@ARTICLE{10.3389/fonc.2020.00675, AUTHOR={Schreier, Jan and Attanasi, Francesca and Laaksonen, Hannu}, TITLE={Generalization vs. Specificity: In Which Cases Should a Clinic Train its Own Segmentation Models?}, JOURNAL={Frontiers in Oncology}, VOLUME={10}, YEAR={2020}, URL={https://www.frontiersin.org/articles/10.3389/fonc.2020.00675}, DOI={10.3389/fonc.2020.00675}, ISSN={2234-943X}, ABSTRACT={As artificial intelligence for image segmentation becomes increasingly available, the question whether these solutions generalize between different hospitals and geographies arises. The present study addresses this question by comparing multi-institutional models to site-specific models. Using CT data sets from four clinics for organs-at-risk of the female breast, female pelvis and male pelvis, we differentiate between the effect from population differences and differences in clinical practice. Our study, thus, provides guidelines to hospitals, in which case the training of a custom, hospital-specific deep neural network is to be advised and when a network provided by a third-party can be used. The results show that for the organs of the female pelvis and the heart the segmentation quality is influenced solely on bases of the training set size, while the patient population variability affects the female breast segmentation quality above the effect of the training set size. In the comparison of site-specific contours on the male pelvis, we see that for a sufficiently large data set size, a custom, hospital-specific model outperforms a multi-institutional one on some of the organs. However, for small hospital-specific data sets a multi-institutional model provides the better segmentation quality.} }