Hepatic fibrosis, or the excessive accumulation of extracellular matrix proteins, such as collagen, is the hallmark of the most prevalent type of chronic liver disease. Advanced liver fibrosis has adverse consequences such as cirrhosis, liver failure, and portal hypertension, which frequently call for liver transplantation. Current research on liver fibrosis is heavily focused on understanding the molecular mechanisms underlying this disorder and provides an up-to-date overview of deep learning models used in experimental liver fibrosis research. We evaluated the original and augmented mice liver dataset using a convolutional neural network, VGG16, and a stratified k-fold cross validation model. The results obtained from VGG16 models were taken into consideration due to their suitable object recognition and classification algorithm. Our study suggested that the deep learning VGG16 model can classify healthy and fibrotic liver cells with an accuracy of 95% despite training and validation loss. This study creates a foundation for future research that will employ deep learning models as a non-invasive tool to gauge the severity of the disease and identify the best treatment course to hinder the advancement of fibrosis.