Auto-Seg (SO-0012)

by Agada Medical, Ltd.  · Based in Israel → — Software that processes CT images of the spine and pelvis to automatically segment and label vertebrae and pelvis bones, assisting spine surgeons in assessment and surgical planning for adult patients.
Neurosurgery Orthopedics Radiology

Regulatory Status Disclosed

Overview

Auto-Seg (SO-0012) by Agada Medical, Ltd. is an advanced AI-enabled software designed to automate the segmentation of spinal structures in medical imaging. This tool aims to enhance the efficiency and accuracy of radiological assessments, particularly for spine-related conditions.

By leveraging artificial intelligence, Auto-Seg can automatically identify and delineate various anatomical components of the spine from imaging data. This capability significantly reduces the manual effort and time traditionally required by radiologists and clinicians for detailed spinal analysis, allowing them to focus more on diagnosis and treatment planning.

The software is particularly beneficial in scenarios requiring precise measurements and consistent segmentation across multiple images or patient studies. Its automation features contribute to improved workflow in radiology departments and clinics dealing with a high volume of spinal imaging, ultimately supporting better patient care through more streamlined and accurate diagnostic processes.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • AI-powered spine auto-segmentation
  • Automated anatomical delineation
  • Enhanced imaging workflow efficiency
  • Support for various medical imaging modalities
  • Improved accuracy in spinal analysis

Use Cases

  • Radiological assessment of spinal conditions
  • Pre-operative planning for spinal surgeries
  • Monitoring disease progression in spine disorders
  • Research and clinical trials involving spinal imaging
  • Streamlining radiology department workflows

What Physicians Need to Know

DICOM Support & Standards
Auto-Seg (SO-0012) processes CT DICOM images and outputs 3D segmentation masks in DICOM format, STL, and NIfTI files.
PACS Integration Method
The system imports spine and pelvis CT studies as DICOM from an encrypted USB workflow and exports results to an encrypted USB.
AI Model Architecture (deep learning approach)
The software is a software-only AI/ML image processing system that utilizes four convolutional neural network models to segment and label the spine (thoracic and lumbar vertebrae) and pelvis in CT images. It uses non-adaptive machine learning models.
Processing Speed (per study)
Segmentation time is within 10 minutes.
FDA Clearance Pathway (510k/De Novo)
Auto-Seg (SO-0012) received FDA 510(k) clearance (K253628) on June 29, 2026.
Supported Modalities (CT/MRI/X-ray/US)
The tool supports CT imaging of the spine and pelvis.
Sensitivity & Specificity Data
No exact-product, version-specific sensitivity or specificity endpoints were established for this submission in the reviewed evidence.
RSNA/ACR Validation
No specific RSNA or ACR validation for Auto-Seg (SO-0012) was found in the provided information.
Physician Tip

Auto-Seg (SO-0012) is designed to enhance surgical planning for spine procedures by providing automated 3D segmentations of vertebrae and pelvis from CT scans. Physicians should review and confirm the automatically generated labels and segmentations, as the software supports clinical decision-making but does not provide direct diagnoses or treatment recommendations. The output in DICOM, STL, and NIfTI formats allows for flexible integration into various planning systems.

The current integration method involves importing and exporting DICOM data via encrypted USB. For seamless workflow, consider how this fits into your existing PACS and surgical planning systems, and evaluate potential for more direct network integration if needed. The software runs on a standard personal computer with a GPU.

Details

Category Radiology & Imaging AI
Pricing Unknown
DeploymentImports spine and pelvis CT studies as DICOM from an encrypted USB workflow and exports results to encrypted USB; local round-trip acceptance remains necessary. Runs on standard personal computer with GPU.
Compliance
BAA AvailableUnknown
HIPAA CompliantUnknown
FDA Status Cleared AI-estimated
Integrations
EHR Not specified
Specialties Neurosurgery, Orthopedics, Radiology

Ratings & Reviews

No reviews yet. Be the first to review this tool!

Rate Auto-Seg (SO-0012)

Clinical Value
Ease of Use
Integration
Support & Docs
Value for Money
No press coverage or publications on file yet. Know of some? Suggest an edit →

Videos

Product demos, reviews, and walkthroughs for Auto-Seg (SO-0012).

Loading videos...

