Related Experiment Video
Updated: Jul 1, 2025
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
Published on: November 19, 2018
Automatic classification of acute lymphoblastic leukemia cells and lymphocyte subtypes based on a novel convolutional
Morteza MoradiAmin1,2, Mitra Yousefpour1, Nasser Samadzadehaghdam3
1Department of Physiology, Faculty of Medicine, AJA University of Medical Sciences, Tehran, Iran.
Insights
This study introduces a novel convolutional neural network (CNN) for accurate automated diagnosis of Acute Lymphoblastic Leukemia (ALL), achieving 97% accuracy in distinguishing ALL from similar lymphocyte subtypes without manual feature extraction.
Area of Science:
- Medical diagnostics
- Computational biology
- Image analysis
Background:
- Acute lymphoblastic leukemia (ALL) diagnosis relies on manual morphological analysis, which is time-consuming and error-prone.
- Distinguishing ALL from similar lymphocyte subtypes presents a significant challenge in manual diagnosis.
- Automated systems are needed to improve the accuracy and efficiency of ALL detection.
Purpose of the Study:
- To develop an automated system for accurate classification of ALL cells.
- To differentiate ALL from normal, atypic, and reactive lymphocytes without manual feature extraction.
- To evaluate a novel convolutional neural network (CNN) against established deep learning models.
Main Methods:
- Image preprocessing using histogram equalization for contrast enhancement.
- Fuzzy C-means clustering for robust segmentation of cell nuclei.
- A novel three-layer CNN for classifying segmented nuclei into six distinct classes.
Main Results:
- The proposed CNN achieved approximately 97% accuracy in classifying six ALL and lymphocyte subtypes.
- The model outperformed VGG-16, DenseNet, and Xception in this classification task.
- Performance exceeded that of existing studies focused on 6-class ALL diagnosis.
Conclusions:
- Deep neural networks can effectively eliminate the need for manual feature extraction in ALL classification.
- The developed CNN offers a highly accurate and efficient automated solution for ALL diagnosis.
- This approach shows significant promise for improving pediatric cancer diagnostics.
Abstract:
Acute lymphoblastic leukemia (ALL) is a life-threatening disease that commonly affects children and is classified into three subtypes: L1, L2, and L3. Traditionally, ALL is diagnosed through morphological analysis, involving the examination of blood and bone marrow smears by pathologists. However, this manual process is time-consuming, laborious, and prone to errors. Moreover, the significant morphological similarity between ALL and various lymphocyte subtypes, such as normal, atypic, and reactive lymphocytes, further complicates the feature extraction and detection process. The aim of this study is to develop an accurate and efficient automatic system to distinguish ALL cells from these similar lymphocyte subtypes without the need for direct feature extraction. First, the contrast of microscopic images is enhanced using histogram equalization, which improves the visibility of important features. Next, a fuzzy C-means clustering algorithm is employed to segment cell nuclei, as they play a crucial role in ALL diagnosis. Finally, a novel convolutional neural network (CNN) with three convolutional layers is utilized to classify the segmented nuclei into six distinct classes. The CNN is trained on a labeled dataset, allowing it to learn the distinguishing features of each class. To evaluate the performance of the proposed model, quantitative metrics are employed, and a comparison is made with three well-known deep networks: VGG-16, DenseNet, and Xception. The results demonstrate that the proposed model outperforms these networks, achieving an approximate accuracy of 97%. Moreover, the model's performance surpasses that of other studies focused on 6-class classification in the context of ALL diagnosis. RESEARCH HIGHLIGHTS: Deep neural networks eliminate the requirement for feature extraction in ALL classification The proposed convolutional neural network achieves an impressive accuracy of approximately 97% in classifying six ALL and lymphocyte subtypes.
More Related Videos
09:11Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
Published on: January 27, 2023
05:24Two Flow Cytometric Approaches of NKG2D Ligand Surface Detection to Distinguish Stem Cells from Bulk Subpopulations in Acute Myeloid Leukemia
Published on: February 21, 2021
