Search Results

AdvantageSim™ MD is used to prepare geometric and anatomical data relating to a proposed external beam radiotherapy treatment prior to dosimetry planning. Anatomical volumes can be defined automatically or manually in three dimensions using a set of CT images acquired with the patient in the proposed treatment position. Definition of the anatomical volumes may be assisted by additional CT, MR or PET studies that have been co-registered with the planning CT scan. Additionally, CT & PET data from a respiratory tracked examination may be used to allow the user to define the target or treatment volume over a defined range of the respiratory cycle.

The geometric parameters of a proposed treatment field are selected to allow non-dosimetric, interactive optimization of field coverage. Defined anatomical structures and geometric treatments fields are displayed on transverse images, on reformatted sagittal, coronal or oblique images, on 3 D views created from the images, or on a beam eye's view display with or without the display of defined structures with or without the display of digitally reconstructed radiograph.

AdvantageSim™ MD is a CT/MR/PET oncology application used by clinicians (radiologist, radiation oncologist, medical oncologist nuclear medicine physicians and trained healthcare professional) to assist treatment planning.

AdvantageSim MD with MR pelvic organ at risk segmentation Option is used to provide MR based prostate and pelvic organs-at-risk segmentation. A suite of semi-automated MR based organ segmentation contouring allows generating complex structures around organs at risk. These contours overlay on the co-registered CT planning image.

The segmentation methods in the modified device are semi-automatic. The user has to place seed points to identify an inner point of the organ to contour.

The software offers a suite of manual contour editing tools enabling the user to edit, modify, or change contours generated from the MR segmentation tools to their desired configuration based on their medical and clinical knowledge and experience. The results provided by the software needs to be approved by the experienced clinician and can always be modified or corrected by him/her. It is up to the expert user to accept the result without any change, reject it completely and delineate manually, or modify the result and then save it. The software does not provide any auto-detection or auto-saving functionalities.

Same as the predicate devices, the clinician retains the ultimate responsibility for making the pertinent diagnosis and patient management decisions based on their standard practices and visual comparison of the individual images, regardless of the accuracy of the output generated by the software.

Here's an analysis of the provided text to fulfill your request:

Acceptance Criteria and Study for GE Healthcare AdvantageSim™ MD with MR pelvic organ at risk segmentation Option

1. Table of Acceptance Criteria and Reported Device Performance:

Important Note: The document focuses on demonstrating substantial equivalence to predicate devices rather than providing specific numerical acceptance criteria and performance metrics (e.g., Dice coefficients, Hausdorff distances, specific time savings). The reported performance is generally qualitative or comparative.

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "consented clinical images" but does not specify the number of cases.
• Data Provenance: "consented clinical images" - the country of origin is not specified, but the submission is from GE Hungary Kft. The study appears to be retrospective as it uses existing clinical images.

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

• Number of Experts: Three.
• Qualifications of Experts: "board certified Radiation Oncologists who were considered experts."

4. Adjudication Method for the Test Set:

• The document does not explicitly state a formal adjudication method (e.g., 2+1, 3+1). It describes the experts assessing accuracy, precision, and efficiency, and providing qualitative feedback. It implies each expert evaluated the software's performance, but not how disagreements were resolved to establish a single ground truth.

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

• The study described is a usability study that compared the new software against manual methods (implied through efficiency and inter-operator variability assessment). It involved "three board certified Radiation Oncologists". While it involved multiple readers, it is not explicitly labeled as an "MRMC comparative effectiveness study" in the sense of a formal statistical study with defined effect sizes of improvement with AI assistance.
• Effect Size of Human Reader Improvement: Not quantitatively reported. The document states it has "the potential to reduce inter-operator variability" and provides "statistically significant and practically meaningful clinical efficiency improvements," but no numerical effect size is given.

6. Standalone Performance Study:

• Yes, a standalone performance was performed. The device's segmentation methods are described as "semi-automatic" where "the user has to place seed points to identify an inner point of the organ to contour." The software then generates contours. The study assessed the software's output in terms of accuracy, precision, and efficiency, even though a clinician would typically review and edit the results. The clinicians evaluated the device's output and how it facilitated their workflow.

7. Type of Ground Truth Used:

• The ground truth for the test set was established by expert consensus/opinion among the three board-certified Radiation Oncologists. They likely compared the device's segmentations against their clinical knowledge and potentially manual segmentations, though this is not explicitly detailed.

8. Sample Size for the Training Set:

• Not specified. The document does not provide any information about the training data or its size.

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

• Not specified. As the training set size and details are absent, the method for establishing its ground truth is also not mentioned.

Ask a specific question about this device

AdvantageSim™ MD is used to prepare geometric and anatomical data relating to a proposed external beam radiotherapy treatment prior to dosimetry planning. Anatomical volumes can be defined automatically or manually in three dimensions using a set of CT images acquired with the patient in the proposed treatment position. Definition of the anatomical volumes may be assisted by additional CT, MR or PET studies that have been co-registered with the planning CT scan. Additionally, CT & PET data from a respiratory tracked examination may be used to allow the user define the target or treatment volume over a defined range of the respiratory cycle. The geometric parameters of a proposed treatment field are selected to allow non-dosimetric, interactive optimization of field coverage. Defined anatomical structures and geometric treatments fields are displayed on transverse images, on reformatted sagittal, coronal or oblique images, on 3 D views created from the images, or on a beam eye's view display with or without the display of defined structures with or without the display of digitally reconstructed radiograph.

AdvantageSim™ MD is a CT/MR/PET oncology application used by clinicians (radiologist, radiation oncologist, medical oncologist, nuclear medicine physicians and trained healthcare professional) to assist treatment planning.

The provided document does not contain information about acceptance criteria or a study that proves the device meets specific acceptance criteria.

The document is a 510(k) Premarket Notification Submission Summary for "GE Healthcare AdvantageSim™ MD with CT Atlas-based Contouring and Re-planning Options." It describes the device, its intended use, and its classification, and notes that the software complies with voluntary standards and underwent quality assurance measures like risk analysis, design reviews, and various testing (integration, performance, safety).

Crucially, under "Summary of Clinical Tests," it explicitly states:

"The subject of this premarket submission, AdvantageSim MD with CT Atlas-based Contouring and Re-planning Options software did not require clinical studies to support substantial equivalence since the two new features have triggered this 510(k) notification, CT atlas-based contouring and CT based re-planning options are part of Mirada’s FDA cleared product."

This indicates that no new clinical study was conducted for this specific 510(k) submission to demonstrate performance against acceptance criteria. Instead, substantial equivalence was established by referencing features already part of an FDA-cleared predicate device (Mirada's product).

Therefore, I cannot provide the requested information from the given text as it explicitly states that clinical studies were not required and thus, no such study demonstrating device performance against acceptance criteria is detailed.

Ask a specific question about this device

1. Both the RAD II KV Imager and RAD II Simulator are used in the field of Radiation Therapy as diagnostic imaging devices for patient positioning verification prior to radiation therapy treatments for cancer.
2. Both the RAD II KV Imager and RAD II Simulator are permanently mounted to the Therapy Head of Linear Accelerators and Cobalt Teletherapy devices.
3. The RAD II KV Imager is an "On Board Imager" intended for usage as a patient positioning verification device.
4. The RAD II KV Imager uses digital imaging to acquire its images, and positioning software to verify and/or adjust patient positioning prior to radiation therapy treatment via a Clinac as prescribed by a Radiation Oncologist.
5. The RAD II Simulator is a "Therapy Attached" Simulator intended for developing and or verifying patient treatment protocols as prescribed by Radiation Oncologist.
6. The RAD II Simulator device uses standard x-ray film to acquire its images, which are reviewed by the Therapist and or Oncologist to either verify or adjust patient positioning prior to radiation therapy treatment via a Clinac as prescribed by a Radiation Oncologist.

The RAD II KV Imaging device is mounted directly to the head of a Linear Accelerator or Cobalt Therapy device. This "Therapy Attached" application has been in use as the RAD II Simulator since 1983 (510K # K834281). With the addition of an FDA approved Digital Imager and Patient Positioning Software, the RAD II KV Imager operates as an "On Board Imaging Device" for Image Guided Radiation Therapy (I.G.R.T.) Protocols.

This 510(k) summary for the Acceletronics RAD II Simulator & RAD II KV Imager focuses on establishing substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a standalone study proving performance against those criteria.

Therefore, many of the requested sections regarding specific acceptance criteria, detailed study results, sample sizes, expert qualifications, and ground truth establishment are not provided in this document. The document primarily relies on comparing the technological characteristics and intended use of the RAD II devices to previously cleared devices.

