A Comparative Analysis on Detecting Physiological Age of Caenorhabditis Elegans Using Deep Learning Techniques

Reliable and efficient automated techniques for correctly estimating the physiological age of Caenorhabditis Elegans are critically needed, particularly for assessing anti-aging medications and for genetic screening research. The main purpose of automating the detection of physiological age was to shorten the processing time and reduce human-based bias. In this paper, we present a comparative analysis among commonly used, and state-of-the-art convolutional neural networks such as ResNet-18, MobileNetV1, EfficientNet (B0), EfficientNet (B1) to determine the physiological age of Caenorhabditis Elegans. We further modified EfficientNet (B0) which is capable of achieving state of the art performance. When trained on a day-by-day labeled dataset, the modified EfficientNet (B0) deep learning technique achieved the highest accuracy in categorizing Caenorhabditis Elegan's age which is 88.5%. On a different stage-by-stage dataset, the proposed model could achieve 89.8% accuracy.