Search Results

Merge Universal Viewer (MUV) is intended to provide internet access to multi-modality softcopy medical images, medical data, reports, and other patient-related information to conduct diagnostic review, processing, analyzing, reporting and sharing of DICOM-compliant medical images and relevant digital data.

MUV provides functionality that allows for creating and outputting digital files suitable for the fabrication of physical replicas, such as 3D printing, using DICOM files as inputs. Physical/3D printed models generated from the digital output files are not for diagnostic use.

MUV is intended to be used by trained healthcare professionals.

MUV can be configured to provide either lossless or lossy compressed images for display. The medical professional user must determine the appropriate level of image data compression that is suitable for their purpose.

Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 MP resolution and meets other technical specifications reviewed and accepted by FDA.

Display monitors used for reading medical images for diagnostic purposes must comply with applicable regulatory approvals and with quality control requirements for their use and maintenance. Use of MUV on mobile devices such as iPhones and iPads is not intended for diagnostic use.

Merge Universal Viewer (formerly known as IBM iConnect Access) is a software application that is intended to provide internet access to multi-modality softcopy medical images, medical data, reports, and other patient-related information to conduct diagnostic review, processing, analyzing, reporting and sharing of DICOM-compliant medical images and relevant digital data. Merge Universal Viewer provides healthcare professionals with access to diagnostic quality images, reports, and various types of patient data over conventional TCP/IP networks.

Merge Universal Viewer was designed with an easy and convenient workflow providing image viewing and manipulation capabilities including but not limited to zoom, pan, window/level, scroll, CINE, link series, and MPR. Additionally, the existing Merge Universal Viewer offers measurement and analysis tools such as line measurement, cross reference lines, rectangle, ellipse, perfect circle, freehand ROI, angle, Cobb angle, calibration, pixel value, plumb lines and cardiac calcium scoring.

A high-level overview of the modifications to the subject device being introduced as part of this 510(k) are as follows:

• Ability to display Mammography CAD SR
• Addition of the Volumetric SUV (Standard Uptake Value) to the measurement tools
• Addition of a DICOM Structured Report (SR) ingestion panel: The "Findings Panel":
  • Display of lung nodule detection and characteristics
  • Generalized lesion tracking (for CT and MR studies)
• Addition of cardiology measurement tools (for cardiac ultrasound studies)
• Miscellaneous updates such as:
  • Cybersecurity improvements to ensure full compliance with FDA's Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions Guidance issued September 27, 2023.
  • The ability to display mammography images in full resolution using a keyboard shortcut
  • Bug fixes
• Labeling update, i.e., revised Indications for Use statement to reflect the new branding as well as to align with the current industry standards to consolidate the information

This FDA 510(k) clearance letter and summary for Merge Universal Viewer (MUV) K250301 primarily focuses on administrative and functional updates, and the "device" in question is medical image management and processing software (MUV). The provided document does not contain explicit acceptance criteria or details of a rigorous clinical study demonstrating the performance of the MUV in a diagnostic context against specific metrics like sensitivity, specificity, or reader agreement improvement.

The document states:

• "No clinical testing was performed as part of performance testing for MUV 9.0." (Page 9)
• The modifications are primarily a "branding update," "consolidation of information," and addition of features (e.g., display of Mammography CAD SR, Volumetric SUV, DICOM SR ingestion panel, cardiology measurement tools, cybersecurity improvements, full-resolution mammography display with keyboard shortcut, bug fixes). (Pages 7-8)
• The comparison is primarily focused on "technological characteristics" and "intended use" relative to predicate devices, and internal software verification and validation. (Page 8-9)

Therefore, based solely on the provided text, it is not possible to fill out the requested information regarding acceptance criteria and a study proving "the device meets the acceptance criteria" in terms of clinical diagnostic performance. The acceptance criteria described are internal to software development and regulatory compliance, not clinical diagnostic accuracy.

However, I will address what can be inferred or directly stated from the provided document regarding the requested categories:

Based on the provided FDA 510(k) Clearance Letter and Summary for Merge Universal Viewer (MUV) K250301, the "acceptance criteria" and "study proving the device meets the acceptance criteria" are focused on software functionality, safety, and equivalence to predicate devices, rather than a clinical performance study with specific diagnostic accuracy metrics.

Here's a breakdown of the information available:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not specified for any of the described tests (software verification, cybersecurity, usability, design validation). The document describes the types of tests performed on the software, not the number of specific cases or data points used.
• Data Provenance: Not specified. Given the nature of the tests (software verification, cybersecurity, usability, design validation), the "data" would be test results and logs generated during internal development and validation, rather than patient imaging data used in a clinical performance study. The document states "No clinical testing was performed." (Page 9)

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.
  • For software verification, cybersecurity, and design validation, these would likely be internal software engineers, quality assurance personnel, and subject matter experts on medical imaging systems.
  • For usability testing, "trained healthcare professionals" are mentioned as the intended users, but the specific qualifications of those who participated in usability testing are not detailed.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable or not specified. The described tests are about software functionality, usability, and security, not clinical diagnostic interpretation requiring adjudication of reader opinions.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• MRMC Study: No, an MRMC comparative effectiveness study was not performed. The document explicitly states: "No clinical testing was performed as part of performance testing for MUV 9.0." (Page 9)
• Effect Size: Not applicable.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Standalone Performance: No, a standalone performance study of an algorithm in a diagnostic context was not performed. The device is a viewer, not an AI diagnostic algorithm meant to be used standalone. It displays data, including "Mammography CAD SR" and "DICOM Structured Report (SR) ingestion panel," which implies it can display outputs from other algorithms, but it is not itself an algorithm generating diagnostic interpretations.

7. The Type of Ground Truth Used

• Type of Ground Truth: For the software validation and verification, the "ground truth" would be the expected functionality, design specifications, and security requirements laid out by the developers and in regulatory guidance. It is not clinical ground truth (e.g., pathology, expert consensus, outcomes data) as no clinical performance study was conducted.

8. The Sample Size for the Training Set

• Training Set Sample Size: Not applicable. MUV is an image viewer and management system, not a machine learning model that undergoes a "training" phase with a dataset in the typical sense of AI/ML development for diagnostic tasks.

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

• Training Set Ground Truth Establishment: Not applicable, as MUV is not an AI/ML model for diagnostic training.

In summary, the provided FDA document focuses on the safety and effectiveness of the Merge Universal Viewer 9.0 primarily through demonstrating:

• Its functional integrity through software verification and design validation.
• Its cybersecurity resilience.
• Its usability for trained healthcare professionals.
• Its substantial equivalence to previously cleared predicate devices for image management and viewing, including the display of information from other diagnostic tools (like CAD SR or structured reports), but not its own diagnostic performance or improvement in human reader accuracy.

Ask a specific question about this device

Merge Hemo displays, measures, and records physiological data from patients undergoing invasive catheter-based diagnostic and interventional procedures.

The Hemo System can visualize and capture vital sign values including ECG, impedance respiration, SpO2 and Pleth waveforms, invasive blood pressure, temperature, non-invasive blood pressure (NIBP), Thermodilution cardiac output and Fractional Flow Reserve (FFR). The system can display and capture 12 Lead resting ECG to visualize arrhythmias, and ST-segment changes. Some Hemo systems have an option to measure and display Side-stream End Tidal Carbon Dioxide (EtCO2) along with apnea and respiration rates calculated from the EtCQ2 waveforms. The system can also perform specified calculations from captured or manually entered values.

The hemodynamic portion of the system is comprised of the Patient Data Module (PDM) and the Merge Hemo Monitor PC.

All vital parameters are acquired in the PDM. This data is then transmitted to the Merge Hemo Monitor PC. All data can then be displayed on the Merge Hemo Monitor PC. User-adjustable visual alarms available in the system alert the operator to anomalous occurrences and facilitate timely responses.

Patient allergies and current medication information can be entered by the user and displayed by the system. If desired and using a third-party database, the Hemo system can display drug or drug-to-allergy interaction information.

The Merge Hemodynamic system is intended for use in invasive catheter-based diagnostic and interventional procedure laboratories and in pre- and post-procedure care areas in professional health care facilities. The Merge Hemo system is intended for use under the close supervision of qualified medical personnel. The system is not intended patient monitoring or in situations where arrhythmia detection is required. This system is used in the diagnosis and treatment of cardiovascular, peripheral vascular, and cardiac diseases. The system is designed for patients of Infant to Adult ages. The system is to be used in invasive procedural laboratories under the direct supervision of physicians, nurses, and technicians.

The Merge Hemo, Model RCSV2 device is a hemodynamics recording computer system that monitors, measures, displays, records and stores various physiologic and blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices. The system is used for documenting and monitoring patients undergoing diagnostic and interventional catheter-based procedures. The procedures can be performed in the clinical areas of invasive cardiology, interventional radiology, and cardiac electrophysiology.

The device consists of off-the-shelf computer hardware such as personal computers and servers, a Patient Data Module (PDM) that acquires patient vitals received from accessories such as ECG electrodes, invasive catheters/pressure transducers, and temperature probes, and transmits them to the Merge Hemo Monitor.

The Merge Hemo system includes a Record Station with options to add a Procedure Room Hemo Monitor or a Remote Operators Terminal (ROT). The Record Station Workstation for Merge Hemo, Model RCSV2 is made up of medical grade Hemo Client and Hemo Monitor All-in-One computers with built-in display monitors.

The new PDM component, the ARGUS PB-3000 manufactured by Schiller AG, acquires the following patient vitals: ECG, Invasive Blood Pressure, SpO2, Non-Invasive Blood Pressure, Temperature, Cardiac Output, and CO2, digitizes the signals, and transmits them to the Hemo Monitor in the Record Station. The Client side of the Record Station is responsible for the documentation, display, storage, and distribution of the data acquired during the procedure.

The provided text does not contain typical acceptance criteria and a study proving device performance as might be found in a clinical trial summary. Instead, it describes a 510(k) premarket notification for a medical device (Merge Hemo, Model RCSV2) and outlines the regulatory process and the types of non-clinical performance data submitted to demonstrate substantial equivalence to a predicate device.

The "acceptance criteria" here refer to compliance with various electrical safety, electromagnetic compatibility, usability, and software development standards, rather than specific performance metrics like sensitivity or specificity for a diagnostic device. The "study" is a compilation of non-clinical tests demonstrating adherence to these standards.

Here's the breakdown of the information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify a "test set" in terms of patient data for evaluating diagnostic performance. The testing described is primarily non-clinical, focusing on hardware and software compliance with regulatory standards. Therefore, information on sample size and data provenance (country of origin, retrospective/prospective) for a clinical test set is not applicable/provided.

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

This information is not applicable/provided as no clinical ground truth establishment using experts is described for diagnostic performance evaluation. The "ground truth" for the non-clinical tests would be the specifications and requirements of the various standards the device is tested against.

4. Adjudication Method

This information is not applicable/provided as no clinical study requiring adjudication of expert interpretations is described.

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

No MRMC study is mentioned. The application is for a hemodynamic monitoring system, not a diagnostic imaging AI system that typically undergoes MRMC studies. The document states: "Clinical testing was not required to demonstrate the safety and effectiveness of Merge Hemo, Model RCSV2." Therefore, the effect size of human readers with/without AI assistance is not applicable/provided.

6. Standalone (Algorithm Only) Performance Study

The document describes the device as a "hemodynamics recording computer system" and lists various vital parameters it monitors, measures, displays, and records. It also mentions "specified calculations from captured or manually entered values" and "same software algorithms" for physiological parameters.

While software verification and validation are mentioned, there is no separate "standalone performance study" of an algorithm without human involvement in the sense of a diagnostic AI product. The system is designed to acquire and display physiological data for qualified medical personnel to use in diagnosis and treatment. The performance evaluation focuses on the system's ability to accurately acquire, process, and display data in compliance with medical device standards, rather than an autonomous diagnostic algorithm's accuracy.

7. Type of Ground Truth Used

The "ground truth" for the described performance evaluation (electrical safety, EMC, software V&V, usability) is the requirements and specifications outlined in the applicable international and national standards (e.g., IEC 60601 series, ISO 14971, IEC 62304). The device is tested to ensure it operates within the defined limits and behaviors stipulated by these standards.

8. Sample Size for the Training Set

This information is not applicable/provided. As explained, the "study" is a non-clinical evaluation of compliance with regulatory standards, not a machine learning model training and testing process involving patient data in the typical sense for AI/ML devices.

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

This information is not applicable/provided for the reason stated above.

Ask a specific question about this device

The IBM iConnect Access application provides internet access to multi-modality softcopy medical images, reports, and other patient-related information to conduct diagnostic review, planning and reporting through the interactive display and manipulation of medical data. IBM iConnect Access provides healthcare professional tools to aid in interpreting medical images including:

• · Displaying DICOM compliant medical images and non-DICOM content using XDS
• · Reformatting images, including creation of MPRs, MIPS, MinIPs, color/monochrome 3D volume rendered images
  · Manipulating displayed images via control of slice interval, obliquity, perspective, rotation, window/ level, crop, zoom, color/monochrome transformation, sculpting, straightening the display of curved structures, and creating images perpendicular to a curvilinear path.
• · Creating individually captured DICOM images that can be displayed and stored in a PACS
  • Measuring coronary calcium, which is intended for non-invasive identification of calcified atherosclerotic plaques in the coronary arteries using tomographic medical image data and clinically accepted calcium scoring algorithms.
  · Creating and outputting digital files suitable for the fabrication of physical replicas, such as 3D printing, using DICOM files as inputs. Physical/3D printed models generated from the digital output files are not for diagnostic use.

The IBM iConnect Access application can be configured to provide either lossless or lossy compressed images for display. The medical professional user must determine the appropriate level of image data compression that is suitable for their purpose.

Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 MP resolution and meets other technical specifications reviewed and accepted by FDA.

Display monitors used for reading medical images for diagnostic purposes must comply with applicable regulatory approvals and with quality control requirements for their use and maintenance. Use of IBM iConnect Access application on mobile devices such as iPhones and iPads is not intended for diagnostic use.

IBM iConnect Access provides healthcare professionals with access to diagnostic quality images, reports, and various types of patient data over conventional TCP/IP networks.

With no download or application-specific installation required on the user's computer, healthcare professionals can use IBM iConnect Access with a standard internet browser to view exams and patient information including but not limited to the following content: Diagnostic Reports. Kev Images, Presentation Series, Modality Imaging, Scope/ Surgery Videos, Visible Light, and File Attachments.

IBM iConnect Access was designed with an easy and convenient workflow providing image viewing and manipulation capabilities including but not limited to zoom, pan, window/ level, scroll, CINE, link series, line/ angle/ ROI measurements, and MPR.

The software displays patient studies and other patient data but does not interpret or provide a diagnosis. Medical diagnosis is the responsibility of the user.

When configured by an Administrator, patients can view their radiological information via portals that launch IBM iConnect Access and provide the ability to view clinical results, modality imaging, key images, scope/surgery videos, and associated clinical documentation. The role for patient access is limited to zooming the image, panning the image, and scrolling through a series of images.

The IBM iConnect Access 3D advanced imaging solution supports MIP (maximum intensity project), MPR (multiplanar reconstruction), 3D volume rendering, and cardiac calcium scoring. Reading physicians, referring physicians, and other appropriate healthcare personnel and can employ advanced image processing and display from local or remote locations.

IBM iConnect Access provides advanced image segmentation and editing tools for the purpose of creating digital 3D anatomical models. These models can be exported as STL files for the purpose of fabricating physical replicas, such as 3D printing. Physical/3D printed models generated from the digital output files are not for diagnostic use.

IBM iConnect Access can be used to query and retrieve content from the IBM iConnect Enterprise Archive. IBM iConnect Enterprise Archive is a software system that supports storage and communications of medical images and data. Qualified system administrators monitor and maintain the software in their healthcare enterprise environment.

IBM iConnect Suite is an offering that combines the image storage capability of IBM iConnect Enterprise Archive with the diagnostic viewer capability of IBM iConnect Access.

This 510(k) premarket notification describes the IBM iConnect Access (v8.0), a Picture Archiving and Communication System (PACS), which is substantially equivalent to a previously cleared version (IBM iConnect Access v7.0, K182290).

The primary focus of this submission revolves around the addition of new features related to 3D model manipulation and export for 3D printing. Because it is a PACS system and the changes are primarily functional enhancements to existing capabilities (e.g., image manipulation, 3D reconstruction, and data export), the submission states that clinical studies are not required to demonstrate safety and effectiveness.

Therefore, the following information, which would typically be found in a study demonstrating clinical performance, is not available in this document:

• A table of acceptance criteria and reported device performance (for clinical endpoints)
• Sample sizes for test sets and data provenance
• Number of experts and their qualifications for establishing ground truth
• Adjudication method
• MRMC comparative effectiveness study results
• Standalone algorithm performance
• Type of ground truth used (for clinical validation)
• Sample size for the training set
• Ground truth establishment for the training set

The document does, however, provide information regarding non-clinical testing for the new features.

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

The document does not provide a formal table with acceptance criteria and reported device performance metrics in the way one would typically see for a diagnostic AI device. Instead, it describes compliance with voluntary standards and in-house testing for the new features.

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

The document mentions "in-house testing of de-identified CT and MRI DICOM images" but does not specify the sample size or the data provenance (country of origin, retrospective/prospective nature).

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, as clinical ground truth establishment by experts for specific diagnostic performance metrics was not part of this submission. The testing focused on technical functionality.

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

Not applicable, as no clinical adjudication of diagnostic findings from a test set is described.

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 conducted or reported. The device is a PACS system with added image manipulation and export features, not an AI-assisted diagnostic tool in the sense of providing specific interpretations.

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

The device's functionality is to provide tools for healthcare professionals; it does not operate in a standalone diagnostic manner. The document does not describe standalone algorithm performance.

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

For the non-clinical testing described, the "ground truth" was likely the expected technical output for the interactive segmentation and mesh generation features, rather than clinical ground truth (e.g., pathology confirmed disease presence). The document states: "in-house testing of de-identified CT and MRI DICOM images confirmed that interactive segmentation of digital 3D models and mesh generation for STL file creation was acceptable." This implies a verification against pre-defined technical specifications for the output.

8. The sample size for the training set

Not applicable. The description does not involve a training set for an AI model that performs diagnostic interpretation. The software's new features are based on algorithms for image manipulation and geometric processing, not typically requiring a distinct "training set" in the context of deep learning for image classification or detection.

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

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

Ask a specific question about this device

Merge PACS™ is a Picture Archiving and Communication System (PACS) for multi-modality (CT, MR, PT, US, MG, BTO, CR, DR/DX, NM, XA, RF, secondary capture (SC), and other DICOM-compliant modalities) image processing and display, diagnostic reading and reporting, communication, printing, and storage of medical imaging studies and other patient data. Intended clinical users include radiologists, orthopedic and other surgeons, referring physicians, and other qualified medical professionals.

Merge PACS, a software medical device, is a standards-based medical imaging diagnostic workstation that serves as an adjunct to assist the clinician to view, read, and report their findings. Merge PACS processes and displays medical images from DICOM-compliant modalities. The device is designed to enable efficient workflows by maintaining clinicians' worklists and retrieving and managing studies for reading, reporting, communication, and storage.

Merge PACS software runs on off-the-shelf computer hardware and can be configured to operate standalone or to integrate with vendor-neutral imaging archives (VNAs) such as iConnect Enterprise Archive (iCEA) via DICOM protocol, for image storage, and with radiological and hospital information systems (RIS and HIS) and medical record systems (EMR, EHR, etc.) via HL7.

Merge PACS can be accessed from within the hospital or enterprise, or from remote locations via web-based access. Images viewed on mobile devices should not be used for diagnostic purposes.

The focus of this premarket notification is on the addition of the Region Analysis Area and Region Analysis Volume tools, which allows for additional clinical analysis of images, including volumetric Standard Uptake Value (SUV) calculation. There has been a minor change in the indications for use statement from the previous Merge PACS device, with the removal of the optional Reach component which is no longer offered. Additional non-significant changes since the previous submission will be discussed.

This document (K192455) is a 510(k) summary for a Picture Archiving and Communication System (PACS) called "Merge PACS." It describes the device, its intended use, and compares it to predicate devices to demonstrate substantial equivalence.

Acceptance Criteria and Device Performance (Based on provided text):

The document does not explicitly present a table of quantitative acceptance criteria for the Merge PACS device's performance, as it focuses on demonstrating substantial equivalence to a predicate device rather than presenting novel performance metrics. The primary "performance" discussed is the addition of new features and the continued meeting of existing specifications.

However, based on the narrative and the comparison table, we can infer some "acceptance criteria" and "performance" in terms of functionality and safety equivalence to the predicate. The key "significant change" introduced is related to SUV (Standardized Uptake Value) Calculation for PET images.

Here's an interpretation based on the information provided, framed as acceptance criteria and performance:

1. Table of Implied Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance:

• Test Set Sample Size: The document does not specify a separate "test set" sample size in the context of clinical performance evaluation (e.g., for diagnostic accuracy). The non-clinical testing performed includes "Testing on unit level," "Integration testing," and "Performance testing." These tests would have used various forms of data, but the specific volume or type of imaging data is not detailed.
• Data Provenance: The document does not provide details on the country of origin of data or whether it was retrospective or prospective. Given that no new clinical studies were required, any data used for internal verification and validation would likely be existing, retrospective data.

3. Number of Experts and Qualifications for Ground Truth:

• The document states: "The subject of this premarket submission, Merge PACS, did not require clinical studies to support substantial equivalence." Therefore, there is no information provided on the number or qualifications of experts used to establish ground truth for a clinical test set in the context of diagnostic performance. The ground truth for the functional verification and validation would be against product specifications and established DICOM standards.

