EUVIMEDEUVIMED entdecken
Crossref

AI Based Bone Marrow Disorder Prediction Using Deep Learning

Keerthana T C, Yashaswini J

International Journal of Innovative Research in Computer and Communication Engineering · 11.07.2026 · 14 (7)

DOI: 10.15680/ijircce.2026.1407036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Research in Computer and Communication Engineering, online erschienen am 11.07.2026. Verfasst von Keerthana T C und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bone marrow disorders such as Aplastic Anemia, Leukemia, Lymphoma, and Myelodysplastic Syndrome (MDS) are serious haematological diseases that require early and accurate diagnosis for effective treatment. Traditional diagnosis through microscopic examination is time-consuming, labor-intensive, and highly dependent on the expertise of hematologists. To address these challenges, this project presents an AI-Based Bone Marrow Disorder Detection System using deep learning techniques for automated disease classification and explainable diagnosis. The proposed system utilizes the YOLOv8 Classification model to classify bone marrow microscopic images into five categories: Aplastic Anemia, Leukemia, Lymphoma, Myelodysplastic Syndrome (MDS), and Normal. Before classification, the images are pre-processed through resizing and normalization to improve model performance. The trained model predicts the disease class and generates confidence scores for each category, enabling reliable and accurate diagnosis. To enhance the interpretability of the model, the system integrates ResNet18-based Multi-layer Grad-CAM++, which generates heatmaps highlighting the important regions of the image responsible for the prediction. These visual explanations help healthcare professionals understand the model's decision-making process and increase confidence in AI-assisted diagnosis. The proposed system aims to reduce diagnosis time, improve diagnostic accuracy, minimize human error, and support haematologists in clinical decision-making. It serves as an effective AI-assisted clinical decision-support tool for the early detection and classification of bone marrow disorders.

Zitieren

APA

C, K. T., & J, Y. (2026). AI Based Bone Marrow Disorder Prediction Using Deep Learning. International Journal of Innovative Research in Computer and Communication Engineering, 14(7). https://doi.org/10.15680/ijircce.2026.1407036

Vancouver

C KT, J Y. AI Based Bone Marrow Disorder Prediction Using Deep Learning. International Journal of Innovative Research in Computer and Communication Engineering. 2026;14(7). doi:10.15680/ijircce.2026.1407036

BibTeX
@article{C2026,
  author = {C, Keerthana T and J, Yashaswini},
  title = {AI Based Bone Marrow Disorder Prediction Using Deep Learning},
  journal = {International Journal of Innovative Research in Computer and Communication Engineering},
  year = {2026},
  volume = {14},
  number = {7},
  doi = {10.15680/ijircce.2026.1407036}
}
Kostenlos starten →