Deep Learning Model-Based Detection of Anemia from Conjunctiva Images

Anemia is characterized by a reduction in red blood cells, leading to insufficient levels of hemoglobin, the molecule responsible for carrying oxygen. The current standard method for diagnosing anemia involves analyzing blood samples, a process that is time-consuming and can cause discomfort to participants. This study offers a comprehensive analysis of non-invasive anemia detection using conjunctiva images processed through various machine learning and deep learning models. The focus is on the palpebral conjunctiva, which is highly vascular and unaffected by melanin content.

Conjunctiva images from both anemic and non-anemic participants were captured using a smartphone. A total of 764 conjunctiva images were augmented to 4,315 images using the deep convolutional generative adversarial network model to prevent overfitting and enhance model robustness. These processed and augmented images were then utilized to train and test multiple models, including statistical regression, machine learning algorithms, and deep learning frameworks.

The stacking ensemble framework, which includes the models VGG16, ResNet-50, and InceptionV3, achieved a high area under the curve score of 0.97. This score demonstrates the framework's exceptional capability in detecting anemia through a noninvasive approach.

This study introduces a noninvasive method for detecting anemia using conjunctiva images obtained with a smartphone and processed using advanced deep learning techniques.