Here's a breakdown of the information available and what is not provided:

1. Table of Acceptance Criteria and Reported Device Performance

This document does not provide a table of acceptance criteria with specific performance metrics (e.g., accuracy, precision, sensitivity, specificity) for the RAD II Simulator & RAD II KV Imager. Instead, it claims substantial equivalence based on:

• Technological Characteristics: As detailed in Exhibit C-4 (page 2), comparing components like X-ray tube, generator, imager type (digital vs. film), and software with predicate devices.
• Intended Use: For verification of patient position and treatment fields in radiation therapy.

Example Comparison (from Exhibit C-4, not formal acceptance criteria):

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

• Not provided. The submission focuses on substantial equivalence based on technical specifications and intended use, not on specific clinical or performance testing data with a defined test set.

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

• Not provided. There is no mention of a test set with established ground truth or expert involvement in such a process within this document.

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

• Not provided. Due to the absence of a described test set and ground truth establishment, no adjudication method is 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

• Not applicable/Not provided. This submission is for a device that aids in patient positioning and image acquisition in radiation therapy. It is not an AI-assisted diagnostic tool for human readers in a way that an MRMC study on reader improvement would typically be conducted. Therefore, no information on human reader improvement with/without AI assistance is presented.

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

• Not provided. The document does not describe a standalone performance study. The device is intended to be used by radiation therapists and oncologists for patient positioning verification. The "standalone" performance in this context would likely refer to the image quality and accuracy of positioning measurements, but specific studies are not detailed.

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

• Not provided. As there is no described performance study or test set, the type of ground truth used is not mentioned.

8. The sample size for the training set

• Not applicable/Not provided. This device is a hardware and software system for image acquisition and patient positioning, not a machine learning model that requires a "training set" in the conventional sense. The "Theraview Software" is mentioned, but its development process (e.g., if it uses machine learning and thus a training set) is not detailed.

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

• Not applicable/Not provided. (See point 8)

Summary of what is available and the overall approach:

The manufacturer, Acceletronics, Inc., is seeking 510(k) clearance for the RAD II Simulator & RAD II KV Imager by demonstrating substantial equivalence to predicate devices. This means they are asserting their device is as safe and effective as devices already on the market without needing to conduct extensive new clinical trials to prove efficacy from scratch.

• Predicate Devices: Several predicate devices are identified, including Varian Medical Systems On-Board Imager, Varian Medical Systems Portal Vision, Elekta Synergy, Oldelft Simulux-HP, and Haynes Radiation Ltd., Inc. RAD II Simulator.
• Description of Equivalence: The submission highlights that the RAD II KV Imager operates as an "On Board Imaging Device" for Image Guided Radiation Therapy (IGRT) protocols, similar to predicate devices A-C. The RAD II Simulator is likened to predicate devices D&E as a "Radiation Therapy Simulator."
• Technological Characteristics Comparison (Exhibit C-4): This table compares specific components and features (X-ray tube, generator, imager type, software) of the RAD II systems with the predicate devices, emphasizing their similarities. The key difference noted for the RAD II KV Imager is its advanced digital imaging compared to the older film-based RAD II Simulator, and some differences in imager/cassette mounting designs.
• Intended Use Statement: The intended uses for both the KV Imager (patient position verification) and the Simulator (developing and verifying treatment protocols) are clearly stated and aligned with the intended uses of the predicate devices.

In essence, the "study" mentioned is the comparison of the device's technical specifications and intended use to legally marketed predicate devices, which is the basis for a 510(k) clearance. Clinical performance data or specific acceptance criteria with supporting studies are generally not required for substantial equivalence claims unless there are significant technological differences or new indications for use.

Ask a specific question about this device

Oncentra Simulation is an accessory to a radiation therapy simulation system which is intended to prepare patients for radiation therapy. The Simulator emulates the geometrical positions of radiation therapy treatment machines. Using conventional radiographic and fluorographic system, patients are positioned, filmed and marked to prepare them for treatment.

Oncentra Simulation 2.3 is a revision of the image handling software of the Simulix Evolution. This software has been adapted such that images can be acquired and processed from an Image Intensifier such as used on the Nucletron Radiotherapy simulators Simulix MC, Simulix HP and Simulix HQ. This makes it a replacement for the predicate device DTI (K954055). The PC based simulator workstation comes with functionality to support simulation procedures: Image acquisition, Image display, Image enhancement and multiple views, Database and DICOM Import / Export functionality, Simulator controls. The modification to the previously cleared device K033470 is: Added support for Image Intensifiers. The software runs on a PC on a Windows XP platform.

This 510(k) submission for Oncentra Simulation 2.3 is a special 510(k) for a software revision and focuses on demonstrating substantial equivalence to a predicate device (Simulix Evolution, K033470). It does not contain the detailed study information typically found in an original 510(k) or PMA submission regarding acceptance criteria, performance studies, or ground truth establishment.

Here's an analysis based on the provided text, highlighting what is not available in this document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state specific acceptance criteria in terms of diagnostic performance metrics (e.g., sensitivity, specificity, AUC). Instead, it focuses on demonstrating that the revised software, Oncentra Simulation 2.3, performs its intended functions (image acquisition, display, enhancement, database functionality, simulator controls, and support for Image Intensifiers) adequately and is substantially equivalent to the predicate device.

The "performance" described is functional equivalence, not diagnostic accuracy. The key performance aspect mentioned is "Added support for Image Intensifiers." This is a functional addition, and its 'performance' is implicitly met if the system successfully interfaces with and processes images from Image Intensifiers as intended.

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

Not specified. This document describes a software revision and its functional equivalence to a predicate device. It does not detail a study involving a test set of patient data with specific sample sizes. The evaluation would have been more about verifying the software's functionality and compatibility rather than analyzing a clinical dataset.

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

Not applicable/Not specified. Since there's no mention of a clinical test set requiring ground truth for diagnostic accuracy, there's no information on experts or their qualifications.

4. Adjudication Method for the Test Set:

Not applicable/Not specified. As there is no clinical test set described, no adjudication method is mentioned.

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

No. This type of study is not mentioned or implied by the document. The submission focuses on substantial equivalence based on technological considerations and functional performance, not a comparative effectiveness study involving human readers.

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

Not applicable/Not specified. The device is a simulation system, an accessory to radiation therapy. It's an imaging and planning tool used by humans, not an AI algorithm making independent diagnostic decisions. The "algorithm" in this context refers to the software's functional logic, not a standalone diagnostic AI.

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

Not applicable/Not specified. As no clinical performance study involving diagnostic accuracy is described, no ground truth types are mentioned. The ground truth for a software revision like this would likely be engineering specifications and functional testing results.

8. The sample size for the training set:

Not applicable/Not specified. This is a software revision, not a machine learning model that requires a training set in the conventional sense. The "training" for the software would involve development, testing against specifications, and verification/validation activities.

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

Not applicable/Not specified. Again, this is not a machine learning context. The "ground truth" for software development typically refers to design specifications, requirements, and expected functional behavior, which are verified through various software testing methodologies.

In summary:

This 510(k) submission pertains to a software revision for a radiation therapy simulation system. It demonstrates substantial equivalence primarily by showing that the updated software (Oncentra Simulation 2.3) has the same intended use and similar technological characteristics to a legally marketed predicate device, with the key modification being "Added support for Image Intensifiers." The document does not contain information about clinical performance studies, diagnostic accuracy metrics, test/training sets, or expert evaluations in the context of ground truth establishment. Such detailed clinical performance data is typically found in submissions for novel devices or devices with significant changes affecting clinical outcomes, not usually for a functional software update like this one.

Ask a specific question about this device

The IKOEngelo™ System is indicated for use by radiation oncologists, medical physicists, and medical dosimetrists for tumor and normal tissue contour delineation to support the radiotherapy treatment planning process. The resulting information may then be exported to a treatment planning system for dose calculation.

The IKOEngelo version 2.0 device is a software system upgraded from version 1.0. This submitted new version has better contour modification tool, faster image files loading and display, and a new function for image fusion. For the same purpose of version 1.0, this software will assist radiation oncologists with the assistance of physicists and dosimetrists to more efficiently perform contour delineation of the tumor target and normal tissue on patient's CT images.

The provided document is a 510(k) summary for the IKOEngelo™ Software Version 2.0. It describes the device's intended use and technological characteristics, and importantly, highlights the verification and validation aspects. However, it does not contain a detailed study proving the device meets explicit acceptance criteria in the format requested.

The document states that "The validation test results have demonstrated that the contour modification tools were improved with efficiency and versatility, the image file loading and display were faster and the new image fusion functions were similar to the predicate device." This is a general statement about meeting validation goals rather than specific acceptance criteria with quantitative performance metrics.

