An innovative methodology for segmenting vessel like structures using artificial intelligence and image processing
Reynaldo Villarreal, Sindy Chamorro-Solano, Steffen Cantillo, Roberto Pestana-Nobles, Sair Arquez, Yolanda Vega-Sampayo, Leonardo Pacheco-Londoño, Jheifer Paez, Nataly Galan-Freyle, Cristian Ayala, Paola Amar · 2024
Read An innovative methodology for segmenting vessel like structures using artificial intelligence and image processing by Reynaldo Villarreal, Sindy Chamorro-Solano, Steffen Cantillo, Roberto Pestana-Nobles, Sair Arquez, Yolanda Vega-Sampayo, Leonardo Pacheco-Londoño, Jheifer Paez, Nataly Galan-Freyle, Cristian Ayala, Paola Amar (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11621118.txt.
Description
Reynaldo Villarreal and ten co-authors published a 2024 methods paper on teaching computers to trace thin vessel like structures in images. Capillary networks matter in eye scans, plant leaves, and even circuit boards, but their fine, branching shapes vary enough to defeat simple image rules.
The authors assembled a pipeline from three parts: a super resolution module that sharpens images, a U-Net style segmentation network, and a thresholding step that turns soft predictions into clean masks. The system was trained and tested on three very different datasets, eye fundus photos, citrus leaves, and printed circuit boards. In each case it had to pick out the filament network at pixel level. The authors report strong tracing performance across all three, arguing the recipe generalizes beyond medicine.
Catalog record
| CREATOR | Reynaldo Villarreal, Sindy Chamorro-Solano, Steffen Cantillo, Roberto Pestana-Nobles, Sair Arquez, Yolanda Vega-Sampayo, Leonardo Pacheco-Londoño, Jheifer Paez, Nataly Galan-Freyle, Cristian Ayala, Paola Amar |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |