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

Autor:	Thomson, Bart R., Jasper Nijkamp, Oleksandra Ivashchenko, Ferdinand van der Heijden, Smit, Jasper N., Kok, Niels F. M., Kuhlmann, Koert F. D., Ruers, Theo J. M., Matteo Fusaglia
Přispěvatelé:	Nanobiophysics, Technical Medicine
Rok vydání:	2019
Předmět:	Segmentation Liver Ultrasound Image and Video Processing (eess.IV) FOS: Electrical engineering electronic engineering information engineering eess.IV Deep learning Electrical Engineering and Systems Science - Image and Video Processing U-Net
Zdroj:	University of Twente Research Information (Pure Portal) ISSUE=2;TITLE=2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019
DOI:	10.48550/arxiv.1907.12109
Popis:	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). Comment: 3 pages, conference extended abstract. MIDL 2019 [arXiv:1907.08612]
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13c1056ee301743dea3faee14e36c238 Zobrazit plný text záznamu