Object detection in histology: A multi-dataset benchmark and test-time inference
Dragoș-Vasile Leordean, Eugen-Richard Ardelean · 2026
Read Object detection in histology: A multi-dataset benchmark and test-time inference by Dragoș-Vasile Leordean, Eugen-Richard Ardelean (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/plos-pone-0354618.txt.
Description
Dragoș-Vasile Leordean and Eugen-Richard Ardelean published this 2026 benchmark study of artificial intelligence that finds objects in microscope images of tissue. They ran the newest YOLO detector family against several rival architectures on five histology data sets, using shared training rules and measuring accuracy, speed, and computing cost.
One mid-generation model, YOLOv11, performed strongly across most collections. The authors also add a rescoring trick that spreads confident labels to neighboring boxes, lifting results most when the base model's confidence is poorly calibrated. Their comparison aims to guide labs choosing detection software.
Catalog record
| CREATOR | Dragoș-Vasile Leordean, Eugen-Richard Ardelean |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70518 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |