TY - JOUR
T1 - Automated segmentation of acute stroke lesions using a data-driven anomaly detection on diffusion weighted MRI
AU - Nazari-Farsani, Sanaz
AU - Nyman, Mikko
AU - Karjalainen, Tomi
AU - Bucci, Marco
AU - Isojärvi, Janne
AU - Nummenmaa, Lauri
PY - 2020
Y1 - 2020
N2 - Background Successful delineation of lesions in acute ischemic strokes (AIS) is crucial for increasing the likelihood of good clinical outcome for the patient. New methods We developed a fully automated method to localize and segment AIS lesions in variable locations for 192 multimodal 3D-magnetic resonance images (MRI) including 106 stroke and 86 healthy cases. The method works based on the Crawford-Howell t-test and comparison of stroke images to healthy controls. We then developed a classifier to discriminate the images into stroke or non-stroke categories following the lesion segmentation. Results The mean Dice similarity coefficient (DSC) for the test set was 0.50 ± 0.21 (min-max: 0.07–0.83) and mean net overlap was 0.66 ± 0.18 (min-max: 0.22–1). The experimental results for the classification of strokes from non-strokes showed mean accuracy, precision, sensitivity, and specificity of 73 %, 0.77 %, 84 %, and 69 %, respectively. Comparison with existing method The performance of our methods is comparable with previously published approaches based on machine learning and/or deep learning lesion segmentation techniques. However, most of the previously published methods have yielded low sensitivity, are computationally heavy, and difficult to interpret. The present approach is a significant improvement because it does not require high computation power and memory and can be implemented on a desktop workstation and integrated into the routine clinical diagnostic pipeline. Conclusions The current method is straightforward, fast, and shows good agreement with the lesions identified by human experts.
AB - Background Successful delineation of lesions in acute ischemic strokes (AIS) is crucial for increasing the likelihood of good clinical outcome for the patient. New methods We developed a fully automated method to localize and segment AIS lesions in variable locations for 192 multimodal 3D-magnetic resonance images (MRI) including 106 stroke and 86 healthy cases. The method works based on the Crawford-Howell t-test and comparison of stroke images to healthy controls. We then developed a classifier to discriminate the images into stroke or non-stroke categories following the lesion segmentation. Results The mean Dice similarity coefficient (DSC) for the test set was 0.50 ± 0.21 (min-max: 0.07–0.83) and mean net overlap was 0.66 ± 0.18 (min-max: 0.22–1). The experimental results for the classification of strokes from non-strokes showed mean accuracy, precision, sensitivity, and specificity of 73 %, 0.77 %, 84 %, and 69 %, respectively. Comparison with existing method The performance of our methods is comparable with previously published approaches based on machine learning and/or deep learning lesion segmentation techniques. However, most of the previously published methods have yielded low sensitivity, are computationally heavy, and difficult to interpret. The present approach is a significant improvement because it does not require high computation power and memory and can be implemented on a desktop workstation and integrated into the routine clinical diagnostic pipeline. Conclusions The current method is straightforward, fast, and shows good agreement with the lesions identified by human experts.
KW - Acute ischemic stroke
KW - Brain imaging
KW - Automated lesion segmentation
KW - MRI
KW - DWI
U2 - 10.1016/j.jneumeth.2019.108575
DO - 10.1016/j.jneumeth.2019.108575
M3 - Article
SN - 0165-0270
VL - 333
JO - Journal of Neuroscience Methods
JF - Journal of Neuroscience Methods
ER -