Scholarlink

<p>Accurate morphological classification of blood leukocytes remains a cornerstone of hematological diagnostics but still relies on manual expertise, leading to variability across laboratories. The CytologIA data challenge was organized to benchmark artificial intelligence (AI) models for automated classification of normal and pathological leukocytes from peripheral blood smears. Twenty hematology laboratories from France, Belgium, and Switzerland contributed to a multicentric, expert-annotated database of 69,168 images encompassing 23 leukocyte classes. A total of 245 teams from academia, hospitals, and industry participated in the challenge. The top-performing model—combining a YOLOX-based detection module with an ensemble of transformer and convolutional classifiers—achieved a balanced accuracy of 0.94 on the hidden test set, markedly outperforming the baseline CNN (0.82). While abundant cell types such as neutrophils were identified with near-perfect accuracy (&gt;0.97), rarer and morphologically overlapping categories remained challenging. All data and models were released openly on data.gouv.fr and GitHub to ensure full reproducibility. CytologIA represents the first large-scale, open, and collaborative AI benchmark in hematological morphology, establishing a new reference for the development of robust, transferable diagnostic algorithms across institutions</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multicentric data challenge for artificial intelligence-based classification of leukocytes: results from the CytologIA consortium

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月15日

查看全文
  • Elise Sourdeau,
  • Franck Geneviève,
  • Lucile Baseggio,
  • Bouchra Badaoui,
  • Charles Chevalier,
  • Mélanie Pannetier,
  • Alexandre Janel,
  • Ahmadreza Arbab,
  • Laurent Weinmann,
  • Camille Debord,
  • Patrick Cohen,
  • Agathe Maillon,
  • Sandrine Girard,
  • Frédérique Dubois,
  • Véronique Baccini,
  • Pierre Lemaire,
  • Yaël Berda-Haddad,
  • Thomas Tassin,
  • Anne-Camille Faure,
  • Soufiane Azdad,
  • Samy Dahmani,
  • Lauriane Armand,
  • Agathe Delaune,
  • Naama Bak,
  • Paul Steffen,
  • Eric Ben Hamou,
  • Valérie Bardet,
  • Thomas Boyer

摘要

Accurate morphological classification of blood leukocytes remains a cornerstone of hematological diagnostics but still relies on manual expertise, leading to variability across laboratories. The CytologIA data challenge was organized to benchmark artificial intelligence (AI) models for automated classification of normal and pathological leukocytes from peripheral blood smears. Twenty hematology laboratories from France, Belgium, and Switzerland contributed to a multicentric, expert-annotated database of 69,168 images encompassing 23 leukocyte classes. A total of 245 teams from academia, hospitals, and industry participated in the challenge. The top-performing model—combining a YOLOX-based detection module with an ensemble of transformer and convolutional classifiers—achieved a balanced accuracy of 0.94 on the hidden test set, markedly outperforming the baseline CNN (0.82). While abundant cell types such as neutrophils were identified with near-perfect accuracy (>0.97), rarer and morphologically overlapping categories remained challenging. All data and models were released openly on data.gouv.fr and GitHub to ensure full reproducibility. CytologIA represents the first large-scale, open, and collaborative AI benchmark in hematological morphology, establishing a new reference for the development of robust, transferable diagnostic algorithms across institutions