The characteristics of magnetic resonance imaging ( mri ) of the brains and spinal cords of 11 dogs with histologically confirmed granulomatous meningoencephalomyelitis ( gme ) were determined. The lesions were in the brain of eight of the dogs, in the brain and spinal cord of two, and in the spinal cord alone in one dog. A single lesion was present in four of the dogs and multiple lesions were found in six. In one dog with intracranial signs, no visible lesions could be detected on mri . No meningeal enhancement was detected in T1‐weighted images post‐contrast, or in fluid attenuation inversion recovery ( flair ) images, but there were histological lesions in the meninges in nine of the dogs. The T2‐weighted images and flair sequences were characterised in all cases by hyperintensity, whereas the signal intensity of the lesions on T1‐weighted images was variable. After the administration of paramagnetic contrast, some of the lesions showed no enhancement, but others showed marked patterns of enhancement. The lesions in 10 of the dogs were easily identifiable by mri and the images had several unifying characteristics, but they could not be considered disease‐specific.

Multifocal haemorrhages associated with Angiostrongylus vasorum infection were observed in the central nervous system of four dogs with neurological signs including depression, seizures, spinal pain and paresis. In magnetic resonance images the majority of the lesions were isointense or slightly hyperintense in T1‐weighted images, hyperintense in T2‐weighted images and hypointense in T2*‐weighted (gradient echo) images, compatible with haemorrhages more than seven days old. Lesions were found in the brain of three of the dogs and in the spinal cord of two. The cerebrospinal fluid contained high concentrations of protein and evidence of erythrophagia. All the dogs had coagulopathy and pulmonary haemorrhage of varying severity. A vasorum larvae were detected in the faeces of each of the dogs. Neural A vasorum was confirmed at postmortem examination in two dogs.

Distinguishing between meningeal-based and intra-axial lesions by means of magnetic resonance (MR) imaging findings may occasionally be challenging. Meningiomas and gliomas account for most of the total primary brain neoplasms in dogs, and differentiating between these two forms is mandatory in choosing the correct therapy. The aims of the present study are: 1) to determine the accuracy of a deep convolutional neural network (CNN, GoogleNet) in discriminating between meningiomas and gliomas in pre- and post-contrast T1 images and T2 images; 2) to develop an image classifier, based on the combination of CNN and MRI sequence displaying the highest accuracy, to predict whether a lesion is a meningioma or a glioma. Eighty cases with a final diagnosis of meningioma (n = 56) and glioma (n = 24) from two different institutions were included in the study. A pre-trained CNN was retrained on our data through a process called transfer learning. To evaluate CNN accuracy in the different imaging sequences, the dataset was divided into a training, a validation and a test set. The accuracy of the CNN was calculated on the test set. The combination between post-contrast T1 images and CNN was chosen in developing the image classifier (trCNN). Ten images from challenging cases were excluded from the database in order to test trCNN accuracy; the trCNN was trained on the remainder of the dataset of post-contrast T1 images, and correctly classified all the selected images. To compensate for the imbalance between meningiomas and gliomas in the dataset, the Matthews correlation coefficient (MCC) was also calculated. The trCNN showed an accuracy of 94% (MCC = 0.88) on post-contrast T1 images, 91% (MCC = 0.81) on pre-contrast T1-images and 90% (MCC = 0.8) on T2 images. The developed trCNN could be a reliable tool in distinguishing between different meningiomas and gliomas from MR images.