Search Results

The syngo.CT Lung CAD VC30 device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest that may have been initially overlooked. The syngo.CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read.

Siemens Healthcare GmbH intends to market the syngo.CT Lung CAD which is a medical device that is designed to perform CAD processing in thoracic CT examinations for the detection of solid pulmonary nodules ≥ 3.0 mm in size. The device processes images acquired with Siemens multi-detector CT scanners with 4 or more detector rows.

The syngo.CT Lung CAD device supports the full range of nodule locations (central, peripheral) and contours (round, irregular). The detection performance of the syngo.CT Lung CAD device is optimized for nodules between 3.0 mm and 20.0 mm in size.

The syngo.CT Lung CAD sends a list of nodule candidate locations to a visualization application, such as syngo MM Oncology, or a visualization rendering component, which generates output images series with the CAD marks superimposed on the input thoracic CT images for use in a second reader mode. syngo MM Oncology (FDA clearance K191309) is implemented on the syngo.via platform (FDA clearance K191040), which provides a common framework for various other applications implementing specific clinical workflows (but are not part of this clearance) to display the CAD marks. The syngo.CT Lung CAD device is intended to be used as a second reader only after the initial read is completed.

The subject device and the predicate device has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep learning technology. Specifically, the predicate VC20 uses feature-based and Machine Learning whereas the current VC30 uses algorithms based on Convolutional Neural Networks. This does not introduce new types of safety or effectiveness concerns. In particular, as demonstrated by the statistical analysis and results of the standalone benchmark evaluations:

i. The standalone accuracy has been shown not only to be non-inferior but actually superior to that of the device and
ii. The marks generated by the two devices have been shown to be reasonably consistent.

This device description holds true for the subject device, syngo.CT Lung CAD, software version VC30, as well as the predicate device, syngo.CT Lung CAD, software version VC20.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for syngo.CT Lung CAD (VC30):

Device Name: syngo.CT Lung CAD (VC30)
Intended Use: A Computer-Aided Detection (CAD) tool to assist radiologists in the detection of solid pulmonary nodules (≥ 3.0 mm) during review of multi-detector computed tomography (MDCT) examinations of the chest. It's an adjunctive tool to alert radiologists to initially overlooked regions of interest, used as a second reader after the radiologist's initial read.

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on demonstrating non-inferiority and superiority to the predicate device rather than explicitly stating acceptance criteria with numerical targets for metrics like sensitivity or specificity. However, based on the conclusions regarding "standalone accuracy" and "false positive rate," we can infer the implicit criteria and the reported performance as comparative to the predicate.

Note: The document describes the study as a "standalone benchmark evaluation" focused on comparing VC30's performance to VC20's. Specific numerical metrics for sensitivity, specificity, or FPs are not provided in this summary, but the conclusions about superiority and reduction in FPs serve as the performance statement.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size for Test Set: The document states that "The endpoints to establish meaningful and statistically relevant performance and equivalence of the device and sample size were considered and defined as part of the test protocols." However, the specific number of cases or nodules in the test set is not provided in this summary.
• Data Provenance: Not explicitly stated regarding country of origin. The document mentions "Non-clinical performance testing was performed at various levels for verification and validation of the device intended use and to ensure safety and effectiveness." It does not specify if the data was retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• Number of Experts: Not specified in the provided text.
• Qualifications of Experts: Not specified in the provided text.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified in the provided text. The document refers to "ground truth" but does not detail the method by which it was established.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study: The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI vs. without AI assistance. The study described is a "standalone benchmark evaluation" comparing the performance of the new AI algorithm (VC30) to the previous algorithm (VC20).
• Effect Size of Human Improvement: Not applicable, as no MRMC study is detailed here.

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: Yes, a standalone study was done. The document explicitly states: "The standalone performance test proved that the standalone sensitivity of syngo.CT Lung CAD VC30 is superior to that of syngo.CT Lung CAD VC20 (predicate) and the false positive rate improved (reduced)."

7. Type of Ground Truth Used

• Type of Ground Truth: The document refers to "ground truth" for the test set, stating that it was established to define "meaningful and statistically relevant performance." However, the specific method (e.g., expert consensus, pathology, follow-up outcomes) for establishing this ground truth is not detailed in the provided summary.

8. Sample Size for the Training Set

• Sample Size for Training Set: The document does not provide the sample size used for the training set. It only mentions that the "fundamental technology has been replaced by deep learning technology," indicating a training process was involved.

9. How the Ground Truth for the Training Set Was Established

• How Ground Truth for Training Set Was Established: The document does not provide details on how the ground truth for the training set was established. It only describes the functional components of the new syngo.CT Lung CAD VC30 as using Convolutional Neural Networks (CNN) for lung segmentation, candidate generation, feature calculation, and candidate classification, which inherently require labeled training data.