4. Adjudication Method for the Test Set:

• Since no clinical studies were performed requiring human interpretation and ground truth establishment for diagnostic performance, no adjudication method (e.g., 2+1, 3+1) is mentioned or implied.

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

• No MRMC comparative effectiveness study was done or mentioned. The submission explicitly states, "The subject of this premarket submission, Merge PACS, did not require clinical studies to support substantial equivalence." The device is a PACS system, and the focus is on its basic functionality, image display, and measurement tools, rather than a direct diagnostic aid that would typically undergo such a study.

6. Standalone (Algorithm Only) Performance:

• This device is a PACS system, which is a tool for clinicians to view and manipulate medical images. It is not an AI diagnostic algorithm or an "algorithm only" device in the sense of providing automated diagnoses or confidence scores. Its "performance" is in its ability to correctly acquire, store, display, and process images and data. Therefore, the concept of a "standalone" (algorithm-only) performance is not directly applicable in the way it would be for a CADx or AI detection algorithm.
• The document implies that the device's measurement capabilities (e.g., SUV calculation) are part of the overall system and are validated through non-clinical means against expected mathematical outputs or standard benchmarks.

7. Type of Ground Truth Used:

• For the significant change (3D SUV calculation), the "ground truth" would likely be derived from:
  • Physics-based or Phantom Data: Verified calculations on known phantom images with defined SUV values.
  • Reference Standard Implementations: Comparison of calculated SUVs against established, validated algorithms (e.g., from the reference predicate Xelis Fusion or other industry-standard software).
  • Mathematical/Computational Verification: Demonstrating that the algorithms correctly implement the SUV calculation formulas.
• For the PACS functionalities in general, the ground truth for "acceptance" is often:
  • DICOM Conformance: Data transmission, storage, and display adhere to DICOM standards.
  • Software Requirements Specifications: The software performs as intended according to detailed design documents.
  • User Interface/Experience Expectations: The tools function as designed for user interaction.

8. Sample Size for the Training Set:

• As this is primarily a PACS system with new measurement tools, and not an AI/ML algorithm that requires a "training set" in the traditional sense, no information on a training set sample size is provided. The development process involved "Design Reviews," "Testing on unit level," "Integration testing," and "Performance testing," which are typical for software validation but do not typically involve a separate "training set."

9. How Ground Truth for Training Set Was Established:

• Given that there is no "training set" for an AI/ML algorithm, the question of how its ground truth was established is not applicable to this submission. The "ground truth" for the development and verification of the PACS system's features would be based on:
  • Medical standards and protocols (e.g., DICOM).
  • Mathematical accuracy for measurements (e.g., SUV calculation).
  • Functional requirements and specifications.
  • Comparison to the performance of predicate devices.

Ask a specific question about this device

Merge Cardio software product is an integrated multi-modality image and information system designed to perform the necessary functions required for import, export, review, analysis, quantification, reporting, and database management of digital cardiovascular images, documents, and data related to cardiology. Merge Cardio offers support for third-party applications in order to enable the use of commercially available tools and specified applications for analysis, quantification, and reporting. Merge Cardio software runs on standard information technology hardware and software, using standard information technology operating systems and user interfaces. Communication and data exchange are done using standard protocols. The modular design allows configurability to tailor the image import and communications solution to the needs of the user. The number of modalities and reporting and/or viewing sites can be configured per system.

Merge Cardio is a software medical device that is an integrated multi-modality image cardiovascular information management system. The Merge Cardio system is intended to allow authorized health care professionals the ability to import, export, review, analyze, quantify, report and manage digital cardiovascular images, documents, and data related to cardiology. The study list supports workflow management by providing a robust study list with configurable informational columns supporting navigation, current study and reporting status, and prior study availability and relevancy. The
system offers standard image
controls such as brightness
contrast, zoom, and cine playback controls; as well modality specific tools such as R-wave sync and frame rate sync. The system allows users to review images, annotate images, perform digital subtraction on XA images, perform quantitative measurements on images (based on modality and anatomy including quantitative coronary analysis, left ventricular analysis, distance, angle, velocity, slope, area, velocity time integral, and volume), derive US measurements, and generate clinical reports. The system provides the ability to create clinical reports for Adult Echo, Pediatric Echo, Vascular US, Nuclear Medicine, Cath/Peripheral Invasive, Electrophysiology, Cardiac CT, and Cardiac MR. Merge Cardio runs on standard information technology hardware and software, using standard information technology operating systems and user interfaces. Communication and data exchange are done using standard protocols.

The provided document, K192276 for Merge Cardio, does not contain information about acceptance criteria or a study that specifically proves the device meets those criteria. Instead, it is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device for regulatory clearance.

This document explicitly states:

• "Summary of Clinical Tests: The subject of this premarket submission. Merge Cardio, did not require clinical studies to support substantial equivalence." (Page 10)
• The non-clinical testing performed includes: Risk Analysis, Requirements Review, Design Reviews, Unit level code reviews, Integration testing, Performance testing, and Safety testing from risk analysis. (Page 9-10)
• The device is a "Picture archiving and communications system (PACS)" (Page 5), which is software designed for managing medical images and data, rather than an AI/ML-driven device with performance metrics like sensitivity, specificity, or AUC as primary acceptance criteria.

While the document details many system features and functionalities, it does not present acceptance criteria in the form of quantitative performance targets (e.g., sensitivity, specificity, or accuracy) that would be typically found for diagnostic AI/ML models. It focuses on functional equivalence to a predicate device.

