To generate evidence regarding the safety and efficacy of artificial intelligence (AI) enabled medical devices, AI models need to be evaluated on a diverse population of patient cases, some of which may not be readily available. We propose an evaluation approach for testing medical imaging AI models that relies on in silico imaging pipelines in which stochastic digital models of human anatomy (in object space) with and without pathology are imaged using a digital replica imaging acquisition system to generate realistic synthetic image datasets. Here, we release M-SYNTH, a dataset of cohorts with four breast fibroglandular density distributions imaged at different exposure levels using Monte Carlo x-ray simulations with the publicly available Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) toolkit. We utilize the synthetic dataset to analyze AI model performance and find that model performance decreases with increasing breast density and increases with higher mass density, as expected. As exposure levels decrease, AI model performance drops with the highest performance achieved at exposure levels lower than the nominal recommended dose for the breast type.
We analyse and classify the sentiments of a text data constructed from movie reviews. For this, we use the kernel-based approach from quantum machine learning algorithms. In order to compose a quantum kernel, we use a circuit constructed using a combination of different Pauli rotational gates where the rotational parameter is a classical non-linear function of data points obtained from the text data. For analysing the performance of the proposed model, we analyse the quantum model using decision tree, gradient boosting classifier, and classical and quantum support vector machines. Our results show that quantum kernel model or quantum support vector machine outperforms all other algorithms used for analysis in terms of all evaluation metrics. In comparison to a classical support vector machine, the quantum support vector machine leads to significantly better results even with increased number of features or dimensions. The results clearly demonstrate increase in precision score by $9.4 \%$ using a quantum support vector machine as against a classical support vector machine if the number of features are $15$.