Differentiating malignancy from liver parenchyma in Ex-Vivo OCT images using anomaly detection
Ulrich Krispel, Alexander Pamler, Caroline Girmen, Niels König, Robert Schmitt, Eva Eggeling, Sören Büsker, Oliver Beetz, Felix Oldhafer, Daniel Truhn, Florian W. R. Vondran, Iakovos Amygdalos · 2026
Read Differentiating malignancy from liver parenchyma in Ex-Vivo OCT images using anomaly detection by Ulrich Krispel, Alexander Pamler, Caroline Girmen, Niels König, Robert Schmitt, Eva Eggeling, Sören Büsker, Oliver Beetz, Felix Oldhafer, Daniel Truhn, Florian W. R. Vondran, Iakovos Amygdalos (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/PMC13254120.txt.
Description
Ulrich Krispel and co-authors test a scan method to spot liver cancer in a 2026 study. Optical coherence tomography, a light-based scan, was paired with anomaly detection, a method trained only on normal tissue. The data set held 173 images from 69 patients having liver surgery, covering three cancer types and healthy liver.
A pre-trained Vision Transformer model reached 80 percent sensitivity and 78 percent specificity, with 79 percent accuracy overall. The aim is faster checks during surgery than frozen section tests now used. The authors note the data set was small and noisy, but call the approach promising.
Catalog record
| CREATOR | Ulrich Krispel, Alexander Pamler, Caroline Girmen, Niels König, Robert Schmitt, Eva Eggeling, Sören Büsker, Oliver Beetz, Felix Oldhafer, Daniel Truhn, Florian W. R. Vondran, Iakovos Amygdalos |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57521 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |