Timely Diagnosis of Acute Lymphoblastic Leukemia Using Artificial Intelligence‐Oriented Deep Learning Methods

Abstract

Background. Leukemia is fatal cancer in both children and adults and is divided into acute and chronic. Acute lymphoblastic leukemia (ALL) is a subtype of this cancer. Early diagnosis of this disease can have a significant impact on the treatment of this disease. Computational intelligence-oriented techniques can be used to help physicians identify and classify ALL rapidly. Materials and Method. In this study, the utilized dataset was collected from a CodaLab competition to classify leukemic cells from normal cells in microscopic images. Two famous deep learning networks, including residual neural network (ResNet-50) and VGG-16 were employed. These two networks are already trained by our assigned parameters, meaning we did not use the stored weights; we adjusted the weights and learning parameters too. Also, a convolutional network with ten convolutional layers and 2 ∗ 2 max-pooling layers—with strides 2—was proposed, and six common machine learning techniques were developed to classify acute lymphoblastic leukemia into two classes. Results. The validation accuracies (the mean accuracy of training and test networks for 100 training cycles) of the ResNet-50, VGG-16, and the proposed convolutional network were found to be 81.63%, 84.62%, and 82.10%, respectively. Among applied machine learning methods, the lowest obtained accuracy was related to multilayer perceptron (27.33%) and highest for random forest (81.72%). Conclusion. This study showed that the proposed convolutional neural network has optimal accuracy in the diagnosis of ALL. By comparing various convolutional neural networks and machine learning methods in diagnosing this disease, the convolutional neural network achieved good performance and optimal execution time without latency. This proposed network is less complex than the two pretrained networks and can be employed by pathologists and physicians in clinical systems for leukemia diagnosis.

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].…”

Hybrid Techniques for the Diagnosis of Acute Lymphoblastic Leukemia Based on Fusion of CNN Features

“…Pradeep et al [ 14 ] used three CNN models to extract image features of an ALL dataset and classify them by RF and SVM. Sorayya et al [ 15 ] modified the weights and parameters of the ResNet50 and VGG16 models to train the ALL dataset. They also proposed six machine-learning algorithms and a convolutional network with ten convolutional layers and a classification layer.…”

Multiple Types of Cancer Classification Using CT/MRI Images Based on Learning Without Forgetting Powered Deep Learning Models

“…al. [7] for detecting acute lymphoblastic leukemia. In addition, the authors presented a CNN with 10 convolutional layers and six common machine learning algorithms for dividing leukemia into two groups.…”