Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

TRUSTED: The Paired 3D Transabdominal Ultrasound and CT Human Data for Kidney Segmentation and Registration Research (2310.12646v1)

Published 19 Oct 2023 in eess.IV and cs.CV

Abstract: Inter-modal image registration (IMIR) and image segmentation with abdominal Ultrasound (US) data has many important clinical applications, including image-guided surgery, automatic organ measurement and robotic navigation. However, research is severely limited by the lack of public datasets. We propose TRUSTED (the Tridimensional Renal Ultra Sound TomodEnsitometrie Dataset), comprising paired transabdominal 3DUS and CT kidney images from 48 human patients (96 kidneys), including segmentation, and anatomical landmark annotations by two experienced radiographers. Inter-rater segmentation agreement was over 94 (Dice score), and gold-standard segmentations were generated using the STAPLE algorithm. Seven anatomical landmarks were annotated, important for IMIR systems development and evaluation. To validate the dataset's utility, 5 competitive Deep Learning models for automatic kidney segmentation were benchmarked, yielding average DICE scores from 83.2% to 89.1% for CT, and 61.9% to 79.4% for US images. Three IMIR methods were benchmarked, and Coherent Point Drift performed best with an average Target Registration Error of 4.53mm. The TRUSTED dataset may be used freely researchers to develop and validate new segmentation and IMIR methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. ESR. Abdominal applications of ultrasound fusion imaging technique: liver, kidney, and pancreas. \JournalTitleInsights into Imaging 10, 6 (2019).
  2. Leroy, A. et al. Percutaneous renal puncture, requirements and preliminary results. \JournalTitlearXiv preprint physics/0610209 (2006).
  3. Fu, Y. et al. Biomechanically constrained non rigid MR-TRUS prostate registration using deep learning based 3d point cloud matching. \JournalTitleMedical image analysis 67, 101845 (2021).
  4. Least-squares fitting of two 3-d point sets. \JournalTitleIEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-9, 698–700, https://doi.org/10.1109/TPAMI.1987.4767965 (1987).
  5. Point clouds registration with probabilistic data association. In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 4092–4098, https://doi.org/10.1109/IROS.2016.7759602 (2016).
  6. Hirose, O. A bayesian formulation of coherent point drift. \JournalTitleIEEE Transactions on Pattern Analysis and Machine Intelligence 43, 2269–2286, https://doi.org/10.1109/TPAMI.2020.2971687 (2021).
  7. Pointnetlk: Robust and efficient point cloud registration using pointnet. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019).
  8. Sarode, V. et al. Pcrnet: Point cloud registration network using pointnet encoding (2019).
  9. Local normalized cross correlation for geo-registration. In Proceedings of 2012 9th International Bhurban Conference on Applied Sciences and Technology (IBCAST), 70–74, https://doi.org/10.1109/IBCAST.2012.6177529 (2012).
  10. den Brinker, A. C. Calculation of the local cross-correlation function on the basis of the laguerre transform. \JournalTitleIEEE transactions on signal processing 41, 1980–1982 (1993).
  11. Hale, D. Fast local cross-correlations of images. In 2006 SEG Annual Meeting (OnePetro, 2006).
  12. Haskins, G. et al. Learning deep similarity metric for 3d mr–trus image registration. \JournalTitleInternational journal of computer assisted radiology and surgery 14, 417–425 (2019).
  13. Quicksilver: Fast predictive image registration - a deep learning approach. \JournalTitleNeuroImage 158, 378–396, https://doi.org/10.1016/j.neuroimage.2017.07.008 (2017).
  14. Hu, Y. et al. Label-driven weakly-supervised learning for multimodal deformable image registration. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 1070–1074, https://doi.org/10.1109/ISBI.2018.8363756 (2018).
  15. Hu, Y. et al. Weakly-supervised convolutional neural networks for multimodal image registration. \JournalTitleMedical image analysis 49, 1–13 (2018).
  16. Voxelmorph: A learning framework for deformable medical image registration. \JournalTitleIEEE Transactions on Medical Imaging 38, 1788–1800, https://doi.org/10.1109/TMI.2019.2897538 (2019).
  17. Chen, J. et al. Transmorph: Transformer for unsupervised medical image registration. \JournalTitleMedical Image Analysis 82, 102615, https://doi.org/10.1016/j.media.2022.102615 (2022).
  18. Chen, Y. et al. Mr to ultrasound image registration with segmentation-based learning for hdr prostate brachytherapy. \JournalTitleMedical Physics 48, 3074–3083 (2021).
  19. Karnik, V. V. et al. Assessment of image registration accuracy in three-dimensional transrectal ultrasound guided prostate biopsy. \JournalTitleMedical physics 37, 802–813 (2010).
  20. Detection of kidney abnormalities in noisy ultrasound images. \JournalTitleInternational Journal of Computer Applications 120 (2015).
  21. Kettenbach, J. et al. Robot-assisted biopsy using ultrasound guidance: initial results from in vitro tests. \JournalTitleEuropean radiology 15, 765–771 (2005).
  22. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. \JournalTitleNature Methods 18, 203 – 211 (2020).
  23. Chen, J. et al. Transunet: Transformers make strong encoders for medical image segmentation. \JournalTitlearXiv preprint arXiv:2102.04306 (2021).
  24. Cao, H. et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In Computer Vision–ECCV 2022 Workshops: Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III, 205–218 (Springer, 2023).
