Approaches for enhancing the informativeness and quality of clinical trials: Innovations and principles for implementing multicenter trials from the Trial Innovation Network.

One challenge for multisite clinical trials is ensuring that the conditions of an informative trial are incorporated into all aspects of trial planning and execution. The multicenter model can provide the potential for a more informative environment, but it can also place a trial at risk of becoming uninformative due to lack of rigor, quality control, or effective recruitment, resulting in premature discontinuation and/or non-publication. Key factors that support informativeness are having the right team and resources during study planning and implementation and adequate funding to support performance activities. This communication draws on the experience of the National Center for Advancing Translational Science (NCATS) Trial Innovation Network (TIN) to develop approaches for enhancing the informativeness of clinical trials. We distilled this information into three principles: (1) assemble a diverse team, (2) leverage existing processes and systems, and (3) carefully consider budgets and contracts. The TIN, comprised of NCATS, three Trial Innovation Centers, a Recruitment Innovation Center, and 60+ CTSA Program hubs, provides resources to investigators who are proposing multicenter collaborations. In addition to sharing principles that support the informativeness of clinical trials, we highlight TIN-developed resources relevant for multicenter trial initiation and conduct.

Development, implementation, and dissemination of operational innovations across the trial innovation network.

Improving the quality and conduct of multi-center clinical trials is essential to the generation of generalizable knowledge about the safety and efficacy of healthcare treatments. Despite significant effort and expense, many clinical trials are unsuccessful. The National Center for Advancing Translational Science launched the Trial Innovation Network to address critical roadblocks in multi-center trials by leveraging existing infrastructure and developing operational innovations. We provide an overview of the roadblocks that led to opportunities for operational innovation, our work to develop, define, and map innovations across the network, and how we implemented and disseminated mature innovations.

Bayesian deep learning outperforms clinical trial estimators of intracerebral and intraventricular hemorrhage volume.

BACKGROUND AND PURPOSE: Intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) clinical trials rely on manual linear and semi-quantitative (LSQ) estimators like the ABC/2, modified Graeb and IVH scores for timely volumetric estimation from CT. Deep learning (DL) volumetrics of ICH have recently approached the accuracy of gold-standard planimetry. However, DL and LSQ strategies have been limited by unquantified uncertainty, in particular when ICH and IVH estimates intersect. Bayesian deep learning methods can be used to approximate uncertainty, presenting an opportunity to improve quality assurance in clinical trials. METHODS: A DL model was trained to simultaneously segment ICH and IVH using diagnostic CT data from the Minimally Invasive Surgery Plus Alteplase for ICH Evacuation (MISTIE) III and Clot Lysis: Evaluating Accelerated Resolution of IVH (CLEAR) III clinical trials. Bayesian uncertainty approximation was performed using Monte-Carlo dropout. We compared the performance of our model with estimators used in the CLEAR IVH and MISTIE II trials. The reliability of planimetry, DL, and LSQ volumetrics in the setting of high ICH and IVH intersection is quantified using consensus estimates. RESULTS: Our DL model produced volume correlations and median Dice scores of .994 and .946 for ICH in MISTIE II, and .980 and .863 for IVH in CLEAR IVH, respectively, outperforming LSQ estimates from the clinical trials. We found significant linear relationships between ICH uncertainty, Dice scores (r = -.849), and relative volume difference (r = .735). CONCLUSION: In our validation clinical trial dataset, DL models with Bayesian uncertainty approximation provided superior volumetric estimates to LSQ methods with real-time estimates of model uncertainty.

Post-Trial Enhanced Deployment and Technical Performance with the MISTIE Procedure per Lessons Learned.

