TY - JOUR
T1 - A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies
AU - Ganiler, Onur
AU - Oliver, Arnau
AU - Diez Donoso, Santiago
AU - Freixenet, Jordi
AU - Vilanova, Joan C.
AU - Beltran, Brigitte
AU - Ramió-Torrentà, Lluís
AU - Rovira, Àlex
AU - Lladó, Xavier
PY - 2014/1/1
Y1 - 2014/1/1
N2 - Introduction: Time-series analysis of magnetic resonance images (MRI) is of great value for multiple sclerosis (MS) diagnosis and follow-up. In this paper, we present an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies. Methods: The proposed pipeline for detecting new lesions consists of the following steps: skull stripping, bias field correction, histogram matching, registration, white matter masking, image subtraction, automated thresholding, and postprocessing. We also combine the results of PD-w and T2-w images to reduce false positive detections. Results: Experimental tests are performed in 20 MS patients with two temporal studies separated 12 (12M) or 48 (48M) months in time. The pipeline achieves very good performance obtaining an overall sensitivity of 0.83 and 0.77 with a false discovery rate (FDR) of 0.14 and 0.18 for the 12M and 48M datasets, respectively. The most difficult situation for the pipeline is the detection of very small lesions where the obtained sensitivity is lower and the FDR higher. Conclusion: Our fully automated approach is robust and accurate, allowing detection of new appearing MS lesions. We believe that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.
AB - Introduction: Time-series analysis of magnetic resonance images (MRI) is of great value for multiple sclerosis (MS) diagnosis and follow-up. In this paper, we present an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies. Methods: The proposed pipeline for detecting new lesions consists of the following steps: skull stripping, bias field correction, histogram matching, registration, white matter masking, image subtraction, automated thresholding, and postprocessing. We also combine the results of PD-w and T2-w images to reduce false positive detections. Results: Experimental tests are performed in 20 MS patients with two temporal studies separated 12 (12M) or 48 (48M) months in time. The pipeline achieves very good performance obtaining an overall sensitivity of 0.83 and 0.77 with a false discovery rate (FDR) of 0.14 and 0.18 for the 12M and 48M datasets, respectively. The most difficult situation for the pipeline is the detection of very small lesions where the obtained sensitivity is lower and the FDR higher. Conclusion: Our fully automated approach is robust and accurate, allowing detection of new appearing MS lesions. We believe that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.
KW - 3D subtraction
KW - Brain MRI longitudinal analysis
KW - Lesion change detection
KW - Multiple sclerosis
UR - http://www.scopus.com/inward/record.url?scp=84902826592&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902826592&partnerID=8YFLogxK
U2 - 10.1007/s00234-014-1343-1
DO - 10.1007/s00234-014-1343-1
M3 - Article
C2 - 24590302
AN - SCOPUS:84902826592
VL - 56
SP - 363
EP - 374
JO - Neuroradiology
JF - Neuroradiology
SN - 0028-3940
IS - 5
ER -