CNN-Based Identification of Pathogens of Concern in Shrimp

TL;DR

This paper shows how AI can quickly and accurately diagnose three major shrimp diseases using microscope images, offering a low-cost solution for farmers.

Contribution

The study demonstrates the practical feasibility of lightweight CNN-based tools for real-time shrimp disease diagnosis in the field.

Findings

Both MobileNet and EfficientNet achieved over 95% accuracy in identifying shrimp diseases from tissue images.

MobileNet was found to be faster and more efficient, making it suitable for on-site deployment.

The models can help bridge the gap between laboratory-grade diagnostics and field-level usability.

Abstract

Shrimp farming plays an important role in global food production, but it is often threatened by diseases that damage the shrimp’s digestive organ, the hepatopancreas. These diseases can cause slow growth, weakness, or even sudden death, leading to serious financial losses for farmers. Traditional diagnosis requires laboratory tests, which are costly, slow, and not always available in small-scale farms. In this study, we used modern computer vision, a form of artificial intelligence that learns to recognize patterns in images to help identify three major shrimp diseases from microscope slides of tissue samples. We tested two lightweight computer models, MobileNet and EfficientNet, to see how well they could recognize diseased tissue compared to healthy tissue. Both models performed very well, achieving over 95% accuracy with MobileNet proving especially fast and efficient. These results show that artificial intelligence could be used as a practical, affordable tool for farmers and veterinarians to diagnose shrimp diseases quickly, even in areas with limited laboratory facilities.

Concerning shrimp diseases, including acute hepatopancreatic necrosis disease (AHPND), hepatopancreatic parvovirus (HPV) infection and Enterocytozoon hepatopenaei (EHP) microsporidiosis negatively impact shrimp aquaculture through acute mortality, chronic growth retardation or compromised health that increases susceptibility to concurrent infections. All three diseases damage hepatopancreas, a vital organ for nutrient absorption and growth, though their clinical outcomes differ: AHPND is typically associated with rapid, high mortality, EHP primarily causes chronic production losses and HPV, while currently of lower pathogenic significance, may still impair health under certain conditions. Outbreak severity is often intensified by poor water quality, inadequate farm management, antibiotic misuse and pathogen vectors, leading to substantial economic losses. Timely and accurate diagnosis is therefore critical for effective disease management. This study investigates two convolutional neural network (CNN) architectures, EfficientNet and MobileNet. A curated and preprocessed dataset was used to fine-tune both models with a standardized custom classification head, ensuring a controlled backbone comparison. Experimental results show both architectures achieving over 95% accuracy, with MobileNet providing faster inference suitable for on-site deployment. These findings demonstrate the practical feasibility of lightweight CNN-based diagnostics tools for real-time, scalable, and cost-efficient health monitoring in shrimp aquaculture, bridging the gap between the laboratory-grade performance and field-level usability.

Figures