Back

A Generative AI Framework to Predict Cardiomyocyte Contraction Function from Single Static Images.

Kowalczewski, A.; Wang, C.; Wang, X.; Yang, H.; Qin, Z.; Ma, Z.

2026-04-24 bioengineering
10.64898/2026.04.22.720172 bioRxiv
Show abstract

Understanding how cardiomyocyte structure governs contractile function is fundamental to cardiac biology and disease modeling, yet current approaches rely on time-resolved imaging and computationally intensive analysis. Here, we present a generative artificial intelligence (AI) framework that directly predicts contractile behavior of human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) from single static images. Our approach integrates a U-Net-based generator with a patch-based generative adversarial network (GAN) discriminator to translate morphological and sarcomere structural features into pixel-resolved contraction heatmaps. This U-Net-GAN model achieved high predictive accuracy, with structural similarity index (SSIM) values up to 0.84 using combined morphological and structural inputs. To further enhance performance and generalizability, we incorporated synthetic cell-function pairs generated via a generative AI StyleGAN2 framework, improving prediction accuracy and perceptual similarity. Importantly, region-specific and whole-cell analyses revealed that AI predictions capture biologically meaningful structure-function relationships, with sarcomere organization strongly associated with both contractile output and prediction fidelity. Reconstruction error emerged as an interpretable metric reflecting localized inefficiencies in sarcomere-to-contraction coupling. Together, this framework establishes a scalable and interpretable strategy for inferring cardiomyocyte function from static morphology, eliminating the need for time-lapse imaging. More broadly, this work positions generative AI as a powerful tool for bridging cellular structure and function, enabling high-throughput functional phenotyping and advancing in vitro cardiac modeling.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Advanced Science
249 papers in training set
Top 0.7%
14.0%
2
Nature Biomedical Engineering
42 papers in training set
Top 0.1%
14.0%
3
Nature Methods
336 papers in training set
Top 1.0%
10.2%
4
Nature Medicine
117 papers in training set
Top 0.3%
6.7%
5
Nature Communications
4913 papers in training set
Top 30%
6.2%
50% of probability mass above
6
Nature Machine Intelligence
61 papers in training set
Top 0.6%
4.7%
7
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 21%
3.5%
8
Cell Reports
1338 papers in training set
Top 16%
3.5%
9
Cell Systems
167 papers in training set
Top 5%
2.8%
10
PLOS Computational Biology
1633 papers in training set
Top 12%
2.5%
11
Science Advances
1098 papers in training set
Top 11%
2.5%
12
Science Translational Medicine
111 papers in training set
Top 2%
2.0%
13
IEEE Transactions on Medical Imaging
18 papers in training set
Top 0.2%
2.0%
14
Science
429 papers in training set
Top 13%
1.8%
15
Communications Biology
886 papers in training set
Top 8%
1.7%
16
Scientific Reports
3102 papers in training set
Top 62%
1.5%
17
Cell Reports Medicine
140 papers in training set
Top 6%
1.2%
18
Nature Cell Biology
99 papers in training set
Top 4%
0.9%
19
Cancer Research
116 papers in training set
Top 3%
0.8%
20
ACS Photonics
13 papers in training set
Top 0.5%
0.7%
21
iScience
1063 papers in training set
Top 33%
0.7%
22
eLife
5422 papers in training set
Top 59%
0.7%