Search Results

Sim&Size enables visualization of cerebral blood vessels for preoperational planning and sizing for neurovascular interventions and surgery. Sim&Size also allows for the ability to computationally model the placement of neurointerventional devices.

General functionalities are provided such as:

• Segmentation of neurovascular structures
• Automatic centerline detection
• Visualization of X-Ray based images for 2D review and 3D reconstruction
• Placing and sizing tools
• Reporting tools

Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition.

Sim&Size is a Software as a Medical Device (SaMD) for simulating neurovascular implantable medical devices. The product enables visualization of cerebral blood vessels for preoperational planning for neurovascular interventions and surgery. It uses an image of the patient produced by 3D rotational angiography. It offers clinicians the possibility of simulating neurovascular implantable medical devices in the artery or in the aneurysm to be treated through endovascular surgery and provides support in the treatment for the sizing and positioning of implantable medical devices.

Each type of implant device is simulated in a simulation module of Sim&Size:

• FDsize, a module that allows pre-operationally planning Flow-Diverter (FD) devices.
• IDsize, a module that allows pre-operationally planning Intrasaccular (ID) devices.
• STsize, a module that allows pre-operationally planning Stent (ST) devices.
• FCsize, a module that allows pre-operationally planning First and filling coils (FC) devices.

N/A

Ask a specific question about this device

SIMDA Abutments are intended for use with dental implants as a support for single or multiple tooth prostheses in the maxilla or mandible of a partially or fully edentulous patient.

It is compatible with the following systems:

Pre-Milled Blank, Patient-specific abutment

Ti-Base abutment

Multi-unit abutment

Multi-unit Abutment is only compatible with Straumann BLX Implant System.

All digitally designed abutments for use with SIMDA Abutments are intended to be sent to a SIMDA validated milling center for manufacture.

SIMDA Abutment is intended for use as an aid in prosthetic restoration. It consists of Pre-Milled Blank, Ti-Base, Multi-unit Abutment, Multi-unit Base. It has a pre-manufactured connection interface that fits directly to an endosseous dental implant.

Pre-milled Blank Design
This device is a patient-specific abutment composed of titanium alloy (Ti-6Al-4V ELI, ASTM F136) which is designed by a clinician or lab, and milled at a SIMDA validated milling center.

Pre-Milled Blank Design Limitation for Patient-specific abutment:

Pre-Milled Blank Design Limitation for Patient-specific abutment:
Astra OsseoSpeed EV, Astra Tech OsseoSpeed TX is minimum and maximum abutment angle 0~15 º

Ti-Base Abutment
Ti Base consists of a two-piece abutment, where the titanium base is a pre-manufactured titanium component that will be used to support a CAD/CAM-designed zirconia superstructure (the second part of the two-piece abutment) that composes the final abutment.

Ti Base are provided non-sterile therefore must be sterilized after the cementation of the patient-specified superstructure.

Raw material blanks

• InCoris Zi (ZrO2) by Sirona Dental Systems GmbH, L size blanks, cleared under K123664.

Cement

• RelyX Unicem 2Automix by 3M ESPE, cleared under K100756.

Design Limitation for Zirconia superstructure:

Multi-unit Abutment and Base
Multi-unit Abutment which are placed into the dental implant to provide support for the prosthetic restoration. The abutments are made of Titanium grade Ti-6A1-4V ELI (meets ASTM Standard F136). The Multi-unit Abutment has a post height less than 4mm and are always combined with Multi-unit Base, increasing the post height to a minimum of 4.5mm.

N/A

Ask a specific question about this device

Chemfort® 28-day 20 mm Vial Adaptor is a single use, sterile Closed System Transfer Device (CSTD) that mechanically prohibits the release of drugs, including antineoplastic and hazardous drugs, in vapor, aerosol or liquid form during preparation, reconstitution, compounding and administration, thus minimizing exposure of individuals, healthcare personnel, and the environment to hazardous drugs.

Chemfort® 28-day 20 mm Vial Adaptor prevents the introduction of microbial and airborne contaminants into the drug or fluid path for up to 28 days or 10 activations.

