Combining Deep Learning Models for Cytological Image Classification

The classification of medical images has greatly advanced due to improvements in imaging technologies and the application of deep learning. This study presents an automatic system for classifying peripheral blood cells, leveraging deep learning and transfer learning techniques to enhance performance and efficiency. We developed three designs combining convolutional architectures: VGG16, InceptionV3and ResNet50. The first design combines VGG16 and InceptionV3, the second concatenates InceptionV3and ResNet50, and the third associates VGG16 and ResNet50. Experiments were conducted on the Peripheral Blood Cell (PBC) dataset, containing 17,092 images across eight distinct classes. The results demonstrate the effectiveness of our approach, achieving a maximum accuracy of 99%.