Therefore,Based on the provided text for K192276, I cannot fulfill the request for information regarding acceptance criteria and the study proving the device meets them in the context of an AI/ML diagnostic system. The document does not describe such a study or criteria for this specific device.

Ask a specific question about this device

The IBM iConnect Access application provides internet access to multi-modality softcopy medical images, reports, and other patient-related information to conduct diagnostic review, planning and reporting through the interactive display and manipulation of medical data. IBM iConnect Access provides healthcare professional tools to aid in interpreting medical images including:

o Displaying DICOM compliant medical images and non-DICOM content using XDS

o Reformatting images. including creation of MPRs. MIPS. MinIPs. color/monochrome 3D volume rendered images o Manipulating displayed images via control of slice interval, obliquity, perspective, rotation, window/ level, crop, zoom, color/monochrome transformation, sculpting, straightening the display of curved structures, and creating images perpendicular to a curvilinear path.

o Creating individually captured DICOM images that can be displayed and stored in a PACS

o Measuring coronary calcium, which is intended for non-invasive identification of calcified atherosclerotic plaques in the coronary arteries using tomographic medical image data and clinically accepted calcium scoring algorithms.

The IBM iConnect Access application can be configured to provide either lossless or lossy compressed images for display. The medical professional user must determine the appropriate level of image data compression that is suitable for their purpose.

Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 MP resolution and meets other technical specifications reviewed and accepted by FDA.

Display monitors used for reading medical images for diagnostic purposes must comply with applicable regulatory approvals and with quality control requirements for their use and maintenance. Use of IBM iConnect Access application on mobile devices such as iPhones and iPads is not intended for diagnostic use.

IBM iConnect Access provides healthcare professionals with access to diagnostic quality images, reports, and various types of patient data over conventional TCP/IP networks.

With no application-specific installation required on the user's computer, healthcare professionals can use IBM iConnect Access with a standard internet browser to view studies and patient information including but not limited to the following content: Diagnostic Reports, Key Images, Presentation Series, Modality Imaging, Scope/ Surgery Videos, Visible Light, and File Attachments.

IBM iConnect Access was designed with an easy and convenient workflow providing image viewing and manipulation capabilities including but not limited to zoom, pan, window/ level, scroll, cine, link series, line/ angle/ ROI measurements, and MPR.

The software displays patient studies and other patient data but does not interpret or provide a diagnosis. Medical diagnosis is the responsibility of the user.

The IBM iConnect Access 3D advanced imaging solution supports MIP (maximum intensity project). MPR (multiplanar reconstruction). 3D volume rendering, and cardiac calcium scoring. Reading physicians, referring physicians, and other appropriate healthcare personnel can employ advanced image processing and display from local or remote locations.

IBM iConnect Access can be used to query retrieve content from the IBM iConnect Enterprise Archive. IBM iConnect Enterprise Archive is a software system that supports storage and communications of medical images and data. Qualified system administrators monitor and maintain the software in their healthcare enterprise environment.

IBM iConnect Access along with IBM iConnect Enterprise Archive comprise a cloud based solution marketed as iConnect Cloud Archive. The IBM iConnect Access 3D advanced imaging solution option is not available on iConnect Cloud Archive.

The provided text is a 510(k) Summary for the IBM iConnect Access device. It does not contain specific acceptance criteria or details of a study that proves the device meets those criteria. Instead, it focuses on demonstrating substantial equivalence to predicate devices through a comparison of features and stating that internal verification and validation testing confirmed product specifications.

Therefore, many of the requested details about acceptance criteria, study design, and performance metrics cannot be extracted from this document.

However, I can provide what information is available:

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

The document does not explicitly state quantitative acceptance criteria or detailed reported device performance in terms of specific metrics (e.g., sensitivity, specificity, accuracy). It generally asserts that "product specifications have been met" based on internal verification and validation. The table in the "Comparison with Predicate" section outlines features and capabilities, and the rationale column often states "Substantially Equivalent."

2. Sample size used for the test set and the data provenance

This information is not provided in the document. The document states "Results from internal verification and validation testing performed in accordance with Watson Health Imaging design control processes confirm that IBM iConnect Access product specifications have been met." It does not specify the sample size, type of data used (e.g., patient cases, synthetic data), or its provenance for these internal tests.

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

This information is not provided in the document. The document does not describe the establishment of a "ground truth" using experts for the purpose of validating the device's performance against clinical outcomes.

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

This information is not provided in the document. No details on adjudication methods for a test set are mentioned.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not mentioned in the document. The IBM iConnect Access device is described as a Picture Archiving and Communication System (PACS) with advanced imaging capabilities, not an AI-assisted diagnostic tool that would typically undergo such a study to evaluate human reader improvement.

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

The document does not detail a standalone performance study in the way it might for an AI algorithm. It describes the device as providing "healthcare professional tools to aid in interpreting medical images," and explicitly states, "The software displays patient studies and other patient data but does not interpret or provide a diagnosis. Medical diagnosis is the responsibility of the user." This indicates it's not a standalone diagnostic algorithm. The cardiac calcium scoring feature is described as "using tomographic medical image data and clinically accepted calcium scoring algorithms," suggesting it integrates existing, accepted algorithms rather than presenting a novel standalone algorithm for independent validation in this submission.

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

The document does not specify the type of ground truth used, as it does not detail a clinical study with a defined ground truth for device performance evaluation. The "ground truth" for the verification and validation largely refers to the device meeting its own design specifications and intended functionality, and demonstrating substantial equivalence to predicate devices.

