An Attention-Based Convolutional Neural Network for Acute Lymphoblastic Leukemia Classification

Abstract

Leukemia is a kind of blood cancer that influences people of all ages and is one of the leading causes of death worldwide. Acute lymphoblastic leukemia (ALL) is the most widely recognized type of leukemia found in the bone marrow of the human body. Traditional disease diagnostic techniques like blood and bone marrow examinations are slow and painful, resulting in the demand for non-invasive and fast methods. This work presents a non-invasive, convolutional neural network (CNN) based approach that utilizes medical images to perform the diagnosis task. The proposed solution consisting of a CNN-based model uses an attention module called Efficient Channel Attention (ECA) with the visual geometry group from oxford (VGG16) to extract better quality deep features from the image dataset, leading to better feature representation and better classification results. The proposed method shows that the ECA module helps to overcome morphological similarities between ALL cancer and healthy cell images. Various augmentation techniques are also employed to increase the quality and quantity of training data. We used the classification of normal vs. malignant cells (C-NMC) dataset and divided it into seven folds based on subject-level variability, which is usually ignored in previous methods. Experimental results show that our proposed CNN model can successfully extract deep features and achieved an accuracy of 91.1%. The obtained findings show that the proposed method may be utilized to diagnose ALL and would help pathologists.

Intra‐nucleus mosaic pattern (InMop) and whole‐cell Haralick combined‐descriptor for identifying and characterizing acute leukemia blasts on single cell peripheral blood images

“…Among deep-learning strategies, VGG16 has been commonly reported for leukemia detection [36][37][38], with outstanding results in one of the herein tested databases (accuracy of 97.04 ± 1.21 for D1) [39,40]. The present work extends this evaluation to the D2 database for the VGG16, while the D1 test is performed under a five-fold scheme which is considered more general than a simple leave-on-out strategy, as already reported [40].…”

“…This experiment takes two of the best state‐of‐the‐art CNNs for this task, and separately trains each to classify blast and nonblasts in D1 and D2, that is, VGG16 [28] and RESNEXT [29] are considered as baseline. Among deep‐learning strategies, VGG16 has been commonly reported for leukemia detection [36–38], with outstanding results in one of the herein tested databases (accuracy of 97.04 ± 1.21 for D1) [39, 40]. The present work extends this evaluation to the D2 database for the VGG16, while the D1 test is performed under a five‐fold scheme which is considered more general than a simple leave‐on‐out strategy, as already reported [40].…”

CAB‐Net: Convolutional attention BLSTM network for enhanced leukocyte classification

“…The PBC dataset is imbalanced, therefore to overcome the potential for overfitting we apply data preprocessing techniques similarly employed by Rastogi et al and Zakir Ullah et al 7,23 in their research. For PBC dataset we implemented two distinct approaches: undersampling and oversampling.…”

Lightweight EfficientNetB3 Model Based on Depthwise Separable Convolutions for Enhancing Classification of Leukemia White Blood Cell Images

“…The experiment results indicate that the authors' presented method has the highest classification accuracy at 95.18%. Using a CNN-based ECA module, M-Zakir et al [63] improved the CNN hyperparameters and achieved 91.10% accuracy on the dataset. To detect images of cells, P.Cho et al [64] proposed a vision transfer model and achieved an accuracy of 88.20% on the dataset.…”