The Chemfort® Closed System Transfer Device (CSTD) is a system of components that allows the reconstitution of liquid or pre-dissolved powder drugs into infusion bags, flexible bottles or syringes. Single, partial or multiple vials can be used for each infusion solution container. The Chemfort® CSTD prevents contamination of the user or the environment by the drug through the use of elastomeric seals and an active carbon filter.

The components of the predicate Chemfort® CSTD system are:

• Vial Adaptor 20 mm with 13 mm Vial Converter
• Vial Adaptor 28 mm
• Vial Adaptor 32 mm
• Syringe Adaptor
• Syringe Adaptor Lock
• Luer Lock Adaptor
• Bag Adaptor SP

Each of the Chemfort® system components is available separately.

This submission introduces a new version of the 20mm Vial Adaptor to the Chemfort® CSTD system, called the Chemfort® 28-day 20 mm Vial Adaptor, as a range extension. This new Vial Adaptor differs from the predicate Vial Adaptor only with respect to the usage time limitation, which is extended from 7 to 28 days, but with the same limit of 10 activations. This change is reflected in the Indications for Use statement and the device labeling.

N/A

Ask a specific question about this device

The Archimedes APD system is an Automated Peritoneal Dialysis system indicated for acute and chronic peritoneal dialysis for adult patients in clinical and home use. A care partner is not required. The following therapies are supported: Continuous Cyclic Peritoneal Dialysis (CCPD) and Intermittent Peritoneal Dialysis (IPD). Mid-day exchanges are not supported.

The proposed system is an automated peritoneal dialysis (APD) cycler which consists of a heater unit, control unit, cart, drain containers, and disposable tubing set.

N/A

Ask a specific question about this device

Chemfort® is a single use, sterile Closed System Transfer Device (CSTD) that mechanically prohibits the release of drugs, including antineoplastic and hazardous drugs, in vapor, aerosol or liquid form during administration and preparation, thus minimizing exposure of individuals, healthcare personnel, and the environment to hazardous drugs. Chemfort® prevents the introduction of microbial and airborne contaminants into the drug or fluid path for up to 7 days.

The Chemfort® Closed System Transfer Device (CSTD) is developed by Simplivia Healthcare Ltd. The system is used by pharmacists, nurses or other healthcare professionals to prepare drugs, including cytotoxic drugs, and allow the safe reconstitution of powder and liquid drugs transfer for infusion containers (infusion bags, semi-rigid bottles, and collapsible plastic containers), injection, or administration. It is supplied sterile with a sterility assurance level (SAL) of 10-6.

The Chemfort® Female Luer Lock Adaptor is part of the Chemfort® system of devices. The Chemfort® Female Luer Lock Adaptor is intended for the safe drug transfer from one syringe to another and allows closed access via Chemfort® devices to any standard male Luer connection (see below in more details).

1. Syringe to Syringe connection:
   The Chemfort® Female Luer Lock Adaptor is connected to the Chemfort® Luer Lock Adaptor. The Chemfort® Luer Lock Adaptor port is connected to an empty / saline containing syringe (syringe "A"), equipped with a Chemfort® Syringe Adaptor or Chemfort® Syringe Adaptor Lock. A drug containing syringe (syringe "B"), equipped with a Chemfort® Syringe Adaptor or Chemfort® Syringe Adaptor Lock is connected to the Chemfort® Female Luer Lock Adaptor. This assembly of devices allows drug transfer from one syringe "A" to the other, syringe "B", for drug dilution (if syringe "A" contains saline) or drug dosage (if syringe "A" is empty). This procedure allows safe drug transfer from one syringe to another. The drug in Syringe "A" can then be injected to an intravenous (IV) bag through the Chemfort® spike or in a bolus through another Chemfort® Luer Lock Adaptor connected to a Y-site on an IV set.

Note that this procedure also involves the Chemfort® Vial Adaptor to allow to withdraw the drug from the drug vial to syringe "B".

2. Connection to IV sets:
   The Chemfort® Female Luer Lock Adaptor is connected to an IV set through the luer lock connection (proximal end or infusion line). The Chemfort® port can then connect to one of the Chemfort® Closed Administration (CADM) IV sets. This setup transfers an open IV set connection to a closed connection.

