Automatic Diagnosis of Malaria from Thin Blood Smear Images using Deep Convolutional Neural Network with Multi-Resolution Feature Fusion

TL;DR

This paper introduces DilationNet and DeepFusionNet, a deep learning framework that combines multi-resolution feature extraction and fusion to diagnose malaria from blood smear images with over 99.5% accuracy.

Contribution

It proposes a novel multi-resolution deep neural network architecture with feature fusion for rapid and accurate malaria diagnosis from blood smear images.

Findings

Achieved over 99.5% accuracy on a public dataset.

Outperformed existing state-of-the-art methods.

Demonstrated effective multi-resolution feature fusion for medical image analysis.

Abstract

Malaria, a life-threatening disease, infects millions of people every year throughout the world demanding faster diagnosis for proper treatment before any damages occur. In this paper, an end-to-end deep learning-based approach is proposed for faster diagnosis of malaria from thin blood smear images by making efficient optimizations of features extracted from diversified receptive fields. Firstly, an efficient, highly scalable deep neural network, named as DilationNet, is proposed that incorporates features from a large spectrum by varying dilation rates of convolutions to extract features from different receptive areas. Next, the raw images are resampled to various resolutions to introduce variations in the receptive fields that are used for independently optimizing different forms of DilationNet scaled for different resolutions of images. Afterward, a feature fusion scheme is introduced with the proposed DeepFusionNet architecture for jointly optimizing the feature space of these individually trained networks operating on different levels of observations. All the convolutional layers of various forms of DilationNets that are optimized to extract spatial features from different resolutions of images are directly transferred to provide a variegated feature space from any image. Later, joint optimization of these spatial features is carried out in the DeepFusionNet to extract the most relevant representation of the sample image. This scheme offers the opportunity to explore the feature space extensively by varying the observation level to accurately diagnose the abnormality. Intense experimentations on a publicly available dataset show outstanding performance with accuracy over 99.5% outperforming other state-of-the-art approaches.