Hepatic vessel segmentation using a reduced filter 3D U-Net in ultrasound imaging

Bart R. Thomson, Jasper Nijkamp, Oleksandra Ivashchenko, Ferdinand van der Heijden, Jasper N. Smit, Niels F.M. Kok, Koert F.D. Kuhlmann, Theo J.M. Ruers, Matteo Fusaglia

Research output: Contribution to conferenceAbstract

17 Downloads (Pure)

Abstract

Accurate hepatic vessel segmentation on ultrasound (US) images can be an important tool in the planning and execution of surgery, however proves to be a challenging task due to noise and speckle. Our method comprises a reduced filter 3D U-Net implementation to automatically detect hepatic vasculature in 3D US volumes. A comparison is made between volumes acquired with a 3D probe and stacked 2D US images based on electromagnetic tracking. Experiments are conducted on 67 scans, where 45 are used in training, 12 in validation and 10 in testing. This network architecture yields Dice scores of 0.740 and 0.781 for 3D and stacked 2D volumes respectively, comparing promising to literature and inter-observer performance (Dice = 0.879).
Original languageEnglish
Number of pages4
Publication statusPublished - 28 Jul 2019
Event2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019 - London, United Kingdom
Duration: 8 Jul 201910 Jul 2019
Conference number: 2

Conference

Conference2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019
Abbreviated titleMIDL
CountryUnited Kingdom
CityLondon
Period8/07/1910/07/19

Keywords

  • Deep learning
  • Segmentation
  • Liver
  • Ultrasound
  • U-Net
  • eess.IV

Fingerprint Dive into the research topics of 'Hepatic vessel segmentation using a reduced filter 3D U-Net in ultrasound imaging'. Together they form a unique fingerprint.

  • Cite this

    Thomson, B. R., Nijkamp, J., Ivashchenko, O., Heijden, F. V. D., Smit, J. N., Kok, N. F. M., ... Fusaglia, M. (2019). Hepatic vessel segmentation using a reduced filter 3D U-Net in ultrasound imaging. Abstract from 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019, London, United Kingdom.