Image-based analysis of lymphoma cell heterogeneity: Comparative study of CRYO and FFPE techniques

Aisha Tursynkozha, Amanali Bekbolat, Dana Yerpasheva, Alfarabi Issakhanov, Ardak Kashkynbayev, Ivan Vorobjev · 2026

Read Image-based analysis of lymphoma cell heterogeneity: Comparative study of CRYO and FFPE techniques by Aisha Tursynkozha, Amanali Bekbolat, Dana Yerpasheva, Alfarabi Issakhanov, Ardak Kashkynbayev, Ivan Vorobjev (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-13660656.txt.

Description

Reading lymphoma tissue under a microscope starts with outlining every cell nucleus, a slow manual task that software can speed up. A six-author team tested three deep learning tools on lymphoma sections, then compared two ways of preparing the tissue. One is the classic wax-embedding method; the other is a newer rapid-freeze method meant to preserve samples better.

One tool, DeepLabV3, gave the most exact pixel-level outlines when trained on large marked-up sets. The StarDist tools did better with little training data and traced borders and single nuclei more faithfully. Overall, the frozen samples segmented about as well as the classic ones, with small differences that changed direction by tool. The authors conclude that both preparation routes suit computer-based pathology work, which widens the options for labs adopting the newer freezing method.

Catalog record

CREATORAisha Tursynkozha, Amanali Bekbolat, Dana Yerpasheva, Alfarabi Issakhanov, Ardak Kashkynbayev, Ivan Vorobjev
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13660656

Browse the full library · About the Tower of Babel