Theragnostic Gadolinium-Based Nanoparticles Safely Augment X-ray Radiation Effects in Patients with Cervical Cancer.

Activated guided irradiation by X-ray (AGuIX) nanoparticles are gadolinium-based agents that have the dual benefit of mimicking the effects of a magnetic resonance imaging (MRI) contrast agent used in a clinical routine and enhancing the radiotherapeutic activity of conventional X-rays (for cancer treatment). This "theragnostic" action is explained on the one hand by the paramagnetic properties of gadolinium and on the other hand by the generation of high densities of secondary radiation following the interaction of ionizing radiation and high-Z atoms, which leads to enhanced radiation dose deposits within the tumors where the nanoparticles accumulate. Here, we report the results of a phase I trial that aimed to assess the safety and determine the optimal dose of AGuIX nanoparticles in combination with chemoradiation and brachytherapy in patients with locally advanced cervical cancer. AGuIX nanoparticles were administered intravenously and appropriately accumulated within tumors on a dose-dependent manner, as assessed by T1-weighted MRI, with a rapid urinary clearance of uncaught nanoparticles. We show that the observed tumor accumulation of the compounds can support precise delineation of functional target volumes at the time of brachytherapy based on gadolinium enhancement. AGuIX nanoparticles combined with chemoradiation appeared well tolerated among the 12 patients treated, with no dose-limiting toxicity observed. Treatment yielded excellent local control, with all patients achieving complete remission of the primary tumor. One patient had a distant tumor recurrence. These results demonstrate the clinical feasibility of using theranostic nanoparticles to augment the accuracy of MRI-based treatments while focally enhancing the radiation activity in tumors.

Automatic gross tumor volume segmentation with failure detection for safe implementation in locally advanced cervical cancer.

Background and Purpose: Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features. Methods and materials: We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient ( DSC ) < T and DSC ⩾ T . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing. Results: Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC ( SDSC 3 mm ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16, SDSC 3 mm =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( M =0) on the test cohort. Failure detection could generate precision ( P = 0.88 ), recall ( R = 0.75 ), F1-score ( F = 0.81 ), and accuracy ( A = 0.86 ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values. Conclusions: Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.