Ask a specific question about this device

MOBILETT Elara Max is a mobile device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. MOBILETT Elara Max enables radio-graphic exposures of the whole body and may be used on pediatric. adult and bariatric patients. It can also be used for emergency applications. MOBILETT Elara Max is not indicated for mammographic imaging.

The MOBILETT Elara Max is a mobile X-ray system with a solid state x-ray imager (SSXI). The system is designed to provide X-ray imaging by healthcare professionals. Rechargeable batteries support cable less operation and motor-driven movements to the point of care. The mobile generator is positioned at bedside and the X-ray system is directed to the anatomical area to be imaged. The image detector is placed perpendicular to the central beam behind this anatomical area. The system features a collimator with a light field that mimics the x-ray field to limit the field of exposure to the area to be imaged. Exposure may be released via remote control. The image data acquired by the detector are send wireless to the mobile unit.

The purpose of this submission is a new software version VF10, some minor hardware changes and the new device name MOBILETT Elara Max. The new software VF10 will introduce the following new features:

• The operating system will be MS Windows 10
• New cybersecurity features
• Additional pediatric programs
• Implementing a "Virtual Machine" that supports hospital IT
• The SSXIs have been updated
• The EMC (Electromagnetic Compatibility was tested according to the IEC 4th edition)
• The image processing algorithms (Diamond View MAX) will be used for exposures without grid.
• The Mobilett Elara will be coated with an anti-microbial paint

The provided text is a 510(k) summary for the Siemens MOBILETT Elara Max, a mobile X-ray system. The document focuses on demonstrating substantial equivalence to a predicate device (MOBILETT MIRA), primarily through non-clinical testing and comparison of technical characteristics, particularly regarding a new software version (VF10) and minor hardware changes.

*Crucially, this document does not contain any information about an AI-powered medical device or a clinical study that establishes acceptance criteria and then proves the device meets those criteria using expert consensus, MRMC studies, or specific performance metrics like sensitivity/specificity.

The device, MOBILETT Elara Max, is a standard X-ray imaging system. The updates described (new software, cybersecurity features, updated SSXIs, antimicrobial paint) are enhancements to the existing X-ray system, not features that introduce AI for diagnostic interpretation or require a clinical study with expert readers to establish diagnostic performance.

Therefore, I cannot fulfill your request to describe acceptance criteria and a study proving an AI device meets them based on the provided text. The document is primarily a regulatory submission demonstrating substantial equivalence for a conventional medical imaging device.

Ask a specific question about this device

The MULTIX Impact system is a radiographic system used in hospitals, clinics, and medical practices. MULTIX Impact enables radiographic exposures of the whole body including: skull, chest, abdomen, and extremities and may be used on pediatric, adult and bariatric patients. Exposures may be taken with the patient sitting, standing, or in the prone position. The MULTIX Impact system is not meant for mammography.

The MULTIX Impact uses digital detectors for generating diagnostic images by converting x-rays into image signals. The MULTIX Impact is also designed to be used with conventional film/screen or Computed Radiography (CR) cassettes.

The MULTIX Impact Radiography X-ray system is a modular system of X-ray components (floor-mounted X-ray tube, Bucky wall stand, Bucky table, X-ray generator, portable wireless detectors) similar to the predicate the Multix Fusion Max. This 510(k) submission describes modifications to the predicate device the Multix Fusion Max cleared via K162971. The following modifications have been made to the cleared predicate device and the new system will be branded the MULTIX Impact:

1. A new 43x35cm Wireless detector, 3543DR 1.
2. A new X-ray tube and a new generator
3. An optional 40 line grid with grid suppression algorithm
4. Wireless Remote Control Console
5. An optional All-in-one PC containing touch screen function
6. An optional positioning assistance camera
7. Upgrade software to VA10
8. Upgrade operator system from Windows XP to Windows 10

The Siemens MULTIX Impact X-ray system is a modification of the predicate device, the Multix Fusion Max (K162971). The submission focuses on demonstrating substantial equivalence rather than presenting an effectiveness study for a new clinical claim. Therefore, the information provided primarily concerns performance testing to confirm that the modifications do not negatively impact safety or effectiveness.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a submission demonstrating substantial equivalence to a predicate device for an X-ray system, the acceptance criteria are generally focused on demonstrating that various component modifications do not degrade performance below the predicate's established levels, and that the device meets relevant safety and performance standards. Formal "acceptance criteria" for a specific clinical task are not explicitly stated for the device as a whole in the way they would be for a diagnostic AI algorithm. Instead, the comparison is to the predicate and established standards.

2. Sample Size Used for the Test Set and Data Provenance

The document describes modifications to an existing X-ray system and its components. The "test set" here refers to the actual physical device and its components undergoing verification and validation testing, rather than a dataset of medical images for a diagnostic algorithm.

• Sample Size for Test Set: Not applicable in the context of a dataset of cases. The testing was performed on the MULTIX Impact system itself and its components.
• Data Provenance: Not applicable in the clinical data sense. The testing is described as "Non-clinical tests... during product development" and "testing for verification and validation." This implies internal testing by the manufacturer.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

Not applicable. This is not a study requiring expert clinical read-outs for ground truth. The "ground truth" for this submission is adherence to technical specifications, performance standards (like DQE, MTF), and safety requirements, which are evaluated by engineering and quality control processes.

4. Adjudication Method for the Test Set

Not applicable. There is no mention of clinical image adjudication for ground truth establishment. Technical performance and safety are verified through engineering tests.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No MRMC study was performed or is mentioned. This submission is for an X-ray system, not an AI-powered diagnostic device, and it focuses on demonstrating substantial equivalence of modified hardware and software components, not on comparative effectiveness with human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Not applicable. The device is an X-ray system, which is inherently used with human operators. There is no "algorithm only" performance claim. The software modifications are part of the overall X-ray system's functionality.

7. The Type of Ground Truth Used

The "ground truth" for this submission relates to:

• Technical Specifications: Ensuring components meet their specified performance parameters (e.g., DQE, MTF for the detector, power output for the generator).
• Compliance with Standards: Verification that the device adheres to recognized national and international standards (IEC, ISO, NEMA).
• Safety and Effectiveness: Demonstration that modifications do not introduce new safety risks or degrade the overall effectiveness of the predicate device, as evaluated through risk analysis and functional testing.

8. The Sample Size for the Training Set

Not applicable. This is not an AI/machine learning device that requires a training set of data.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there is no training set for an AI algorithm.

Ask a specific question about this device

Ysio Max is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. Ysio Max enables radiographic and tomographic exposures of the whole body and may be used on pediatric, adult and bariatric patients. It can also be used for emergency applications.

Ysio Max is not for mammography examinations.

The Ysio Max is a stationary X-ray system for radiography. The main components are the X-ray generator, the X-ray tube with collimator supported by a ceiling rail system. The Ysio Max comes with SSXIs (Solid State X-ray Imagers) that can be mobile or fixed in the Bucky tray. An image processing and data management system (syngo FLC) completes the radiographic suite.

The purpose of this submission is the upgrade to a new software version VF10 and minor hardware changes. The modified Yisio Max will introduce the following new features:

• The operating system will be MS Windows 10
• New cybersecurity features
• Additional pediatric programs
• Implementing a "Virtual Machine" that supports hospital IT
• The SSXIs have been updated
• The EMC (Electromagnetic Compatibility was tested according to the IEC . 4th edition)
• . The image processing algorithms (Diamond view Plus) will be used for exposures without grid.

The provided text is a 510(k) premarket notification for a medical device called Ysio Max. It focuses on demonstrating substantial equivalence to a predicate device after a software upgrade (VF10) and minor hardware changes.

Based on the provided document, the device (Ysio Max with VF10 software) is a stationary X-ray system, not an AI/ML-powered device for which acceptance criteria typically involve performance metrics like sensitivity, specificity, or AUC.

Therefore, the acceptance criteria and study detailed in the document are primarily related to demonstrating that the updated device maintains the same safety and effectiveness as its predicate device and complies with relevant performance standards, rather than proving a specific diagnostic accuracy or improvement in human reader performance using AI assistance.

Here's a breakdown of the information as it applies to this specific submission, addressing your points where relevant:

1. A table of acceptance criteria and the reported device performance:

The acceptance criteria are implicitly tied to demonstrating continued substantial equivalence to the predicate device and compliance with applicable industry standards and FDA regulations. Performance is reported through comparisons to the predicate and confirmation of adherence to standards.

2. Sample sizes used for the test set and the data provenance:

• Test Set Sample Size: The document does not specify a "test set" in the context of an AI/ML algorithm being evaluated on a dataset of patient cases. Instead, the testing is described as verification and validation (V&V) testing of the software and hardware components, and performance measurements of the X-ray detectors against technical specifications. These are engineering and performance tests, not clinical studies on a patient cohort for diagnostic AI.
• Data Provenance: Not applicable in the context of diagnostic data for AI. The testing is internal to the manufacturer.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not applicable as this is not an AI/ML diagnostic system requiring expert interpretation as ground truth. The "ground truth" for the device's performance is adherence to engineering specifications and regulatory standards.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

