Search Results

CT Collaboration Live is indicated for remote communication with CT console (via chat, call, video call, screen sharing and remote access) by a qualified remote clinical user for consultation, guidance, support, and training in real time. Remote access must be granted by the CT technologist operating the system. Remote access is only available for Philips CT systems supporting CT Collaboration Live connectivity capabilities. Images reviewed remotely are not for diagnostic use.

The proposed CT Collaboration Live is a software application integrated in Philips Computed Tomography (CT) X-Ray CT 5300 Systems. CT Collaboration Live enables two-way communication of text, voice, image, and video information between a CT system operator and a remote user on a Windows device. CT Collaboration Live facilitates: 1) peer-to-peer consultation and training, 2) system-level remote sharing & operation, 3) access to live image feed and 4) remote expert user(s) and physician consultation. CT Collaboration Live functionality includes a remote-control feature in which the CT system operator may grant a qualified remote user control of the CT system parameters via a virtual control panel and virtual touch screen.

I am sorry, but the provided text does not contain the detailed information necessary to answer your request regarding acceptance criteria and a study proving device performance.

The document is a 510(k) summary for Philips Healthcare's "CT Collaboration Live" device. It primarily focuses on demonstrating substantial equivalence to a predicate device (Collaboration Live, K200179) rather than detailing specific acceptance criteria and the results of a primary study to prove those criteria were met for the new device.

Here's a breakdown of what is and is not in the document, relating to your request:

What is mentioned (but not in enough detail for your request):

• Acceptance Criteria: The text states, "All tests were used to support substantial equivalence of the proposed CT Collaboration Live and to demonstrate that CT Collaboration Live: ... Meets the acceptance criteria and is adequate for its intended use." However, it does not provide a table of these acceptance criteria or the specific performance metrics achieved against them.
• Study (Non-Clinical Performance Data): The document mentions "Non-clinical performance software verification testing has been performed" and that "Software verification activities demonstrate that the CT Collaboration Live software application meets the design input requirements." It also states, "The summary and conclusion of results are provided in the System Verification Test Report." However, the actual results of this testing that would prove the device met acceptance criteria are not included in this document.
• No Clinical Study: It explicitly states, "The proposed CT Collaboration Live did not require a clinical study since substantial equivalence to the predicate device Collaboration Live (K200179) was demonstrated."

What is NOT mentioned (which are required for your request):

• A table of acceptance criteria and reported device performance.
• Sample size used for the test set and data provenance.
• Number of experts used to establish ground truth and their qualifications.
• Adjudication method for the test set.
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done, or the effect size of human readers with/without AI assistance.
• Whether a standalone performance study was done.
• The type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

This document serves as a regulatory submission demonstrating substantial equivalence, not a detailed technical report on specific performance metrics or clinical study results.

Ask a specific question about this device

The CT 5300 is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipments and accessories. The CT 5300 is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by etther a governmental body or professional medical society.

• Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The proposed device is a whole-body computed tomography (CT) X-Ray System featuring a continuously rotating x-ray tube, detectors, and gantry with multi-slice capability. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body taken at different angles and planes. This system also includes signal analysis and display equipment, patient and equipment supports, components, and accessories. The CT 5300 has a 72 cm bore and includes a detector array that provides 50 cm scan field of view (FOV). The main components (detection system, the reconstruction algorithm, and the x-ray system) that are used in the proposed device have the same fundamental design characteristics and are based on comparable technologies as the current marketed predicate Philips Incisive CT K212441(April 27, 2022).

The key system modules and functionalities are:

1. Gantry
   The Gantry consists of 4 main internal units:
   a. X-Ray Tube – produces X-rays necessary for scanning.
   b. High voltage generator - produces high voltage power supply to X-ray tube, consists of system Interface Unit, Power Block Unit and Anode Drive Unit.
   c. A-plane: adjusts the slice thickness during axial scan and monitor the changes of X-ray.
   d. DMS (Data Management System) – absorbs X-ray radiation by detectors and converts it to digital readout.
2. Patient Table (Couch)
   The Couch is used to position the patient. Carries the patient in and out through the Gantry bore synchronized with the scan.
3. Console
   The console is used to operate the system and monitor the scan. The Operator console includes a computer, monitors and CTBOX.
4. CT on Trailer Kit
   The CT 5300 installed and secured on a trailer requires locking motion parts during trailer transportation and unlocking motion parts before CT operations. Besides being installed in hospital, the CT may also be installed on trailer to be transported to designated locations for use within a professional healthcare environment.

The CT 5300 on Trailer Kit has the same fundamental design characteristics and technologies as the current marketed Philips Incisive CT on trailer (K211168 - November 22, 2021). The CT on Trailer configuration is identical to the K211168 trailer configuration. The CT system should only be used in designated locations for use with appropriate radiation controls and safety measures.

