Employing deep convolutional neural networks for segmenting the medial retropharyngeal lymph nodes in CT studies of dogs. Issue 6 (25th July 2022)

• Record Type: Journal Article
• Authors: Schmid, David; Scholz, Volkher B.; Kircher, Patrick R.; Lautenschlaeger, Ines E.
• Is Part Of: Veterinary radiology & ultrasound. Volume 63:Issue 6(2022)
• Page Start: 763
• Page End: 770
• Publication Date: 2022-07-25
• Subjects: artificial intelligence -- automated segmentation -- canine head; Veterinary radiology -- Periodicals; Radiologie vétérinaire -- Périodiques; Échographie vétérinaire -- Périodiques; Radiography -- Periodicals; Ultrasonography -- Periodicals; Diagnosis -- Periodicals; Veterinary Medicine -- Periodicals; Societies, Medical -- Periodicals; 636.089607
• DOI: 10.1111/vru.13132
• Languages: English
• ISSNs: 1058-8183

Abstract

Abstract: While still in its infancy, the application of deep convolutional neural networks in veterinary diagnostic imaging is a rapidly growing field. The preferred deep learning architecture to be employed is convolutional neural networks, as these provide the structure preferably used for the analysis of medical images. With this retrospective exploratory study, the applicability of such networks for the task of delineating certain organs with respect to their surrounding tissues was tested. More precisely, a deep convolutional neural network was trained to segment medial retropharyngeal lymph nodes in a study dataset consisting of CT scans of canine heads. With a limited dataset of 40 patients, the network in conjunction with image augmentation techniques achieved an intersection‐overunion of overall fair performance (median 39%, 25 percentiles at 22%, 75 percentiles at 51%). The results indicate that these architectures can indeed be trained to segment anatomic structures in anatomically complicated and breed‐related variating areas such as the head, possibly even using just small training sets. As these conditions are quite common in veterinary medical imaging, all routines were published as an open‐source Python package with the hope of simplifying future research projects in the community.