Skip to main content

Achieving enhanced accuracy and strength performance with parallel programming for invariant affine point cloud registration

Abstract

Affine-transform of tomographic images maps pixels from image to world coordinates. However, affine transform application on each pixel consumes much time. Extraction of the point cloud of interest from the background is another challenge. The benchmark algorithms use approximations, therefore, compromising accuracy. Because of this fact, there arises a need for affine registration for 3D reconstruction. In this work, we present a computationally efficient affine registration of Digital Imaging and COmmunications in Medicine (DICOM) images. We introduce a novel GPU accelerated hierarchical clustering algorithm using Gaussian thresholding of inter-coordinate distances followed by maximal mutual information score merging for clutter removal. We also show that the reconstructed 3d models using our methodology have a best-case minimum error of 0.18 cm against physical measurements and have higher structural strength. This algorithm should apply to reconstruction, 3D printing, virtual reality, and 3D visualization.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

References

  1. Asamoah D, Oppong E, Oppong S, Danso J (2018) Measuring the performance of image contrast enhancement technique. Int J Comput Appl 181(22):0975–8887

    Google Scholar 

  2. Bernardini F, Mittleman J, Rushmeier H, Silva C, Taubin G (1999) The ball-pivoting algorithm for surface reconstruction. IEEE Trans Vis Comput Graph 5(4):349–359. https://doi.org/10.1109/2945.817351

    Article  Google Scholar 

  3. Bohak C, Lesar Ž, Lavric P, Marolt M (2020) Web-Based 3D Visualisation of Biological and Medical Data. In: Rea P. (ed) Biomedical Visualisation. Advances in Experimental Medicine and Biology, vol. 1235. Springer, Cham, DOI https://doi.org/10.1007/978-3-030-37639-01

  4. Boileau P, Cheval D, Gauci M, Holzer N, Chaoui J, Walch G (2018) Automated Three-Dimensional measurement of glenoid version and inclination in arthritic shoulders. J Bone Jt Surg 100(1):57–65. https://doi.org/10.2106/jbjs.16.01122

    Article  Google Scholar 

  5. Bone CT-Scan Data (2020) Retrieved 23 November 2020, from https://isbweb.org/data/vsj/

  6. Bradley P, Fayyad U, Reina C (1998) Scaling Clustering Algorithms to Large Databases. International Conference On Knowledge Discovery And Data Mining AAAI Press 4(1998):9–15. contentId= 22512748 content/view/22512748

    Google Scholar 

  7. Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F (2013) The cancer imaging archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26(6):1045–1057

    Article  Google Scholar 

  8. Glaser D, Doan J, Newton P (2012) Comparison of 3-Dimensional spinal reconstruction accuracy. Spine 37(16):1391–1397. https://doi.org/10.1097/brs.0b013e3182518a15

    Article  Google Scholar 

  9. Introduction to DICOM. Retrieved 22 November 2020, from https://dicomiseasy.blogspot.com/p/introduction-to-dicom.html

  10. Kajiya J (1983) New techniques for ray tracing procedurally defined objects. ACM SIGGRAPH Computer Graphics 17(3):91–102. https://doi.org/10.1145/964967.801137

    Article  Google Scholar 

  11. Kanitsar A, Fleischmann D, Wegenkittl R, Felkel P, Groller E (2002) CPR - Curved planar reformation, IEEE Visualization, 2002 VIS

  12. Kazhdan M, Bolitho M, Hoppe H (2006) Poisson surface reconstruction. Eurographics Symposium On Geometry Processing, pp. 61–70

  13. Khan U (2020) usmankhanakbar/AffineModelling. Retrieved 5 December 2020, from https://github.com/usmankhanakbar/AffineModelling

  14. Khan U, Khan U, Yasin A, Shafi I, Abid M (2020) CPU-GPU Rendering of CT scan images for vertebra reconstruction from CT scan images with a calibration policy. Medical Imaging And Radiation Sciences, pp 1–5. https://doi.org/10.31487/j.mirs.2020.01.02

  15. Khan U, Yasin A, Abid M, Shafi I, Khan S (2018) A methodological review of 3D reconstruction techniques in tomographic imaging. J Med Syst, 42(10). https://doi.org/10.1007/s10916-018-1042-2

  16. Kim M, Huh K, YI W, Heo M, Lee S, Choi S (2012) Evaluation of accuracy of 3D reconstruction images using multi-detector CT and cone-beam CT. Imaging Sci Dent 42(1):25. https://doi.org/10.5624/isd.2012.42.1.25

    Article  Google Scholar 

  17. Kumar S, KS H, Shetty S (2019) Validation of modified feature-based 3D modeling of scoliotic spine. Cogent Engineering, 6(1). https://doi.org/10.1080/23311916.2019.1623854

  18. Lacroute P, Levoy M (1994) Fast volume rendering using a shear-warp factorization of the viewing transformation. In: Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH, p 94

