DWI-Based Neural Fingerprinting Technology: A Preliminary Study on Stroke Analysis
Table 1
Clustering result and evaluation.
Clinical reference
Manual ROI
Semiautomatic ROI
Automatic ROI
Euclidean distance
Cosine distance
Euclidean distance
Cosine distance
Euclidean distance
Cosine distance
Subject 1
1
1
1
1
1
1
1
Subject 2
1
1
1
1
1
1
1
Subject 3
1
1
1
1
1
1
1
Subject 4
1
1
1
1
1
1
3
Subject 5
1
1
1
1
1
1
1
Subject 6
1
1
1
1
1
1
1
Subject 7
1
1
1
1
1
3
1
Subject 8
1
1
1
1
1
3
1
Subject 9
2
2
1
3
2
1
3
Subject 10
2
2
2
3
2
2
3
Subject 11
2
2
1
2
2
2
2
Subject 12
3
3
3
1
3
3
3
Subject 13
2
2
1
2
1
1
3
Subject 14
2
2
1
2
2
2
2
Subject 15
2
2
2
2
1
2
2
Subject 16
3
3
3
1
3
2
2
Subject 17
2
2
1
3
2
3
1
Subject 18
2
2
1
2
2
3
3
Subject 19
3
3
3
1
3
1
3
value
ā
1
0.69
0.75
0.89
0.6
0.66
Clinical reference classification and DWI-based neural fingerprinting clustering results are shown. For the clinical reference, 1 represents the normal control; 2 represents the group with acute stroke lesion; and 3 represents the group with stroke sequela. For manual, semiautomatic, and automatic ROI methods, different numbers are different clustering labels.