MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation?

详细信息    查看全文

• 作者：Christine Egger^a ; ^{christine.egger@usz.ch} ; Roland Opfer^a ; ^b ; Chenyu Wang^c ; ^d ; Timo Kepp^b ; Maria Pia Sormani^e ; Lothar Spies^b ; Michael Barnett^c ; ^d ; Sven Schippling^a
• 关键词：Magnetic resonance imaging ; Fluid-attenuated inversion recovery ; Multiple sclerosis ; Automated lesion segmentation ; Inter-rater variability ; Dice coefficient
• 刊名：NeuroImage: Clinical
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：13
• 期：Complete
• 页码：264-270
• 全文大小：671 K
• 卷排序：13

文摘

Fully automated and manual MS lesion segmentation on FLAIR images were compared. Automated FLAIR lesion volume segmentation holds up with manual annotation. When using DC and ICC, SPM8 based algorithm performed better than recent updates.