• Not applicable. This is not a study involving human reader interpretations of medical images that would require adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC study was not done. The document explicitly states: "For the subject of this premarket submission, Siemens did not do an evaluation of the clinical image quality as X-ray technology; geometry and SSXI changes are minor." This device is an X-ray system itself, not an AI assistant intended to improve human reader performance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Not applicable. The Ysio Max is a medical imaging device (a stationary X-ray system), not a standalone diagnostic algorithm. Its performance is measured by its ability to generate images and comply with technical and safety standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• The "ground truth" for this submission is based on engineering specifications, compliance with standardized test methods (e.g., IEC standards for electrical safety, EMC, radiation protection), and measurable physical characteristics of the detectors (DQE, MTF). It's a technical "ground truth" rather than a clinical diagnostic one.

8. The sample size for the training set:

• Not applicable. This is not an AI/ML device that requires a training set of data.

9. How the ground truth for the training set was established:

• Not applicable for the same reason mentioned above.

Ask a specific question about this device

Luminos Agile Max is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. The system has medical applications ranging from gastrointestinal examinations to cranial, skeletal, thoracic and lung exposures as well as examinations of the urogenital tract. The unit may also be used in emergency applications, lymphography, endoscopy, myelography, venography, arthrography, interventional radiology, digital angiography and digital subtraction angiography (DSA). The system may be used on pediatric, adult and bariatric patients.

Luminos Agile Max is not for mammography examinations.

Luminos dRF Max is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. The system has medical applications ranging from gastrointestinal examinations to cranial, skeletal, thoracic and lung exposures as well as examinations of the urogenital tract. The unit may also be used in emergency applications, lymphography, endoscopy, myelography, venography, arthrography, interventional radiology, digital angiography and digital subtraction angiography (DSA). The system may be used on pediatric, adult and bariatric patients.

Luminos dRF Max is not for mammography examinations.

Multitom Rax is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. The system has medical applications ranging from gastrointestinal examinations to cranial, skeletal, thoracic and lung exposures as well as examinations of the urogenital tract. The unit may also be used in emergency applications, lymphography, endoscopy, myelography, venography, arthrography, interventional radiology, digital angiography and digital subtraction angiography (DSA). The system may be used on pediatric, adult and bariatric patients

Multitom Rax is not for mammography examinations.

Uroskop Omnia Max is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. The system is designed primarily for urological diagnosis and the support of urological therapeutic applications such as examinations and small interventions of the urogenital tract. The table supports endourological and minimal invasive surgery in urology as there are transurethral interventions (e.g. ureterorenoscopy (URS), double stent placement, cystoscopy. transurethral resection of bladder tumors (TURB), transurethral resection of the prostate (TURP)), percutaneous urological procedures (e.g. percutaneous nephrostomy (PCN), percutaneous nephrolitholapaxy (PCNL)), urological X-ray diagnosis (e.g. survey imaging of the kidney, ureter, and bladder (KUB), intravenous pyelogram (IVP), retrograde pyelography), micturition cystourethrogram (MCU), videourodynamics, laparoscopic procedures and minor open urological interventions. The system may be used on pediatric, adult and bariatric patients.

Uroskop Omnia Max is not for mammography examinations.

All four radiology imaging devices are stationary X-ray systems for radiography and fluoroscopy. They use the same X-ray generator, the same X-ray tube and similar collimators. They also share the same imaging and system control device: The Fluorospot Compact. The reason for this submission is the upgrade of all systems to the software VF10. This new software will bring the following new features to the devices: IEC 4th for EMC, Windows 10, Cybersecurity package, Pediatric package, Use hospital IT (e.g. RIS) on modality, 16 fps mode for 3D (Multitom Rax only), SSXI update. The image processing algorithms (Diamond View Plus) will be used for exposures without grid and fluoroscopy image processing algorithms will be enhanced and called "Clearview". Also the name suffix "Max" is being established as an addition to the product name of Luminos Agile, Luminos dRF and Uroskop Omnia.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Siemens Medical Solutions X-ray systems:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a pass/fail quantifiable manner, but rather presents a comparison demonstrating that the updated devices (with VF10 software) are "substantially equivalent" to their predicate devices. The performance metrics revolve around various technical specifications, particularly for the detectors and compliance with regulatory standards.

2. Sample Size Used for the Test Set and Data Provenance

The document explicitly states: "For the subject of this premarket submission, Siemens did not do an evaluation of the clinical image quality as x-ray technology; geometry and SSXI changes are minor."

This indicates there was no dedicated clinical test set in terms of patient images. The evaluation primarily relied on non-clinical performance data, engineering verification and validation testing, and compliance with standards. Therefore, information regarding sample size, country of origin, or retrospective/prospective nature of a clinical test set is not applicable.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

As there was no clinical evaluation with a dedicated test set evaluated by experts, this information is not applicable. The ground truth for the non-clinical performance data (e.g., DQE, MTF) would be derived from physical measurements and calibrated test equipment, not expert human assessment.

