In recent years, image classification has undergone significant advancements, notably through the integration of techniques inspired by principles from quantum mechanics. This chapter introduces an image classification model that combines neural network principles with concepts from quantum computing. The process encompasses two main stages: data preprocessing and image classification. During the data preprocessing phase, the original dataset is scaled and normalized. The proposed quantum neural network (QNN) approaches are then applied to the processed dataset. The proposed QNN is based on using quantum circuits instead of traditional convolution filters. A quantum neural network typically consists of three components: an encoder, a quantum layer, and a measurement. The encoder component is formed from a list of gates that are passed. This part has four RY gates, one for each qubit. Then, the ansatz with six trainable parameters and Hadamard non-parameterized circuits is used in the quantum layer. Finally, each qubit is assessed using Pauli-Z. To evaluate the performance of the proposed model, four benchmark datasets are used: two medical datasets (BreastMNIST and PneumoniaMNIST) and two nonmedical datasets (FashionMNIST and MNIST). The experimental results revealed that, unlike the state-of-the-art models, the proposed image classification model demonstrated good classification accuracy despite the small input image size. Furthermore, the results showed that the proposed QNN approach can lead to a considerable improvement in the performance of traditional neural networks.