Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use. / Hindsholm, Amalie Monberg; Cramer, Stig Præstekjær; Simonsen, Helle Juhl; Frederiksen, Jette Lautrup; Andersen, Flemming; Højgaard, Liselotte; Ladefoged, Claes Nøhr; Lindberg, Ulrich.
I: Clinical Neuroradiology, Bind 32, 2022, s. 643–653.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use
AU - Hindsholm, Amalie Monberg
AU - Cramer, Stig Præstekjær
AU - Simonsen, Helle Juhl
AU - Frederiksen, Jette Lautrup
AU - Andersen, Flemming
AU - Højgaard, Liselotte
AU - Ladefoged, Claes Nøhr
AU - Lindberg, Ulrich
N1 - Publisher Copyright: © 2021, The Author(s).
PY - 2022
Y1 - 2022
N2 - Purpose: To implement and validate an existing algorithm for automatic delineation of white matter lesions on magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) on a local single-center dataset. Methods: We implemented a white matter hyperintensity segmentation model, based on a 2D convolutional neural network, using the conventional T2-weighted fluid attenuated inversion recovery (FLAIR) MRI sequence as input. The model was adapted for delineation of MS lesions by further training on a local dataset of 93 MS patients with a total of 3040 lesions. A quantitative evaluation was performed on ten test patients, in which model-generated masks were compared to manually delineated masks from two expert delineators. A subsequent qualitative evaluation of the implemented model was performed by two expert delineators, in which generated delineation masks on a clinical dataset of 53 patients were rated acceptable (< 10% errors) or unacceptable (> 10% errors) based on the total number of true lesions. Results: The quantitative evaluation resulted in an average accuracy score (F1) of 0.71, recall of 0.77 and dice similarity coefficient of 0.62. Our implemented model obtained the highest scores in all three metrics, when compared to three out of the box lesion segmentation models. In the clinical evaluation an average of 94% of our 53 model-generated masks were rated acceptable. Conclusion: After adaptation to our local dataset, the implemented segmentation model was able to delineate MS lesions with a high clinical value as rated by delineation experts while outperforming popular out of the box applications. This serves as a promising step towards implementation of automatic lesion delineation in our MS clinic.
AB - Purpose: To implement and validate an existing algorithm for automatic delineation of white matter lesions on magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) on a local single-center dataset. Methods: We implemented a white matter hyperintensity segmentation model, based on a 2D convolutional neural network, using the conventional T2-weighted fluid attenuated inversion recovery (FLAIR) MRI sequence as input. The model was adapted for delineation of MS lesions by further training on a local dataset of 93 MS patients with a total of 3040 lesions. A quantitative evaluation was performed on ten test patients, in which model-generated masks were compared to manually delineated masks from two expert delineators. A subsequent qualitative evaluation of the implemented model was performed by two expert delineators, in which generated delineation masks on a clinical dataset of 53 patients were rated acceptable (< 10% errors) or unacceptable (> 10% errors) based on the total number of true lesions. Results: The quantitative evaluation resulted in an average accuracy score (F1) of 0.71, recall of 0.77 and dice similarity coefficient of 0.62. Our implemented model obtained the highest scores in all three metrics, when compared to three out of the box lesion segmentation models. In the clinical evaluation an average of 94% of our 53 model-generated masks were rated acceptable. Conclusion: After adaptation to our local dataset, the implemented segmentation model was able to delineate MS lesions with a high clinical value as rated by delineation experts while outperforming popular out of the box applications. This serves as a promising step towards implementation of automatic lesion delineation in our MS clinic.
KW - Clinical implementation
KW - Convolutional neural network
KW - Magnetic resonance imaging
KW - White matter hyperintensity
U2 - 10.1007/s00062-021-01089-z
DO - 10.1007/s00062-021-01089-z
M3 - Journal article
C2 - 34542644
AN - SCOPUS:85115198206
VL - 32
SP - 643
EP - 653
JO - Clinical Neuroradiology
JF - Clinical Neuroradiology
SN - 1869-1439
ER -
ID: 304145856