The Chemfort® Female Luer Lock Adaptor can be in contact with concentrated or diluted drugs.

The Chemfort® Female Luer Lock Adaptor is a single-use device intended for use on adults, children and infants.

The provided FDA 510(k) clearance letter and supporting documentation (Chemfort® Female Luer Lock Adaptor 510(k) Summary) describe the performance testing and acceptance criteria for a physical medical device, not a software or AI-driven diagnostic device.

Therefore, many of the requested categories in your prompt (e.g., number of experts for ground truth, adjudication method, MRMC study, sample size for training set, how ground truth for training set was established, standalone performance) are not applicable to this type of device submission. These categories are typically relevant for AI/ML-based diagnostic devices where performance data relies heavily on expert annotations, comparative effectiveness studies involving human readers, and distinct training/test datasets.

However, I can extract the relevant acceptance criteria and performance data for the Chemfort® Female Luer Lock Adaptor based on the provided document.

Acceptance Criteria and Device Performance for Chemfort® Female Luer Lock Adaptor

This document outlines the performance data and acceptance criteria for the Chemfort® Female Luer Lock Adaptor, a physical medical device. The study performed demonstrates the device's adherence to established safety and performance standards for intravascular administration sets.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are primarily based on established international standards and internal validation procedures for medical devices of this type. The "Results" column from the provided Table 2 in the 510(k) summary indicates that all tests met their acceptance criteria, demonstrating the device's compliance.

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

• Sample Size: The document does not explicitly state the numerical sample sizes for each performance test (e.g., number of units tested for particulate analysis, bidirectional flow, etc.). However, it indicates that "Simplivia conducted several performance tests to demonstrate that the Chemfort® Female Luer Lock Adaptor is safe and effective..." implying a sufficient number of samples were tested to meet the requirements of the listed standards and internal procedures.
• Data Provenance: The tests were conducted by Simplivia Healthcare LTD. (an Israeli company) for regulatory submission to the FDA. The data provenance is laboratory testing performed by the manufacturer, rather than clinical data from human subjects. The tests are prospective in nature, as they involve testing newly manufactured devices against predetermined specifications.

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

This question is not applicable to the type of device being cleared. The "ground truth" for the performance of a physical device like the Chemfort® Female Luer Lock Adaptor is established by adherence to validated engineering specifications, material properties, and functionality defined by international standards (e.g., ISO, USP) and internal quality control procedures. It does not involve expert interpretations of images or signals for diagnostic purposes.

4. Adjudication Method for the Test Set

This question is not applicable. Adjudication methods (like 2+1, 3+1) are used to resolve discrepancies in expert annotations or interpretations, typically in studies involving human readers or AI outputs for diagnostic tasks. For a physical device, performance is evaluated against objective, measurable criteria with pass/fail outcomes, not subjective interpretations requiring adjudication.

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

No, an MRMC comparative effectiveness study was not done. MRMC studies are specific to evaluating the diagnostic performance of medical imaging devices or AI algorithms, often comparing human reader performance with and without AI assistance across multiple cases. This device is an intravascular administration set, not an imaging or diagnostic AI device.

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

This question is not applicable. There is no "algorithm" to be evaluated in a standalone manner for this physical device. Its function is mechanical and fluidic.

7. The Type of Ground Truth Used

The "ground truth" for this device is based on engineering specifications, material science, and compliance with recognized international standards (e.g., ISO 80369-7, ISO 10993 series, USP monographs). These standards define the acceptable performance characteristics, physical properties, and safety profiles for devices of this type. For example, for "Luer Test," the ground truth is defined by the dimensional and functional requirements of ISO 80369-7:2021. For "Biocompatibility," the ground truth is defined by the specific tests and acceptance criteria within the ISO 10993 series.

8. The Sample Size for the Training Set

This question is not applicable. This device is a physical product, not an AI/ML model that requires a training set.

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

This question is not applicable for the same reason as #8.

Ask a specific question about this device

TumorSight Viz is intended to be used in the visualization and analysis of breast magnetic resonance imaging (MRI) studies for patients with biopsy proven early-stage or locally advanced breast cancer. TumorSight Viz supports evaluation of dynamic MR data acquired from breast studies during contrast administration. TumorSight Viz performs processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

TumorSight Viz also includes user-configurable features for visualizing and analyzing findings in breast MRI studies. Patient management decisions should not be made based solely on the results of TumorSight Viz.