In addition to the above components and the software operating them, each system includes hardware and software for data acquisition, display, manipulation, storage and filming as well as post-processing into views other than the original axial images.

Upgrades Kit is available to upgrade earlier Incisive CT installations to latest version.

The provided document is a 510(k) Premarket Notification from Philips Healthcare (Suzhou) Co., Ltd. for their CT 5300 Computed Tomography X-Ray System. The purpose of this document is to demonstrate "Substantial Equivalence" to a legally marketed predicate device (Philips Incisive CT, K212441) and thus does not include acceptance criteria or detailed study results for standalone AI/ML device performance.

Instead, the document focuses on showing that the new CT 5300 system (which incorporates an updated version of the "Precise Image" and "Precise Position" algorithms) is as safe and effective as the predicate device.

However, based on the limited information provided regarding the "Precise Image" algorithm update, I can attempt to extract the relevant details and structure them according to your request, while highlighting what information is not present.

Please note: This document's primary goal is to establish substantial equivalence of the entire CT system, not to provide a detailed clinical validation study for a new AI/ML algorithm that is the subject of separate regulatory submissions (like a De Novo or full PMA). The "Precise Image" and "Precise Position" modifications are treated as part of the overall system's equivalence demonstration.

Device: CT 5300 (incorporating updated Precise Image and Precise Position algorithms)

Study Proving Device Meets Acceptance Criteria (as described for the specific algorithms):

The document states: "Non-Clinical verification and or validation tests have been performed... Non-Clinical verification and or validation test results demonstrate that the proposed device... Meets the acceptance criteria and is adequate for its intended use."

Specifically for "Precise Image": "Precise Image (K210760) was modified for use in the CT 5300 system. With no changes to the algorithm architecture, new models were introduced to enable the reconstruction of a new organ type (cardiac), support more slice thickness and increment combinations, a new scan mode (high resolution head), and more clinical scenarios for body and head. All models were adequately trained and successfully compared using half-dose Precise Image reconstructions with full-dose iDose4 reconstructions. The comparative image quality assessment using phantoms demonstrated acceptable performance for the new models used in Precise Image. Additionally, a comparative image evaluation by two US Board Certified Radiologists of 126 image set pairs (including cases with pathology) comprising 31 unique patients representing the newly supported reconstructions. The comparative image assessment demonstrated that half-dose images processed by Precise Image in CT 5300, including both new and original existing models, are of equal or greater diagnostic quality compared to full dose images processed by iDose4. The comparative external image assessment confirms the validity of successful bench testing and clinical image quality evaluations, and when taken together, demonstrate Precise Image in CT 5300 to be as safe and effective as the predicate, and thus substantially equivalent to Precise Image (K210760) in predicate Incisive CT (K212441)."

For "Precise Position": "Precise Position (originally cleared in K203514) was modified for use in the CT 5300 with no change to the design of the AI algorithm, the body joints detection algorithm including CNN architecture, model parameters, inference pipeline, pre- and post-processing is same as what is used in the predicate Incisive CT. The original model was trained using a broad dataset and performance data using clinical images demonstrate the model can further support more exams (cardiac, spine, runoff)."

1. Table of Acceptance Criteria and Reported Device Performance

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

• Precise Image:

  • Clinical Image Evaluation: 126 image set pairs "comprising 31 unique patients".
  • Data Provenance: Not explicitly stated, but "two US Board Certified Radiologists" implies the data used for the reading study was likely relevant to US clinical practice. It is mentioned as "retrospective clinical data" in the "Summary of Clinical Data" section (Page 10), but further details on geographical origin or specific institutions are not provided. The study is described as a "comparative image evaluation," which is by nature retrospective.
  • Phantom Study: Not specified (number of phantoms/scans).

• Precise Position:

  • Clinical Images: "performance data using clinical images" was used, but the specific sample size of images/patients for this evaluation is not provided.
  • Data Provenance: Not explicitly stated, but the "original model was trained using a broad dataset," suggesting varied provenance. The evaluation here uses "clinical images" and is implicitly retrospective.

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

• Precise Image:

  • Number of Experts: Two (2)
  • Qualifications: "US Board Certified Radiologists"
  • Experience: Not specified (e.g., number of years of experience).

• Precise Position: Not explicitly stated for performance evaluation, but the "original model was trained using a broad dataset" which often implies some form of expert annotation or clinical data used as ground truth during training. For the evaluation of its extended support, it's mentioned that the model was tested with "performance data using clinical images," but details on expert review for this test set are not provided.

4. Adjudication Method for the Test Set

• Precise Image: The document describes a "comparative image evaluation by two US Board Certified Radiologists." It does not specify an adjudication method (e.g., 2+1, 3+1, or consensus reading). It's possible they read independently and their findings were compared, or they may have reached a consensus without formal arbitration by a third party.

