Back

Unambiguous signatures of malignancies extracted from images of growing cells

2026-01-13 oncology Title + abstract only
View on medRxiv
Show abstract

As malignant transformation arises from dysregulated cellular programming with characteristic morphological changes, we hypothesized that cancer cells exhibit a unique morphological signature detectable in microscopy images of cells in vitro and in situ across modalities. To test this, we developed CellSign, an AI-based framework to generate Cell Dynamics Fingerprints, which (a) reconstruct morphological progression, (b) remove physiological variation, and (c) support automated malignancy assess...

Predicted journal destinations

1
Nature Communications
483 training papers
Top 0.4% 24.9%
2
Scientific Reports
701 training papers
Top 7% 16.4%
3
PLOS Computational Biology
141 training papers
Top 1% 8.7%
4
Proceedings of the National Academy of Sciences
100 training papers
Top 0.5% 6.7%
5
PLOS Digital Health
88 training papers
Top 5% 5.6%
6
eLife
262 training papers
Top 6% 5.6%
7
PLOS ONE
1737 training papers
Top 84% 4.3%
8
Cancers
57 training papers
Top 5% 2.2%
9
Frontiers in Oncology
34 training papers
Top 4% 2.2%
10
Clinical Cancer Research
22 training papers
Top 3% 2.2%
11
iScience
74 training papers
Top 7% 1.3%
12
Cancer Medicine
17 training papers
Top 4% 1.1%
13
Communications Medicine
63 training papers
Top 4% 1.1%
14
Computers in Biology and Medicine
39 training papers
Top 7% 1.1%
15
Cell Reports
25 training papers
Top 2% 0.8%
16
British Journal of Cancer
22 training papers
Top 5% 0.8%
17
Nature Genetics
72 training papers
Top 10% 0.8%
18
Nature
58 training papers
Top 9% 0.8%
19
Communications Biology
36 training papers
Top 4% 0.8%
20
npj Digital Medicine
85 training papers
Top 19% 0.8%
21
International Journal of Molecular Sciences
39 training papers
Top 9% 0.5%
22
Cell Reports Medicine
49 training papers
Top 9% 0.5%
23
PeerJ
46 training papers
Top 12% 0.5%
24
Nature Medicine
88 training papers
Top 24% 0.5%
25
Brain Communications
79 training papers
Top 10% 0.5%
26
JAMA Network Open
125 training papers
Top 38% 0.5%
27
BMC Cancer
21 training papers
Top 7% 0.5%