NSNerissa Stander

Nerissa Stander

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nerissa Stander has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Pilot study: external validation of commercial veterinary radiology artificial intelligence services shows deficiencies in interpretation of general practice–sourced canine abdominal radiographs

    by Doris Ma, Josephine E. Faulkner, Nerissa Stander, Anthea Raisis, Stephen Joslyn

    Objective: To evaluate the diagnostic performance of commercial veterinary radiology AI platforms on general practice canine abdominal radiographs with confirmed diagnoses. Methods: For this pilot study, canine abdominal radiographs with definitive diagnoses were collected and submitted to 6 AI platforms between September and December 2024. Confirmation of diagnosis was obtained with surgery, necropsy, CT, ultrasound, cytology, or treatment response when appropriate. Results: 53 cases were selected and submitted to AI platforms. After platform rejections, 307 evaluations were available for analysis. When differentiating cases with pathology (51 of 53) and without pathology (2 of 53), platform performance was variable and mostly low to moderate, including mean accuracy (70% to 90%), balanced accuracy (60% to 65%), and Matthews correlation coefficient (–0.08 to 0.43). Across all platforms, classification of radiographic findings (labels) showed low sensitivity (28% to 78%), F 1 score (28% to 51%), and positive predictive value (25% to 54%) due to frequent missed diagnoses. Matthews correlation coefficient was higher (0.16 to 0.45), as it was less impacted by label misclassification. Small intestinal obstruction, a critical finding, was often not identified, with a sensitivity of 23% to 69%. Conclusions: Diagnostic performance varied between the 6 AI platforms tested and was overall low to moderate for this small sample. Even the best-performing algorithm had notable limitations, and none appeared suitable for clinical use in their current form. Clinical Relevance: Further independent external validations on a larger scale and performance gains are needed before AI platforms can be safely integrated into clinical practice.


  • Open Access

    Computed tomographic, ultrasonographic, MRI and radiographic findings of a venous malformation with phleboliths in the thoracic limb of a dog

    by Kevin Kang, Robert M. Kirberger, Giselle Hosgood, Nerissa Stander

    An 11‐month‐old entire male Rottweiler was referred for further investigation of raised, soft, compressible, non‐pulsatile, subcutaneous tubular structures along the right antebrachium that had been diagnosed to be a vascular malformation on histopathology of a subcutaneous biopsy. Computed tomographic (CT) with angiography did not reveal an arteriovenous malformation or fistula. Ultrasonography of the limb demonstrated a venous malformation with thrombi and phleboliths. An MRI study of the limb was consistent with a venous malformation with small rounded luminal signal voids that were confirmed to be phleboliths. Radiography at follow‐up demonstrated phleboliths. This is the first report describing the combined CT, ultrasonographic, MRI and radiographic characteristics of venous malformation with phleboliths in a limb of a dog.


  • Algorithmic estimation of adrenal volume based on body weight and CT landmarks in dogs

    by Ryan Swepson, Giselle Hosgood, Nerissa Stander

    Computed tomographic (CT) methods for quantifying adrenal size are helpful for identifying and directing management of adrenal disease in dogs. This retrospective, observational study aimed to use CT to determine anatomic landmarks associated with adrenal gland volume in dogs, and subsequently develop an algorithm to estimate adrenal volume for individual subjects. Abdominal CT images from 150 dogs without adrenal disease were assessed. The volume of the left and right adrenals, as well as dimensions from anatomic structures, were measured. Predictive models for adrenal volume were examined with cross validation. A further 29 dogs were used for external validation and model fit. Dogs in the test cohort weighed from 3.1 to 67.5 kg (mean 24.4 kg) with left (VLA) and right (VRA) adrenal volume ranging from 0.23 to 2.84 cm3(mean 1.22 cm3) and 0.14 to 2.97 cm3(mean 1.11 cm3), respectively. A predictive model for each adrenal based on weight (W) and L1 height (HL1) best explained the adrenal volume, with external validation confirming model fit. The final models, adjusted for bias, were:VLA = 0.154 + (0.02 × W) + (0.07 × HL1) (adjR2 = 0.62); andVRA = −0.116 + (0.02 × W) + (0.06 × HL1) (adjR2 = 0.64). In dogs undergoing CT, these algorithms can be used to estimate expected adrenal volume and allow comparison with the actual volume measured on CT, facilitating interpretation of CT findings, and clinical decision‐making.