Back

AI-based radiomics for pancreatic cysts: high diagnostic performance amid a persistent translational gap

2026-02-12 radiology and imaging Title + abstract only
View on medRxiv
Show abstract

BackgroundAI-based radiomics has demonstrated promising diagnostic performance for pancreatic cystic neoplasms, yet clinical translation remains limited. Whether this reflects insufficient model performance or structural limitations of the evidence base remains unclear. MethodsWe performed a systematic review and diagnostic test accuracy meta-analysis of AI-based radiomics in pancreatic cyst (2015-2025), addressing two clinically relevant tasks (Q1: cyst type differentiation/Q2: malignancy or h...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 1% 23.4%
2
PLOS ONE
1737 training papers
Top 60% 9.5%
3
Nature Communications
483 training papers
Top 16% 6.3%
4
PLOS Digital Health
88 training papers
Top 6% 4.1%
5
BMJ Open
553 training papers
Top 38% 4.1%
6
eLife
262 training papers
Top 11% 4.1%
7
Diagnostics
36 training papers
Top 0.7% 2.2%
8
npj Digital Medicine
85 training papers
Top 9% 2.0%
9
Cancers
57 training papers
Top 5% 2.0%
10
BMC Cancer
21 training papers
Top 4% 1.4%
11
Journal of Clinical Medicine
77 training papers
Top 13% 1.4%
12
Frontiers in Medicine
99 training papers
Top 13% 1.4%
13
Frontiers in Oncology
34 training papers
Top 5% 1.4%
14
BMC Medicine
155 training papers
Top 19% 1.4%
15
eBioMedicine
82 training papers
Top 6% 1.2%
16
Gut
17 training papers
Top 2% 1.0%
17
Computers in Biology and Medicine
39 training papers
Top 8% 1.0%
18
Human Brain Mapping
53 training papers
Top 8% 1.0%
19
Frontiers in Genetics
32 training papers
Top 6% 1.0%
20
PLOS Computational Biology
141 training papers
Top 11% 1.0%
21
NeuroImage
36 training papers
Top 5% 1.0%
22
Imaging Neuroscience
18 training papers
Top 2% 1.0%
23
Scientific Data
30 training papers
Top 4% 0.8%
24
Clinical Cancer Research
22 training papers
Top 4% 0.8%
25
PLOS Global Public Health
287 training papers
Top 33% 0.8%
26
NeuroImage: Clinical
77 training papers
Top 12% 0.8%
27
Cureus
64 training papers
Top 27% 0.5%