8. The sample size for the training set

The document does not provide information about a training set since it focuses on a PACS system and its comparison to predicate devices, not on a machine learning model that would require a distinct training set.

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

As there is no mention of a training set, this information is not applicable/provided.

Ask a specific question about this device

Merge PACS™ is a Picture Archiving and Communication System (PACS) for multi-modality (CT, MR, PT, US, MG, BTO, CR, DR/DX, NM, XA, RF, secondary capture (SC), and other DICOM-compliant modalities) image processing and display, diagnostic reading and reporting, communication, printing, and storage of medical imaging studies and other patient data.

Intended clinical users include radiologists, orthopedic and other surgeons, referring physicians, technologists, and other qualified medical professionals. Data can be received directly from acquisition modalities, CAD systems, and other image processing systems, or indirectly via importing. Data that is not DICOM-compliant, such as photos, can be converted to DICOM format by Merge PACS.

Merge PACS provides image manipulation tools to enable users to view and compare images such as: linkinq, MPR, MIP, 3D image fusion/registration of CT, MR, and PET; as well as CVR (Color Volume Rendering), measurements (linear distances, angles, areas, SUV, etc.), and annotations (for example, outline and label regions of interest, label spinal vertebrae).

The Real Time Worklist (RTWL) displays the real-time status of radiology activity and provides customizable workflow management capabilities. Communication of critical results is facilitated and documented through optional, configurable components.

The Patient Dashboard provides a composite view of patient data, both imaging and non-imaging. The optional Reach component provides clinicians with secure, proactive communication and access to clinical reports and images. Multi-tier patient identity matching provides a comprehensive view even when dealing with multiple disparate patient identities.

Order and report information generated by the HIS/RIS and report creation systems are received and displayed via the transmission of HL7 messaging. Lossless (reversible) and lossy (irreversible) image compression are supported for viewing, storage and communication.

Merge PACS displays full fidelity DICOM images for use in the diagnostic interpretation of mammography using MG or BTO images. Thick slab MIP presentation can be applied to BTO images.

Lossy compressed images and digitized screen film images must not be used for primary diagnosis of mammography studies, and only display monitors that have regulatory clearance for mammography interpretation should be used for the interpretation of mammography studies.

Merge PACS™, a software medical device, is a standards-based medical imaging diagnostic workstation that serves as an adjunct to assist the clinician to view, read, and report their findings. Merge PACS processes and displays medical images from DICOM-compliant modalities. The device is designed to enable efficient workflows by maintaining clinicians' worklists and retrieving and managing studies for reading, reporting, communication, and storage.

Merge PACS software runs on off-the-shelf computer hardware and can be configured to operate standalone or to integrate with vendor-neutral imaging archives (VNAs) such as iConnect Enterprise Archive (iCEA) for image storage, and with radiological and hospital information systems (RIS and HIS) and medical record systems (EMR, EHR, etc.).

Merge PACS can be accessed from within the hospital or enterprise, or from remote locations via web-based access. Images viewed on mobile devices must not be used for diagnostic review.

The focus of this premarket notification is on the addition of the ability to "fuse" images for viewing (image fusion) and on the ability to measure Standardized Uptake Values (SUV) on PET (Positron Emission Tomography) images.

The provided text is a 510(k) Pre-market Notification for the Merge PACS™ system. It outlines the device's intended use, comparison to predicate devices, and performance data. However, it explicitly states that clinical studies were not required, meaning specific acceptance criteria with reported performance, sample sizes, and expert reviews as requested in your prompt were not applicable or performed for this submission.

The document focuses on demonstrating substantial equivalence to existing devices (AMICAS PACS 6.0 and Fujifilm Synapse PACS) by comparing features and technologies, rather than proving performance against predefined quantitative acceptance criteria through clinical trials.

Therefore, many of the requested details cannot be extracted from this document. Here's what can be provided based on the text:

Key Takeaway: The submission is based on demonstrating substantial equivalence through feature comparison and non-clinical testing, not on meeting specific quantitative acceptance criteria established via clinical studies.

Summary of Device Performance (Based on Non-Clinical Testing and Feature Comparison):

Since no clinical studies with specific acceptance criteria were conducted, the "performance" is described in terms of compliance and functional validation.

• Acceptance Criteria and Reported Device Performance: Not applicable as defined by your prompt (no quantitative clinical acceptance criteria provided or met). The "acceptance" is based on functional verification through non-clinical testing and comparison to predicates.

  Table (Hypothetical, based on functional claims, not quantitative performance):

• Sample size for the test set and data provenance: Not specified for any quantitative testing that would establish "test set" performance. The non-clinical testing would have involved internal datasets, but details on size, origin, or retrospective/prospective nature are not provided.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. No ground truth established by experts for performance evaluation was mentioned. The "ground truth" for the non-clinical tests would have been the expected functional output.
• Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. No expert adjudication method was mentioned.
• 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 done. The device is a PACS system, not an AI for diagnostic assistance in the traditional sense that "improves human readers."
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The device is a software workstation with various functionalities, not a standalone AI algorithm with a distinct "performance" metric that would be evaluated in isolation from human interaction. Its functions (like SUV calculation) are tools for human users. Non-clinical tests confirmed these functions performed "as expected," which is a form of standalone functional validation.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For the non-clinical tests, the "ground truth" was likely the expected outcome of direct functional tests (e.g., if you input X, the SUV calculation should yield Y; if you overlay two images, they should align based on DICOM coordinates). There was no mention of using clinical outcomes, pathology, or expert consensus as a ground truth for performance evaluation in the context of "acceptance criteria."
• The sample size for the training set: Not applicable. The document describes a PACS system which is a software medical device, not a machine learning or AI model that typically has a "training set." The development of the software would involve traditional software engineering and testing processes, not a dataset-driven training phase in the AI sense.
• How the ground truth for the training set was established: Not applicable, as there is no "training set" in the context of an AI/ML model for this device.

