**5. Conclusions**

In this paper, we have proposed a multi-stage method based on GANs to generate multi-organ segmentation of chest X-ray images. Unlike existing image generation algorithms, in the proposed approach, generation occurs in three stages, starting with "dots", which represent anatomical parts, and initially involves low-resolution images. After the first step, the resolution is increased to translate "dots" into label maps. We performed this step with Pix2PixHD, thus making the information grow and obtaining the labels for each anatomical part taken into consideration. Finally, Pix2PixHD is also used for translating the label maps into the corresponding chest X-ray images. The usefulness of our method was demonstrated especially when there were few images in the training set, an affordable problem thanks to the multi-stage nature of the approach.

It is worth observing that our method can be employed for any type of image, not exclusively medical ones, while synthetic and real images can concur in solving the segmentation problem (being used for pre-training and for fine-tuning the segmentation network, respectively), with a significant increase in performance. As a matter of future research,

the proposed approach will be extended to other, more complex domains, such as that of natural images.

**Author Contributions:** Conceptualization, G.C. and P.A.; methodology, G.C. and P.A.; software, G.C. and P.A.; validation, G.C., P.A., T.M., M.B. and F.S.; formal analysis, G.C. and P.A.; investigation, G.C.; resources, P.A., M.B. and F.S.; data curation, G.C.; writing—original draft preparation, G.C.; writing—review and editing, G.C., P.A., T.M., M.B. and F.S.; visualization, G.C., P.A., T.M., M.B. and F.S.; supervision, M.B. and F.S.; project administration, M.B. and F.S.; funding acquisition, G.C., M.B. and F.S. All authors have read and agreed to the published version of the manuscript.

**Funding:** The APC was funded by Università degli Studi di Firenze.

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** http://db.jsrt.or.jp/eng.php.

**Acknowledgments:** In addition to Tommaso Mazzierli, who is one of the authors of this work, we would like to thank Gabriella Gaudino and Valentina Vellucci for their contribution in the analysis of the segmentations.

**Conflicts of Interest:** The authors declare no conflict of interest.
