Hybrid quantum neural networks for computer-aided sex diagnosis in forensic and physical anthropology

Abstract

The determination of sex from skeletal remains is essential for forensic science and the reconstruction of demographic patterns in ancient communities. This study aims to develop and evaluate hybrid deep-quantum neural network architectures to improve the accuracy and robustness of sex estimation from calvarium shape data. Deep learning has reached new heights in a number of scientific fields, while quantum techniques have the potential to process data in unique ways, offering benefits such as parallel processing and superposition. In the study, we investigate how an integration of deep learning and quantum computing will optimize sex estimation based on the shape complexity of calvarium, specifically through the algorithm based on Fast Fourier Transform of calvarium shapes. In previous studies with the same data, the highest achieved accuracy was 82.25%, utilizing classical machine learning and neural networks, such as Multilayer Perceptron. To improve the performance, we used four different neural network models: the classical Multilayer Perceptron and Convolutional Neural Network, along with Hybrid Quantum Classical Neural Networks, including Hybrid Quantum Classical Convolutional Networks on the morphological variations of the curve representing the sagittal profile of the calvarium. All the models outperformed the experts and improved the previous findings, achieving over 82.4% accuracy. Furthermore, the experiments on stability and accuracy over small datasets showed that one of proposed hybrid networks outperforms classical analogue on a small amount of data. The final performance of the hybrid models is better than the classical results and the best result achieved is 87.4%. We also launched the best hybrid model on the QPU, and the achieved accuracy of 90.71% is comparable to the classical simulation at 92.14%. Our research benefited significantly from new tools for analyzing quantum variational algorithms, which are inaccessible to classical methods, enabling us to reach higher results. This study not only demonstrates success in solving the specific task but also opens new possibilities for the application of quantum technologies in anthropology.