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
Website Contact
Claim this tool
Is this the maker? Claim the company →

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 — 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.
Data ExportUnknown
Compliance
BAA AvailableUnknown AI-estimated
HIPAA CompliantUnknown AI-estimated
FDA Status Cleared AI-estimated

FDA-cleared radiology AI listing for CT/CTA. It provides three-dimensional segmentation and labels to support spine-surgery planning and assessment by spine surgeons. The software uses validated AI algorithms and does not provide direct diagnoses but supports clinical decision-making.
Integrations
EHR Not specified
Specialties Neurosurgery, Orthopedics, Radiology

Social Proof

Customersunknown
Notable
unknown

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

Press & Coverage

FDA
K253628 - 510(k) Premarket Notification - FDA
Agada Medical, Ltd. received 510(k) clearance for Auto-Seg (SO-0012) on August 31, 2026, a device for automated radiological image processing and analysis. The device is intended to provide automated radiological image processing and analysis tools.
2026-08
Agada Medical, Ltd.
Auto-Seg (SO-0012), Spine Auto-Seg (SO-0012) | Agada Medical, Ltd. radiology AI profile
Auto-Seg (SO-0012) is an FDA-cleared radiology AI listing for CT/CTA that accepts spine and pelvis CT images and provides three-dimensional segmentation and labels to support spine-surgery planning and assessment by spine surgeons. The FDA submission-level decision material includes device, software, performance, safety, and/or usability verification.
2026-09
RadAISlice
Auto-Seg (SO-0012), Spine Auto-Seg (SO-0012) | FDA Radiology AI Device - RadAISlice
Agada Medical, Ltd.'s Auto-Seg (SO-0012) is software that processes CT images of the spine and pelvis for automatic segmentation and labeling of vertebrae and pelvis bones, assisting spine surgeons in musculoskeletal assessment and surgical planning for adults. The device underwent extensive non-clinical validation, demonstrating high accuracy and meeting acceptance criteria for segmentation and labeling.
2026-06
Innolitics
Q2 2026 AI/ML FDA Clearances and De Novos - Innolitics
Auto-Seg (SO-0012) from Agada Medical was among the 86 AI/ML devices authorized by the FDA in Q2 2026. It is a 510(k) cleared device for radiology, specifically for 3D vertebrae and pelvis segmentation/labeling from CT DICOM images to aid surgeons in musculoskeletal assessment and surgical planning.
2026-07
FDA
List of Artificial Intelligence-Enabled Medical Devices - FDA
The FDA's list of Artificial Intelligence-Enabled Medical Devices includes Auto-Seg (SO-0012) by Agada Medical, Ltd., categorized under Radiology with product code QIH and cleared on June 29, 2026. This list provides transparency for healthcare providers and patients regarding medical devices utilizing AI technologies.
2026-06
FDA
TPLC - Total Product Life Cycle - FDA
The FDA's Total Product Life Cycle database shows Agada Medical, Ltd.'s Auto-Seg (SO-0012), Spine Auto-Seg (SO-0012) as substantially equivalent, with the product code QIH for automated radiological image processing software. This device falls under regulation number 892.2050, device class 2.
2026-09

Videos

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

No videos found. Search YouTube directly

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

Surgical Reality Viewer
Surgical Reality
Oncology AI
Surgical Reality offers CE- and FDA-certified AI-powered 3D medical imaging and surgical planning software that transforms CT scans into patient-specific 3D models for thoracic surgery, enhancing precision in complex lung procedures.
Oxipit ChestLink
Oxipit (part of Sectra group)
Clinical Decision Support & Reference
Oxipit ChestLink is the world's first CE Class IIb-certified autonomous AI application for healthy chest X-ray reporting, capable of identifying normal studies with 99.9% sensitivity. It automates the reporting of normal chest X-rays, reducing radiologist workload and improving efficiency.
Cercare Medical Oncology Virtual Expert
Cercare Medical
Neurology AI
Cercare Medical's Oncology Virtual Expert is an AI-powered brain tumor segmentation module that provides fast, consistent, and semi-automated tumor analysis from standard MRI data, designed for on-premise deployment within existing clinical radiology workflows.
CARPL.ai
CARPL.ai
Developer Tools & APIs
CARPL.ai is a vendor-neutral Artificial Intelligence (AI) platform that allows radiologists to access, assess, and integrate radiology AI solutions in their clinical practice. It provides a single user interface, a single data channel, and a single procurement channel for the testing, deployment, and monitoring of AI solutions in clinical radiology workflows.
CoLumbo C-Spine
Smart Soft Healthcare AD
Clinical Decision Support & Reference
CoLumbo C-Spine is an AI-powered software that processes and analyzes cervical spine MRI exams, assisting clinicians in diagnosis and assessment.
SubtleHD-CT
Subtle Medical, Inc.
Radiology & Imaging AI
Subtle Medical's SubtleHD-CT is an AI software designed to enhance the quality and resolution of CT scans, reducing noise and improving image clarity. [7]

See all Radiology & Imaging AI tools →

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