Spatial encoding and growth-related change of sheep lung radiomic features

David Collie ^1,2 Chris Cousens ³ Steven H Wright ^1,2 Ziyuan Chang ^1,2 James Meehan ^1,2 Helen Brown ^1,2 Calum Gray ⁴ Tom J Macgillivray ⁵ David Griffiths ³ Chad E Eckert ⁶ Nicole Storer ⁶ Mark Gray ^1,2*

• ¹ Roslin Institute, University of Edinburgh, Edinburgh, Scotland, United Kingdom
• ² Royal (Dick) School of Veterinary Studies, University of Edinburgh, Edinburgh, Scotland, United Kingdom
• ³ Moredun Research Institute, Penicuik, Scotland, United Kingdom
• ⁴ Edinburgh Imaging Facilities, University of Edinburgh, Edinburgh, Scotland, United Kingdom
• ⁵ Centre for Clinical Brain Sciences, Edinburgh Medical School, University of Edinburgh, Edinburgh, Scotland, United Kingdom
• ⁶ Johnson & Johnson Medtech (US), Brunswick, New Jersey, United States

Different regions of the small ruminant lung exhibit variable susceptibility to specific lung pathologies. Such susceptibility may be reflected in regional lung radiomic features extracted from computed tomography (CT) images. Here we investigated whether region-specific variation in radiomic features exists in ovine lungs and if these features remain stable over time. Thoracic CT image data sets from thirty young adult sheep were subject to an image segmentation protocol directed towards partitioning the lung into individual lobar and sub-lobar segments for radiomic feature analysis. Following steps to identify and remove unstable and non-reproducible, as well as highly correlated features, 22 features remained which were used as input to principal component (PC) analysis. The significance of segment-related influence on PC scores was determined and visualised. For six sheep, successive CT images were acquired at monthly intervals for a period of nine months in order to assess time-dependent variation in radiomic features. Results indicated that there was a significant difference in radiomic features derived from different lung segments.Visualisation of PC scores highlighted differences between caudodorsal and cranioventral lung, between lobar and sub-lobar segments, and suggestions of bias towards one or other lung.Significant changes in PC scores occurred over time. With few exceptions largely similar changes occurred across all segments in this regard. Overall, our results indicate that although sheep lung radiomic features are influenced by the lung segment of origin, their variation over time is largely consistent throughout the lung. Such influence should be borne in mind when interpreting radiomic features and their changes over time.