EUVIMEDEUVIMED entdecken
Crossref

Extraction of Novel Features and Diagnosis Prediction in Myelodysplastic Neoplasm Using a Weakly Supervised Artificial Intelligence Model Based on Normal Megakaryocytes

Sosuke Ishijima iD, Ethan N Okoshi iD, Makoto Kawamoto, Ryuta Matsuda iD, Takuma Odate, Kamran M Mirza iD, Junya Fukuoka iD

Pathology International · 2025

DOI: 10.1111/pin.70049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pathology International, 2025. Verfasst von Sosuke Ishijima und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology Informatics, Graduate School of Biomedical Sciences, Nagasaki University, Nagasaki, Japan. Hauptthemen laut MEDLINE: Myelodysplastic Syndromes, Megakaryocytes, Artificial Intelligence, Supervised Machine Learning. Die Arbeit nennt 24 Literaturangaben. Gefördert von: The authors received no specific funding for this work..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Evaluation of bone marrow pathology can be challenging for nonspecialist pathologists due to its morphological complexities. Despite advances in artificial intelligence for other organ systems, research in bone marrow biopsy field remains limited. This study presents an artificial intelligence model developed to classify myeloid diseases based on morphologically normal megakaryocytes in hematoxylin‐eosin‐stained bone marrow biopsy specimens. The model integrates two deep learning components: one for detecting bone marrow regions, and the other for identifying megakaryocytes, along with an XGBoost‐based classifier that leverages extracted features to differentiate between normal cases, myelodysplastic neoplasm, and immune thrombocytopenic purpura. The model achieved exceptional accuracy, with area under the curve values of 0.9996 (bone marrow detection) and 0.9997 (megakaryocyte detection). For disease classification, myelodysplastic neoplasm versus normal performed well, with an area under the curve of 0.879. Feature analysis revealed that the percentage of megakaryocyte among all cells and the number of adjacent megakaryocytes within various distances were significantly correlated with disease prediction. This study introduces the first artificial intelligence model capable of classifying myelodysplastic neoplasm versus normal based on normal megakaryocyte morphology. This model demonstrates potential not only for diagnostic assistance but also for uncovering novel histological features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Myelodysplastic SyndromesMegakaryocytesArtificial IntelligenceSupervised Machine LearningHumansBone MarrowPurpura, Thrombocytopenic, IdiopathicMaleDeep LearningFemale

Stichwörter der Autor:innen

artificial intelligencebone marrowdeep learningimmune thrombocytopenic purpuramegakaryocytemyelodysplastic neoplasm

Autor:innen und Institutionen

  • Department of Pathology Informatics, Graduate School of Biomedical Sciences, Nagasaki University, Nagasaki, Japan.
  • Department of Pathology, Kameda Medical Center, Chiba, Japan.
  • Department of Clinical Laboratory, Kameda Medical Center, Chiba, Japan.
  • Department of Pathology and Clinical Laboratories, Michigan Medicine, Ann Arbor, Michigan, USA.

ORCID-Profile: Sosuke Ishijima, Ethan N Okoshi, Ryuta Matsuda, Kamran M Mirza, Junya Fukuoka

Förderung

  • The authors received no specific funding for this work.

Zitieren

APA

Ishijima, S., Okoshi, E. N., Kawamoto, M., Matsuda, R., Odate, T., Mirza, K. M., & Fukuoka, J. (2025). Extraction of Novel Features and Diagnosis Prediction in Myelodysplastic Neoplasm Using a Weakly Supervised Artificial Intelligence Model Based on Normal Megakaryocytes. Pathology International. https://doi.org/10.1111/pin.70049

Vancouver

Ishijima S, Okoshi EN, Kawamoto M, Matsuda R, Odate T, Mirza KM, et al. Extraction of Novel Features and Diagnosis Prediction in Myelodysplastic Neoplasm Using a Weakly Supervised Artificial Intelligence Model Based on Normal Megakaryocytes. Pathology International. 2025. doi:10.1111/pin.70049

BibTeX
@article{Ishijima2025,
  author = {Ishijima, Sosuke and Okoshi, Ethan N and Kawamoto, Makoto and Matsuda, Ryuta and Odate, Takuma and Mirza, Kamran M and Fukuoka, Junya},
  title = {Extraction of Novel Features and Diagnosis Prediction in Myelodysplastic Neoplasm Using a Weakly Supervised Artificial Intelligence Model Based on Normal Megakaryocytes},
  journal = {Pathology International},
  year = {2025},
  doi = {10.1111/pin.70049}
}
Kostenlos starten →