  25. Zhou, H.-Y. et al. nnformer: Interleaved transformer for volumetric segmentation. \JournalTitlearXiv preprint arXiv:2109.03201 (2021).
  26. Cotr: Convolution in transformer network for end to end polyp detection. \JournalTitle2021 7th International Conference on Computer and Communications (ICCC) 1757–1761 (2021).
  27. Full contextual attention for multi-resolution transformers in semantic segmentation. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 3223–3232, https://doi.org/10.1109/WACV56688.2023.00324 (2023).
  28. Yu, W. et al. Liver vessels segmentation based on 3d residual u-net. In 2019 IEEE International Conference on Image Processing (ICIP), 250–254, https://doi.org/10.1109/ICIP.2019.8802951 (2019).
  29. Gibson, E. et al. Automatic multi-organ segmentation on abdominal ct with dense v-networks. \JournalTitleIEEE Transactions on Medical Imaging 37, 1822–1834, https://doi.org/10.1109/TMI.2018.2806309 (2018).
  30. Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 3–11 (Springer, 2018).
  31. Shape feature loss for kidney segmentation in 3d ultrasound images (BMVC, 2021).
  32. Zeng, Q. et al. Label-driven magnetic resonance imaging (mri)-transrectal ultrasound (trus) registration using weakly supervised learning for mri-guided prostate radiotherapy. \JournalTitlePhysics in Medicine & Biology 65, 135002 (2020).
  33. Xu, X. et al. Polar transform network for prostate ultrasound segmentation with uncertainty estimation. \JournalTitleMedical Image Analysis 78, 102418 (2022).
  34. 3d u-net: Learning dense volumetric segmentation from sparse annotation. In Ourselin, S., Joskowicz, L., Sabuncu, M. R., Unal, G. & Wells, W. (eds.) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, 424–432 (Springer International Publishing, Cham, 2016).
  35. V-net: Fully convolutional neural networks for volumetric medical image segmentation. \JournalTitle2016 Fourth International Conference on 3D Vision (3DV) 565–571 (2016).
  36. Orientation estimation of abdominal ultrasound images with multi-hypotheses networks. In Medical Imaging with Deep Learning (2022).
  37. Global multi-modal 2d/3d registration via local descriptors learning. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VI, 269–279 (Springer, 2022).
  38. MR to Ultrasound Registration for Prostate Challenge - Dataset, https://doi.org/10.5281/zenodo.7870105 (2023).
  39. Andrey, F. et al. Open-source image registration for MRI-TRUS fusion-guided prostate interventions. \JournalTitleInternational Journal of Computer Assisted Radiology and Surgery 10, 925–934 (2015).
  40. Andrey, F. et al. 3d slicer as an image computing platform for the quantitative imaging network. \JournalTitleMagnetic Resonance Imaging 30, 1323–1341, https://doi.org/10.1016/j.mri.2012.05.001 (2012). Funding Information: We would like to thank all current and past users and developers of 3D Slicer for their contribution to this software. The authors have been supported in part by the following NIH grants. BWH: U01CA151261, P41EB015898, P41RR13218, U54EB005149 and 1R01CA111288 ; University of Iowa: U01-CA140206 ; GE: P41RR13218 and U54EB005149 ; MGH: 1U01CA154601-01 and 4R00LM009889-03 . We are grateful to the various agencies and programs that funded support and development of 3D Slicer over the years.
  41. Yang, G. et al. Automatic segmentation of kidney and renal tumor in ct images based on 3d fully convolutional neural network with pyramid pooling module. In 2018 24th International Conference on Pattern Recognition (ICPR), 3790–3795 (IEEE, 2018).
  42. Automated renal segmentation in healthy and chronic kidney disease subjects using a convolutional neural network. \JournalTitleMagnetic Resonance in Medicine 86, 1125–1136 (2021).
  43. Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation. \JournalTitleIEEE Transactions on Medical Imaging 23, 903–921 (2004).
  44. A deformation model for non-rigid registration of the kidney. In Medical Imaging 2009: Visualization, Image-Guided Procedures, and Modeling, vol. 7261, 1022–1030 (SPIE, 2009).
  45. Automatic ct-ultrasound registration for diagnostic imaging and image-guided intervention. \JournalTitleMedical image analysis 12, 577–585 (2008).
  46. A modified hausdorff distance for object matching. In Proceedings of 12th International Conference on Pattern Recognition, vol. 1, 566–568 vol.1, https://doi.org/10.1109/ICPR.1994.576361 (1994).
  47. Evaluating the impact of intensity normalization on mr image synthesis. In Medical Imaging 2019: Image Processing, vol. 10949, 890–898 (SPIE, 2019).
  48. Jacobsen, N. et al. Analysis of intensity normalization for optimal segmentation performance of a fully convolutional neural network. \JournalTitleZeitschrift für Medizinische Physik 29, 128–138 (2019).
  49. Cardoso, M. J. et al. Monai: An open-source framework for deep learning in healthcare (2022). 2211.02701.
  50. Efficient implementation of marching cubes’ cases with topological guarantees. \JournalTitleJournal of graphics tools 8, 1–15 (2003).
  51. Du, S. et al. Robust rigid registration algorithm based on pointwise correspondence and correntropy. \JournalTitlePattern Recognition Letters 132, 91–98 (2020).
  52. Biomechanical kidney model for predicting tumor displacement in the presence of external pressure load. In 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), 810–813 (IEEE, 2014).
  53. Intensity-based registration of freehand 3d ultrasound and ct-scan images of the kidney. \JournalTitleInternational journal of computer assisted radiology and surgery 2, 31–41 (2007).

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now