摘要
The SOrensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.
学科与关键词
- A Model of Population and Subject (MOPS) Intensities With Application to Multiple Sclerosis Lesion SegmentationTomas-Fernandez, Xavier*; Warfield, Simon K.IEEE Transactions on Medical Imaging, 2015, 34(6): 1349-1361.被引 47
- A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosisCerri, Stefano*; Puonti, Oula; Meier, Dominik S.; Wuerfel, Jens; Muhlau, Mark; Siebner, Hartwig R.; Van Leemput, KoenNeuroImage, 2021, 225: 117471.被引 63
- Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS studyde Sitter, Alexandra*; Steenwijk, Martijn D.; Ruet, Aurelie; Versteeg, Adriaan; Liu, Yaou; van Schijndel, Ronald A.; Pouwels, Petra J. W.; Kilsdonk, Iris D.; Cover, Keith S.; van Dijk, Bob W.; Ropele, Stefan; Rocca, Maria A.; Yiannakas, Marios; Wattjes, Mike P.; Damangir, Soheil; Frisoni, Giovanni B.; Sastre-Garriga, Jaume; Rovira, Alex; Enzinger, Christian; Filippi, Massimo; Frederiksen, Jette; Ciccarelli, Olga; Kappos, Ludwig; Barkhof, Frederik; Vrenken, HugoNeuroImage, 2017, 163: 106-114.被引 25
