Unsupervised machine learning to analyze corneal tissue surfaces
Identifying/classifying damage features on soft materials, such as tissues, is much more challenging than on classical, hard materials—but nevertheless important, especially in the field of bio-tribology. For instance, cartilage samples from osteoarthritic patients exhibit surface damage even at ear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-12-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0159502 |
| _version_ | 1797366990091845632 |
|---|---|
| author | Carolin A. Rickert Fabio Henkel Oliver Lieleg |
| author_facet | Carolin A. Rickert Fabio Henkel Oliver Lieleg |
| author_sort | Carolin A. Rickert |
| collection | DOAJ |
| description | Identifying/classifying damage features on soft materials, such as tissues, is much more challenging than on classical, hard materials—but nevertheless important, especially in the field of bio-tribology. For instance, cartilage samples from osteoarthritic patients exhibit surface damage even at early stages of tissue degeneration, and corneal tissues can be damaged by contact lenses when the ocular lubrication system fails. Here, we employ unsupervised machine learning (ML) methods to assess the surface condition of a soft tissue by detecting and classifying different wear morphologies as well as the severity of surface damage they represent. We show that different clustering methods, especially a k-means clustering algorithm, can indeed achieve a—from a material science point of view—meaningful classification of those tissue samples. Our study pinpoints the ability of unsupervised ML models to guide or even replace human decision processes for the analysis of complex surfaces and topographical datasets that—either owing to their complexity or the sample size—exceed the capability of the human brain. |
| first_indexed | 2024-03-08T17:11:27Z |
| format | Article |
| id | doaj.art-07b74463cf5e490ebe4254a569dd5050 |
| institution | Directory Open Access Journal |
| issn | 2770-9019 |
| language | English |
| last_indexed | 2024-03-08T17:11:27Z |
| publishDate | 2023-12-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj.art-07b74463cf5e490ebe4254a569dd50502024-01-03T19:54:29ZengAIP Publishing LLCAPL Machine Learning2770-90192023-12-0114046107046107-1210.1063/5.0159502Unsupervised machine learning to analyze corneal tissue surfacesCarolin A. Rickert0Fabio Henkel1Oliver Lieleg2School of Engineering and Design, Department of Materials Engineering, Technical University of Munich, Boltzmannstraße 15, 85748 Garching, GermanySchool of Engineering and Design, Department of Materials Engineering, Technical University of Munich, Boltzmannstraße 15, 85748 Garching, GermanySchool of Engineering and Design, Department of Materials Engineering, Technical University of Munich, Boltzmannstraße 15, 85748 Garching, GermanyIdentifying/classifying damage features on soft materials, such as tissues, is much more challenging than on classical, hard materials—but nevertheless important, especially in the field of bio-tribology. For instance, cartilage samples from osteoarthritic patients exhibit surface damage even at early stages of tissue degeneration, and corneal tissues can be damaged by contact lenses when the ocular lubrication system fails. Here, we employ unsupervised machine learning (ML) methods to assess the surface condition of a soft tissue by detecting and classifying different wear morphologies as well as the severity of surface damage they represent. We show that different clustering methods, especially a k-means clustering algorithm, can indeed achieve a—from a material science point of view—meaningful classification of those tissue samples. Our study pinpoints the ability of unsupervised ML models to guide or even replace human decision processes for the analysis of complex surfaces and topographical datasets that—either owing to their complexity or the sample size—exceed the capability of the human brain.http://dx.doi.org/10.1063/5.0159502 |
| spellingShingle | Carolin A. Rickert Fabio Henkel Oliver Lieleg Unsupervised machine learning to analyze corneal tissue surfaces APL Machine Learning |
| title | Unsupervised machine learning to analyze corneal tissue surfaces |
| title_full | Unsupervised machine learning to analyze corneal tissue surfaces |
| title_fullStr | Unsupervised machine learning to analyze corneal tissue surfaces |
| title_full_unstemmed | Unsupervised machine learning to analyze corneal tissue surfaces |
| title_short | Unsupervised machine learning to analyze corneal tissue surfaces |
| title_sort | unsupervised machine learning to analyze corneal tissue surfaces |
| url | http://dx.doi.org/10.1063/5.0159502 |
| work_keys_str_mv | AT carolinarickert unsupervisedmachinelearningtoanalyzecornealtissuesurfaces AT fabiohenkel unsupervisedmachinelearningtoanalyzecornealtissuesurfaces AT oliverlieleg unsupervisedmachinelearningtoanalyzecornealtissuesurfaces |