Automating digital pathology processing to identify ganglia in seromuscular biopsies from patients with Hirschsprung's disease may be able to provide objective measures and minimize evaluation time for expert pathologists. This adjunctive tool has the potential to improve surgical success for treatment. With thirty patient images, we proposed and evaluated an image processing pipeline that identifies colon tissue structures containing myenteric ganglia. This is an undertaking that is the first of its kind. From whole slide images of calretinin-stained colon sections, we initially segmented the muscularis propria using a convolutional neural network resulting in a mean inclusion of myenteric plexus of 95.96%. Then, colour thresholding identified myenteric plexus regions with a mean inclusion of ganglia of 99.2%. Finally, within these ideal search spaces, we segmented and classified ganglia candidates to achieve an overall mean precision and recall of 64.8% and 80.2%, respectively. Preliminary results encourage further development of these algorithms.