View all on YouTube

Frequently Asked Questions

Auto-Seg (SO-0012) is an AI-powered software that processes CT images of the spine and pelvis to automatically segment and label vertebrae and pelvis bones. It's intended to assist spine surgeons by providing detailed 3D segmentation outputs for assessing musculoskeletal diseases and surgical planning for adult patients. The software uses validated AI algorithms to support clinical decision-making but does not provide direct diagnoses or treatment recommendations.
Auto-Seg (SO-0012) by Agada Medical, Ltd. has undergone extensive non-clinical validation, including software verification/validation, labeling verification, risk management, human factors/usability testing, and cybersecurity testing, all in accordance with FDA guidance. It is an FDA-cleared device, and its performance was assessed with high accuracy for segmentation and labeling.
Yes, there are several AI auto-segmentation solutions available, including those from Radformation, Limbus, Siemens, RayStation, and MVision AI Contour+. AutoSeg is noted for its browser-based collaborative contour review, vendor-neutral DICOM RTSTRUCT workflow, and clinical AI assistant. The best solution depends on a clinic's specific needs, including their existing treatment planning system, imaging modalities, and collaboration requirements.
While AI auto-segmentation significantly reduces delineation time, manual correction remains necessary, especially for organs with limited image contrast from surrounding tissues. AI-based auto-segmentation models can also be considered 'black boxes,' making model interpretability challenging and results dependent on the training data. Therefore, extensive evaluation is crucial before clinical implementation to understand accuracy and limitations.
Auto-Seg (SO-0012) has demonstrated high accuracy, with segmentation DICE coefficients greater than 0.8 for both spine and pelvis, and labeling accuracy exceeding 99%. Performance is typically assessed using metrics like the DICE coefficient for segmentation accuracy, labeling accuracy, and processing time. While volumetric overlap indices are common, spatial distance-based metrics and dosimetric parameters are also important for a comprehensive evaluation of auto-segmentation tools.

Related Tools

RADIN Health
RADIN Health
Clinical Decision Support & Reference
RADINA is an AI-powered platform by RADIN Health designed to optimize radiology workflows, enhance diagnostic accuracy, and streamline reporting.
VERITON CT 400 Series Digital SPECT/CT System (VERITON CT 416/464)
Spectrum Dynamics Medical
Oncology AI
The VERITON CT 400 Series is a digital SPECT/CT system with a 360-degree gantry and 12 swiveling CZT detectors, offering high sensitivity and quantitative accuracy for a wide range of nuclear medicine applications, including advanced theranostics imaging.
VERITON CT 300 Series Digital SPECT/CT System (VERITON CT 316/364)
Spectrum Dynamics Medical
Radiology & Imaging AI
The VERITON-CT 300 Series Digital SPECT/CT System is a new-generation SPECT/CT system that wraps 360° around the patient's body contour for a personalized exam, utilizing 12 digital CZT detectors for accurate and confident diagnoses.
ACUSON Sequoia Diagnostic Ultrasound System, ACUSON Sequoia Select Diagnostic Ultrasound System, ACUSON Origin Diagnostic Ultrasound System, ACUSON Origin ICE Diagnostic Ultrasound System
Siemens Medical Solutions, USA
Cardiology AI
Siemens Healthineers offers advanced AI-powered ultrasound systems, including the ACUSON Origin for comprehensive cardiovascular care and the ACUSON Sequoia for high-performance general imaging with BioAcoustic™ technology.
syngo.via MI Workflows, syngo MBF
Siemens Medical Solutions USA
Cardiology AI
syngo.via MI Workflows, syngo MBF is an intelligent, integrated imaging software that helps address the challenges of interpreting, managing, and sharing complex data from molecular imaging scanners, providing automated workflows and advanced visualization for various clinical applications.
MAGNETOM Vida, MAGNETOM Sola, MAGNETOM Lumina, MAGNETOM Altea
Siemens Medical Solutions USA
Radiology & Imaging AI
Siemens Medical Solutions USA, Inc. provides innovative medical technologies and services that enhance healthcare delivery, specializing in advanced medical imaging systems like the MAGNETOM MRI series.

See all Radiology & Imaging AI tools →

More from Agada Medical

Auto-Seg (SO-0012), Spine Auto-Seg (SO-0012)
Agada Medical
Radiology & Imaging AI
Agada Medical develops AI-powered software for spine surgery planning and assessment, utilizing predictive analytics and machine learning to improve outcomes and reduce costs.

View company profile →

Suggest an Edit → | Report an issue | Last Verified: 2026-09-23 | First Added: 2026-09-23
AI Tool Finder
AI-powered search. Results may not be comprehensive.