A deep learning framework for histopathological analysis of pixel-level extracellular matrix variation in standard H&E-stained images
Merlijn van Breugel, Esmée de Jong, Henk J Buikema, Ilya Petoukhov, Martijn C Nawijn, Janette K Burgess, Wim Timens · 2026
Read A deep learning framework for histopathological analysis of pixel-level extracellular matrix variation in standard H&E-stained images by Merlijn van Breugel, Esmée de Jong, Henk J Buikema, Ilya Petoukhov, Martijn C Nawijn, Janette K Burgess, Wim Timens (2026) 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/PMC13562512.txt.
Description
Merlijn van Breugel and six colleagues teach a deep learning model to read the fine pixel patterns of the material between cells in tissue slides. Most image tools target cells or whole structures, leaving the extracellular matrix, the woven scaffold of connective tissue, largely ignored. Human eyes can barely tell two airway wall layers apart in standard pink-and-purple stained slides. The 2026 method steers the model toward those cell-free zones and blanks out cells at random so they cannot mislead it.
Trained this way, the model separated the two airway layers with a test score of 0.84 on the standard curve measure. The team then applied the approach to lung tissue from people with chronic obstructive pulmonary disease as a proof of principle. Differences across patients became measurable quantities. The authors offer the pipeline as a reusable way to study tissue scaffolds that routine microscopy overlooks.
Catalog record
| CREATOR | Merlijn van Breugel, Esmée de Jong, Henk J Buikema, Ilya Petoukhov, Martijn C Nawijn, Janette K Burgess, Wim Timens |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62356 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |