Premium
Technical Note: A new zeolite PET phantom to test segmentation algorithms on heterogeneous activity distributions featured with ground‐truth contours
Author(s) -
Soffientini Chiara D.,
De Bernardi Elisabetta,
Casati Rosangela,
Baselli Giuseppe,
Zito Felicia
Publication year - 2017
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.12014
Subject(s) - imaging phantom , ground truth , zeolite , homogeneity (statistics) , homogeneous , segmentation , nuclear medicine , computer science , materials science , biomedical engineering , artificial intelligence , algorithm , mathematics , chemistry , medicine , machine learning , biochemistry , catalysis , combinatorics
Purpose Design, realization, scan, and characterization of a phantom for PET Automatic Segmentation ( PET ‐ AS ) assessment are presented. Radioactive zeolites immersed in a radioactive heterogeneous background simulate realistic wall‐less lesions with known irregular shape and known homogeneous or heterogeneous internal activity. Method Three different zeolite families were evaluated in terms of radioactive uptake homogeneity, necessary to define activity and contour ground truth. Heterogeneous lesions were simulated by the perfect matching of two portions of a broken zeolite, soaked in two different 18 F‐ FDG radioactive solutions. Heterogeneous backgrounds were obtained with tissue paper balls and sponge pieces immersed into radioactive solutions. Results Natural clinoptilolite proved to be the most suitable zeolite for the construction of artificial objects mimicking homogeneous and heterogeneous uptakes in 18 F‐ FDG PET lesions. Heterogeneous backgrounds showed a coefficient of variation equal to 269% and 443% of a uniform radioactive solution. Assembled phantom included eight lesions with volumes ranging from 1.86 to 7.24 ml and lesion to background contrasts ranging from 4.8:1 to 21.7:1. Conclusions A novel phantom for the evaluation of PET ‐ AS algorithms was developed. It is provided with both reference contours and activity ground truth, and it covers a wide range of volumes and lesion to background contrasts. The dataset is open to the community of PET ‐ AS developers and utilizers.