AI overlay for intracranial-haemorrhage volume measurement

Under reviewPilotDeveloping evidence

Undergoing in-depth clinical, technical and governance review.

Segments and quantifies haemorrhage volume on serial non-contrast head CT to support neurosurgical decision-making and follow-up.

Plain-language summary

Choose an audience and generate a tailored summary on demand. The AI uses only what is on this page.

Clinical context

Clinical problem: Detect a condition
Point of care: Intra-operative
Nature of AI output: A classification
Clinical specialty: Radiology
Care setting: Hospital — inpatient
Patient population: Adults with confirmed intracranial haemorrhage requiring serial CT imaging.
Intended use: Segments and quantifies haemorrhage volume on serial non-contrast head CT to support neurosurgical decision-making and follow-up.

Technology

AI technique: Deep learning, Computer vision
Input data: Medical imaging
Output type: Segmentation
Autonomy level: Informs a human (advisory)
Model provenance: Vendor proprietary
Model version: aspects-3.0
Built on a general-purpose model: No

Deployment

Status: Pilot
Country: Germany
Deployment date: 1 November 2024
Sites: 1

Regulatory & governance

EU AI Act risk tier: High-risk
High-risk basis: Annex I — medical device
Medical device: Yes
EU MDR class: Class IIa
CE marking: CE marked
FDA status: 510(k) cleared
ISO 14971 risk class: Medium
GDPR processing basis: Public interest
GDPR DPIA: Completed
Data identifiability: Pseudonymised
Explainability method: Post-hoc
Human oversight model: Neurosurgeon signs every volume measurement before it informs management.

NICE evidence standards

ESF tier: Tier C — treat / diagnose / calculate risk
Evidence category: Category 3

Performance summary

Headline metric: Sensitivity
Value: 0.94
Subgroup performance assessed: Yes
Known bias signals: —

Similar deployments

Looking for close matches in the Library…

Safety signals

Post-deployment concerns flagged by clinicians, patients or monitoring (proposal §3.7). High or critical signals re-enter a validated use case into maturation automatically.

Volume under-segmentation on three sequential follow-up scans; vendor notified.
Raised 17 May 2026, 21:01
HighInvestigating

Evidence records

Studies and evaluations attached to this use case.

Prospective observational
Time saved: 8
Population: Acute neurosurgical pathway pilot — minutes saved per case
Retrospective validation
Sensitivity: 0.94
Population: Multi-centre ICH cohort, 3k scans

Contributors

Deploying organisation: [demo] Charité – Universitätsmedizin Berlin · Hospital / health system · Germany
AI vendor: [demo] Brainomix · United Kingdom
Product name: e-ASPECTS