Learning from Pseudo-Labels: Deep Networks Improve Consistency in Longitudinal Brain Volume Estimation

Zhan, Geng; Wang, Dongang; Cabezas, Mariano; Bai, Lei; Kyle, Kain; Ouyang, Wanli; Barnett, Michael; Wang, Chenyu

doi:10.2139/ssrn.4373977

Cited by 1 publication

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…negative PBVC), as determined by the two quantitative methods, was discordant in 24/295 (8.1%) of cases, highlighting methodological concerns when applying these tools to individual patients over single, relatively short epochs. Compared to SIENA, we have recently shown that DeepBVC, the brain atrophy algorithm embedded in iQ-MS, demonstrates greater stability and superior performance in test-retest experiments; and is more robust to variance in imaging acquisition [18].…”

Section: Discussionmentioning

confidence: 99%

“…Longitudinal metrics are reported, but returned to the user with a protocol inconsistency warning. Longitudinal whole brain volume change is measured by iQ-MS with the integrated DeepBVC algorithm [18]. Automated estimation of substructure (whole grey matter, thalamus) volume change is produced by a combination of AI-based segmentation and the application of a Jacobian integration method [19].…”

Section: Core Technologymentioning

confidence: 99%

“…Quantification of longitudinal percentage brain volume change (PBVC) between the current and prior scan was determined by a modified hybrid of FMRIB's SIENA [32] on previously determined 'pathological cut-offs' of brain atrophy using SIENA [21], against which the relevant iQ-MS algorithm has been previously validated [18].…”

Section: Core Mri Reading Laboratorymentioning

confidence: 99%

“…The datasets analysed in the current study are available from the corresponding author on reasonable request and with a relevant research agreement. The underlying code for iQ-Solutions TM is not publicly available for proprietary reasons; however, code for specific individual algorithms is described in the relevant references [16][17][18].…”

Section: Data Availabilitymentioning

confidence: 99%

See 3 more Smart Citations

Ai-Based Mri Monitoring in Multiple Sclerosis: Real-World Clinical Validation

Barnett,

Wang,

Beadnall

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Modern management of MS targets No Evidence of Disease Activity (NEDA): no clinical relapses, no magnetic resonance imaging (MRI) disease activity and no disability worsening. While MRI is the principal tool available to neurologists for monitoring clinically silent MS disease activity and, where appropriate, escalating treatment, standard radiology reports are qualitative and may be insensitive to the development of new or enlarging lesions. Existing quantitative neuroimaging tools lack adequate clinical validation. In 397 multi-center MRI scan pairs acquired in routine practice, we demonstrate superior case-level sensitivity of a clinically integrated AI-based tool over standard radiology reports (93.3% vs 58.3%), relative to a consensus ground truth, with minimal loss of specificity. We also demonstrate equivalence of the AI-tool with a core clinical trial imaging lab for lesion activity and quantitative brain volumetric measures, including percentage brain volume loss (PBVC), an accepted biomarker of neurodegeneration in MS (mean PBVC -0.32% vs -0.36% respectively), whereas even severe atrophy (>0.8% loss) was not appreciated in radiology reports. Finally, the AI-tool additionally embeds a clinically meaningful, experiential comparator that returns a relevant MS patient centile for lesion burden, revealing, in our cohort, inconsistencies in qualitative descriptors used in radiology reports. AI-based image quantitation enhances the accuracy of, and value-adds to, qualitative radiology reporting. Scaled deployment of these tools will open a path to precision management for patients with MS.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Core Technologymentioning

confidence: 99%

Section: Core Mri Reading Laboratorymentioning

confidence: 99%

Section: Data Availabilitymentioning

confidence: 99%

See 2 more Smart Citations

Ai-Based Mri Monitoring in Multiple Sclerosis: Real-World Clinical Validation

Barnett,

Wang,

Beadnall

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Learning from Pseudo-Labels: Deep Networks Improve Consistency in Longitudinal Brain Volume Estimation

Cited by 1 publication

References 0 publications

Ai-Based Mri Monitoring in Multiple Sclerosis: Real-World Clinical Validation

Ai-Based Mri Monitoring in Multiple Sclerosis: Real-World Clinical Validation

Contact Info

Product

Resources

About