Skip to main content
QMSQMS
QMS
  • Welcome to your QMS
  • Quality Manual
  • Procedures
  • Records
  • Legit.Health Plus Version 1.1.0.0
    • CAPA Plan - BSI CE Mark Closeout
    • Index
    • Overview and Device Description
    • Information provided by the Manufacturer
    • Design and Manufacturing Information
      • R-TF-012-019 SOUPs
        • Aioboto3
        • Albumentations
        • Argon2-CFFI
        • Authlib
        • Boto3
        • Dependency Injector
        • Dill
        • FastAPI
        • PyTorch Grad-CAM
        • Httpx
        • NumPy
        • PyNVML
        • OpenCV
        • Pillow
        • Psutil
        • Pydantic
        • Pydantic Settings
        • PyYAML
        • Segmentation Models PyTorch
        • Starlette
        • Timm
        • PyTorch
        • TorchVision
        • Ultralytics YOLO
        • Uvicorn
      • R-TF-012-028 Software Requirement Specification
      • R-TF-012-029 Software Architecture Description
      • R-TF-012-030 Software Configuration Management Plan
      • R-TF-012-031 Product requirements specification
      • R-TF-012-037 Labeling and IFU Requirements
      • R-TF-012-040 Documentation level FDA
      • R-TF-012-041 Software Classification 62304
      • R-TF-012-043 Traceability Matrix
      • Review meetings
    • GSPR
    • Benefit-Risk Analysis and Risk Management
    • Product Verification and Validation
    • Post-Market Surveillance
  • Legit.Health Plus Version 1.1.0.1
  • Legit.Health Utilities
  • Licenses and accreditations
  • Applicable Standards and Regulations
  • Pricing
  • Public tenders
  • Legit.Health Plus Version 1.1.0.0
  • Design and Manufacturing Information
  • R-TF-012-019 SOUPs
  • Ultralytics YOLO

Ultralytics YOLO

General Information​

FieldValue
Package Nameultralytics
Manufacturer / VendorUltralytics Inc.
Software CategoryLibrary
Primary DocumentationDocumentation, GitHub, PyPI
Programming Language(s)Python
LicenseAGPL-3.0 (Enterprise license available)
Deployed Version(s)>=8.3.50
Most Recent Available Version8.4.7
Last Review Date2026-01-26

Overview​

Ultralytics is a state-of-the-art computer vision library that provides implementations of the YOLO (You Only Look Once) family of object detection models. The library supports multiple vision AI tasks including object detection, instance segmentation, image classification, pose estimation, and oriented bounding box detection, with models optimized for both accuracy and inference speed.

Within the medical device software, ultralytics serves as the foundational object detection framework in the legithp-expert detection module. It powers multiple clinical expert microservices for automated lesion detection in dermatological images:

  • Acneiform lesion detection: Identifying pustules, papules, and other acne-related clinical signs
  • Hair follicle detection: Counting and localizing hair follicles for alopecia assessment and hair density analysis
  • Hive detection: Localizing urticarial wheals in clinical images
  • Inflammatory nodular lesion detection: Detecting abscesses, draining tunnels, and nodules using oriented bounding boxes for improved accuracy on irregularly shaped lesions
  • Head detection: Auxiliary detection for image preprocessing and region-of-interest extraction

The library was selected for its comprehensive YOLOv8 implementation, support for both axis-aligned and oriented bounding boxes (essential for irregularly shaped dermatological lesions), active maintenance with regular security updates, efficient inference on both CPU and GPU hardware, and extensive model export capabilities for deployment optimization.

Functional Requirements​

The following functional capabilities of this SOUP are relied upon by the medical device software.

Requirement IDDescriptionSource / Reference
FR-001Load pre-trained YOLO model weights from .pt checkpoint filesYOLO class constructor
FR-002Perform object detection inference on RGB image arraysYOLO.__call__() method
FR-003Return detection results with bounding box coordinates and confidence scoresResults class
FR-004Support axis-aligned bounding boxes (xyxy format) for standard detectionBoxes class
FR-005Support oriented bounding boxes (xyxyxyxy format) for rotated detectionOBB class
FR-006Provide class label mapping from model vocabularyResults.names property
FR-007Support configurable confidence thresholds for detection filteringconf parameter
FR-008Support configurable IoU thresholds for non-maximum suppressioniou parameter
FR-009Support class-agnostic NMS for multi-class detection scenariosagnostic_nms parameter
FR-010Enable device placement (CPU/CUDA) for inference optimizationYOLO.to() method

Performance Requirements​

The following performance expectations are relevant to the medical device software.

