Bayesian deep learning outperforms clinical trial estimators of intracerebral and intraventricular hemorrhage volume. Issue 5 (17th April 2022)

• Record Type: Journal Article
• Authors: Sharrock, Matthew F.; Mould, W. Andrew; Hildreth, Meghan; Ryu, E. Paul; Walborn, Nathan; Awad, Issam A.; Hanley, Daniel F.; Muschelli, John
• Is Part Of: Journal of neuroimaging. Volume 32:Issue 5(2022)
• Page Start: 968
• Page End: 976
• Publication Date: 2022-04-17
• Subjects: clinical trials -- intracerebral hemorrhage -- neural networks -- neuroimaging; Diagnostic imaging -- Periodicals; Nervous system -- Diseases -- Diagnosis -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Système nerveux -- Maladies -- Diagnostic -- Périodiques; Imagerie médicale; Neuroimagerie; Neurologie; Système nerveux; Périodique électronique (Descripteur de forme); Ressource Internet (Descripteur de forme); 616.804754
• DOI: 10.1111/jon.12997
• Languages: English
• ISSNs: 1051-2284

Abstract

Abstract: 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.