Evaluation of QCNN-LSTM for Disability Forecasting in Multiple Sclerosis using Sequential Multisequence MRI

Introduction: Quantum Convolutional Neural Network (QCNN) - Long Short-Term Memory (LSTM) models were studied to provide sequential relationships for each timepoint in MRIs of patients with Multiple Sclerosis (MS). In this pilot study, we compare three QCNN-LSTM models for binary classification of MS disability benchmarked against classical neural network architectures. Our hypothesis is that quantum models will provide competitive performance. Methods: Matrix Product State (MPS), Reverse Multistate Entanglement Renormalization Ansatz (MERA), and Tree-Tensor Network (TTN) circuits were paired with LSTM layer to process near-annual MRI data of patients diagnosed with MS. These were benchmarked against a Visual Geometry Group (VGG16)-LSTM and a Video Vision Transformer (ViViT). Predicted logits were measured against ground truth labels of each patient’s Extended Disability Severity Score (EDSS) using binary cross-entropy loss. Training/Validation/Holdout Testing was partitioned using 5-fold cross validation with a total split of 60:20:20. Levene’s test of variance was used to measure statistical difference and Student’s t-test for paired model differences in mean. Results: The MPS-LSTM, Reverse MERA-LSTM, and TTN-LSTM had holdout testing ROC-AUC of 0.70, 0.77, and 0.81, respectively (p-value 0.915). VGG16-LSTM and ViViT performed similarly with ROC-AUC of 0.73 and 0.77, respectively (p-value 0.631). Overall variance and mean were not statistically significant (p-value 0.713), however, time to train was significantly faster for the QCNN-LSTMs (39.4 seconds per fold vs. 224.3 and 217.5, respectively, p-value <0.001). Conclusion: QCNN-LSTM models perform competitively compared to their classical counterparts with greater efficiency in train time. Clinically, these can add value in terms of efficiency to time-dependent deep learning prediction of disease progression based upon medical imaging.