Citations

Abstract BACKGROUND Interpretation of serial magnetic resonance imaging (MRI) for glioblastoma following radiation therapy (RT) is complicated by difficulty differentiating tumor from treatment-related changes, even using updated RANO criteria. The incorporation of novel imaging such as 3,4-dihydroxy-6-[18F]-fluoro-L-phenylalanine (18F-DOPA) PET/CT to post-treatment serial imaging may improve prognostication and better facilitate future treatment decisions. METHODS The secondary analysis of a recent phase II prospective clinical trial of 18F-DOPA PET/CT-directed dose-escalated RT included patients with IDH-wildtype, MGMT-unmethylated glioblastoma who underwent post-treatment serial 18F-DOPA PET/CT surveillance. Quantitative features were extracted from pre-RT and post-RT serial PET/CT images, and robust prognostic features were selected using an in-house workflow. Both an automated machine learning (ML) algorithm and an interpretable ML algorithm were utilized to correlate surveillance PET image features with subsequent survival of greater than 12 months versus less than 12 months from the surveillance timepoint. Changes from pre-RT to post-RT PET/CT (delta model) were also assessed for association with post-RT survival and validated with a separate cohort. RESULTS Thirty-five patients with IDH-wildtype, MGMT-unmethylated glioblastoma who had at least one available (range: 1-14) post-treatment 18F-DOPA PET/CT were included. Twenty-four were used for model training, while 11 were used for validation. Ultimately, a five-feature post-RT model utilizing two shape, two texture, and one first-order radiomic feature was selected. For the delta model, five texture, two shape, and one first order radiomic feature were selected. The models show 90% accuracy in predicting survival < 12 months post-surveillance on the training set, and 68%-73% accuracy (AUC 0.64-0.73) for the validation cohort. Delta features were significantly associated with overall survival (p < 0.05). CONCLUSIONS Post-RT serial 18F-DOPA PET/CT imaging can help distinguish true tumor progression in patients with glioblastoma using a radiomics model. Tumor response evaluated for changes from pre-RT to post-RT 18F-DOPA PET/CT also predicted subsequent overall survival.

AbstractBackgroundThe growing adoption of magnetic resonance imaging (MRI)‐guided radiation therapy (RT) platforms and a focus on MRI‐only RT workflows have brought the technical challenge of synthetic computed tomography (sCT) reconstruction to the forefront. Unpaired‐data deep learning‐based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired‐ and unpaired‐data results can be limiting.PurposeWe present two distinct approaches aimed at improving unpaired‐data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired‐data setting.MethodsComparisons are made between the following models: (1) the paired‐data fully convolutional DenseNet (FCDN), (2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, (3) the unpaired‐data CycleGAN, (4) the CycleGAN with the IDOL training strategy, and (5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five‐fold cross‐validation scheme, with the patient‐specific IDOL models being trained for the five patients of fold 3, chosen at random.ResultsIn both the paired‐ and unpaired‐data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired‐ and unpaired‐data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal‐to‐noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired‐data approach in fold 3; MAE: 20%; bone MAE: 16%; PSNR: 10%; SSIM: 2%), and differences in body MAE between the ensemble approach and the paired‐data approach are statistically insignificant.ConclusionsWe have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired‐data setting offer significant improvements in image quality metrics for the unpaired‐data sCT reconstruction task. Closing the gap between paired‐ and unpaired‐data approaches is a step toward fully enabling these powerful and attractive unpaired‐data frameworks.

Abstract1q gain (+1q) is the most common high‐risk cytogenetic abnormality (HRCA) in patients with multiple myeloma (MM). However, its prognostic value remains unclear in the era of novel agents. Here, we retrospectively analyzed the impact of +1q on the outcomes of 934 patients newly diagnosed with MM. +1q was identified in 53.1% of patients and verified as an independent variate for inferior overall survival (OS) (hazard ratio, 1.400; 95% confidence interval, 1.097–1.787; p = .007). Concurrence of other HRCAs (particularly t(14;16) and del(17p)) further exacerbated the outcomes of patients with +1q, suggesting prognostic heterogeneity. Thus, a risk‐scoring algorithm based on four risk variates (t(14;16), hypercalcemia, ISS III, and high LDH) was developed to estimate the outcomes of patients with +1q. Of the patients, 376 evaluable patients with +1q were re‐stratified into low (31.6%), intermediate (61.7%), and high risk (6.7%) groups, with significantly different progression‐free survival and OS (p < .0001), in association with early relapse of the disease. The prognostic value of this model was validated in the CoMMpass cohort. While attaining undetectable MRD largely circumvented the adverse impact of +1q, it scarcely ameliorated the outcome of the patients with high risk, who likely represent a subset of patients with extremely poor survival. Hence, patients with +1q are a heterogeneous group of high‐risk patients, therefore underlining the necessity for their re‐stratification. The proposed simple risk‐scoring model can estimate the outcomes of patients with +1q, which may help guide risk‐adapted treatment for such patients.

Previously we showed the generation of a protein trap library made with the gene-break transposon (GBT) in zebrafish ( Danio rerio ) that could be used to facilitate novel functional genome annotation towards understanding molecular underpinnings of human diseases (Ichino et al, 2020). Here, we report a significant application of this library for discovering essential genes for heart rhythm disorders such as sick sinus syndrome (SSS). SSS is a group of heart rhythm disorders caused by malfunction of the sinus node, the heart’s primary pacemaker. Partially owing to its aging-associated phenotypic manifestation and low expressivity, molecular mechanisms of SSS remain difficult to decipher. From 609 GBT lines screened, we generated a collection of 35 zebrafish insertional cardiac (ZIC) mutants in which each mutant traps a gene with cardiac expression. We further employed electrocardiographic measurements to screen these 35 ZIC lines and identified three GBT mutants with SSS-like phenotypes. More detailed functional studies on one of the arrhythmogenic mutants, GBT411 , in both zebrafish and mouse models unveiled Dnajb6 as a novel SSS causative gene with a unique expression pattern within the subpopulation of sinus node pacemaker cells that partially overlaps with the expression of hyperpolarization activated cyclic nucleotide gated channel 4 (HCN4), supporting heterogeneity of the cardiac pacemaker cells.