4. Adjudication Method for the Test Set

Since there was no clinical test set requiring human interpretation, an adjudication method is not applicable.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was done. The submission explicitly states "Siemens did not do an evaluation of the clinical image quality." Therefore, no effect size of human readers improving with AI vs. without AI assistance can be reported. The device is an X-ray imaging system, not an AI-based diagnostic tool for interpretation.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance Study

No standalone performance study of an algorithm was done in the context of image interpretation or diagnostic accuracy. The "software update VF10" relates to the operating system, cybersecurity, feature enhancements, and control of the imaging hardware, not a new diagnostic algorithm that would operate in a standalone manner. The performance data presented (DQE, MTF) are intrinsic characteristics of the imaging detectors themselves, measured objectively, and not an "algorithm-only" performance in a diagnostic sense.

7. Type of Ground Truth Used

For the non-clinical performance evaluation, the ground truth was based on:

• Physical measurements and industry standards: For detector performance metrics like DQE and MTF. These are objectively measured using specified test conditions and equipment.
• Compliance with regulatory and consensus standards: For safety, electromagnetic compatibility, software life cycle, and radiation control.
• Engineering verification and validation: To confirm software requirements are met and system functionality aligns with user needs.

There was no "expert consensus, pathology, or outcomes data" used as ground truth for a clinical efficacy study.

8. Sample Size for the Training Set

The document primarily describes a software upgrade and associated hardware (detector) changes for existing X-ray systems. It does not refer to a machine learning or AI algorithm that would require a "training set" of data. Therefore, the sample size for a training set is not applicable.

9. How the Ground Truth for the Training Set Was Established

Since there was no training set for a machine learning algorithm, this information is not applicable.

Ask a specific question about this device

The MAMMOMAT Revelation is intended to be used for mammography exams, screening, diagnostics, biopsies and dual energy procedures under the supervision of medical professionals. The Mammography images can be inter hard copy film or soft copy workstation.

With Biopsy Option:

The InSpect feature for MAMMOMAT Revelation with HD Biopsy options is intended to provide digital X-ray images of core biopsy specimens in order to allow rapid verification that the correct tissue has been excised with the biopsy procedure.

MAMMOMAT Revelation is a floor-mounted full field digital mammography system for screening, diagnostic and biopsy procedures on standing, seated or recumbent patients.

The system consists of an examination stand with X-ray generator, a gantry with tube housing assembly and mammography support table including detector, and an acquisition workstation with a radiation shield. The MAMMOMAT Revelation comes with a variety of compression plates and a biopsy attachment for diagnostic adjunct procedures.

The MAMMOMAT Revelation features an updated detector (LMAM 2v2), an upgrade to the MS Windows 10 operating system, the capability to do contrast enhanced mammography and tomosynthesis guided biopsy.

The Siemens MAMMOMAT Revelation device was evaluated in non-clinical bench tests. Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Size and Data Provenance for Test Set:

The provided document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective) for the bench tests. These tests are non-clinical and conducted in a laboratory setting.

3. Number of Experts and Qualifications for Ground Truth of Test Set:

Not applicable. The tests described are bench tests focused on technical performance metrics (detector characteristics, image quality, targeting accuracy) and do not involve human readers or expert-established ground truth in the traditional sense of a clinical study. The "ground truth" for these tests would be the established physical and technical specifications or reference measurements.

4. Adjudication Method for Test Set:

Not applicable. As these are bench tests, an adjudication method for human interpretation is not relevant. The results are based on direct measurement and comparison against defined technical criteria.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No. The document describes non-clinical bench tests. There is no mention of an MRMC comparative effectiveness study involving human readers.

6. Standalone (Algorithm Only) Performance:

The document describes tests of the physical device's characteristics and its features. It does not specifically detail a "standalone" algorithm performance study without a human-in-the-loop, as the device is a medical imaging system. The "algorithm" here would refer to the internal image processing and AEC calculations, which are components of the system test.

7. Type of Ground Truth Used:

The ground truth for these non-clinical tests is based on:

• Established specifications and performance of the predicate device (for detector characteristics).
• Defined technical standards and internal system test records (for dual energy image quality).
• Physical measurements against a known target in a phantom (for targeting accuracy).

8. Sample Size for Training Set:

Not applicable. The document describes tests for a medical imaging device, not an AI or machine learning algorithm that typically requires a separate training set. The "MAMMOMAT Revelation" is a physical mammography system.

9. How Ground Truth for Training Set Was Established:

Not applicable, as there is no mention of a separate training set for an AI algorithm.

