QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps

•We propose QSMRim-Net for identification of chronic active MS lesions on QSM.•QSMRim-Net is novel deep learning model that fuses convolutional and radiomic features.•QSMRim-Net uses DeepSMOTE, a novel method to handle imbalanced classification.•QSMRim-Net outperforms other state of the art methods...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:NeuroImage clinical Ročník 34; s. 102979
Hlavní autori: Zhang, Hang, Nguyen, Thanh D., Zhang, Jinwei, Marcille, Melanie, Spincemaille, Pascal, Wang, Yi, Gauthier, Susan A., Sweeney, Elizabeth M.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Netherlands Elsevier Inc 01.01.2022
Elsevier
Predmet:
Algorithms
Brain - diagnostic imaging
Brain - pathology
Chronic active lesions
Convolutional neural network
Humans
Magnetic Resonance Imaging - methods
Multiple sclerosis
Multiple Sclerosis - diagnostic imaging
Multiple Sclerosis - pathology
Neural Networks, Computer
Quantitative susceptibility mapping
Radiology
Radiomic features
Regular
Multiple sclerosis
Chronic active lesions
Quantitative susceptibility mapping
Radiomic features
Convolutional neural network
radiomic features
quantitative susceptibility mapping
chronic active lesions
multiple sclerosis
convolutional neural network
ISSN:2213-1582, 2213-1582
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•We propose QSMRim-Net for identification of chronic active MS lesions on QSM.•QSMRim-Net is novel deep learning model that fuses convolutional and radiomic features.•QSMRim-Net uses DeepSMOTE, a novel method to handle imbalanced classification.•QSMRim-Net outperforms other state of the art methods when applied to QSM. Chronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim + lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim + lesions on QSM. QSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3 T for 172 MS patients. Rim + lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim + and 3986 rim negative (rim−) lesions. Our automated rim + detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim + lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data. On a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim + lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim + lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92). This study develops a novel automated deep neural network for rim + MS lesion identification using T2-FLAIR and QSM images.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2213-1582
2213-1582
DOI:10.1016/j.nicl.2022.102979