European Journal of Nuclear Medicine and Molecular Imaging
Error mitigation enables PET radiomic cancer characterization on quantum computers
Sasan Moradi, Clemens P. Spielvogel, Denis Krajnc, Christoph Brandner, Stefan Hillmich, Robert Wille, Tatjana Traub‐Weidinger, Xiang Li, Marcus Hacker, Wolfgang Drexler, László Papp
Abstract Background Cancer is a leading cause of death worldwide. While routine diagnosis of cancer is performed mainly with biopsy sampling, it is suboptimal to accurately characterize tumor heterogeneity. Positron emission tomography (PET)-driven radiomic research has demonstrated promising results when predicting clinical endpoints. This study aimed to investigate the added value of quantum machine learning both in simulator and in real quantum computers utilizing error mitigation techniques to predict clinical endpoints in various PET cancer patients. Methods Previously published PET radiomics datasets including 11C-MET PET glioma, 68GA-PSMA-11 PET prostate and lung 18F-FDG PET with 3-year survival, low-vs-high Gleason risk and 2-year survival as clinical endpoints respectively were utilized in this study. Redundancy reduction with 0.7, 0.8, and 0.9 Spearman rank thresholds (SRT), followed by selecting 8 and 16 features from all cohorts, was performed, resulting in 18 dataset variants. Quantum advantage was estimated by Geometric Difference (GD Q ) score in each dataset variant. Five classic machine learning (CML) and their quantum versions (QML) were trained and tested in simulator environments across the dataset variants. Quantum circuit optimization and error mitigation were performed, followed by training and testing selected QML methods on the 21-qubit IonQ Aria quantum computer. Predictive performances were estimated by test balanced accuracy (BACC) values. Results On average, QML outperformed CML in simulator environments with 16-features (BACC 70% and 69%, respectively), while with 8-features, CML outperformed QML with + 1%. The highest average QML advantage was + 4%. The GD Q scores were ≤ 1.0 in all the 8-feature cases, while they were > 1.0 when QML outperformed CML in 9 out of 11 cases. The test BACC of selected QML methods and datasets in the IonQ device without error mitigation (EM) were 69.94% BACC, while EM increased test BACC to 75.66% (76.77% in noiseless simulators). Conclusions We demonstrated that with error mitigation, quantum advantage can be achieved in real existing quantum computers when predicting clinical endpoints in clinically relevant PET cancer cohorts. Quantum advantage can already be achieved in simulator environments in these cohorts when relying on QML.
Abstract Background Cancer is a leading cause of death worldwide. While routine diagnosis of cancer is performed mainly with biopsy sampling, it is suboptimal to accurately characterize tumor heterogeneity. Positron emission tomography (PET)-driven radiomic research has demonstrated promising results when predicting clinical endpoints. This study aimed to investigate the added value of quantum machine learning both in simulator and in real quantum computers utilizing error mitigation techniques to predict clinical endpoints in various PET cancer patients. Methods Previously published PET radiomics datasets including 11C-MET PET glioma, 68GA-PSMA-11 PET prostate and lung 18F-FDG PET with 3-year survival, low-vs-high Gleason risk and 2-year survival as clinical endpoints respectively were utilized in this study. Redundancy reduction with 0.7, 0.8, and 0.9 Spearman rank thresholds (SRT), followed by selecting 8 and 16 features from all cohorts, was performed, resulting in 18 dataset variants. Quantum advantage was estimated by Geometric Difference (GD Q ) score in each dataset variant. Five classic machine learning (CML) and their quantum versions (QML) were trained and tested in simulator environments across the dataset variants. Quantum circuit optimization and error mitigation were performed, followed by training and testing selected QML methods on the 21-qubit IonQ Aria quantum computer. Predictive performances were estimated by test balanced accuracy (BACC) values. Results On average, QML outperformed CML in simulator environments with 16-features (BACC 70% and 69%, respectively), while with 8-features, CML outperformed QML with + 1%. The highest average QML advantage was + 4%. The GD Q scores were ≤ 1.0 in all the 8-feature cases, while they were > 1.0 when QML outperformed CML in 9 out of 11 cases. The test BACC of selected QML methods and datasets in the IonQ device without error mitigation (EM) were 69.94% BACC, while EM increased test BACC to 75.66% (76.77% in noiseless simulators). Conclusions We demonstrated that with error mitigation, quantum advantage can be achieved in real existing quantum computers when predicting clinical endpoints in clinically relevant PET cancer cohorts. Quantum advantage can already be achieved in simulator environments in these cohorts when relying on QML.
The combination of quantum computing with machine learning which forms quantum machine learning (QML) presents promising advances for healthcare purposes with specific applications in predicting cancer outcomes. The research investigates how QML can work together with the quantitative imaging analysis techniques in radiomics to improve prediction methods for lung cancer results. The proposed quantum neural network (QNN) model attempts to predict lung cancer patient 5-year survival status of lung cancer patient by radiomic features extracted from CT scan images. Quantum artificial intelligence showed promise in lung cancer prognosis because its evaluation included a balanced accuracy score of 0.71 and ROC-AUC performance metric of 0.71. The current approach has three major challenges due to data biases, restricted quantum hardware capabilities and insufficient evidence to demonstrate the quantum speedup benefits. In this study QML's clinical potential was noted in this research with operational and developmental pathways moving forward.