Therefore, many of the requested fields cannot be filled directly from the provided text.

Here is an attempt to structure the available information, with clear indications where information is not present in the document:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not specified.
• Data Provenance (country of origin, retrospective/prospective): Not specified.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

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

• Adjudication Method: Not specified.

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

• MRMC Study: Not specified or implied. The device is a software system to assist radiation oncologists, physicists, and dosimetrists, but no comparative effectiveness study with human readers (with vs. without AI assistance) is mentioned.
• Effect Size: Not applicable, as no MRMC study is detailed.

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

• Standalone Performance: Not explicitly stated as a standalone evaluation. The validation statement indicates "The validation test results have demonstrated that...", suggesting an evaluation of the software's functionality, but it's unclear if this was algorithm-only or if it involved human interaction/evaluation of the output. The device's intended use is to "assist" human experts, implying it's not a standalone diagnostic tool.

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

• Type of Ground Truth: Not specified. The document mentions "contour delineation of the tumor target and normal tissue on patient's CT images" as the core function, but how the "truth" for these contours was established for validation is not described.

8. The sample size for the training set

• Sample Size: Not specified. (The document describes validation, not specifically training of a machine learning model, though the term "improved" tools could imply some form of iterative development and testing).

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

• Ground Truth Establishment: Not specified. (As above, training set details are not provided).

Ask a specific question about this device

The Integrated Brachytherapy - Digital (IBU-D) is intended to be used for the visualization, localization and confirmation of the volume and the size of the brachytherapy irradiation field(s), using a fluoroscopic and/or radiographic system.

Integrated Brachytherap Unit - Digital (IBU-D) is a modification to the Integrated Brachytherapy Unit (IBU) in which the Image Intensifier of the IBU is replaced by a Flat Panel image detector. The Flat Panel image detector used in the IBU-D is the same Flat Panel image detector as used in Nucletron's Simulix Evolution product (K03347).

The Integrated Brachytherpay Unit – Digital (IBU-D) is a localization and simulation device for a Brachy radiation therapy department. It consists of a gantry that supports an L-arm and a C-arm which can rotate isocentrically. The C-arm houses an X-ray tube housing assembly with collimator on one side and a flat panel image detector. The movements of the IBU-D are manually driven, after the relevant electrical locks are lifted. The mobile IBU patient table has mechanical motions which can be controlled from a hand pendant affixed to the table. Images are displayed and managed by a PC based workstation running specialized software.

The system makes also use of the same third party X-ray tube and X-ray high tension generator as used in the Simulix Evolution system.

The Flat Panel image detector which replaces the current Image intensifier is a Amorphous silicon, digital detector, with a square image area of 41 x 41 cm.

The PC based workstation runs the same software as the workstation of the Simulix Evolution system. It supports the following functionality:

• . Image acquisition
• Image display .
• Image annotation .
• Database and DICOM Import / Export functionality
• Position read out and display of the IBU-D gantry. .
• Control of the IBU-D beam limiting device. .

This 510(k) summary (K072445) describes the Integrated Brachytherapy Unit - Digital (IBU-D), a modification of an existing device. It focuses on the substantial equivalence to a predicate device and does not contain detailed information about specific acceptance criteria or a dedicated study proving device performance against those criteria in a quantitative manner as typically found in clinical validation studies for AI/ML devices.

The submission primarily states that the IBU-D is a modification where the Image Intensifier of the original IBU (K973848) is replaced by a Flat Panel image detector. The flat panel detector and the workstation software are the same as used in Nucletron's Simulix Evolution product (K03347). The "study" here is essentially a demonstration of substantial equivalence based on the technological similarity and identical intended use to legally marketed predicate devices, rather than a clinical trial assessing performance against specific metrics.

Therefore, many of the requested elements (like sample size, number of experts, adjudication methods, MRMC studies, standalone performance with specific metrics, and detailed ground truth establishment for a training set) are not typically found in this type of 510(k) summary for a hardware modification of a conventional medical device. The "reported device performance" is implicitly that it performs equivalently to the predicate devices for its intended use.

