Premium
Automated detection and measurement of uterine peristalsis in cine MR images
Author(s) -
Watanabe Koichi,
Kataoka Masako,
Yano Kojiro,
Nishio Shuro,
Umehana Masaki,
Kido Aki,
Togashi Kaori
Publication year - 2015
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.24817
Subject(s) - peristalsis , magnetic resonance imaging , software , intensity (physics) , nuclear medicine , computer science , medicine , biomedical engineering , artificial intelligence , radiology , anatomy , physics , optics , programming language
Purpose To evaluate the ability of automated software to quantify uterine peristalsis on cine magnetic resonance imaging (MRI). Materials and Methods At 1.5T, half‐Fourier acquisition single‐shot turbo spin echo (HASTE) techniques were used to obtain 60 serial images over 3 minutes (TR/TE 3000/80 msec) in a midsagittal plane of the uterus. Thirty‐two cine MR datasets, obtained from 16 healthy females, were analyzed. Uterine peristalsis was defined as the traveling waves of decreasing signal intensity on the endometrium‐junctional zone border. The software detected traveling waves by identifying the neighboring areas showing similar patterns of signal intensity decrease in a different timing. Quantification of uterine peristaltic wave using the fully automated software was compared to qualitative visual evaluation by two readers. Results The mean number (and standard deviation) of peristaltic waves detected by the fully automated software and visual evaluations (readers 1 and 2) were 5.4 (3.0), 4.7 (3.1), and 4.5 (3.1) per 3 minutes, respectively. Quantification by fully automated software demonstrated excellent agreement with repeated measurement (weighted kappa 0.99) and with qualitative visual evaluations (range 0.89–0.95), comparable to interreader agreement by visual evaluations (range 0.89–0.93). Conclusion The fully automated software can be used to quantify uterine peristalsis comparable to visual evaluation. J. Magn. Reson. Imaging 2015;42:644–650.