Back
#1
22.7%
Top 0.1%
18.1%
Top 20%
9.2%
Top 0.4%
6.6%
Top 4%
5.1%
Top 81%
5.1%
Top 0.4%
4.0%
Top 31%
3.1%
Top 0.8%
2.0%
Top 5%
1.6%
Top 10%
1.4%
Top 4%
1.2%
Top 1%
0.7%
Top 5%
0.7%
Top 6%
0.7%
Top 54%
0.7%
Top 19%
0.7%
Top 10%
0.7%
Top 5%
0.7%
Pipeline Evaluation of a State-of-the-Art AI Algorithm for Detection of Focal Cortical Dysplasia: Insights into Potential Failure Sources
2026-01-15
radiology and imaging
Title + abstract only
View on medRxiv
Show abstract
PurposeMELD Graph is a state-of-the-art artificial intelligence (AI) model for automated detection of focal cortical dysplasia (FCD), but its performance remains limited, highlighting the need to investigate which aspects of the pipeline affect its accuracy. MethodsA retrospective failure-mode analysis of the MELD Graph pipeline was performed in 242 subjects, with model predictions and FreeSurfer segmentations reviewed to classify errors as segmentation-associated or algorithm-related. FCD imag...
Predicted journal destinations
1
Human Brain Mapping
53 training papers
2
NeuroImage: Clinical
77 training papers
3
Scientific Reports
701 training papers
4
NeuroImage
36 training papers
5
Brain Communications
79 training papers
6
PLOS ONE
1737 training papers
7
Imaging Neuroscience
18 training papers
8
Nature Communications
483 training papers
9
Scientific Data
30 training papers
10
Annals of Neurology
43 training papers
11
Frontiers in Neurology
74 training papers
12
Alzheimer's Research & Therapy
31 training papers
13
Cerebral Cortex
15 training papers
14
Epilepsia
27 training papers
15
Frontiers in Neuroscience
29 training papers
16
eLife
262 training papers
17
PLOS Digital Health
88 training papers
18
Computers in Biology and Medicine
39 training papers
19
Biological Psychiatry Global Open Science
23 training papers