Back
Top 3%
18.8%
Top 35%
18.8%
Top 2%
8.3%
Top 0.2%
6.8%
Top 26%
4.1%
Top 7%
3.4%
Top 2%
3.2%
Top 4%
2.1%
Top 1%
2.1%
Top 1.0%
2.1%
Top 0.6%
2.1%
Top 27%
1.6%
Top 5%
1.6%
Top 3%
1.6%
Top 7%
1.6%
Top 1%
1.4%
Top 13%
1.4%
Top 0.1%
1.4%
Top 18%
1.0%
Top 5%
1.0%
Top 66%
0.8%
Top 13%
0.8%
Top 8%
0.8%
Quality versus quantity of training datasets for artificial intelligence-based whole liver segmentation
2026-02-18
radiology and imaging
Title + abstract only
View on medRxiv
Show abstract
Artificial intelligence (AI) based segmentation has many medical applications but limited curated datasets challenge model training; this study compares the impact of dataset annotation quality and quantity on whole liver AI segmentation performance. We obtained 3,089 abdominal computed tomography scans with whole-liver contours from MD Anderson Cancer Center (MDA) and a MICCAI challenge. A total of 249 scans were withheld for testing of which 30, MICCAI challenge data, were reserved for externa...
Predicted journal destinations
1
Scientific Reports
701 training papers
2
PLOS ONE
1737 training papers
3
PLOS Digital Health
88 training papers
4
Computers in Biology and Medicine
39 training papers
5
Nature Communications
483 training papers
6
npj Digital Medicine
85 training papers
7
NeuroImage
36 training papers
8
Human Brain Mapping
53 training papers
9
Heliyon
57 training papers
10
Diagnostics
36 training papers
11
Scientific Data
30 training papers
12
eLife
262 training papers
13
Journal of the American Medical Informatics Association
53 training papers
14
eBioMedicine
82 training papers
15
NeuroImage: Clinical
77 training papers
16
Imaging Neuroscience
18 training papers
17
Frontiers in Medicine
99 training papers
18
Archives of Clinical and Biomedical Research
18 training papers
19
Journal of Clinical Medicine
77 training papers
20
Frontiers in Oncology
34 training papers
21
BMJ Open
553 training papers
22
PLOS Computational Biology
141 training papers
23
Cancers
57 training papers