Quantitative Analysis of Distinct Colon Crypt Branching Modes Using Interpretable Machine Learning
We present a machine learning model capable of distinguishing both modes of crypt branching patterns. Furthermore, using a hand-crafted feature approach allowed us to directly interpret the classification criteria of our algorithm, rendering it more transparent and interpretable than black box classification models.
Authors
- Michael Vieth (ORCID: https://orcid.org/0000-0002-4336-7721)
- Daniel Firmbach
- Nic G. Reitsam (ORCID: https://orcid.org/0000-0002-0070-3158)
- Christian Matek (ORCID: https://orcid.org/0000-0001-8528-8581)
- Bianca Grosser (ORCID: https://orcid.org/0000-0003-4957-4876)
- Corinna Lang‐Schwarz (ORCID: https://orcid.org/0000-0001-8631-2600)
- Markus Eckstein (ORCID: https://orcid.org/0000-0001-5418-3349)
- Carlos A. Rubio (ORCID: https://orcid.org/0000-0003-3879-5729)
- Arndt Hartmann
Institutions
- Karolinska University Hospital (SE)
- University of Augsburg (DE)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- University Hospital Augsburg (DE)
- Bayreuth Medical Center (DE)
- Universitätsklinikum Erlangen (DE)
- Comprehensive Cancer Center Erlangen (DE)
- Technical University of Munich (DE)
Publication Details
- Journal
- Inflammatory Bowel Diseases
- Published
- 2025-09-22
- DOI
- https://doi.org/10.1093/ibd/izaf230
- Citations
- 2
- Primary Topic
- Cryptographic Implementations and Security
- Type
- article
- Field-Weighted Citation Impact
- 4.96