Ask a specific question about this device

Insight BD is a software application for the volumetric density assessment of digital x-ray images of the breast to aid health care professionals in the assessment of breast tissue composition. Insight BD is not a diagnostic aid and should be used only as adjunctive information when the final assessment of breast density category is made visually by medical professionals.

The Siemens volumetric breast density analysis application software Insight BD provides volumetric assessment of digital x-ray images of the breast, including both digital mammograms and raw tomosynthesis projection images.

The assessment consists of generating and evaluating density maps where the value at each pixel represents the thickness of fibroglandular tissue above that pixel. From those density maps the software calculates quantitative values, namely

• . volume of fibroglandular tissue in the breast in cm³
• breast volume in cm³ .
• . volumetric breast density in %
• . breast density grade

The breast density grade is computed by thresholding of the volumetric breast density and conforms to BI-RADS® 5th Edition breast composition categories. The masking effect of dense fibroglandular tissue is automatically included in the results.

Insight BD is a software option for the Siemens digital mammography systems. Insight BD may be installed either on Siemens released PC hardware or on the Siemens digital mammography systems. Breast Density results are stored in the DICOM header and can be used for further documentation.

Here's an analysis of the acceptance criteria and the study proving the device meets those criteria, based on the provided text for the Siemens Insight BD (K172832) device.

Device Name: Insight BD
K Number: K172832

The provided text focuses on demonstrating substantial equivalence to a predicate device (Volpara Imaging Software, K152028). While it mentions various performance assessments, it does not explicitly state specific quantitative "acceptance criteria" and "reported device performance" in a structured table as requested. Instead, it describes various tests performed to demonstrate consistency, reproducibility, and equivalence to the predicate.

Therefore, the table below will be constructed based on the types of performance assessments described, with the "Acceptance Criteria" inferred from the need to show "similar" or "expected" results, and "Reported Device Performance" reflecting the general statement that the device was found compliant or similar to expectations/predicate.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

The document consistently uses the phrase "substantial data sets" to describe the sample sizes for reproducibility and equivalence testing, but does not provide specific numbers for the exact sample size of the test sets.

Data Provenance:

• Country of Origin: Not explicitly stated, but the manufacturing site is Forchheim, Germany (Siemens Healthcare GmbH). The lack of specific country for the data implies it could be multi-national or from Siemens' internal clinical collaborators.
• Retrospective or Prospective: Not explicitly stated. Given the use of "available from MQSA qualified radiologists" and "same woman had been imaged," it strongly suggests a retrospective collection of existing image data.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The document mentions "MQSA qualified radiologists" for establishing BI-RADS® 5th Edition density categories based on visual assessment.

• Number of Experts: Not specified. The document states "a BI-RADS® 5th Edition density category was available from MQSA qualified radiologists," implying multiple radiologists might have contributed to the "available" categories, but it doesn't specify if this was a consensus reading or individual readings used for comparison.
• Qualifications: "MQSA qualified radiologists." This implies they are certified to interpret mammograms in the U.S. and have relevant clinical experience in breast imaging.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1) for resolving disagreements among experts during the ground truth establishment for the visual assessment comparison. It simply states that BI-RADS categories were "available from MQSA qualified radiologists," which could imply a single read or an already adjudicated consensus (though not explicitly stated).

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a MRMC comparative effectiveness study was not explicitly done/described in the context of comparing human readers with AI assistance versus without AI assistance.

The study focuses on validating the standalone performance of Insight BD and its relationship to visual assessment and equivalence to a predicate. It does not evaluate the impact of the AI on human reader performance.

6. Standalone Performance Study (Algorithm Only)

Yes, standalone performance was done. The entire "Performance Data" Section 9 describes tests where the Insight BD software (algorithm only) was run on datasets to assess:

• Measurement accuracy (against phantoms)
• Reproducibility across different views and imaging modes
• Consistency with known biological trends (age-related density decrease)
• Relationship to visual assessment (comparison of algorithm output to radiologist-assigned BI-RADS categories)
• Equivalence to the predicate device

These are all evaluations of the algorithm's output directly.

7. Type of Ground Truth Used

Multiple types of "ground truth" or reference standards were used:

• Known values from breast phantoms: For measurement accuracy. This is an objective, engineered truth.
• Expected and known medical trends (decrease in breast density with age): For consistency analysis. This represents biological/clinical truth.
• BI-RADS® 5th Edition density categories available from MQSA qualified radiologists: For comparing the algorithm's output to human visual assessment. This is an expert consensus/visual assessment ground truth, though the consensus process isn't detailed.
• Predicate device output: For assessing equivalence. This uses another validated device's output as a reference, implying its output serves as a de facto "truth" for comparative purposes.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set for the Insight BD algorithm. It only discusses the "Performance Data" for the test (validation) phase.

