“… lesion load, SI, Jaccard index, FPF, TPF | 1st, 2nd | | ( Cerasa et al, 2011 ) | 11 MS | FLAIR | cellular neural network | skull stripping | DSC, total lesion load | 1st, 2nd | |
( Kuwazuru et al, 2011 ) | 3 MS | T1-w, T2-w, FLAIR | SVM and artificial neural network | enhancement by subtraction of background | accuracy, SI, sensitivity, number of FP | 1st, 2nd | |
( Bilello et al, 2013 ) | 88 MS | FLAIR | image subtraction | skull stripping, b.c. | with and without CAD: lesion count and location, PPV, NPV, sensitivity, specificity, efficiency, AUC, lesion-wise sensitivity, FPR and PPV, time spent, clinical reporting | 1st, 2nd, 3rd, 4th, 5th | |
( Hindsholm et al, 2021 ) | 93 MS | FLAIR | 2D CNN | normalisation, cropping or zero padding | DSC, recall, F1, precision, qualitative assessment of output lesion masks | 1st, 2nd | |
( Roy et al, 2015 ) | 10 MS | MPRAGE and FLAIR | patch based with temporal information from timepoints | normalisation | DSC, LTPR, LFPR, AVD | 1st, 2nd | |
( Bouman et al, 2023 ) | 198 MS | DIR or PSIR generated artificially from T1-w, T2-w, PD-w or FLAIR | U-Net-like | MNI reg., skull stripping, b.c. | lesions count, precision | 1st, 2nd | |
( Sitter et al, 201... |
…”