Search Results
Found 1 results
510(k) Data Aggregation
(197 days)
X-RAY TV SYSTEM SONIALVISION G4
The equipment is intended to be used for the fluoroscopy/radiography diagnosis in hospital.
The equipment must only be operated by qualified personnel, such as radiography technicians or those with equivalent qualifications.
The equipment is used for total patient population.
The equipment is NOT intended to be used for Mammography screening.
The equipment is NOT intended to be used for interventional procedure.
The equipment is used for radiographic, fluoroscopic, angiographic and pediatric examinations.
Stored images in the equipment can be used for re-monitoring, image processing, storing to optical media (CD/DVD), and sending to DICOM server.
The Tomosynthesis option for the SONIAL VISION G4 is intended to generate tomographic images of human anatomy including chest or extremities. Tomosynthesis technique is used to produce a specific cross-sectional plane of the body by reconstruction of tomographic acquisition. The device is not intended for mammographic applications.
The Shimadzu SONIALVISION G4 is a universal X-ray RF system offering radiographic, fluoroscopic, angiographic and tomosynthesis techniques. Tomosynthesis technique is enabled by additional software option to the digital radiography system of the SONIALVISION G4. The Shimadzu SONIALVISION G4 is floor mounted table, and the system can be configured with Digital Radiography System, X-ray High Voltage Generator, Collimator and X-ray Tube.
The acceptance criteria and study proving device performance are described below for the Shimadzu X-ray TV System SonialVision G4 with the Tomosynthesis option (K142341). This device is intended to add the "Tomosynthesis technique" to its indications for use.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state numerical acceptance criteria with pass/fail thresholds. Instead, the study aims to demonstrate substantial equivalence to a predicate device (Discovery XR656 with VolumeRad) for the tomosynthesis capability. The reported performance is summarized as follows:
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Non-clinical Performance: Equivalent accuracy of tomographic acquisition | Measured accuracy of tomographic acquisition for the new device and the secondary predicate device were compared. The result indicated equivalent performance to acquire images by tomosynthesis technique. Phantom images of both devices were also compared, supporting substantial equivalence. |
| Clinical Performance: Equivalent diagnostic capability for tomosynthesis images across various anatomies | Multiple clinical images taken by tomosynthesis technique for both the new device and the secondary predicate device were compared across several different anatomies. From the overall clinical review, it was concluded that the new device is substantially equivalent to the secondary predicate device in terms of diagnostic capability. |
| Radiation Safety: Equivalent radiation characteristics and safety profile for tomosynthesis technique | Non-clinical bench testing and clinical performance testing, along with associated dose information of each image, were executed. The result demonstrated substantial equivalence to the secondary predicate device. |
| Software Verification and Validation: Meets FDA guidance for software in medical devices, without affecting safety and effectiveness | Software verification and validation testing were conducted as recommended by FDA guidance. The level of concern was identified, and documentation consistent with that level was provided. Based on risk analysis, the software difference (for tomosynthesis) was determined not to affect safety and effectiveness. |
2. Sample Size Used for the Test Set and Data Provenance
- Non-clinical Performance Testing (Tomosynthesis): The document mentions "phantom images" and "accuracy of tomographic acquisition of two devices was measured." It does not specify the exact number of phantom images or measurements, but it refers to a comparative evaluation.
- Clinical Performance Testing (Tomosynthesis): "Multiple clinical images taken by tomosynthesis technique were compared on several different anatomies." The exact number of clinical cases or images is not specified.
- Data Provenance: The document does not explicitly state the country of origin but mentions a "U.S. certified Radiologist" for the clinical study, implying the clinical data was likely collected or reviewed in the U.S.
- Retrospective or Prospective: Not specified, but the nature of a clinical comparison study often leans towards retrospective analysis of collected images for initial clearance.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Clinical Performance Testing: "concurrence clinical study was executed by an U.S. certified Radiologist."
- Number of Experts: One (1) U.S. certified Radiologist.
- Qualifications: "U.S. certified Radiologist." No specific years of experience are mentioned.
4. Adjudication Method for the Test Set
- The document states that a "concurrence clinical study was executed by an U.S. certified Radiologist" and involved an "overall clinical review." This suggests a single reader's judgment was used for comparison, rather than a multi-reader adjudication process (e.g., 2+1, 3+1). No explicit adjudication method is described beyond the single expert's review.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, an MRMC comparative effectiveness study is not explicitly mentioned for this submission. The clinical review was conducted by a single U.S. certified Radiologist comparing images from the new device and the predicate. Therefore, there is no reported effect size of how much human readers improve with AI vs. without AI assistance, as the primary goal was to show equivalence of the tomosynthesis capability itself, not human performance with AI assistance.
6. Standalone (Algorithm Only) Performance Study
- While the tomosynthesis technique is "enabled by additional software option," the evaluation focuses on the performance of the overall device implementing the technique (i.e., the integrated system), rather than just the isolated algorithm performance. The non-clinical and clinical tests compare the complete device's tomosynthesis output and diagnostic capability against a predicate device. So, not a standalone algorithm-only study in the typical sense of evaluating AI performance in isolation.
7. Type of Ground Truth Used
- Non-clinical Performance: Phantom images with known characteristics were used to assess the "accuracy of tomographic acquisition."
- Clinical Performance: The "diagnostic capability" was assessed through comparison of "multiple clinical images" by a "U.S. certified Radiologist" against images from the predicate device. This implies the ground truth for diagnostic capability was established by expert consensus/opinion (from the single radiologist) in comparison to a known clinically accepted device. No mention of pathology or outcomes data is made for the purpose of establishing ground truth for the device's performance.
8. Sample Size for the Training Set
- The document does not specify a sample size for any training set. The submission focuses on verification and validation of the tomosynthesis feature, primarily through comparison with a predicate device, rather than the development and training of a new AI/machine learning model whose training data would need to be described.
9. How the Ground Truth for the Training Set Was Established
- As no training set is discussed or implied for a new AI/machine learning model, the method for establishing its ground truth is not applicable and not provided in the document. The tomosynthesis option is described as an "additional software option" that enables the technique rather than a newly trained AI system.
Ask a specific question about this device
Page 1 of 1