Analysis of Modern Computer Vision Models for Blood Cell Classification

TL;DR

This paper evaluates recent deep learning models like MaxVit and EfficientNetV2 for blood cell classification, aiming to improve speed and accuracy over traditional methods in medical diagnostics.

Contribution

It introduces the application of cutting-edge neural network architectures to blood cell classification, demonstrating their effectiveness and efficiency in hematological analysis.

Findings

EfficientNetV2 achieved the highest accuracy among tested models.

Deep learning models significantly outperformed traditional manual and automated methods.

The study highlights the potential for rapid, reliable blood cell classification using modern architectures.

Abstract

The accurate classification of white blood cells and related blood components is crucial for medical diagnoses. While traditional manual examinations and automated hematology analyzers have been widely used, they are often slow and prone to errors. Recent advancements in deep learning have shown promise for addressing these limitations. Earlier studies have demonstrated the viability of convolutional neural networks such as DenseNet, ResNet, and VGGNet for this task. Building on these foundations, our work employs more recent and efficient models to achieve rapid and accurate results. Specifically, this study used state-of-the-art architectures, including MaxVit, EfficientVit, EfficientNet, EfficientNetV2, and MobileNetV3. This study aimed to evaluate the performance of these models in WBC classification, potentially offering a more efficient and reliable alternative to current methods. Our approach not only addresses the speed and accuracy concerns of traditional techniques but also explores the applicability of innovative deep learning models in hematological analysis.