Skip to main content
QMSQMS
QMS
  • Welcome to your QMS
  • Quality Manual
  • Procedures
  • Records
    • GP-001 Documents and records control
    • GP-002 Quality planning
      • Deprecated
      • R-002-001 Quality objectives list_2024_001
      • R-002-001 Quality objectives list_2025
      • R-002-002 Quality objectives_2024_001
      • R-002-002 Quality objectives_2024_002
      • R-002-002 Quality objectives_2024_003
      • R-002-002 Quality objectives_2024_004
      • R-002-002 Quality objectives_2024_005
      • R-002-002 Quality objectives_2025_001
      • R-002-002 Quality objectives_2025_002
      • R-002-002 Quality objectives_2025_003
      • R-002-002 Quality objectives_2025_004
      • R-002-002 Quality objectives_2025_005
      • R-002-003 Quality indicators_2024
      • R-002-004 Annual management review report
      • R-002-005 Quality Calendar_2025
      • R-002-006 SWOT and CAME analysis
      • R-002-007
        • R-002-007 Process validation card 2023_001
        • R-002-007 Process validation card 2023_002
        • R-002-007 Process validation card 2023_003
        • R-002-007 Process validation card 2023_004
        • R-002-007 Process validation card 2023_005
        • R-002-007 Process validation card 2023_006
        • R-002-007 Process validation card 2023_007
        • R-002-007 Process validation card 2023_008
        • R-002-007 Process validation card 2023_009
        • R-002-007 Process validation card 2023_010
        • R-002-007 Process validation card 2023_011
        • R-002-007 Process validation card 2023_012
        • R-002-007 Process validation card 2023_014
        • R-002-007 Process validation card 2023_015
        • R-002-007 Process validation card 2023_016
        • R-002-007 Process validation card 2023_017
        • R-002-007 Process validation card 2023_018
        • R-002-007 Process validation card 2024_001
        • R-002-007 Process validation card 2024_002
      • R-002-008 Quality and regulatory roadmap
      • R-002-009 Regulatory requirements review report
    • GP-003 Audits
    • GP-004 Vigilance system
    • GP-005 HR and training
    • GP-007 Post-market surveillance
    • GP-009 Sales
    • GP-010 Suppliers
    • GP-012 Design, Redesign and Development
    • GP-018 Infrastructure and facilities
    • GP-019 Software validation
    • GP-023 Change control management
    • GP-050 Data Protection
    • GP-051 Security violations
    • GP-052 Data Privacy Impact Assessment (DPIA)
    • GP-200 Remote Data Acquisition in Clinical Investigations
  • TF_Legit.Health_Plus
  • Licenses and accreditations
  • External documentation
  • Records
  • GP-002 Quality planning
  • R-002-007
  • R-002-007 Process validation card 2024_001

R-002-007 Process validation card 2024_001

Process​

Design and development

Requirements​

We require an annotation tool that offers full organizational control, ensuring that image data remains within our secure environment without the need for third-party involvement. Additionally, the tool should possess the versatility to annotate various shapes and categories, empowering us to accurately label diverse datasets for our specific needs.

Selection description​

We have chosen to use CVAT as image annotation tool, which has the following characteristics:

  • Versatility: CVAT supports a wide range of annotation types including bounding boxes, polygons, keypoints, and more, catering to diverse annotation needs in medical image analysis.
  • Collaborative features: With its web-based interface and multi-user support, CVAT enables collaborative annotation efforts, allowing multiple annotators to work on the same dataset simultaneously, enhancing efficiency and consistency.
  • Customizability: CVAT offers customization options such as custom attributes and labels, enabling adaptation to specific annotation requirements in healthcare applications, ensuring the annotation schema aligns with the needs of the medical domain.
  • Scalability: Designed to handle large-scale datasets, CVAT provides efficient tools for managing and annotating extensive collections of medical images, facilitating the development of robust computer vision models for healthcare.
  • Integration capabilities: CVAT offers integration with popular deep learning frameworks and data management platforms, streamlining the workflow from annotation to model training, making it a seamless choice for developing advanced computer vision solutions in healthcare.
  • Security measures: CVAT prioritizes data security with features such as user authentication, role-based access control, and secure data transmission protocols. These measures ensure that sensitive medical image data remains protected, complying with healthcare industry standards and regulations.
  • Audit trails: CVAT maintains detailed audit trails, recording every annotation action and user interaction. This accountability feature enhances transparency and traceability, critical for maintaining the integrity and confidentiality of medical datasets, especially in environments with strict privacy requirements.
  • On-premises deployment: For organizations with heightened security concerns, CVAT offers an on-premises deployment option. This allows healthcare institutions to have complete control over their annotation environment, ensuring that the entire annotation workflow occurs within a secure, locally managed infrastructure.
  • Regular security updates: CVAT is actively maintained, with regular updates and security patches. This commitment to ongoing development ensures that any potential vulnerabilities are promptly addressed, keeping the annotation tool resilient against emerging security threats in the healthcare domain.

Validation​

CVAT (Computer Vision Annotation Tool) is a comprehensive annotation tool designed for labeling images and videos with bounding boxes, polygons, and keypoints, making it ideal for developing computer vision models in healthcare as it streamlines the annotation process for medical image datasets, ensuring accurate and efficient labeling for training robust algorithms to aid in diagnosis and treatment.

Record signature meaning​

  • Author: JD-005 Alfonso Medela
  • Review and approval: JD-001 Andy Aguilar
Previous
R-002-007 Process validation card 2023_018
Next
R-002-007 Process validation card 2024_002
  • Process
  • Requirements
  • Selection description
  • Validation
  • Record signature meaning
All the information contained in this QMS is confidential. The recipient agrees not to transmit or reproduce the information, neither by himself nor by third parties, through whichever means, without obtaining the prior written permission of Legit.Health (AI LABS GROUP S.L.)