However, based on the provided text, I can infer and summarize the acceptance criteria and "study" information as best as possible within the context of this 510(k) submission:

1. Table of Acceptance Criteria and Reported Device Performance

Given that this 510(k) is for a hardware modification (swapping an image intensifier for a flat panel detector) and relies on substantial equivalence, explicit quantitative acceptance criteria for performance metrics (like sensitivity, specificity, accuracy) are not provided in this document. The "acceptance criteria" are implicitly met if the device functions as intended and is substantially equivalent to the predicate device.

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

This submission does not describe a clinical "test set" in the traditional sense of evaluating diagnostic performance on a patient dataset. The "study" for this 510(k) is a technical and functional verification that the modified device functions correctly and is substantially equivalent to existing devices. Therefore, details regarding sample size, country of origin, or retrospective/prospective nature of a clinical test set are not provided.

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

Not applicable. As no clinical test set for diagnostic performance evaluation is described, there is no mention of experts being used to establish ground truth or their qualifications.

4. Adjudication Method for the Test Set

Not applicable. Without a clinical test set requiring ground truth establishment, no adjudication method is mentioned.

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

No MRMC comparative effectiveness study is mentioned. This submission does not include an evaluation of human readers' performance with or without AI assistance, as it concerns a hardware replacement in a radiation therapy simulation system, not an AI/ML diagnostic aid.

6. Standalone (Algorithm Only) Performance Study

Not applicable. This device is a hardware system for visualization and localization in brachytherapy, not an AI algorithm. Therefore, a standalone algorithm performance study is not relevant or described.

7. Type of Ground Truth Used

Not applicable. The submission focuses on technological equivalence and functional verification, not on diagnostic accuracy against a specific ground truth like pathology or outcomes data.

8. Sample Size for the Training Set

Not applicable. There is no mention of a "training set" as this is not an AI/ML device that requires data for model training.

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

Not applicable. As there is no training set mentioned, there is no information on how its ground truth would have been established.

In summary: K072445 is a 510(k) submission for a hardware modification to an existing medical device. The "study" conducted for this submission is a demonstration of substantial equivalence based on the technological characteristics and identical intended use compared to legally marketed predicate devices. It does not provide the detailed performance metrics, sample sizes, expert qualifications, or study methodologies typically associated with clinical validation of diagnostic or AI/ML devices.

Ask a specific question about this device

The IKOEngelo™ System is intended for use in tumor and normal tissue contour delineation to support the radiotherapy treatment planning process.
The IKOEngelo™ System is indicated for use by radiation oncologists, medical physicists, and medical dosimetrists for tumor and normal tissue contour delineation to support the radiotherapy treatment planning process. The resulting information may then be exported to a treatment planning system for dose calculation.

The IKOEngelo device is a software system that will assist radiation oncologists, with the assistance of physicists and dosimetrists, to more efficiently perform contour delineation of the tumor target and normal tissue on patient's CT images.
The sequence of events is illustrated in the following bullet items and diagram:

• Import patient's CT images. .
• Select the proper Expert Case (including the CT image data set and . contours) to match patient's CT.
• Automatically fuse the images to align patient's CT image data sets . with those of the Expert Case.
• Run deformable segmentation to auto-contour on the patient's CT . images.
• Review patient's contours and modify them if necessary. .
• Approval by qualified radiation oncologist. .
• Export patient's CT with its contours to the treatment planning system . used by the facility.

The provided text does not contain detailed information about specific acceptance criteria or the study that definitively proves the device meets such criteria. It primarily focuses on the device's description, intended use, and a comparison to a predicate device for 510(k) submission. Therefore, much of the requested information is not available in the provided document.

However, based on the information that is present, here's what can be extracted and inferred:

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

The document does not explicitly state acceptance criteria or provide a table of reported device performance against those criteria. It offers a "Predicate Comparison Table" which outlines functional equivalence to the QwikSIM Virtual Simulation System (K013531). This comparison serves as the basis for demonstrating substantial equivalence for regulatory purposes, rather than a direct performance study against defined acceptance criteria.

Predicate Comparison Table (Indicating Functional Equivalence, not specific performance metrics against acceptance criteria):

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

This information is not provided in the document. The document describes a general comparison to a predicate device but does not detail a specific test set, its size, or data provenance (e.g., country of origin, retrospective/prospective).

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.

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

This information is not provided in the document.

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:

This information is not provided in the document. The document describes the device as a software system to assist radiation oncologists, physicists, and dosimetrists, implying a human-in-the-loop scenario. However, no MRMC study or its results are mentioned.