Requirement IDDescriptionAcceptance Criteria
PR-001Detection inference shall complete within acceptable API latency boundsInference completes within the overall request timeout
PR-002Memory usage shall scale predictably with model size and input resolutionNo memory leaks during repeated inference operations
PR-003GPU utilization shall be efficient for batch-size-1 inferenceSingle-image processing without unnecessary overhead

Hardware Requirements​

The following hardware dependencies or constraints are imposed by this SOUP component.

Requirement IDDescriptionNotes / Limitations
HR-001CUDA-compatible GPU recommended for optimal performanceCPU execution supported but significantly slower
HR-002Sufficient GPU memory for model weights and activationsMemory requirements scale with model variant (nano to extra-large)
HR-003x86-64 or ARM64 processor architecturePre-built wheels available for common platforms

Software Requirements​

The following software dependencies and environmental assumptions are required by this SOUP component.

Requirement IDDescriptionDependency / Version Constraints
SR-001Python runtime environmentPython >=3.8
SR-002PyTorch deep learning frameworkCompatible with torch >=1.8
SR-003NumPy for array operationsRequired for image data handling
SR-004OpenCV for image preprocessingcv2 module for format conversion
SR-005torchvision for model operationsCompatible versions with torch

Known Anomalies Assessment​

This section evaluates publicly reported issues, defects, or security vulnerabilities associated with this SOUP component and their relevance to the medical device software.

Anomaly ReferenceStatusApplicableRationaleReviewed At
Supply Chain Attack (Dec 2024)FixedNoAffected versions 8.3.41, 8.3.42, 8.3.45, 8.3.46 only; the device uses >=8.3.50 which includes remediation2026-01-26
GitHub Actions InjectionFixedNoBuild infrastructure vulnerability exploited in Dec 2024 attack; Ultralytics implemented security hardening post-incident2026-01-26
PyTorch CVE-2025-32434 (torch.load RCE)FixedNoThe device does not use torch.load() with untrusted model files; all models are pre-deployed and signed2026-01-26
PyTorch CVE-2025-2953 (DoS)OpenNoAffects mkldnn_max_pool2d function not used by the device's detection pipelines2026-01-26

The most significant security incident affecting ultralytics was a supply chain compromise in December 2024. Malicious actors exploited a vulnerability in GitHub Actions to inject cryptomining malware into versions 8.3.41, 8.3.42, 8.3.45, and 8.3.46 on PyPI. The attack was detected and remediated within days, with clean versions released starting from 8.3.43 and definitively from 8.3.47 onwards after API token rotation.

The device's minimum version requirement of >=8.3.50 ensures only post-remediation releases are deployed. Additionally, the device implements the following safeguards:

  • Pinned dependencies: Version constraints prevent accidental installation of compromised versions
  • Internal artifact repository: Production deployments use internally vetted package mirrors rather than direct PyPI access
  • Model file verification: YOLO model weights (.pt files) are pre-deployed and integrity-verified, not downloaded at runtime

According to Ultralytics' security policy, the project employs Snyk scanning, GitHub CodeQL analysis, Dependabot alerts, and secret scanning for continuous security monitoring. The project maintains active security practices and responds promptly to reported vulnerabilities.

Risk Control Measures​

The following risk control measures are implemented to mitigate potential security and operational risks associated with this SOUP component:

  • Version pinning above known-compromised releases (>=8.3.50) ensures only post-remediation versions are deployed
  • Internal package repositories (artifact mirrors) are used rather than direct PyPI access in production
  • Only pre-vetted model weights (.pt files) are deployed; no runtime model downloading
  • Detection services are isolated from external code execution paths
  • Container isolation limits potential impact of any exploitation

Assessment Methodology​

The following methodology was used to identify and assess known anomalies:

  • Sources consulted: National Vulnerability Database (NVD), GitHub Security Advisories, Snyk vulnerability database, vendor security bulletins, and security research publications from Wiz, BleepingComputer, and CSO Online
  • Criteria for determining applicability: Vulnerabilities were assessed based on affected version ranges, attack vectors (supply chain vs. runtime), and whether the device's deployment model exposes the vulnerable functionality

Signature meaning

The signatures for the approval process of this document can be found in the verified commits at the repository for the QMS. As a reference, the team members who are expected to participate in this document and their roles in the approval process, as defined in Annex I Responsibility Matrix of the GP-001, are:

  • Author: Team members involved
  • Reviewer: JD-003, JD-004
  • Approver: JD-001
Previous
TorchVision
Next
Uvicorn
  • General Information
  • Overview
  • Functional Requirements
  • Performance Requirements
  • Hardware Requirements
  • Software Requirements
  • Known Anomalies Assessment
    • Risk Control Measures
    • Assessment Methodology
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.)