• Precise Position: No details on expert review or adjudication method for the specified performance evaluation are provided.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, What was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

• No, a traditional MRMC comparative effectiveness study was not performed as described for human readers with/without AI assistance, in the sense of measuring diagnostic accuracy improvement.
• Instead, for "Precise Image," a comparative image quality assessment was performed between two different reconstruction methods: "half-dose Precise Image reconstructions" (new algorithm) vs. "full-dose iDose4 reconstructions" (predicate algorithm). The goal was to show non-inferiority or superiority of the image quality from the new algorithm at a reduced dose, rather than measuring reader performance improvement with AI assistance.
• The effect size related to reader performance is not applicable in this context as the study was about image quality comparison, not AI-assisted human reading. The conclusion was that the image quality was "equal or greater," which implicitly means readers can perform at least as well with the new images.

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

• Yes, for "Precise Image," a standalone image quality assessment was performed using phantoms. This is described as "The comparative image quality assessment using phantoms demonstrated acceptable performance for the new models used in Precise Image." This evaluates the algorithm's output (image quality) independent of human interpretation of complex clinical cases.
• For "Precise Position," it is a "body joints detection algorithm." While it's part of a workflow to assist patient positioning, a standalone performance metric (e.g., accuracy of joint detection) is not explicitly provided in this document, only that the "original model was trained using a broad dataset" and "performance data using clinical images demonstrate the model can further support more exams."

7. The Type of Ground Truth Used

• Precise Image:

  • Phantom Study: Ground truth would be based on the known characteristics of the phantom and imaging parameters, allowing for objective image quality metrics (e.g., spatial resolution, noise, contrast).
  • Clinical Image Evaluation: The ground truth for comparative diagnostic quality seems to be based on the "full-dose iDose4 reconstructions" themselves and inclusion of "cases with pathology." This implies that the full-dose images (processed by the predicate's iDose4 algorithm) were considered the reference truth against which the new algorithm's images were judged for diagnostic quality. The mention of "cases with pathology" likely means these cases had confirmed diagnoses, which serve as the ultimate ground truth for comparison.

• Precise Position: The ground truth for the training set would likely be human-annotated or verified positions of body joints on CT images. For the evaluation, it's implied that the "clinical images" and the intended "support more exams" served as the basis for performance verification.

8. The Sample Size for the Training Set

• Precise Image: The document states "All models were adequately trained." However, the specific sample size (number of images/patients) used for training the "new models" for Precise Image is not provided.
• Precise Position: The document states "The original model was trained using a broad dataset." The specific sample size (number of images/patients) used for training is not provided.

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

• Precise Image: The document states "All models were adequately trained." For deep learning image reconstruction like Precise Image, training typically involves paired low-dose and standard-dose (or high-quality) images, where the standard-dose images serve as the ground truth reference for the algorithm to learn how to enhance low-dose images. This is inferred but not explicitly stated in the provided text.
• Precise Position: The document states "The original model was trained using a broad dataset." For a "body joints detection algorithm," ground truth for training would typically be established by expert (e.g., radiologist or trained annotator) manual annotation of anatomical landmarks or joint locations on a large dataset of CT images. This is inferred but not explicitly stated in the provided text.

Ask a specific question about this device

The Smart Fit Knee 3.0T coil is designed to be used in conjunction with a Philips 3.0T MR system to produce diagnostic images of the Knee that can be interpreted by a trained physician.

The Smart Fit Knee 3.0T coil is designed to be used in conjunction with a Philips 3.0T MR system to produce diagnostic images of the Knee that can be interpreted by a trained physician.
The Smart Fit Knee 3.0T is a 16-element coil designed for high-resolution imaging of the left or right knee. It is a phased-array, Rx volume coil providing an integrated solution with a base plate, an anterior and a posterior part. Positioning pads are also supplied to support comfortable positioning. The coil can be slightly rotated relative to its base plate to ease coil setup and enhance patient comfort. The coil is used independently and cannot be combined with any other coils. This coil is available for 3.0T MR systems and is compatible with Philips 3.0T MR Scanners.

The provided text describes the Philips Smart Fit Knee 3.0T MRI coil, but it does not contain acceptance criteria for device performance or a detailed study proving the device meets specific performance criteria through clinical effectiveness measures.

Instead, the document focuses on demonstrating substantial equivalence to a predicate device (HRK-127-8 KNEE ARRAY COIL K033567) for regulatory clearance. This is primarily done through technological comparisons and compliance with recognized consensus standards.

