journal article·2026-06Open access

A deep learning enabled in-silico animal study approach for bone tissue engineering

Kai Yao, Penglei Gao, Xiyao Ni, Jia An, Kaizhu Huang, Julia V. Helaehil, Guilherme F. Caetano, Boyang Huang, Jie Sun, Paulo Bartolo

Abstract

Engineered tissue constructs are typically evaluated by extensive animal studies to assess their in vivo efficacy. Histological analysis is the widely used approach. However, this technique is time-consuming and highly dependent on experienced pathologists. Moreover, it provides limited insight into how tissue continuously changes at the same tissue site over time. In this study, we propose a deep learning (DL)-based model, Bone Tissue Prediction Generative Adversarial Network (BTP-GAN), which integrates synthetic histological image generation with a biological tissue growth model to simulate bone tissue development over time. Despite a small training dataset, the generated histological images are biologically meaningful and realistic, owing to three algorithmic modules: the Analysis module, Growth module, and Generation module. Moreover, Ordinary Differential Equations (ODE)-Transformer model can learn the temporal patterns and structural characteristics of real tissue images, enabling the generation of histological images according to various specific generative conditions. The BTP-GAN successfully demonstrates the continuous histological change at the same bone tissue site, relying only on a single input histological image. This in-silico animal study may change the perception of the necessity of extensive animal studies in tissue engineering and provide a practical framework for the future advancement of in-silico tissue engineering.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: 3D Printing in Biomedical Research · Generative Adversarial Networks and Image Synthesis · AI in cancer detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (43)

Show source-provided references
1. Lanza · 2020
2. Histopathological image analysis: a review10.1109/RBME.2009.2034865 ↗
3. Stewart · 2023
4. A review on conventional machine learning vs deep learning
5. Dual attention network for scene segmentation
6. Huang · 2019
7. Non-local neural networks
8. Analyzing and improving the image quality of stylegan
9. Wasserstein generative adversarial networks
10. U-net: convolutional networks for biomedical image segmentation
11. H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes10.1109/TMI.2018.2845918 ↗
12. Unet 3+: a full-scale connected unet for medical image segmentation
13. Understanding robustness of transformers for image classification
14. Intriguing properties of vision transformers
15. Attention is all you need
16. Geirhos · 2018
17. UTNet: a hybrid transformer architecture for medical image segmentation
18. Medical transformer: gated axial-attention for medical image segmentation
19. Generative adversarial networks10.1145/3422622 ↗
20. GANs for biological image synthesis
21. Staingan: stain style transfer for digital histological images
22. Resolution enhancement with a task-assisted GAN to guide optical nanoscopy image analysis and acquisition10.1038/s42256-023-00689-3 ↗
23. Piezoelectric biomaterials for bone regeneration: roadmap from dipole to osteogenesis
24. Recent advances in 3D printing of smart scaffolds for bone tissue engineering and regeneration10.1002/adma.202403641 ↗
25. Fabrication and development of mechanical metamaterials via additive manufacturing for biomedical applications: a review10.1088/2631-7990/ad88e3 ↗
26. Wada · 2022
27. Attention is all you need
28. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions
29. Discrete and continuous models for tissue growth and shrinkage10.1016/j.jtbi.2014.01.041 ↗
30. Generative adversarial networks: an overview10.1109/MSP.2017.2765202 ↗
31. Neural ordinary differential equations
32. A style-based generator architecture for generative adversarial networks
33. The biology of fracture healing10.1016/j.injury.2011.03.031 ↗
34. SegFormer: simple and efficient design for semantic segmentation with transformers
35. Taming transformers for high-resolution image synthesis
36. In vivo study of conductive 3D printed PCL/MWCNTs scaffolds with electrical stimulation for bone tissue engineering10.1007/s42242-020-00116-1 ↗
37. In vivo investigation of polymer-ceramic PCL/HA and PCL/β-TCP 3D composite scaffolds and electrical stimulation for bone regeneration10.3390/polym14010065 ↗
38. Accelerated bone healing via electrical stimulation10.1002/advs.202404190 ↗
39. Effect of electrical stimulation generated by self-powered systems for tissue repair10.1016/j.actbio.2025.05.047 ↗
40. Mechanisms of bone development and repair10.1038/s41580-020-00279-w ↗
41. Bone development10.1016/j.bone.2015.04.035 ↗
42. Pixel super-resolved virtual staining of label-free tissue using diffusion models10.1038/s41467-025-60387-z ↗
43. Using histopathology latent diffusion models as privacy-preserving dataset augmenters improves downstream classification performance10.1016/j.compbiomed.2024.108410 ↗