Advertisement

Deep Learning Based Approach for Assessment of Primary Sjögren’s Syndrome from Salivary Gland Ultrasonography Images

  • Milos RadovicEmail author
  • Arso Vukicevic
  • Alen Zabotti
  • Vera Milic
  • Salvatore De Vita
  • Nenad Filipovic
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 11)

Abstract

Salivary gland ultrasonography (SGUS) has shown a good potential for diagnosing Primary Sjögren’s syndrome (pSS). However, existing scoring procedures (based on the manual analysis and grading of images) need further improvements before being established as standardized diagnostic tools. In this study we developed a deep learning based approach for fast and accurate segmentation of salivary glands extended with the scoring of pSS. Total 471 SGUS images were annotated in terms of semantic segmentation and de Vita scoring system. The dataset has been augmented using standard technique (rotation, flip, random crop) and used for training of a deep learning method for segmentation and classification. Our model achieved 0.935 intersection over union (IoU) for segmentation of salivary glands and 0.854 accuracy for classification of pSS stage on validation images. Here, we give an overview of these achievements and show the results.

Keywords

Deep learning Instance segmentation Primary Sjögren’s syndrome 

Notes

Acknowledgments

This study was funded by the Serbian government (grant agreements III41007 and ON174028) and EU Horizon 2020 RIA programme (HarmonicSS, grant 731944).

References

  1. 1.
    Mavragani, C.P., Moutsopoulos, H.M.: Sjögren syndrome. CMAJ 186(15), E579–E586 (2014)CrossRefGoogle Scholar
  2. 2.
    Hocevar, A., Ambrozic, A., Rozman, B., Kveder, T., Tomsic, M.: Ultrasonographic changes of major salivary glands in primary Sjogren’s syndrome. Diagnostic value of a novel scoring system. Rheumatology 44(6), 768–772 (2005)CrossRefGoogle Scholar
  3. 3.
    Salaffi, F., Carotti, M., Iagnocco, A., Luccioli, F., Ramonda, R., Sabatini, E., De Nicola, M., Maggi, M., Priori, R., Valesini, G., Gerli, R., Punzi, L., Giuseppetti, G.M., Salvolini, U., Grassi, W.: Ultrasonography of salivary glands in primary Sjögren’s syndrome: a comparison with contrast sialography and scintigraphy. Rheumatology 47(8), 1244–1249 (2008)CrossRefGoogle Scholar
  4. 4.
    Milic, V.D., Petrovic, R.R., Boricic, I.V., Marinkovic-Eric, J., Radunovic, G.L., Jeremic, P.D., Pejnovic, N.N., Damjanov, N.S.: Diagnostic value of salivary gland ultrasonographic scoring system in primary Sjogren’s syndrome: a comparison with scintigraphy and biopsy. J. Rheumatol. 36(7), 1495–1500 (2009)CrossRefGoogle Scholar
  5. 5.
    Milic, V.D., Petrovic, R.R., Boricic, I.V., Radunovic, G.L., Pejnovic, N.N., Soldatovic, I., Damjanov, N.S.: Major salivary gland sonography in Sjögren’s syndrome: diagnostic value of a novel ultrasonography score (0–12) for parenchymal inhomogeneity. Scand. J. Rheumatol. 39(2), 160–166 (2009)CrossRefGoogle Scholar
  6. 6.
    De Vita, S., Lorenzon, G., Rossi, G., Sabella, M., Fossaluzza, V.: Salivary gland echography in primary and secondary Sjögren’s syndrome. Clin. Exp. Rheumatol. 10(4), 351–356 (1992)Google Scholar
  7. 7.
    Luciano, N., Baldini, C., Tarantini, G., Ferro, F., Sernissi, F., Varanini, V., Donati, V., Martini, D., Mosca, M., Caramella, D., Bombardieri, S.: Ultrasonography of major salivary glands: a highly specific tool for distinguishing primary Sjögren’s syndrome from undifferentiated connective tissue diseases. Rheumatology 54(12), 2198–2204 (2015)Google Scholar
  8. 8.
    Jousse-Joulin, S., Nowak, E., et al.: Salivary gland ultrasound abnormalities in primary Sjögren’s syndrome: consensual US-SG core items definition and reliability. RMD Open 3(1), e000364 (2017)CrossRefGoogle Scholar
  9. 9.
    Vukicevic, A., Filipovic, N., Milic, V., Zabotti, A., Hocevar, A., Di Lucia, O., Filippou, G., De Vita, S., Frangi, A.F., Tzioufas, A.: Radiomics-based assessment of Primary Sjogren’s Syndrome from salivary gland ultrasonography images. IEEE J. Biomed. Health Inform. (2019).  https://doi.org/10.1109/jbhi.2019.2923773CrossRefGoogle Scholar
  10. 10.
    Litjens, G., Kooi, T., Bejnordi, B.E., Setio, A.A.A., Ciompi, F., Ghafoorian, M., Van Der Laak, J.A., Van Ginneken, B., Sánchez, C.I.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  11. 11.
    Radovic, M., Vukicevic, A., Zabotti, A., Milic, V., De Vita, S., Filipovic, N.: Deep learning based approach for assessment of primary Sjögren’s syndrome from salivary gland ultrasonography images. In: 8th International Conference on Computational Bioengineering (ICCB2019) (2019)Google Scholar
  12. 12.
    Liu, Y.: The Confusing Metrics of AP and mAP for Object Detection/Instance Segmentation (2018). https://medium.com/@yanfengliux/the-confusing-metrics-of-ap-and-map-for-object-detection-3113ba0386ef
  13. 13.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017)Google Scholar
  14. 14.
    Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X.: Mask scoring R-CNN. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  15. 15.
    Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., Change Loy, C., Lin, D.: Hybrid task cascade for instance segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  16. 16.
    Chen, X., Girshick, R., He, K., Dollár, P.: TensorMask: a foundation for dense object segmentation. In: International Conference on Computer Vision (ICCV) (2019)Google Scholar
  17. 17.
    Bolya, D., Zhou, C., Xiao, F., Jae Lee, Y.: YOLACT: real-time instance segmentation. In: International Conference on Computer Vision (ICCV) (2019)Google Scholar
  18. 18.
    Hu, R., Dollár, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  19. 19.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  20. 20.
  21. 21.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: European Conference on Computer Vision (ECCV) (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Milos Radovic
    • 1
    • 2
    Email author
  • Arso Vukicevic
    • 2
    • 3
  • Alen Zabotti
    • 4
  • Vera Milic
    • 5
  • Salvatore De Vita
    • 4
  • Nenad Filipovic
    • 3
  1. 1.Everseen - R&D Centre - BelgradeBelgradeSerbia
  2. 2.Bioengineering Research and Development Center BioIRC KragujevacKragujevacSerbia
  3. 3.Faculty of EngineeringUniversity of KragujevacKragujevacSerbia
  4. 4.Azienda Ospedaliero Universitaria, Santa Maria Della Misericordia di UdineUdineItaly
  5. 5.School of Medicine, Institute of RheumatologyUniversity of BelgradeBelgradeSerbia

Personalised recommendations