The accurate classification of cancer cells in the peripheral blood is essential for the diagnosis of leukemia and has traditionally been carried out by analyzing laboratory images. In this context, the use of deep le...
详细信息
The accurate classification of cancer cells in the peripheral blood is essential for the diagnosis of leukemia and has traditionally been carried out by analyzing laboratory images. In this context, the use of deep learning techniques facilitates decision-making and accelerates the early diagnosis of the disease, allowing preventive measures to be adopted for the patient. This study explores the application of the YOLOv8 deep learning architecture for the classification of cancer cells in blood smear images owing, to its ability to perform this task quickly and accurately. The models were trained on two datasets, ALL and C-NMC Leukemia, and evaluated using top-1 accuracy, top-5 accuracy and loss metrics. The proposed approach achieved a top-1 accuracy of 99.982% and top-5 accuracy of 100% on the validation and test subsets of the ALL dataset respectively, with a final loss of 0.02952. For the C-NMC Leukemia dataset, the model obtained 66.897% and 89.612% top-1 accuracy in the validation and test subsets, respectively, while maintaining 100% top-5 accuracy in both subsets, with a loss of 0.18289. These results demonstrate the effectiveness of YOLOv8 in classifying cancer cells, particularly in the ALL set. However, future strategies such as expanding the data set and fine-tuning the hyperparameters could contribute to better generalization of the model to different data distributions.
暂无评论