CoLumbo is an AI-powered software that utilizes fully convolutional neural networks to automatically read and analyze lumbar spine MRI scans, generating pre-populated reports that include detailed measurements and pathology assessments. This technology reduces radiologists' reporting time by 15% to 25% and decreases errors of omission by up to 15%, enhancing diagnostic accuracy and efficiency in clinical settings.
Funding
€4.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
BECEVNVSAFounders
Product
Problem
Radiologists face increasing workloads and time constraints when interpreting lumbar spine MRI scans, potentially leading to errors of omission and inconsistencies in reporting. Manual analysis and measurement of spinal structures and pathologies are time-consuming and can vary between readers, impacting diagnostic accuracy.
Solution
CoLumbo is an AI-powered software designed to automate the analysis of lumbar spine MRI scans and generate pre-populated reports. Utilizing fully convolutional neural networks and medical domain knowledge, the software automatically segments and measures spinal structures, identifies potential pathologies, and creates a draft report for review. By automating these tasks, CoLumbo reduces radiologists' reporting time and minimizes errors of omission, leading to improved diagnostic accuracy and efficiency. The software also promotes standardization in reporting practices across multiple facilities through customizable pathology threshold levels.
Target Audience
CoLumbo is intended for use by radiologists, particularly generalists and those in hospital and imaging center chains, who seek to improve efficiency, accuracy, and standardization in lumbar spine MRI reporting.
Features
- Automated segmentation of vertebral bodies, discs, nerve roots, and other key anatomical structures in lumbar spine MRI scans
- Detection and measurement of herniations (size, location, migration), protrusions, extrusions, nerve root impingement, and dural sac compression
- Identification of spinal stenosis (central, lateral recess), spondylolisthesis (antero, retro), bulging, hypo/hyper-lordosis, and osteophytes
- Quantification of disc and vertebral body heights, spinal canal diameter, foraminal size, and other clinically relevant measurements
- Customizable threshold levels for suspected pathologies, enabling standardization across multiple sites
- Generation of pre-populated draft reports in multiple languages, including English, Bulgarian, German, French, Spanish, Italian, Romanian, and Polish
- Seamless PACS integration for streamlined workflow