Generalizability of a biopsy-trained artificial intelligence algorithm to TURP and HoLEP specimens for detection of incidental prostate adenocarcinoma

Neşe Yeldir, Burak Uzel, Elif Nur Tekin, Gizem Solmaz Yılmaz, Eren Tekin, Sercan Çayır, İbrahim Serdar Coşkun, Bahar Müezzinoğlu · 2026

Read Generalizability of a biopsy-trained artificial intelligence algorithm to TURP and HoLEP specimens for detection of incidental prostate adenocarcinoma by Neşe Yeldir, Burak Uzel, Elif Nur Tekin, Gizem Solmaz Yılmaz, Eren Tekin, Sercan Çayır, İbrahim Serdar Coşkun, Bahar Müezzinoğlu (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/pmc-13625242.txt.

Description

An AI tool trained to spot prostate cancer on needle biopsies may stumble on tissue taken in other operations. Neşe Yeldir and co-authors tested that transfer on surgery samples from enlarged prostate care. They ran the tool over three thousand two hundred forty-one slide images from three hundred sixty-eight patients. Two operations were covered: shaving the prostate and laser removal of its core. Standard microscope diagnosis served as the truth.

Thirty-five cases held cancer, and the tool caught nearly all of them. The study reports accuracy scores at the case level, plus how flagged slide counts relate to cancer rates. Proving a biopsy tool on surgical tissue could widen its safe use. The authors frame the work as a generalizability check, not a launch.

Catalog record

CREATORNeşe Yeldir, Burak Uzel, Elif Nur Tekin, Gizem Solmaz Yılmaz, Eren Tekin, Sercan Çayır, İbrahim Serdar Coşkun, Bahar Müezzinoğlu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE28 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13625242

Browse the full library · About the Tower of Babel