9. How Ground Truth for the Training Set Was Established

The document does not describe how the ground truth for the training set was established. This information is typically proprietary to the developer and not always fully disclosed in 510(k) summaries, which tend to focus on the validation/testing to demonstrate substantial equivalence.

Ask a specific question about this device

The SC2000 ultrasound imaging system is intended for the following applications: Cardiac. Neo-natal and Fetal Cardiac. Pediatric, Transesophageal, Adult Cephalic, Peripheral Vessel, Abdominal, Musculo-skeletal Conventional, and Musculo-skeletal Superficial applications. The system also provides the ability to measure anatomical structures and calculation packages that provide information that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes. The typical examinations performed using the SC2000 Ultrasound System are:

Cardiac Imaging Applications and Analysis
The system transmits ultrasound energy into adult, pediativ, neonatal, and fetal cardiac patients creating 2D (B). 3D. M-Mode (M), Color Doppler (CD), Color Power Doppler (CPD), Pulsed Wave (PW) Doppler, and Continuous Wave Doppler (CWD) to obtain images and blood flow velocity of the heart, cardiac valves, great vessels, and surrounding anatomical structures to evaluate the presence of pathology. The system may be used to acquire patient electrocardiogram for synchronizing the diastolic and systolic capture of ultrasound images.
The system also supports catheters which are intended for intraluminal visualization of cardiac and great vessel anatomy and physiology as well as visualization of other devices in the heart of adult and pediatric patients. The system has Cardiac Measurements and Calculation Packages that provide information that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes.

Vascular Imaging Applications and Analysis
The system transmits ultrasound energy into various parts of the body of adult patients creating 2D (B), Color Doppler (CD), Color Power Doppler (CPD), Pulsed Wave Doppler (PWD), and Continuous Wave Doppler (CWD) to obtain images and blood flow velocity of the carotid arteries or juggler veins in the neck; superficial and arteries in the arms and legs and abdomen; and surrounding anatomical structures to evaluate the presence of pathology. The system may be used to acquire patient electrocardiogram for synchronizing the diastolic and systolic capture of ultrasound images.
The system has Vascular Measurements and Calculation Packages that provide information that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes.

Superficial Imaging Applications
The system transmits ultrasound energy into various parts of the body of adult patients creating 2D (B), Color Doppler (CD), Color Power Doppler (CPD), Pulsed Wave Doppler (PWD), and Continuous Wave Doppler (CWD) to obtain images and blood flow velocity of conventional or superficial musculoskeletal structures and surrounding anatomical structures to evaluate the presence of pathology. The system may be used to acquire patient electrocardiogram for synchronizing the diastolic and systolic capture of ultrasound images.

Intraoperative Imaging Applications
The system transmits ultrasound energy into various parts of the body of adult patients creating 2D (B), Color Doppler (CD), Color Power Doppler (CPD), and Pulsed Wave Doppler (PWD) to obtain images and blood flow velocity that provide guidance during intraoperative procedures.

Transcranial Imaging Applications
The system transmits ultrasound energy into the cranium of adult patients creating 2D (B), Color Doppler (CD), Color Power Doppler (CPD), Pulsed Wave Doppler (PWD), and Continuous Wave Doppler (CWD) to obtain images and blood flow velocity of the brain and surrounding anatomical structures to evaluate the presence of pathology. The system provides Measurement Packages that provide information that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes.

The ACUSON SC2000™ Diagnostic Ultrasound System is a multi-purpose mobile, software controlled diagnostic ultrasound system, with an on-screen display for thermal and mechanical indices, related to potential bio-effect mechanisms. Its function is to acquire primary or secondary harmonic ultrasound echo data, and display it in the following modes (The following modes below can be operated in combination or individually):

• B-Mode
• M-Mode
• Pulsed (PWD) Doppler Mode
• Continuous (CWD) Doppler Mode
• Color Doppler Mode
• Amplitude Doppler Mode
• Color Velocity Imaging
• 3D Imaging,
• 4D Imaging (3D imaging in real time)

This document, a 510(k) Premarket Notification for the Siemens Acuson SC2000 Diagnostic Ultrasound System, focuses on demonstrating substantial equivalence to a previously cleared predicate device (K170315) rather than proving the detailed performance of a new AI/algorithm-based device against specific acceptance criteria.

Therefore, the requested information regarding acceptance criteria, study details (sample size, data provenance, number of experts, adjudication methods, MRMC studies, standalone performance, ground truth establishment for test and training sets) is not present in this document.

