top of page
Last Updated:
15th May 2023
Genki (‘Healthy’ in Japanese) is an AI powered Chest X-Ray Screening solution that leverages cutting edge AI technology to analyze Chest X-Rays scans to automatically triage patients for different chest pathologies in a speedy and cost-effective way. Using AI to triage TB suspects from Chest X-Rays reduces the burden on radiologist and expensive tests; reducing the turn around time and loss to follow up. Genki can be used as an Genki Edge (Offline) Solution and/or Cloud (Online) in hospitals/facility centers or in mobile X-Ray vans at hotspots. Genki is an End-to-End solution that helps in capturing patient health information, symptomatic data, X-Ray results, radiologist report, analytics and notifications.
Genki has undergone independent third-party evaluation by WHO-supported firms like Friends for International Tuberculosis Relief (FIT) and StopTB Partnership. These evaluation studies have confirmed that the accuracy of DeepTek’s AI solution in triaging TB suspects is at par or better than human experts.
Genki’s strong differentiation is that it ensures AI model accuracies are never compromised by leveraging the “Expert in the loop” model.
Certification
Ministry of Health - Pharmacy and Poisons Board, Kenya
Thai Food and Drug Administration
US Food and Drug Administration
Central Drugs Standard Control Organization
Development Stage
On the Market
Deployment
Online & Offline
Intended Age Group
2+ years
Target Setting
Large -Scale government run TB Screening Programmes, General Hospitals, Primary Health Centers, Teleradiology Centers, etc.
Current Market
Deployment in: India, Philippines, Thailand, Indonesia, and Mongolia
Targeted Market: Asia Pacific Region, Middle East, Africa, USA, Europe
Input
Posterior anterior or anterior-posterior chest X-ray image (Frontal Radiographs) in DICOM/PNG/JPG formats.
Output
Triaged Worklist identifying “TB Suspect” separately
Structured report including:
Heat map/Outline showing regions suspected of TB
Probability score for TB
Locating zone of each abnormality
Probability scores for 20+ pulmonary abnormalities other than TB
Dashboard and Analytics
genki_output_1.png
genki_output_2.png
genki_output_1.png
1/2
Hardware
i5 processor or equivalent, 8 GB RAM (for local installation)
Server
Server location:
Both cloud deployment and local on-premises deployment are supported. Genki can be deployed on any cloud like GCP, Azure, AWS etc. depending on the geography of the client. While offline deployment can be done on any computer or laptop with given specification.
Hardware
i5 processor or equivalent, 8 GB RAM (for local installation)
Integration with X-ray Systems
Integration with PACS and Legacy Systems
Genki can be directly connected to any X-Ray modality irrespective of the vendor. Shimadzu, Philips, Fujifilm, Carestream, etc. are some of the modalities with which Genki feasibility has been successfully verified.
Genki can be connected with the PACS used by the client. Genki details need to be configured in PACS or modality workstation for the DICOM communications.
Software
Cloud deployment: Browser (Chrome, Firefox)
Local deployment: Microsoft Windows / Linux / Docker (all other dependencies will be handled by Docker)
Processing Time
Less than 30 seconds
Data Sharing & Privacy
Data are anonymized before processing and not shared with developers.
Price
Different pricing models like One Time Licensing model or Per Scan Model based on Volume of scans can be provided from case to case basis with annual maintenance cost. Please contact info@deeptek.ai.
Software Updates
Minor updates monthly (for online only), major updates yearly (for online and offline)
Software upgrades are included in the license price
Product Development Method
Supervised and unsupervised deep learning model architectures.
Training
The artificial intelligence models were trained on 1.5 million chest X-rays from over 10 countries.
Reference Standard
Human Readers.
Publications
Please visit https://www.deeptek.ai/publications
This website works best with browsers other than Internet Explorer.
bottom of page