(262 days)
The sterEOS Workstation is intended for use in the fields of musculoskeletal radiology and orthopedics in both pediatric and adult populations as a general PACS device for acceptance. transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system including interactive 2D measurement tools.
When using 2D X-ray images obtained with the EOS Imaging EOS System (K071546), the sterEOS Workstation provides interactive 3D measurement tools:
- to aid in the analysis of scoliosis and related disorders and deformities of the spine in adult patients as well as pediatric patients 7 years and older. The 3D measurement tools include interactive analysis based on a model of bone structures derived from an a priori image data set from 175 patients (91 normal patients, 47 patients with moderate idiopathic scoliosis and 37 patients with severe idiopathic scoliosis), and dry isolated vertebrae data. The model of bone structures is not intended for use in patients with a Cobb's angle > 50 degrees and is not intended for use to assess individual vertebral abnormalities.
- to aid in the analysis of lower limbs alignment and related disorders and deformities based on angle and length measurements. The 3D measurement tools include interactive analysis based either on identification of lower limb alignment landmarks or as for the spine, on a model of bone structures derived from an a priori image data set. The model of bone structures is not intended for use to assess individual bone abnormalities. The 3D package including model-based measurements and torsion angles is indicated only for patients 15 years or older. Only the 2D/3D ruler is indicated for measurements in patient younger than 15 years old.
The sterEOS Workstation is a system for acceptance, transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system, including interactive 2D measurement tools.
When used with 2D X-ray images obtained with the EOS Imaging EOS System (K071546), the sterEOS Workstation provides interactive 3D measurement tools to aid in the analysis of skeletal deformities in spine and lower limbs.
Here's a breakdown of the acceptance criteria and study information for the sterEOS Workstation, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative "acceptance criteria" with specific thresholds for accuracy or precision. Instead, it describes a "performance data" section that generally asserts the device's capabilities and equivalence. The key performance claim is for the lower limb measurement tools.
| Feature / Measurement | Acceptance Criteria (Implicit/General Statement) | Reported Device Performance |
|---|---|---|
| Accuracy and precision of 3D lower limb measurements | Not explicitly defined as a quantitative threshold. Implied as "validated" and "equivalent performance" to conventional methods. | "Accuracy and precision of the automatic measurements computed from the 3D model of the lower limbs have been confirmed with X-ray clinical images. Results validate the interactive 3D measurement tools for lower limb assessment and demonstrate the equivalent performance of the device with conventional measurement methods performed on native X-ray images." |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document does not explicitly state a separate "test set" sample size for the lower limb accuracy and precision validation.
- The "3D reconstruction method" for the lower limb mentions a "database of clinical descriptors measured in 45 lower limbs of healthy adult subjects." This dataset seems to be used for defining the statistical inference and forming a priori models, rather than a distinct testing set for device validation after model creation. It's unclear if these 45 limbs were also part of the "X-ray clinical images" used for performance confirmation.
- Data Provenance: Not specified (e.g., country of origin, retrospective or prospective). The text only mentions "X-ray clinical images."
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not provide details on the number of experts or their qualifications for establishing ground truth for the lower limb measurements. It only mentions "conventional measurement methods" as the comparison for "equivalent performance."
4. Adjudication Method for the Test Set
The document does not describe any adjudication method for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned for the lower limb measurements, nor is any effect size of human readers' improvement with AI assistance discussed. The performance data focuses on the device's standalone measurements compared to conventional methods.
6. Standalone (Algorithm Only) Performance Study
Yes, a standalone performance assessment was done. The "Performance Data" section explicitly states: "Accuracy and precision of the automatic measurements computed from the 3D model of the lower limbs have been confirmed... Results validate the interactive 3D measurement tools for lower limb assessment and demonstrate the equivalent performance of the device with conventional measurement methods performed on native X-ray images." This indicates an evaluation of the algorithm's output against a reference standard.
7. Type of Ground Truth Used
The ground truth for evaluating the lower limb measurements seems to be based on:
- "Conventional measurement methods performed on native X-ray images." This implies manual measurements made by experts directly on the images, which serves as a clinical reference.
8. Sample Size for the Training Set
- Spine Model: 175 patients (91 normal, 47 moderate idiopathic scoliosis, 37 severe idiopathic scoliosis) and 1628 cadaveric vertebrae. This dataset was used to derive the "a priori image data set" for the spine's 3D model.
- Lower Limb Model: 45 lower limbs of healthy adult subjects. This dataset was used to define the "statistical inference" for the parametric models of the tibia and femur.
9. How Ground Truth for the Training Set Was Established
The ground truth for the training sets (for both spine and lower limb models) was established through:
- Clinical descriptors/measurements: Data was derived from patient populations (e.g., normal, moderate/severe idiopathic scoliosis, healthy adults) and cadaveric vertebrae. These "clinical descriptors" would have been established measurements or observations relevant to bone structures and deformities.
- A priori image data set: This refers to the collection of pre-existing data from these patient populations that the models learned from.
- Morpho-realistic models: These are meshed CT volumes of spine/lower limbs, regionalized according to the parametric models, likely serving as detailed anatomical references during model development.
Essentially, the models were developed using a database of known anatomical and pathological characteristics. The document doesn't detail the process of how each individual "clinical descriptor" was established for the training data (e.g., if it was expert consensus on each patient's image, or from medical records, etc.), but it clearly states these were "measured" or derived from a database.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).