TumorSight Viz is an image processing system designed to assist in the visualization and analysis of breast DCE-MRI studies.

TumorSight reads DICOM magnetic resonance images. TumorSight processes and displays the results on the TumorSight web application.

Available features support:

• Visualization (standard image viewing tools, MIPs, and reformats)
• Analysis (registration, subtractions, kinetic curves, parametric image maps, segmentation and 3D volume rendering)

The TumorSight system consists of proprietary software developed by SimBioSys, Inc. hosted on a cloud-based platform and accessed on an off-the-shelf computer.

Here's a breakdown of the acceptance criteria and the study details for the TumorSight Viz device, based on the provided FDA 510(k) clearance letter:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the reported performance metrics, where the device's performance is deemed "adequate" and "clinically acceptable" if the variability is similar to inter-radiologist variability or differences in error are clinically insignificant.

The document states: "We found that all tests met the acceptance criteria, demonstrating adequate performance for our intended use." This indicates that the reported performance metrics were considered acceptable by the regulatory body. For measurements where inter-radiologist variability is provided (e.g., longest dimension, tumor-to-skin), the device's error is compared to this variability. For other metrics, the acceptance is based on demonstrating "adequate performance," implying that the reported values themselves were within a predefined acceptable range.

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

• Sample Size for Test Set: 266 patients (corresponding to 267 samples, accounting for bilateral disease).
• Data Provenance:
  • Country of Origin: U.S.
  • Retrospective/Prospective: The document does not explicitly state "retrospective" or "prospective." However, the description of "DCE-MRI were obtained from... patients" and establishment of ground truth by reviewing images suggests a retrospective acquisition of data for validation. The mention of "All patients had pathologically confirmed invasive, early stage or locally advanced breast cancer" further supports a retrospective gathering of existing patient data.
  • Clinical Sites: More than eight (8) clinical sites in the U.S.

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

• Number of Experts: Three (3) U.S. Board Certified radiologists.
• Qualifications: U.S. Board Certified radiologists. (No specific experience in years is mentioned, but Board Certification implies a high level of expertise.)

4. Adjudication Method for the Test Set

• Adjudication Method: 2+1 (as described in the document).
  • For each case, two radiologists independently measured various characteristics and determined if the candidate segmentation was appropriate.
  • In cases of disagreement between the first two radiologists ("did not agree on whether the segmentation was appropriate"), a third radiologist provided an additional opinion, and the ground truth was established by majority consensus.

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

The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance is directly measured and compared.

Instead, it compares the device's performance to:

1. Ground Truth: Radiologist consensus measurements.
2. Predicate Device: Its own previous version.
3. Inter-radiologist Variability: The inherent variability between human expert readers.

Therefore, no effect size of how much human readers improve with AI vs. without AI assistance is provided, as this type of MRMC study was not detailed.

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

Yes, a standalone performance study was done. The sections titled "Performance Tests" and the tables detailing "Validation Testing (Mean Abs. Error ± Std. Dev.)" describe the algorithm's performance in comparison to the established ground truth. This is a standalone evaluation, as it assesses the device's output intrinsically against expert-derived truth without measuring human interaction or improvement. The statement "The measurements generated from the device result directly from the segmentation methodology and are an inferred reflection of the performance of the deep learning algorithm" supports this.

7. The Type of Ground Truth Used

• Type of Ground Truth: Expert Consensus (specifically, pathologist-confirmed lesions measured and evaluated by a consensus of U.S. Board Certified radiologists). The initial diagnosis of early-stage or locally advanced breast cancer for patient selection was based on pathology ("biopsy proven"). However, the ground truth for measurements and segmentation appropriateness for the study was established by radiologists.

8. The Sample Size for the Training Set

• Sample Size for Training Set: One thousand one hundred fifty-six (1156) patients/samples.

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

The document states: "DCE-MRI were obtained from one thousand one hundred fifty-six (1156) patients from more than fifteen (15) clinical sites in the U.S. for use in training and tuning the device."

