Lung Texture Analysis

Imbio

Lung Texture Analysis ™ from Imbio automatically applies computer vision to transform a standard chest CT into a map of the lung textures to identify ILD’s and other fibrotic conditions (normal, ground glass, reticular, honeycomb and hyperlucent). LTA’s DICOM image series provides a texture overlay on the patient scan to highlight abnormalities and increase diagnostic confidence. LTA’s physician summary report provides quantification of the textures by lung region.
Product specifications Information source: Vendor
Last updated: Sept. 11, 2020
General
Product name Lung Texture Analysis
Company Imbio
Subspeciality Chest
Modality CT
Disease targeted Interstitial lung diseases, fibrosis, UIP
Key-features fibrotic condition identification, percentage of lung affected, volume quantification, report generation
Suggested use Before: stratifying reading process (non, single, double read), adapting worklist order, flagging acute findings
During: perception aid (prompting all abnormalities/results/heatmaps), interactive decision support (shows abnormalities/results only on demand)
Without interference of a radiologist: AI-only diagnosis
Data characteristics
Population All chest CT's, lung cancer screening population, COPD, emphysema, ILD, Covid-19
Input Low dose or HRCT
Input format DICOM
Output Report in PDF or DICOM, overlays, lobe segmentation overlay
Output format DICOM, HL7, PDF
Technology
Integration Integration in standard reading environment (PACS), Integration via AI marketplace or distribution platform, Stand-alone third party application, Stand-alone webbased
Deployment Locally virtualized (virtual machine, docker), Cloud-based, Web based
Trigger for analysis Automatically, right after the image acquisition, On demand, triggered by a user through e.g. a button click, image upload, etc.
Processing time 1 - 10 minutes
Certification
CE Certified, Class IIa
FDA No or not yet
Market presence
On market since 2015
Distribution channels Nuance, Eureka Clinical AI, syngo.via
Countries present (clinical, non-research use) >10
Paying clinical customers (institutes) >20
Research/test users (institutes) >20
Pricing
Pricing model Pay-per-use, Subscription
Based on Number of installations, Number of analyses
Evidence
Peer reviewed papers on performance
Non-peer reviewed papers on performance
Other relevant papers