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

The document states the device will assist radiation oncologists, with assistance of physicists and dosimetrists, to perform contour delineation. It also mentions "Review patient's contours and modify them if necessary" and "Approval by qualified radiation oncologist." This suggests the device is intended for use with human oversight and modification, not as a standalone, fully automated system without human-in-the-loop. Therefore, it is highly likely that a standalone performance study as an algorithm without human interaction was not the primary focus or reported.

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

This information is not provided in the document. The "Expert Case Library" is mentioned as a "Contour Source," which implies pre-existing contours were used, likely established by experts, but the method for their establishment as "ground truth" for validation is not described.

8. The sample size for the training set:

This information is not provided in the document. The document mentions "Select the proper Expert Case (including the CT image data set and contours) to match patient's CT" and "Run deformable segmentation to auto-contour on the patient's CT images." This implies an underlying model that would have been trained, but no details of the training set size are given.

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

This information is not provided in the document. While "Expert Case Library" is identified as a contour source, the method of how those "Expert Cases" (and their contours) were established as ground truth for training (or for the general functioning of the system) is not detailed.

Ask a specific question about this device

Simulix Evolution is a radiation therapy simulation system is intended to prepare patients for radiation therapy. The Simulator emulates the geometrical positions of radiation therapy treatment machines. Using conventional radiographic and fluorographic system, patients are positioned, filmed and marked to prepare them for treatment. The Ocentra Cone Beam CT option for the Simulis Evolution Radiotion Therapy Simulator is intended to assist the Radiation Oncologist in acquiring 3D "multi slice" planning data in patient set-ups for the purpose of radiation therapy treatment planning and patient positioning

Oncentra ConeBeam is an extension to the Nucletron Simulix Evolution system. The Simulix Evolution is a Radiation Therapy Simulation System which is to be used in radiation therapy simulation, using a fluoroscopic and/or radiographic x-ray system for visualizing the volume to be exposed during radiation therapy and confirming the position and size of the therapeutic irradiation field to be applied. The Simulix Evolution is previously cleared under 510(k) #K033470. The Oncentra ConeBeam extension will give the Simulix Evolution system the capability to acquire Computer Tomography (CT) images. This is done by means of scanning the patient with a cone shaped X-ray beam. The cone shaped beam gives the possibility to acquire CT image information of a volume instead of CT image information of a single slice as with conventional fan beam CT. The images acquired with Oncentra ConeBeam will be used for the purpose of radiation therapy planning and to check the positioning of the patient.

I am sorry, but the provided text does not contain information about the acceptance criteria or a study that proves a device meets those criteria. The document is a 510(k) summary for the Nucletron Simulix-Evolution with Oncentra™ ConeBeam, which describes the device, its intended use, and its substantial equivalence to predicate devices, but it does not include details on acceptance criteria or performance studies.

Therefore, I cannot fulfill your request to provide the following information:

1. A table of acceptance criteria and the reported device performance
2. Sample sized used for the test set and the data provenance
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
4. Adjudication method for the test set
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, and its effect size
6. If a standalone performance (algorithm only) study was done
7. The type of ground truth used
8. The sample size for the training set
9. How the ground truth for the training set was established

Ask a specific question about this device

AdvantageSim MD is used to prepare geometric and anatomical data relating to a proposed external beam radiotherapy treatment prior to dosimetry planning. Anatomical volumes can be defined automatically or manually in three dimensions using a set of CT images acquired with the patient in the proposed treatment position. Definition of the anatomical volumes may be assisted by additional CT, MR, PET or SPECT studies that have been co-registered with the planning CT scan. Additionally, CT & PET data from a respiratory tracked examination may be used to allow the user to define the target or treatment volume over a defined range of the respiratory cycle.

The geometric parameters of a proposed treatment field are selected to allow non-dosimetric, interactive optimization of field coverage. Defined anatomical structures and geometric treatments fields are displayed on transverse images, on reformatted sagittal, coronal or oblique images, on 3 D views created from the images, or on a beam eye's view display with or without the display of defined structures with or without the display of digitally reconstructed radiograph.

AdvantageSim MD is used to prepare geometric and anatomical data relating to a proposed external beam radiotherapy treatment prior to dosimetry planning. Anatomical volumes can be defined automatically or manually in three dimensions using a set of CT images acquired with the patient in the proposed treatment position. Definition of the anatomical volumes may be assisted by additional CT, MR, PET or SPECT studies that have been co-registered with the planning CT scan. Additionally, CT & PET data from a respiratory tracked examination may be used to allow the user define the target or treatment volume over a defined range of the respiratory cycle.