However, the document does not explicitly detail how the ground truth for this training set was established. It describes the ground truth establishment method only for the validation dataset (by three U.S. Board Certified radiologists with 2+1 adjudication). For training data, it is common practice to use similar rigorous methods for labeling, but the specifics are not provided in this excerpt.

Ask a specific question about this device

The Shadow Catheter™ is intended to be used in conjunction with steerable guidewires in order to access discrete regions of the coronary and peripheral arterial vasculature, to facilitate placement and exchange of guidewires and other interventional devices, for use during two guidewire procedures and to subselectively infuse/deliver diagnostic or therapeutic agents.

The Shadow Guidewire Positioning Catheter is a dual lumen over-the-wire catheter, compatible with a 6F or larger guiding catheter and 0.014" guidewires. The Catheter is designed to support and aim steerable guidewires. The Catheter consists of a distal tip with markers, torque shaft and guidewire introducer. The distal end of the Catheter (the nosecone) has two ports, one to load a tracking guidewire axially (via distal port) and the other for the positioning guidewire to exit radially (via side port). The distal nosecone is coated with a hydrophilic coating.

The Shadow Catheter™ has three markers in the nosecone. The guidewire introducer accommodates an on-axis tracking guidewire, a tracking guidewire flush port, as well as a positioning guidewire introducer port that doubles as a flush port. The handle may be rotated or orientated to adjust or aim the direction of the positioning guidewire exiting the side port at the distal end.

The Catheter is placed in a packaging hoop, sealed in a Tyvek® pouch, and packaged in a shelf carton. There are no diagnostic or therapeutic agents known to be incompatible with the Shadow Catheter™. The Shadow Catheter™ is sterilized with ethylene oxide.

The provided text is a 510(k) Premarket Notification from the FDA for a medical device called the "Shadow Catheter™." It details the device's description, intended use, technological characteristics, and non-clinical tests performed to demonstrate substantial equivalence to a predicate device.

However, the text does not contain any information about acceptance criteria or a study that proves the device meets those criteria related to an AI/ML-based medical device. The product is a physical catheter, and the testing described focuses on physical properties and biocompatibility. There is no mention of a test set, data provenance, expert ground truth, MRMC studies, or standalone algorithm performance.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance related to AI/ML: The document discusses physical device performance (e.g., bond strength, kink test, flow rate), but not AI/ML performance metrics.
2. Sample size used for the test set and data provenance: No test set is described for AI/ML evaluation.
3. Number of experts used to establish ground truth and qualifications: Not applicable, as there's no AI/ML component.
4. Adjudication method for the test set: Not applicable.
5. MRMC comparative effectiveness study: Not mentioned, as it's not an AI-assisted device.
6. Standalone (algorithm only) performance: Not applicable.
7. Type of ground truth used: Not applicable for AI/ML.
8. Sample size for the training set: No training set is mentioned.
9. How the ground truth for the training set was established: Not applicable.

The document explicitly states: "Clinical Study: Not Applicable. The Shadow Catheter™ was not evaluated in a clinical study." and "The results of the testing met the specified acceptance criteria and did not raise new questions of safety or effectiveness; therefore, the subject device is substantially equivalent to the predicate device." This refers to non-clinical, bench testing of the physical catheter.

In summary, the provided FDA 510(k) document is for a physical medical catheter, not an AI/ML device, and thus does not contain the information required to answer your specific questions regarding AI/ML acceptance criteria and study details.

Ask a specific question about this device

Sim&Size enables visualization of cerebral blood vessels for preoperational planning and sizing for neurovascular interventions and surgery. Sim&Size also allows for the ability to computationally model the placement of neurointerventional devices.

General functionalities are provided such as:

• Segmentation of neurovascular structures
• Automatic centerline detection
• Visualization of X-ray based images for 2D review and 3D reconstruction
• Placing and sizing tools
• Reporting tools

Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition.

Sim&Size is a Software as a Medical Device (SaMD) for simulating neurovascular implantable medical devices. The product enables visualization of cerebral blood vessels for preoperational planning for neurovascular interventions and surgery. It uses an image of the patient produced by 3D rotational angiography. It offers clinicians the possibility of simulating neurovascular implantable medical devices in the artery or in the aneurysm to be treated through endovascular surgery and provides support in the treatment for the sizing and positioning of implantable medical devices.

