Rethinking pathology image analysis through shuffling

Zeyu Liu, Tianyi Zhang, Brian K Chen, Youdan Feng, Shangqing Lyu, Yanli Lei, Nan Ying, Yunlu Feng, Yu Zhao, Peng Zhang, Fan Song, Chenbin Ma, Yufang He, Kenji Kawaguchi, Hwee Kuan Lee, Yueming Jin, Guanglei Zhang · 2026

Read Rethinking pathology image analysis through shuffling by Zeyu Liu, Tianyi Zhang, Brian K Chen, Youdan Feng, Shangqing Lyu, Yanli Lei, Nan Ying, Yunlu Feng, Yu Zhao, Peng Zhang, Fan Song, Chenbin Ma, Yufang He, Kenji Kawaguchi, Hwee Kuan Lee, Yueming Jin, Guanglei Zhang (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/PMC13421454.txt.

Description

Zeyu Liu leads a seventeen-author team proposing, in a 2026 paper, a new training principle for artificial intelligence that reads pathology slides. Cancer diagnosis by microscope remains the gold standard, yet algorithms struggle with tumour patterns that vary across patients, tissues and magnifications.

Their framework, called PASS, works with pathoentities — cells, glands and tissue structures — and deliberately shuffles them within and between samples during training. The shuffling forces the network to learn how parts relate, locally and across a whole slide. Theory supports the approach, and tests on ten datasets covering eight diseases and nine organs showed consistent gains. A rapid on-site evaluation trial in gastroenterology hints at clinical use.

Catalog record

CREATORZeyu Liu, Tianyi Zhang, Brian K Chen, Youdan Feng, Shangqing Lyu, Yanli Lei, Nan Ying, Yunlu Feng, Yu Zhao, Peng Zhang, Fan Song, Chenbin Ma, Yufang He, Kenji Kawaguchi, Hwee Kuan Lee, Yueming Jin, Guanglei Zhang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE101 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13421454

Browse the full library · About the Tower of Babel