EUVIMEDEUVIMED entdecken
Crossref

Automatic classification and segmentation of blast cells using deep transfer learning and active contours

Divine Senanu Ametefe iD, Suzi Seroja Sarnin, Darmawaty Mohd Ali, George Dzorgbenya Ametefe, Dah John, Abdulmalik Adozuka Aliu, Zadok Zoreno

International Journal of Laboratory Hematology · 2024

DOI: 10.1111/ijlh.14305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Laboratory Hematology, 2024. Verfasst von Divine Senanu Ametefe und 6 weiteren Autor:innen. Beteiligte Einrichtung: Wireless Communication Technology Group, College of Engineering, School of Electrical Engineering, Universiti Teknologi MARA (UiTM), Shah Alam, Malay…. Hauptthemen laut MEDLINE: Deep Learning, Precursor Cell Lymphoblastic Leukemia-Lymphoma. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Acute lymphoblastic leukemia (ALL) presents a formidable challenge in hematological malignancies, necessitating swift and precise diagnostic techniques for effective intervention. The conventional manual microscopy of blood smears, although widely practiced, suffers from significant limitations including labor‐intensity and susceptibility to human error, particularly in distinguishing the subtle differences between normal and leukemic cells.

Methods

To overcome these limitations, our research introduces the ALLDet classifier, an innovative tool employing deep transfer learning for the automated analysis and categorization of ALL from White Blood Cell (WBC) nuclei images. Our investigation encompassed the evaluation of nine state‐of‐the‐art pre‐trained convolutional neural network (CNN) models, namely VGG16, VGG19, ResNet50, ResNet101, DenseNet121, DenseNet201, Xception, MobileNet, and EfficientNetB3. We augmented this approach by incorporating a sophisticated contour‐based segmentation technique, derived from the Chan‐Vese model, aimed at the meticulous segmentation of blast cell nuclei in blood smear images, thereby enhancing the accuracy of our analysis.

Results

The empirical assessment of these methodologies underscored the superior performance of the EfficientNetB3 model, which demonstrated exceptional metrics: a recall specificity of 98.5%, precision of 95.86%, F1‐score of 97.16%, and an overall accuracy rate of 97.13%. The Chan‐Vese model's adaptability to the irregular shapes of blast cells and its noise‐resistant segmentation capability were key to capturing the complex morphological changes essential for accurate segmentation.

Conclusion

The combined application of the ALLDet classifier, powered by EfficientNetB3, with our advanced segmentation approach, emerges as a formidable advancement in the early detection and accurate diagnosis of ALL. This breakthrough not only signifies a pivotal leap in leukemia diagnostic methodologies but also holds the promise of significantly elevating the standards of patient care through the provision of timely and precise diagnoses. The implications of this study extend beyond immediate clinical utility, paving the way for future research to further refine and enhance the capabilities of artificial intelligence in medical diagnostics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPrecursor Cell Lymphoblastic Leukemia-LymphomaHumansImage Processing, Computer-AssistedNeural Networks, ComputerLeukocytes

Stichwörter der Autor:innen

Chan‐Vese modelactive contoursacute lymphoblastic leukaemia (ALL)blast celldeep transfer learning

Autor:innen und Institutionen

  • Wireless Communication Technology Group, College of Engineering, School of Electrical Engineering, Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia.
  • Department of Biotechnology, College of Science, Engineering and Technology, Osun State University, Osogbo, Nigeria.
  • College of Computing, Informatics and Mathematics, Universiti Teknologi MARA (UiTM), Puncak Perdana, Malaysia.
  • College of Built Environment, Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia.
  • Faculty of Pharmaceutical Sciences, University of Jos, Jos, Nigeria.

ORCID-Profile: Divine Senanu Ametefe

Zitieren

APA

Ametefe, D. S., Sarnin, S. S., Ali, D. M., Ametefe, G. D., John, D., Aliu, A. A., & Zoreno, Z. (2024). Automatic classification and segmentation of blast cells using deep transfer learning and active contours. International Journal of Laboratory Hematology. https://doi.org/10.1111/ijlh.14305

Vancouver

Ametefe DS, Sarnin SS, Ali DM, Ametefe GD, John D, Aliu AA, et al. Automatic classification and segmentation of blast cells using deep transfer learning and active contours. International Journal of Laboratory Hematology. 2024. doi:10.1111/ijlh.14305

BibTeX
@article{Ametefe2024,
  author = {Ametefe, Divine Senanu and Sarnin, Suzi Seroja and Ali, Darmawaty Mohd and Ametefe, George Dzorgbenya and John, Dah and Aliu, Abdulmalik Adozuka and Zoreno, Zadok},
  title = {Automatic classification and segmentation of blast cells using deep transfer learning and active contours},
  journal = {International Journal of Laboratory Hematology},
  year = {2024},
  doi = {10.1111/ijlh.14305}
}
Kostenlos starten →