  19. Lee S, Kim H, Kim H, Choi J, Cho J (2018) Comparison of Image Enlargement according to 3D Reconstruction in a CT Scan:, Using an Aneurysm Phantom. J Korean Phys Soc 72(7):805–810

    Article  Google Scholar 

  20. Levoy M (1990) A hybrid ray tracer for rendering polygon and volume data. IEEE Comput Graph Appl 10(2):33–40. https://doi.org/10.1109/38.50671

    Article  Google Scholar 

  21. Li C, Chandrasekhar U, Onwubolu G (2020) Advances in Engineering Design and Simulation Select Proceedings of NIRC 2018: Select Proceedings of NIRC 2018 (1st ed., pp 109–121). Lecture Notes on Multidisciplinary Industrial Engineering, Springer

  22. Loizou C, Papacharalambous C, Samaras G, Kyriacou E, Kasparis T, Pantziaris M, et al. (2017) Brain Image and Lesions Registration and 3D Reconstruction in Dicom MRI Images. In: 2017 IEEE 30Th International Symposium On Computer-Based Medical Systems (CBMS), DOI https://doi.org/10.1109/cbms.2017.53

  23. Loizou C, Papacharalambous C, Samaras G, Kyriacou E, Kasparis T, Pantziaris M, et al. (2021) Brain image and lesions registration and 3D reconstruction in dicom MRI images. IEEE International Symposium On Computer-Based Medical Systems, 30th, pp 419–422

  24. Lorensen W, Cline H (1987) Marching cubes: a high resolution 3D surface construction algorithm. ACM SIGGRAPH Computer Graphics 21(4):163–169. https://doi.org/10.1145/37402.37422

    Article  Google Scholar 

  25. Maqbool M (2017) Computed tomography. In: Maqbool M (ed) An introduction to medical physics. Biological and medical physics, biomedical engineering. Springer, Cham, DOI https://doi.org/10.1007/978-3-319-61540-08

  26. Muzi P, Wanner M, Kinahan P (2015) Data From RIDER PHANTOM PET CT. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2015.8WG2KN4W

  27. Naiwen Shaded Surface Display Technique, Csee.umbc.edu, 1996. [Online]. Available: https://www.csee.umbc.edu/ebert/693/NLiao/node5.html

  28. Patel N, Gupta D (2016) A morphometric study of adult human atlas vertebrae in South Gujarat population, India. Int J Res Med Sci [Internet], 4380–6. Available from: http://www.msjonline.org/index.php/ijrms/article/view/291

  29. Pieper S, Halle M, Kikinis R “3D Slicer”, 2004 2nd IEEE International Symposium on Biomedical imaging: Nano to Macro (IEEE Cat No. 04EX821), Arlington, VA, USA, 2004, pp 632–635 vol 1. https://doi.org/10.1109/ISBI.2004.1398617

  30. RadiAnt DICOM Viewer (2020) Retrieved 18 November 2020, from https://www.radiantviewer.com/

  31. Sato Y, Shiraga N, Nakajima S, Tamura S, Kikinis R (1998) Local maximum intensity projection (LMIP. J Comput Assist Tomogr 22(6):912–917

    Article  Google Scholar 

  32. Schulze J, Lang U (2003) The parallelized perspective shear-warp algorithm for volume rendering. Parallel Comput 29(3):339–354. https://doi.org/10.1016/s01678191(02)002508

    Article  Google Scholar 

  33. Sengul G, Kadioglu H (2006) Morphometric anatomy of the atlas and axis vertebrae. Turkish Neurosurgery 16(2):69–76

    Google Scholar 

  34. Sherekar R, Pawar A (2014) A MATLAB image processing approach for reconstruction of DICOM images for manufacturing of customized anatomical implants by using rapid prototyping. Am J Mech Eng 1(5):48–53

    Google Scholar 

  35. Shu X, Tang J, Li Z, Lai H, Zhang L, Yan S (2018) Personalized age progression with Bi-Level aging dictionary learning. IEEE Transactions On Pattern Analysis And Machine Intelligence 40(4):905–917. https://doi.org/10.1109/tpami.2017.2705122

    Article  Google Scholar 

  36. Westover LA (1992) Splatting: a parallel, feed-forward volume rendering algorithm. University of North Carolina at Chapel Hill, Chapel Hill

    Google Scholar 

  37. Zhou W, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image qualifty assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Usman Khan.

Ethics declarations

Conflict of interests

The authors have no conflict of interest

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Khan, U., Yasin, A., Jalal, A. et al. Achieving enhanced accuracy and strength performance with parallel programming for invariant affine point cloud registration. Multimed Tools Appl (2022). https://doi.org/10.1007/s11042-022-13178-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11042-022-13178-3

Keywords

  • Cuda
  • Point cloud
  • Reconstruction
  • Tomography
  • Virtual reality