Each type of implant device is simulated in a simulation module of Sim&Size:

• FDsize, a module that allows pre-operationally planning Flow-Diverter (FD) devices.
• IDsize, a module that allows pre-operationally planning Intrasaccular (ID) devices.
• STsize, a module that allows pre-operationally planning Stent (ST) devices.
• FCsize, a module that allows pre-operationally planning First and filling coils (FC) devices.

Associated with these four modules, a common module is intended to import DICOM and to provide a 3D reconstruction of the vascular tree in the surgical area.

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 Sim&Size:

Acceptance Criteria and Device Performance

The provided document highlights performance testing without explicitly stating quantitative acceptance criteria. However, the nature of the tests implies the device must accurately "predictive behavior of the implantable medical device with its theoretical behavior," accurately "compare the device placement in a silicone phantom model with the device simulation," and accurately "compare the in vitro retrospective cases with the device simulation."

Given the context of a 510(k) submission, the implicit acceptance criterion is that the device's performance is substantially equivalent to the predicate device and that the new features do not raise new questions of safety and effectiveness.

Here's a table based on the types of performance tests conducted:

Study Details:

Based on the provided document, here's what can be inferred about the studies conducted:

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

   • Test Set Sample Size: Not explicitly stated in the document.
   • Data Provenance:
     • "Retrospective in vivo testing" suggests real-world patient data, but the phrase "in vitro retrospective cases" implies these were lab-based re-creations or analyses of that data. The specific country of origin is not mentioned, but given the company's address (Montpellier, France), it's plausible the data could originate from Europe, although this is not confirmed.
     • "Bench testing" uses a "silicone phantom model," which is an experimental setup, not clinical data provenance.
     • "Verification testing" involves comparing theoretical behavior, which doesn't involve a dataset in the same way clinical or phantom models do.

2. 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 refers to "theoretical behavior," "silicone phantom model," and "in vitro retrospective cases" as benchmarks, but it doesn't detail how the ground truth for "in vitro retrospective cases" was established or if experts were involved in defining the "theoretical behavior" or validating the phantom results.

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

   • This information is not provided in the document.

4. 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 is explicitly mentioned. The device "enables visualization of cerebral blood vessels" and "allows for the ability to computationally model the placement of neurointerventional devices," but it's stated that "Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition." This indicates it's a tool for assistance, but the document does not detail studies on human reader performance improvement with this AI.

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

   • The "Verification testing," "Bench testing," and "Retrospective in vivo testing" (comparing simulations to "in vitro retrospective cases") all describe methods that would assess the algorithm's standalone performance without a human in the loop for the actual comparison/measurement, although human input (e.g., in segmentation, placing/sizing tools) is part of the device's intended use. The wording "compares the predictive behavior... with its theoretical behavior" and "compares the device placement... with the device simulation" explicitly refers to the device's performance, implying a standalone assessment of the algorithmic component.

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

   • Theoretical Behavior: Used for "Verification testing" (e.g., physical laws, engineering models of device deployment).
   • Physical Phantom Model: Used for "Bench testing" (measurements from a physical silicone model).
   • "In vitro retrospective cases": Used for "Retrospective in vivo testing." This implies a ground truth derived from actual patient data, analyzed or re-created in a laboratory (in vitro). It's not explicitly stated if this ground truth was pathology or outcomes data, but rather a representation of the in vivo reality.

7. The sample size for the training set:

   • This information is not provided in the document. This section focuses on validation testing, not the training of any underlying models.

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

   • This information is not provided as the document does not detail the training process.

Ask a specific question about this device

TumorSight Viz is intended to be used in the visualization and analysis of breast magnetic resonance imaging (MRI) studies for patients with biopsy proven early-stage or locally advanced breast cancer. TumorSight Viz supports evaluation of dynamic MR data acquired from breast studies during contrast administration. TumorSight Viz performs processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

TumorSight Viz also includes user-configurable features for visualizing findings in breast MRI studies. Patient management decisions should not be made based solely on the results of TumorSight Viz.

