An Explainable MRI-Radiomic Quantum Neural Network to Differentiate Between Large Brain Metastases and High-Grade Glioma Using Quantum Annealing for Feature Selection.

Solitary large brain metastases (LBM) and high-grade gliomas (HGG) are sometimes hard to differentiate on MRI. The management differs significantly between these two entities, and non-invasive methods that help differentiate between them are eagerly needed to avoid potentially morbid biopsies and surgical procedures. We explore herein the performance and interpretability of an MRI-radiomics variational quantum neural network (QNN) using a quantum-annealing mutual-information (MI) feature selection approach. We retrospectively included 423 patients with HGG and LBM (> 2 cm) who had a contrast-enhanced T1-weighted (CE-T1) MRI between 2012 and 2019. After exclusion, 72 HGG and 129 LBM were kept. Tumors were manually segmented, and a 5-mm peri-tumoral ring was created. MRI images were pre-processed, and 1813 radiomic features were extracted. A set of best features based on MI was selected. MI and conditional-MI were embedded into a quadratic unconstrained binary optimization (QUBO) formulation that was mapped to an Ising-model and submitted to D'Wave's quantum annealer to solve for the best combination of 10 features. The 10 selected features were embedded into a 2-qubits QNN using PennyLane library. The model was evaluated for balanced-accuracy (bACC) and area under the receiver operating characteristic curve (ROC-AUC) on the test set. The model performance was benchmarked against two classical models: dense neural networks (DNN) and extreme gradient boosting (XGB). Shapley values were calculated to interpret sample-wise predictions on the test set. The best 10-feature combination included 6 tumor and 4 ring features. For QNN, DNN, and XGB, respectively, training ROC-AUC was 0.86, 0.95, and 0.94; test ROC-AUC was 0.76, 0.75, and 0.79; and test bACC was 0.74, 0.73, and 0.72. The two most influential features were tumor Laplacian-of-Gaussian-GLRLM-Entropy and sphericity. We developed an accurate interpretable QNN model with quantum-informed feature selection to differentiate between LBM and HGG on CE-T1 brain MRI. The model performance is comparable to state-of-the-art classical models.

[Chemoradiotherapy in early stage Hodgkin's lymphoma]. / Chimio-radiothérapie dans les lymphomes de Hodgkin-Stades précoces.

OBJECTIVE: To evaluate the response to and toxicities of chemo-radiotherapy (CT-RT) in patients with early stage Hodgkin lymphoma treated in our institution. MATERIALS AND METHODS: Retrospective study of 42 patients with early stage Hodgkin lymphoma treated between 2002 and 2007. RESULTS: The age of patients ranges from 11 to 57 with a mean of 30.7 years; the sex-ratio is 0.8 (19 males and 23 females). There are 33 cases of nodular-sclerosing Hodgkin lymphoma, 6 of mixed cellularity, one lymphocyte-rich, one interfollicular and one granulomatous. As for the stages, 31 Hodgkin lymphomas are stage IIA, 6 stage IA, 3 bulky and 2 stage IAe. The ABVD protocol was given to 38 patients, the VBVP to 3 patients and the ABV to one patient. IFRT was used with dose ranging from 19.8 to 39.6 Gy. The acute toxicity of chemotherapy was hematologic only, grade 1 anemia accounting for 11.1% and grade 2 anemia for 14.8%, grade 1 leukopenia for 51.8%, grade 2 leukopenia for 333% and grade 3 leukopenia for 14.8%. Dysphagia, radiodermitis and radiomucositis were seen after radiotherapy, accounting for 16.5%, 4.6% and 9.1% respectively. No long-term toxicity of the combined therapy was found. During the follow-up period, one relapse occurred and no death was reported. CONCLUSION: The overall survival (OS), the disease free survival (DFS) and the toxicities of the combined therapy CT-RT of the patients with early stage Hodgkin lymphoma stage IA and IIA treated in our institution were similar to those seen in the literature.