Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maruf, Md., Haque, Md. Mahbubul, Paul, Bishowjit
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911119044509696
author Maruf, Md.
Haque, Md. Mahbubul
Paul, Bishowjit
author_facet Maruf, Md.
Haque, Md. Mahbubul
Paul, Bishowjit
contents Acute lymphoblastic leukemia (ALL) is a prevalent hematological malignancy in both pediatric and adult populations. Early and accurate detection with precise subtyping is essential for guiding therapy. Conventional workflows are complex, time-consuming, and prone to human error. We present a deep learning framework for automated ALL diagnosis from bone marrow smear images. The method combines a robust preprocessing pipeline with convolutional neural networks (CNNs) to standardize image quality and improve inference efficiency. As a key design, we insert a multi-head self-attention (MHSA) block into a VGG19 backbone to model long-range dependencies and contextual relationships among cellular features. To mitigate class imbalance, we train with Focal Loss. Across evaluated architectures, the enhanced VGG19+MHSA trained with Focal Loss achieves 99.25% accuracy, surpassing a strong ResNet101 baseline (98.62%). These results indicate that attention-augmented CNNs, coupled with targeted loss optimization and preprocessing, yield more discriminative representations of leukemic cell morphology. Our approach offers a highly accurate and computationally efficient tool for automated ALL recognition and subtyping, with potential to accelerate diagnostic workflows and support reliable decision-making in clinical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology
Maruf, Md.
Haque, Md. Mahbubul
Paul, Bishowjit
Computer Vision and Pattern Recognition
Machine Learning
I.2.6; I.4.6; I.5.4; J.3
Acute lymphoblastic leukemia (ALL) is a prevalent hematological malignancy in both pediatric and adult populations. Early and accurate detection with precise subtyping is essential for guiding therapy. Conventional workflows are complex, time-consuming, and prone to human error. We present a deep learning framework for automated ALL diagnosis from bone marrow smear images. The method combines a robust preprocessing pipeline with convolutional neural networks (CNNs) to standardize image quality and improve inference efficiency. As a key design, we insert a multi-head self-attention (MHSA) block into a VGG19 backbone to model long-range dependencies and contextual relationships among cellular features. To mitigate class imbalance, we train with Focal Loss. Across evaluated architectures, the enhanced VGG19+MHSA trained with Focal Loss achieves 99.25% accuracy, surpassing a strong ResNet101 baseline (98.62%). These results indicate that attention-augmented CNNs, coupled with targeted loss optimization and preprocessing, yield more discriminative representations of leukemic cell morphology. Our approach offers a highly accurate and computationally efficient tool for automated ALL recognition and subtyping, with potential to accelerate diagnostic workflows and support reliable decision-making in clinical settings.
title Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology
topic Computer Vision and Pattern Recognition
Machine Learning
I.2.6; I.4.6; I.5.4; J.3
url https://arxiv.org/abs/2508.17216