TumorSight Viz is an image processing system designed to assist in the visualization and analysis of breast DCE-MRI studies.

TumorSight reads DICOM magnetic resonance images. TumorSight processes and displays the results on the TumorSight web application.

Available features support:

• . Visualization (standard image viewing tools, MIPs, and reformats)
• . Analysis (registration, subtractions, kinetic curves, parametric image maps, segmentation and 3D volume rendering)
• . Communication and storage (DICOM import, retrieval, and study storage)

The TumorSight system consists of proprietary software developed by SimBioSys, Inc. hosted on a cloud-based platform and accessed on an off-the-shelf computer.

Here's a breakdown of the acceptance criteria and study details for the TumorSight Viz device, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria implicitly relate to the device's performance in comparison to expert variability and the predicate device. The study aims to demonstrate that the error in measurements produced by TumorSight Viz is consistent with the variability observed among expert radiologists.

The table below summarizes the performance metrics from the validation testing, which serves as the reported device performance against the implicit acceptance criterion of being comparable to inter-radiologist variability.

Segmentation Accuracy:

Comparison to Predicate Device and Inter-Radiologist Variability:

The study concludes that "all tests met the acceptance criteria, demonstrating adequate performance for our intended use," and that the "differences in error between the mean absolute errors (MAE) for the predicate and subject device are clinically acceptable because they are on the order of one to two voxels for the mean voxel size in the dataset. These differences are clinically insignificant."

2. Sample Size and Data Provenance

• Test Set (Validation Dataset) Sample Size: 216 patients, corresponding to 217 samples (when accounting for bilateral disease).
• Data Provenance:
  • Country of Origin: U.S. (from more than 7 clinical sites).
  • Retrospective/Prospective: Not explicitly stated, but the description of data collection and review for ground truth suggests it was retrospective. The data was "obtained" and "collected," implying pre-existing data.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three (3)
• Qualifications: U.S. Board Certified radiologists. No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

• Method: Majority Consensus (2+1). For each case, two radiologists independently reviewed measurements and segmentation appropriateness. "In cases where the two radiologists did not agree on whether the segmentation was appropriate, a third radiologist provided an additional opinion and established a ground truth by majority consensus."

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

• Was it done? No, an MRMC study comparing human readers with and without AI assistance was not performed as described in the document. The study primarily focused on the standalone performance of the AI algorithm (TumorSight Viz) and its comparison to the predicate device, with ground truth established by expert radiologists. It did compare the device's measurements to inter-radiologist variability, but not in a human-in-the-loop setup.
• Effect Size: Not applicable, as an MRMC comparative effectiveness study was not performed.

6. Standalone (Algorithm Only) Performance

• Was it done? Yes. The performance metrics listed in the tables (Mean Absolute Error, Volumetric Dice, Surface Dice) are indicators of the standalone performance of the TumorSight Viz algorithm against the established ground truth.

7. Type of Ground Truth Used

• Type: Expert Consensus. The ground truth was established by three (3) U.S. Board Certified radiologists through a defined review and adjudication process (majority consensus).
• For measurements: Radiologists measured various characteristics including longest dimensions and tumor to landmark distances.
• For segmentation: Radiologists reviewed and deemed the candidate segmentation "appropriate."

8. Sample Size for the Training Set

• Training Dataset: 676 samples.
• Tuning Dataset: 240 samples.
• Total Patients for Training and Tuning: 833 patients (corresponding to 916 samples total for training and tuning).

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

The document states that the training and tuning data were used to "train and tune the device," but it does not explicitly describe how the ground truth for this training data was established. It only details the ground truth establishment for the validation dataset. It is common for deep learning models to require labeled data for training, but the process for obtaining these labels for the training set is not provided here.

Ask a specific question about this device

TumorSight Viz is intended to be used in the visualization and analysis of breast magnetic resonance imaging (MRI) studies for patients with biopsy proven early-stage or locally advanced breast cancer. TumorSight Viz supports evaluation of dynamic MR data acquired from breast studies during contrast administration. TumorSight Viz performs processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

TumorSight Viz also includes user-configurable features for visualizing and analyzing findings in breast MRI studies. Patient management decisions should not be made based solely on the results of TumorSight Viz.

