Acute Lymphoblastic Leukemia Blood Cells Prediction Using Deep Learning & Transfer Learning Technique

Abstract

White blood cells called lymphocytes are the target of the blood malignancy known as acute lymphoblastic leukemia (ALL). In the domain of medical image analysis, deep learning and transfer learning methods have recently showcased significant promise, particularly in tasks such as identifying and categorizing various types of cancer. Using microscopic pictures, we suggest a deep learning and transfer learning-based method in this research work for predicting ALL blood cells. We use a pre-trained convolutional neural network (CNN) model to extract pertinent features from the microscopic images of blood cells during the feature extraction step. To accurately categorize the blood cells into leukemia and non-leukemia classes, a classification model is built using a transfer learning technique employing the collected features. We use a publicly accessible collection of microscopic blood cell pictures, which contains samples from both leukemia and non-leukemia, to assess the suggested method. Our experimental findings show that the suggested method successfully predicts ALL blood cells with high accuracy. The method enhances early ALL detection and diagnosis, which may result in better patient treatment outcomes. Future research will concentrate on larger and more varied datasets and investigate the viability of integrating it into clinical processes for real-time ALL prediction.

Advancing Early Leukemia Diagnostics: A Comprehensive Study Incorporating Image Processing and Transfer Learning

“…On the other hand, our model achieves superior accuracy while managing a comparable number of classes. The VGG16 model, as mentioned in [34], achieved an accuracy of 94% across four classes, while another CNN model discussed in reference [31] reached an accuracy of 88.25% in distinguishing between five classes. Furthermore, the strong performance of our method highlights the effectiveness of the InceptionResNet architecture in capturing intricate patterns and features in leukemia cell images.…”

“…But specific details about the dataset's diversity, potential biases, or generalizability to varied clinical scenarios are not explicitly mentioned. Ghongade et al [34] utilized deep learning and TL for predicting ALL in lymphocytes. A pre-trained CNN extracted features from microscopic blood cell images, and a TL-based classification model accurately categorized cells into leukemia and non-leukemia classes.…”

Classification of Human Emotions Based on Javanese Speech Using Convolutional Neural Network and Multilayer Perceptron

“…The CNN algorithm is more efficient than other neural network algorithms, especially in terms of memory and complexity. The need for large data sets is one of the problems with deep learning algorithms, especially CNN, which is a data-hungry model [14].…”