quality of life is inadvertently sacrificed for cuteness in appearance. It is suggested that some physical traits are more likely to be found in pedigree dogs afflicted with several genetic developmental disorders, and the exaggeration of these traits worsen the severity of such disorders. However, identifying and grading these traits is impractical without large-scale medical imaging and invasive surgical procedures. A database comprising CT scans obtained from Cavalier King Charles Spaniels was provided to this study, from which cranial models can be generated with computer vision software. A novel low-cost AI methodology has been developed to identify key physical characteristics, present in crania, associated with genetic developmental diseases affecting the Cavalier. Early AI-led results found a significant bulge on the top of the skull linked to neurological disease with near-perfect sensitivity. Continuing developments of this methodology will assist breeders to better develop sustainable, ethical breeding practices for at-risk pedigree dogs and contribute to reducing quality of life issues arising from genetic developmental disorders.