TumorSight Viz is an image processing system designed to assist in the visualization and analysis of breast DCE-MRI studies.

TumorSight reads DICOM magnetic resonance images. TumorSight processes and displays the results on the TumorSight web application.

Available features support:

• Visualization (standard image viewing tools, MIPs, and reformats)
• Analysis (registration, subtractions, kinetic curves, parametric image maps, segmentation and 3D volume rendering)
• Communication and storage (DICOM import, retrieval, and study storage)

The TumorSight system consists of proprietary software developed by SimBioSys, Inc. hosted on a cloud-based platform and accessed on an off-the-shelf computer.

Here's a summary of the acceptance criteria and study details for TumorSight Viz, based on the provided text:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by demonstrating that the device's performance (Mean Absolute Error and Dice Coefficients) is comparable to inter-radiologist variability and the predicate device, CADstream, and that "all tests met the acceptance criteria".

Additionally, for the direct comparison with the CADstream predicate device and ground truth:

The document states: "The mean absolute error and variability between the automated measurements (Validation Testing) and ground truth for tumor volume (measured in cc) and landmark distances (measured in cm) was similar to the variability between device-to-radiologist measurements and inter-radiologist variability. This demonstrates that the error in measurements is consistent to the variability between expert readers." It also notes: "We found that all tests met the acceptance criteria, demonstrating adequate performance for our intended use." And for the comparison to the predicate: "The differences in error between the mean absolute errors (MAE) for the predicate and subject device are clinically acceptable because they are on the order of one to two voxels for the mean voxel size in the dataset. These differences are clinically insignificant."

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

• Sample Size for Validation (Test Set): 161 patients, corresponding to 163 samples (accounting for bilateral disease).
• Data Provenance: Obtained from six (6) clinical sites in the U.S. All patients had pathologically confirmed invasive, early stage or locally advanced breast cancer. The data was collected to ensure adequate coverage of MRI manufacturer and field strength and similarity with the broader U.S. population for patient age, breast cancer subtype, T stage, histologic subtype, and race/ethnicity. This data is retrospective.

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

• Number of Experts: Seven (7) U.S. Board Certified radiologists.
• Qualifications of Experts: U.S. Board Certified radiologists. Specific experience level (e.g., years of experience) is not explicitly stated beyond "expert readers."

4. Adjudication Method for the Test Set

• Adjudication Method: For each case, two radiologists independently measured various characteristics. If the two radiologists did not agree on whether the candidate segmentation was appropriate, a third radiologist provided an additional opinion and established a ground truth by majority consensus (2+1 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

• The document describes a performance comparison between TumorSight Viz, CADstream (predicate), and ground truth, as well as inter-radiologist variability. However, it does not describe an MRMC comparative effectiveness study directly measuring how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of TumorSight Viz and its comparability to a predicate device and human variability.

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

• Yes, a standalone study was done. The reported performance metrics (Mean Absolute Error, Dice Coefficients) for TumorSight Viz against a radiologist-established ground truth represent the standalone performance of the algorithm. The document explicitly states: "The measurements generated from the device result directly from the segmentation methodology and are an inferred reflection of the performance of the deep learning algorithm."

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

• Type of Ground Truth: Pathologically confirmed breast cancer cases (for patient inclusion) combined with expert consensus of U.S. Board Certified radiologists for specific image measurements and segmentation appropriateness. The ground truth was established by two radiologists measuring characteristics, with a third radiologist adjudicating disagreements by majority consensus.

8. The sample size for the training set

• Training Set Sample Size: 390 samples (from 736 patients mentioned for training and tuning).
• Tuning Set Sample Size: 376 samples (from 736 patients mentioned for training and tuning).

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

• The document states that 736 patients (766 samples) were used for "training and tuning the device." It explicitly mentions that for the validation set, "Seven (7) U.S. Board Certified radiologists reviewed 163 validation samples to establish the ground truth for the dataset..."
• The method for establishing ground truth for the training set is not explicitly detailed in the provided text. It is generally implied that such ground truth would also be established by experts, but the specifics are not given for the training portion.

Ask a specific question about this device