Prostate cancer is among the most prevalent malignancies in men, and early, accurate diagnosis is critical for effective treatment. Traditional machine learning techniques have demonstrated success in analyzing multiparametric magnetic resonance imaging (MRI) and clinical biomarkers; however, their scalability and capacity to model complex feature interactions remain limited. This study proposes an Ensemble Quantum Machine Learning (QML) framework to enhance prostate cancer detection using the PROSTATEx Challenge dataset. Radiomic features were extracted from MRI modalities and clinical attributes, then standardized and reduced using principal component analysis (PCA) to match current quantum hardware constraints. Three quantum classifiers—Quantum Support Vector Machine (QSVM), Variational Quantum Classifier (VQC), and Quantum Neural Network (QNN) - were independently trained and integrated using both soft voting and stacked ensemble strategies. Results from stratified 5-fold cross-validation show that the stacked ensemble outperformed individual models and baseline classifiers, achieving an average accuracy of 88.4%, recall of 89.1%, precision of 87.9%, F1-score of 88.5%, and area under the curve - receiver operating characteristic (AUC-ROC) of 0.94 (stack ensemble). These findings highlight the potential of hybrid quantum-classical ensemble learning to improve diagnostic robustness, particularly in reducing false negatives. Furthermore, validation on real quantum hardware demonstrated consistent performance, underscoring the feasibility of QML in near-term medical applications. This work contributes to the growing intersection of quantum computing and clinical AI, offering a scalable and interpretable approach to precision oncology.
Introduction: In recent years, high-dimensional clinical and genomic data have gained significant importance for prognosis and personalized medicine in breast cancer. But the use of quantum machine learning (QML) on such data is limited by the availability of few qubits, the computation time of quantum simulation, and dimensionality reduction. This work systematically compares several QML architectures for breast cancer classification in the presence of realistic and simulator constraints. Methods: The experiments were performed on a dataset of METABRIC breast cancer patients (2,509 patients). After handling missing values and one-hot encoding, there were 63 features in the processed data set. The feature space was reduced by Principal Component Analysis (PCA) to 12, 4 and 2 components for the implementations of quantum computers, respectively, with 56.10 ± 0.14%, 26.78 ± 0.57% and 16.23 ± 0.33% of the variance retained. Three QML models were tested: Quantum Neural Networks (QNN), Quantum K-Nearest Neighbors (QKNN), and Quantum Support Vector Machines (QSVM), with the models being simulated. Seven classical classification models were tested: Logistic Regression, SVM with RBF kernel, K-Nearest Neighbors, Random Forest, XGBoost, LightGBM and Multilayer Perceptron, both with PCA-matched and full 63-feature representation. All primary results are reported with 5-fold cross validation. Results: Among the evaluated QML architectures, QKNN using 12 principal components achieved the strongest performance, attaining an accuracy of **75.11% ± 3.76%**, an F1-score of **0.7088 ± 0.0433**, and a ROC-AUC of **0.8148 ± 0.0394**. Even though all of the QML models performed significantly poorly in comparison to classical models trained on the entire 63-feature data set, the latter models were able to achieve about **94% accuracy** with XGBoost, Random Forest, and Logistic Regression. The comparison also showed the effect of information loss due to PCA is significant in predictive performance in both classical and quantum models. Discussion: The results show that for high dimensional breast cancer data, currently available simulator-based QML models can learn meaningful patterns with limited quantum resources, but are not as effective as powerful classical machine learning models when complete feature representations are available. The study does not report any sort of quantum advantage or clinical use, but rather a benchmark of current QML architectures that has been rigorously calculated and repeated, with a focus on the impact of dimensionality reduction, validation approaches, and simulator limitations, as well as outlining challenges that need to be overcome prior to practical implementation on real quantum hardware.
Positron emission tomography (PET) with long axial field-of-view (LAFOV) scanners generates unprecedentedly large datasets, posing major challenges for conventional reconstruction algorithms. Recent advances in deep learning have improved PET image quality, yet scaling to high-dimensional data remains computationally demanding. Quantum computing (QC) offers new opportunities to address such challenges. This work presents a pilot study on image denoising using a hybrid quantum-classical autoencoder. The model employs a classical encoder, a quantum bottleneck implemented via a parameterized quantum circuit, and a classical decoder. Using simulated experiments on the medical modified national institute of standards and technology (MedMNIST) dataset with 28 × 28 grayscale images and on PET scan images with 64 × 64, results demonstrated that the quantum bottleneck can effectively recover structural details from noisy inputs. While scaling to large-volume PET data will require advances in quantum hardware, circuit design, and error mitigation, these results highlight the potential of hybrid quantum–classical approaches to complement deep learning in PET reconstruction.
Kernel methods are the basis of most classical machine learning algorithms such as Gaussian Process (GP) and Support Vector Machine (SVM). Computing kernels using noisy intermediate scale quantum (NISQ) devices has attracted considerable attention due to recent progress in the design of NISQ devices. However noise and errors on current NISQ devices can negatively affect the predicted kernels. In this paper we utilize two quantum kernel machine learning (ML) algorithms to predict the labels of a Breast Cancer dataset on two different NISQ devices: quantum kernel Gaussian Process (qkGP) and quantum kernel Support Vector Machine (qkSVM). We estimate the quantum kernels on the 11 qubit IonQ and the 5 qubit IBMQ Belem quantum devices. Our results demonstrate that the predictive performances of the error mitigated quantum kernel machine learning algorithms improve significantly compared to their non-error mitigated counterparts. On both NISQ devices the predictive performances became comparable to those of noiseless quantum simulators and their classical counterparts