OBJECTIVE: We hypothesize that procedure deployment rates and technical performance with minimally invasive surgery and thrombolysis for intracerebral hemorrhage (ICH) evacuation (MISTIE) can be enhanced in post-trial clinical practice, per Phase III trial results and lessons learned. MATERIALS AND METHODS: We identified ICH patients and those who underwent MISTIE procedure between 2017-2021 at a single site, after completed enrollments in the Phase III trial. Deployment rates, complications and technical outcomes were compared to those observed in the trial. Initial and final hematoma volume were compared between site measurements using ABC/2, MISTIE trial reading center utilizing manual segmentation, and a novel Artificial Intelligence (AI) based volume assessment. RESULTS: Nineteen of 286 patients were eligible for MISTIE. All 19 received the procedure (6.6% enrollment to screening rate 6.6% compared to 1.6% at our center in the trial; p=0.0018). Sixteen patients (84%) achieved evaculation target < 15 mL residual ICH or > 70% removal, compared to 59.7% in the trial surgical cohort (p=0.034). No poor catheter placement occurred and no surgical protocol deviations. Limitations of ICH volume assessments using the ABC/2 method were shown, while AI based methodology of ICH volume assessments had excellent correlation with manual segmentation by experienced reading centers. CONCLUSIONS: Greater procedure deployment and higher technical success rates can be achieved in post-trial clinical practice than in the MISTIE III trial. AI based measurements can be deployed to enhance clinician estimated ICH volume. Clinical outcome implications of this enhanced technical performance cannot be surmised, and will need assessment in future trials.

3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for Clinical Trials.

Intracranial hemorrhage (ICH) occurs when a blood vessel ruptures in the brain. This leads to significant morbidity and mortality, the likelihood of which is predicated on the size of the bleeding event. X-ray computed tomography (CT) scans allow clinicians and researchers to qualitatively and quantitatively diagnose hemorrhagic stroke, guide interventions and determine inclusion criteria of patients in clinical trials. There is no currently available open source, validated tool to quickly segment hemorrhage. Using an automated pipeline and 2D and 3D deep neural networks, we show that we can quickly and accurately estimate ICH volume with high agreement with time-consuming manual segmentation. The training and validation datasets include significant heterogeneity in terms of pathology, such as the presence of intraventricular (IVH) or subdural hemorrhages (SDH) as well as variable image acquisition parameters. We show that deep neural networks trained with an appropriate anatomic context in the network receptive field, can effectively perform ICH segmentation, but those without enough context will overestimate hemorrhage along the skull and around calcifications in the ventricular system. We trained with all data from a multi-center phase II study (n = 112) achieving a best mean and median Dice coefficient of 0.914 and 0.919, a volume correlation of 0.979 and an average volume difference of 1.7 ml and root mean squared error of 4.7 ml in 500 out-of-sample scans from the corresponding multi-center phase III study. 3D networks with appropriate anatomic context outperformed both 2D and random forest models. Our results suggest that deep neural network models, when carefully developed can be incorporated into the workflow of an ICH clinical trial series to quickly and accurately segment ICH, estimate total hemorrhage volume and minimize segmentation failures. The model, weights and scripts for deployment are located at https://github.com/msharrock/deepbleed . This is the first publicly available neural network model for segmentation of ICH, the only model evaluated with the presence of both IVH and SDH and the only model validated in the workflow of a series of clinical trials.

Association of Neuronal Injury in the Genu and Body of Corpus Callosum After Cranial Irradiation in Children With Impaired Cognitive Control: A Prospective Study.

PURPOSE: Brain radiation is associated with functional deficits in children. The purpose of this study was to examine white matter integrity as measured by diffusion tensor imaging and associations with region-specific radiation dose and neuropsychological functioning in children treated with cranial irradiation. METHODS AND MATERIALS: A total of 20 patients and 55 age- and sex-matched controls were included in the present study. Diffusion tensor imaging and neuropsychological assessments were conducted at baseline and 6, 15, and 27 months after treatment. The neuropsychological assessment included motor dexterity, working memory, and processing speed. White matter regions were contoured, and the apparent diffusion coefficient (ADC) and fractional anisotropy (FA) were recorded for each participant. Linear mixed effects regression models were used to prospectively compare the associations among ADC, FA, radiation dose to contoured structures, and performance on the neuropsychological assessments over time. RESULTS: The mean prescription dose was 44 Gy (range 12-54). Across visits, compared with the controls, the patients showed a significantly increased ADC across all selected regions and alterations in FA in the dorsal midbrain and corpus callosum (genu, splenium, body). An increased radiation dose to the genu and body of the corpus callosum was associated with alterations in ADC and FA and reduced neuropsychological performance, most notably motor speed and processing. CONCLUSIONS: These prospective data suggest that subcortical white matter, especially the genu and body of the corpus callosum, could be regions with increased susceptibility to radiation-induced injury, with implications for cognitive function.