Quaternion-Valued Convolutional Neural Network Applied for Acute Lymphoblastic Leukemia Diagnosis

TL;DR

This paper demonstrates that quaternion-valued convolutional neural networks can effectively diagnose acute lymphoblastic leukemia from blood smear images, achieving comparable or better accuracy with fewer parameters than real-valued networks.

Contribution

It introduces the application of quaternion-valued CNNs for medical image classification, showing improved efficiency and performance over traditional real-valued models.

Findings

Quaternion CNNs outperform real CNNs in accuracy.

Quaternion CNNs use only 34% of parameters of real CNNs.

Quaternion algebra captures more information with fewer parameters.

Abstract

The field of neural networks has seen significant advances in recent years with the development of deep and convolutional neural networks. Although many of the current works address real-valued models, recent studies reveal that neural networks with hypercomplex-valued parameters can better capture, generalize, and represent the complexity of multidimensional data. This paper explores the quaternion-valued convolutional neural network application for a pattern recognition task from medicine, namely, the diagnosis of acute lymphoblastic leukemia. Precisely, we compare the performance of real-valued and quaternion-valued convolutional neural networks to classify lymphoblasts from the peripheral blood smear microscopic images. The quaternion-valued convolutional neural network achieved better or similar performance than its corresponding real-valued network but using only 34% of its parameters. This result confirms that quaternion algebra allows capturing and extracting information from a color image with fewer parameters.