Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vieira, Guilherme, Valle, Marcos Eduardo
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910287222800384
author Vieira, Guilherme
Valle, Marcos Eduardo
author_facet Vieira, Guilherme
Valle, Marcos Eduardo
contents This paper features convolutional neural networks defined on hypercomplex algebras applied to classify lymphocytes in blood smear digital microscopic images. Such classification is helpful for the diagnosis of acute lymphoblast leukemia (ALL), a type of blood cancer. We perform the classification task using eight hypercomplex-valued convolutional neural networks (HvCNNs) along with real-valued convolutional networks. Our results show that HvCNNs perform better than the real-valued model, showcasing higher accuracy with a much smaller number of parameters. Moreover, we found that HvCNNs based on Clifford algebras processing HSV-encoded images attained the highest observed accuracies. Precisely, our HvCNN yielded an average accuracy rate of 96.6% using the ALL-IDB2 dataset with a 50% train-test split, a value extremely close to the state-of-the-art models but using a much simpler architecture with significantly fewer parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2205_13273
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks
Vieira, Guilherme
Valle, Marcos Eduardo
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Image and Video Processing
This paper features convolutional neural networks defined on hypercomplex algebras applied to classify lymphocytes in blood smear digital microscopic images. Such classification is helpful for the diagnosis of acute lymphoblast leukemia (ALL), a type of blood cancer. We perform the classification task using eight hypercomplex-valued convolutional neural networks (HvCNNs) along with real-valued convolutional networks. Our results show that HvCNNs perform better than the real-valued model, showcasing higher accuracy with a much smaller number of parameters. Moreover, we found that HvCNNs based on Clifford algebras processing HSV-encoded images attained the highest observed accuracies. Precisely, our HvCNN yielded an average accuracy rate of 96.6% using the ALL-IDB2 dataset with a 50% train-test split, a value extremely close to the state-of-the-art models but using a much simpler architecture with significantly fewer parameters.
title Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks
topic Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Image and Video Processing
url https://arxiv.org/abs/2205.13273