Ask a specific question about this device

Merge Hemo displays, measures, and records physiological data from a patient undergoing a cardiac catheterization procedure.

The Hemo System can visualize and capture vital sign values including ECG, impedance respiration, SpO2 and Pleth waveforms, invasive blood pressure, non-invasive blood pressure (NIBP). Thermodilution cardiac output and Fractional Flow Reserve (FFR). The system can display and capture diagnostic quality 12 Lead resting ECG to visualize arrhythmias, and ST-segment changes. Some Hemo systems have an option to measure and display Side-stream End Tidal Carbon Dioxide (EtCO2) along with apnea and respiration rates calculated from the EtCO2 waveform.

The hemodynamic portion of the system is comprised of the Patient Data Module (PDM) and the Merge Hemo Monitor PC. The two units are connected via a serial interface.

All vital parameters are acquired and calculated in the PDM. This data is then transmitted to the Merge Hemo Monitor PC via the serial interface. All data can then be displayed on the Merge Hemo Monitor PC. The Merge Hemo system is not intended to produce alarms for out-of-range conditions.

Patient allergies and current medication information can be entered by the system. If desired and using a third party database the Hemo system can display drug to allergy interaction information.

The system is intended for use in hospital catheterization laboratories and in pre-and post-procedure care areas in the hospital under the close supervision of qualified medical personnel.

Merge Hemo is a hemodynamic recording and display system designed to measure, record, and display vitals signs data for patients undergoing cardiac catheterization procedures.

The addition of a Merge Hemo software feature that provides the ability to calculate and display Fractional Flow Reserve (FFR) values is described. No hardware changes are required in order to enable or perform this functionality.

FFR provides a quantitative assessment of the functional severity of a coronary artery stenosis identified during coronary angiography and cardiac catheterization.

FFR measurement involves determining the ratio between the maximum achievable blood flow in a diseased coronary artery and the theoretical maximum flow in a normal coronary artery.

The Merge Hemo software user interface displays the pressure waveforms from the third party FFR pressure transducers that are placed distal and proximal to the lesion. When the FFR feature is enabled, the system shows the section of each of the waveforms that is used to calculate the mean pressure.

The results of the pressure waveform recording is expressed as a fraction of the normal blood flow in the coronary artery compared to the maximum achievable blood flow in the same artery. An FFR measurement of 1.0 indicates an artery with normal blood flow. FFR measurements less than 0.80 indicate that ischemia could be caused by blood flow blockage.

The Merge Hemo software initially selects segments of the waveforms to use for FFR calculations but the user can easily change where the values are taken by using the touchscreen interface to move the segment markers along the waveforms. The FFR value recalculates accordingly.

Here's a breakdown of the acceptance criteria and study information for the Merge Hemo device based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a table format. However, it describes the performance objective of the FFR calculation and the results of the key comparison study.

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

• Sample Size: The document does not specify a numerical sample size for the test set used in the "Integration Test: Comparison of Merge Hemo System vs. ACIST FFR System" or the "Integration Test: Compatibility of Different FFR Pressure Transducers." It refers to "varying the input pressure values" for the physiologic simulator test and "various makes and models" for the compatibility tests without quantifying the number of data points or instances.
• Data Provenance: The data was generated through in-house bench testing using physiologic simulators and commercially available third-party FFR pressure measurement devices and standard pressure transducers. No patient data (retrospective or prospective) was used for these specific tests according to the document.

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

There were no experts utilized to establish the ground truth for the test set for the FFR calculation. The ground truth was established by:

• The known input values from physiologic simulators.
• The output from a legally marketed predicate FFR system (ACIST RXi Rapid Exchange FFR System, K132474), which was used as the reference standard for comparison.

4. Adjudication Method for the Test Set

Not applicable. There was no human adjudication process described. The comparison was against known values or a predicate device's output.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was Done

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical tests were required in order to demonstrate the proper integration of the measurements into Merge Hemo for the calculation of FFR values."

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

Yes, a standalone performance evaluation was conducted. The tests described ("Physiologic Simulator Test," "Integration Test: Comparison of Merge Hemo System vs. ACIST FFR System," and "Integration Test: Compatibility of Different FFR Pressure Transducers") evaluate the algorithm's calculation and compatibility purely based on its output compared to a reference, without human interaction influencing the FFR calculation itself after the pressure inputs are provided. The user can move segment markers to re-calculate FFR, but the calculation itself is algorithmic.

7. The Type of Ground Truth Used

The ground truth used was:

• Known values from physiologic simulators (for the "Physiologic Simulator Test").
• Comparison against a predicate device's output (ACIST RXi Rapid Exchange FFR System) for the FFR calculation, which itself is a cleared medical device and serves as a de-facto "expert consensus" or established standard in this context.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set or its sample size. This suggests that the FFR calculation feature might not rely on machine learning models that require a separate training set. The description of FFR ("The calculation of the FFR ratio is relatively simple and is well known...") implies a deterministic, algorithm-based calculation rather than a learned model.

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

Since no training set information is provided, this question is not applicable.

Ask a specific question about this device