Hetairos is a histology-based artificial intelligence model for predicting central nervous system tumor methylation subtypes - Summary - MDSpire

Hetairos is a histology-based artificial intelligence model for predicting central nervous system tumor methylation subtypes

  • By

  • Darui Jin

  • Artem Shmatko

  • Areeba Patel

  • Samuel Rutz

  • Lukas Friedrich

  • Rouzbeh Banan

  • Ramin Rahmanzade

  • Philipp Sievers

  • Stefan Hamelmann

  • Daniel Schrimpf

  • Kirsten Göbel

  • Henri Bogumil

  • Sybren L. N. Maas

  • Martin Sill

  • Felix E. Hinz

  • Abigail K. Suwala

  • Felix Keller

  • Antje Habel

  • Gleb Rukhovich

  • Ferdinand Zettl

  • Obada T. Alhalabi

  • Sebastian Ille

  • Jannik Sehring

  • Daniel Amsel

  • Benedikt Wiestler

  • Pedro Piovesan Lago

  • Bogdana Suchorska

  • Olfat Ahmad

  • Dominik Sturm

  • David Reuss

  • Pieter Wesseling

  • Adelheid Wöhrer

  • Frank L. Heppner

  • Ingmar Blümcke

  • Claire Delbridge

  • Martin Jakobs

  • Christel Herold-Mende

  • Sandro M. Krieg

  • Wolfgang Wick

  • David T. W. Jones

  • Stefan M. Pfister

  • Maysa Al-Hussaini

  • Yanghao Hou

  • Felipe D’Almeida Costa

  • Leonille Schweizer

  • Luca Bertero

  • Till Acker

  • Arnault Tauziede-Espariat

  • Pascale Varlet

  • Doron Merkler

  • Kristof Egervari

  • Hildegard Dohmen

  • Pablo Zoroquiain

  • Roger Gejman

  • Sebastian Brandner

  • Xiangzhi Bai

  • Andreas von Deimling

  • Felix Sahm

  • Moritz Gerstung

  • June 10, 2026

  • 0 min

Share

Objective:

To develop and evaluate Hetairos, an AI-based model that classifies whole-slide images of H&E-stained FFPE tissue sections into 102 subtypes of CNS tumors.

Approach:
    Key Findings:
    • Remove the statement about AI-based predictions leading to faster diagnoses.
    • Ensure all findings are directly supported by the source.
    Interpretation:

    Remove unsupported conclusions about the potential of AI.

    Limitations:
    • The model's reliance on high-quality H&E-stained slides may limit its applicability in settings with suboptimal samples.
    • The requirement for substantial computational resources may restrict access to the technology.
    Conclusion:

    Revise to eliminate unsupported claims regarding diagnostic efficiency.

Original Source(s)

Hetairos is a histology-based artificial intelligence model for predicting central nervous system tumor methylation subtypes

  • by Darui Jin, Artem Shmatko, Areeba Patel, Samuel Rutz, Lukas Friedrich, Rouzbeh Banan, Ramin Rahmanzade, Philipp Sievers, Stefan Hamelmann, Daniel Schrimpf, Kirsten Göbel, Henri Bogumil, Sybren L. N. Maas, Martin Sill, Felix E. Hinz, Abigail K. Suwala, Felix Keller, Antje Habel, Gleb Rukhovich, Ferdinand Zettl, Obada T. Alhalabi, Sebastian Ille, Jannik Sehring, Daniel Amsel, Benedikt Wiestler, Pedro Piovesan Lago, Bogdana Suchorska, Olfat Ahmad, Dominik Sturm, David Reuss, Pieter Wesseling, Adelheid Wöhrer, Frank L. Heppner, Ingmar Blümcke, Claire Delbridge, Martin Jakobs, Christel Herold-Mende, Sandro M. Krieg, Wolfgang Wick, David T. W. Jones, Stefan M. Pfister, Maysa Al-Hussaini, Yanghao Hou, Felipe D’Almeida Costa, Leonille Schweizer, Luca Bertero, Till Acker, Arnault Tauziede-Espariat, Pascale Varlet, Doron Merkler, Kristof Egervari, Hildegard Dohmen, Pablo Zoroquiain, Roger Gejman, Sebastian Brandner, Xiangzhi Bai, Andreas von Deimling, Felix Sahm, Moritz Gerstung

  • June 10, 2026

Related Content

Primary cutaneous adenoid cystic carcinoma of the right forearm: a case report and dermoscopic features

Editorial: Innate lymphoid cells in cancer: volume II

Safety and Effectiveness of Direct Oral Anticoagulants Versus Low-Molecular-Weight Heparin for Cancer-Associated Thrombosis: A Systematic Review and Meta-analysis