The geometric parameters of a proposed treatment field are selected to allow nondosimetric, interactive optimization of field coverage. Defined anatomical structures and geometric treatments fields are displayed on transverse images, on reformatted sagittal, coronal or oblique images, on 3 D views created from the images, or on a beam eye's view display with or without the display of defined structures with or without the display of digitally reconstructed radiograph.

The GE Advantage Sim MD has to ensure relations with the following external systems: Data Export, Marking Systems, RT Data Import, Hardcopy, Archiving.

I am sorry, but the provided text does not contain information about acceptance criteria, device performance, a specific study, sample sizes, expert involvement, adjudication methods, or multi-reader multi-case studies. The document is a 510(k) summary for the GE Healthcare Advantage Sim MD, outlining its description, indications for use, comparison to predicate devices, and regulatory clearance. It does not include the detailed study information you are requesting.

Ask a specific question about this device

Simulix Evolution is a radiation therapy simulation system is intended to prepare patients for radiation therapy. The Simulator emulates the geometrical positions of radiation therapy treatment machines. Using conventional radiographic and fluorographic system, patients are positioned, filmed and marked to prepare them for treatment.

Simulix Evolution is a Flat Panel detector option to the Nucletron Simulix HP simulator system. The Simulator emulates the geometrical positions of radiation therapy treatment machines. Using a conventional radiographic and fluorographic system, patients are positioned, filmed and marked to prepare them for treatment. The Simulix Evolution option consists of a digital Flat Panel detector and a PC based simulator workstation. The Flat Panel detector option replaces the current Image Intensifiers. The Flat Panel is a Amorphous silicon, digital detector, with a square image area of 41 by 41 cm. The PC based simulator workstation is the current DTI workstation, but ported to a Windows platform. The PC based simulator workstation comes with functionality to support simulation procedures: Image acquisition, Image display, Image enhancement and multiple views, Database and DICOM Import / Export functionality, Simulator controls.

The provided text describes a 510(k) premarket notification for a medical device called "Simulix Evolution." However, it does not include information about acceptance criteria, device performance studies, sample sizes, ground truth establishment, or expert qualifications in the comprehensive manner requested. The document focuses on establishing substantial equivalence to a predicate device and outlines the device's intended use and technological considerations.

Therefore, many of the requested details cannot be extracted from the given text.

In lieu of the specific details, here's what can be inferred or stated that is missing:

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

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

• Sample Size for Test Set: Not specified.
• Data Provenance (e.g., country of origin of the data, retrospective or prospective): Not specified.
  • Implied: Given it's a submission for a new device, any testing would likely be prospective in a controlled environment, but this is not explicitly stated.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.
  • Implied: For a radiation therapy simulation system, experts would typically be radiation oncologists, medical physicists, and/or radiation therapists.

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

• Adjudication Method: Not specified.

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

• MRMC Comparative Effectiveness Study: Not mentioned.
  • Note: The device described is a simulation system, not an AI diagnostic tool, so an MRMC study comparing human readers with and without AI assistance is not directly relevant to the information provided. The "Simulix Evolution" is described as replacing an Image Intensifier with a Flat Panel detector and porting a workstation to Windows, focusing on hardware and software updates for simulation, not AI-driven interpretation.

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

• Standalone Performance Study: Not explicitly mentioned in terms of quantitative data or metrics. The submission focuses on demonstrating substantial equivalence of the system (hardware and software) to its predicate.

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

• Type of Ground Truth: Not specified.
  • Implied: For a simulation system, ground truth would likely involve established geometrical accuracy measurements, phantom studies, and possibly comparisons to existing simulation data from the predicate device.

8. The sample size for the training set

• Sample Size for Training Set: Not specified.
  • Note: The device is not described as having a machine learning component that would require a 'training set' in the traditional sense of AI algorithm development. The software capabilities mentioned (image acquisition, display, enhancement, database, DICOM) are standard functionalities, not indicative of a learning algorithm.

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

• How Ground Truth for Training Set was Established: Not applicable, as a training set, as typically understood for machine learning, is not indicated by the provided description. If 'training set' refers to data used for software validation or testing, the method of establishing ground truth for such data is not specified.

Ask a specific question about this device