The document explicitly states: "The ACUSON SC2000™ Ultrasound System is a class II device, and uses the same technology and operating principle as the predicate devices; clinical data is not required for substantial equivalence." (Page 24)

This indicates that the submission relies on the established safety and effectiveness of the predicate device and the fact that the modifications to the Acuson SC2000 are not significant enough to warrant new clinical performance studies or specific acceptance performance metrics typically associated with novel AI/algorithm-driven devices.

In summary, this document does not provide the information requested about acceptance criteria and study details for proving a device meets those criteria, because such studies were not deemed necessary for this 510(k) submission based on its substantial equivalence to an existing device.

Ask a specific question about this device

The SC2000 ultrasound imaging system is intended for the following applications: Cardiac. Neo-natal and Fetal Cardiac. Pediatric, Transesophageal, Adult Cephalic, Peripheral Vessel, Abdominal, Musculo-skeletal Conventional, and Musculo-skeletal Superficial applications. The system also provides the ability to measure anatomical structures and calculation packages that provide information that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes. The typical examinations performed using the SC2000 Ultrasound System are:

Cardiac Imaging Applications and Analysis
Vascular Imaging Applications and Analysis
Superficial Imaging Applications
Intraoperative Imaging Applications
Transcranial Imaging Applications

The ACUSON SC2000™ Diagnostic Ultrasound System is a multi-purpose mobile, software controlled diagnostic ultrasound system, with an on-screen display for thermal and mechanical indices, related to potential bio-effect mechanisms. Its function is to acquire primary or secondary harmonic ultrasound echo data, and display it in the following modes (The following modes below can be operated in combination or individually):

• B-Mode
• M-Mode .
• Pulsed (PWD) Doppler Mode .
• Continuous (CWD) Doppler Mode
• Color Doppler Mode .
• Amplitude Doppler Mode
• Color Velocity Imaging .
• 3D Imaging,
• 4D Imaging (3D imaging in real time) .

The provided document is a 510(k) premarket notification for the Siemens ACUSON SC2000™ Diagnostic Ultrasound System (K170315). It primarily details the device's indications for use and asserts substantial equivalence to a previously cleared predicate device (K162221). The document states that clinical data was NOT required for substantial equivalence, as the device is a Class II device and uses the same technology and operating principles as the predicate.

Therefore, the submission does not include any studies proving the device meets specific acceptance criteria based on performance metrics like sensitivity, specificity, or accuracy in a clinical context. The review focuses on technical parameters, safety, and equivalence to a predicate.

However, based on the information provided, I can infer the implied acceptance criteria through compliance with standards and the "Substantial Equivalence Table" (page 22).

Here's a breakdown of the requested information based on the provided text, recognizing the absence of clinical performance studies:

1. A table of acceptance criteria and the reported device performance

Since no clinical performance metrics are reported, the "acceptance criteria" here are implied by the safety and technical standards compliance and the "Same" performance claims against the predicate.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Not applicable. The document explicitly states that "clinical data is not required for substantial equivalence" (page 24). The evaluation was based on non-clinical tests (acoustic output, biocompatibility, cleaning, thermal, electromagnetic, and mechanical safety) and comparison to a predicate device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Not applicable. No clinical test set or expert-established ground truth is mentioned. The assessment was based on engineering and safety standards.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable. No clinical test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This is not an AI/CADe device, and no MRMC study or AI assistance is mentioned.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Not applicable. This is a diagnostic ultrasound system, not an algorithm, and no standalone performance study is mentioned.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

Not applicable. For the determination of substantial equivalence, the "ground truth" was compliance with established medical device safety and performance standards (e.g., IEC 60601 series, NEMA UD series, ISO 10993-1) and the technical specifications of the predicate device (K162221).

8. The sample size for the training set

Not applicable. No algorithms requiring a training set are discussed in the context of this 510(k) submission.

9. How the ground truth for the training set was established

Not applicable. No algorithms requiring a training set are discussed.

Ask a specific question about this device

The MAGNETOM systems [MAGNETOM Avantofit, MAGNETOM Skyrafit] are indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities.

Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/or spectra and the physical parameters derived from the images and/or spectra, when interpreted by a trained physician, yield information that may assist in diagnosis.

The MAGNETOM systems may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

Not Found

This document is a letter from the FDA to Siemens Medical Solutions USA, Inc. regarding their 510(k) premarket notification for the MAGNETOM Avanto and MAGNETOM Skyra devices. It confirms the substantial equivalence of these magnetic resonance diagnostic devices.

The document does not contain any information about acceptance criteria, device performance, a specific study, sample sizes, expert qualifications, adjudication methods, multi-reader multi-case studies, standalone performance, or ground truth establishment.

Therefore, I cannot provide the requested information based on the provided text.

Ask a specific question about this device