Here's a breakdown of the information available and what is missing based on your request:

1. Table of Acceptance Criteria and Reported Device Performance

• Acceptance Criteria: Not explicitly stated as quantifiable performance metrics for clinical effectiveness. The acceptance criteria in this document are implicitly related to compliance with recognized standards and showing similarity to the predicate device in design, intended use, and fundamental scientific technology.
• Reported Device Performance:
  • "The performance test results demonstrate that the proposed Smart Fit Knee 3.0T meets the acceptance criteria and is adequate for its intended use." This is a general statement of compliance, not a report of specific numerical performance metrics.
  • "All clinical images on the proposed coils Smart Fit Knee 3.0T were evaluated by qualified radiologists. No issues with the clinical image quality were seen and images were considered have sufficient quality for diagnostic use." This broadly indicates acceptable image quality based on expert review, but no quantifiable performance metrics (e.g., sensitivity, specificity, SNR values) are provided.

Table based on available information (focused on equivalence and general performance):

Ask a specific question about this device

The Smart Fit TorsoCardiac 1.5T coil is designed to be used in conjunction with a Philips 1.5T MR system to produce diagnostic images of the torso (including chest, abdomen, pelvis), head and neck and heart that can be interpreted by a trained physician.

The Smart Fit Shoulder 1.5T coil is designed to be used in conjunction with a Philips 1.5T MR system to produce diagnostic images of the Shoulder that can be interpreted by a trained physician.

The proposed of Smart Fit Shoulder 1.5T and Smart Fit TorsoCardiac 1.5T are intended to be used in conjunction with a Philips MR-system to enable trained physicians to obtain cross-sectional images of the internal structure of the head, body, or extremities, in any orientation. These images, when interpreted by a trained physician, provide information that may assist diagnosis and therapy planning.

The proposed Smart Fit Torsocardiac 1.5T is a phased array receive-only coil for high resolution diagnostic imaging of the torso (including chest, abdomen, pelvis), head and neck and heart. The coil foam is composed of PU foil, flexible PCB and EVA to provide sufficient flexibility along Left-Right direction for patient body scan. The layers from outside to patient side are: PU foil (outer surface), EVA30 foam, PCBA of the coil and PU foil (inner surface). The foam looks flat at the top surface. A few parts, two feed- board boxes, cable housing and a small connector placed across the central Head-Feet axis are also at the top surface. Inner surface is naturally flat and is bendable along slots to fit well to the patient body.

The proposed Smart Fit Shoulder 1.5T is a phased array receive-only coil for high resolution diagnostic imaging of shoulder. The coil foam is composed of PU foil, flexible PCB and EVA to provide sufficient flexibility along Anterior-Posterior direction for patient shoulder scan. The layers from outside to patient side are: PU foil (outer surface), EVA30 foam, PCBA of the coil, EVA 30 foam, and PU foil (inner surface). A few parts, feed-board boxes, cable housing and a small connector placed across the Head-Feet axis are also at the outer surface. Inner surface is naturally flat and is bendable along slots to fit well to the patient body.

The provided document is a 510(k) Summary of Safety and Effectiveness for Philips Healthcare's Smart Fit TorsoCardiac 1.5T and Smart Fit Shoulder 1.5T MRI coils. It focuses on demonstrating substantial equivalence to predicate devices rather than proving performance against specific acceptance criteria for an AI/ML-driven device through a multi-reader, multi-case study.

Therefore, many of the requested details regarding acceptance criteria for an AI/ML device, ground truth establishment, sample sizes for training/test sets, expert adjudication methods, and MRMC studies are not applicable or explicitly mentioned in this document as it pertains to traditional medical device clearance rather than AI/ML software. The document asserts that "The proposed Smart Fit TorsoCardiac 1.5T and Smart Fit Shoulder 1.5T did not require clinical study since substantial equivalence to the legally marketed predicate device was proven in the comparison in terms of safety and effectiveness."

However, I can extract the information that is present and indicate what is not applicable.

Acceptance Criteria and Device Performance (based on provided text, primarily regarding equivalence to predicate devices and general performance, not AI/ML specific metrics)

• ANSI AAMI ES60601-1:2005/(R)2012 & A1:2012 C1:2009/(R)2012 & A2:2010/(R)2012 (Cons. Text)
• IEC60601-2-33 Ed. 3.2:2015
• IEC60601-1-2 Edition 4.1 2020-09 CONSOLIDATED VERSION
• IEC60601-1-6 Edition 3.1:2013
• ISO 14971 Ed. 3:2019
• IEC 62366 Edition 1.1: 2020-06 CONSOLIDATED VERSION
• ANSI AAMI ISO10993-1:2018 |
  | Signal-to-Noise Ratio (SNR) | Meets acceptance criteria (implied by compliance with NEMA MS 1-2008(R2020)) |
  | Image Uniformity | Meets acceptance criteria (implied by compliance with NEMA MS 3-2008 (R2020)) |
  | Phased Array Coils Characterization | Meets acceptance criteria (implied by compliance with NEMA MS 9-2008 (R2020)) |
  | RF Coil Heating | Meets acceptance criteria (implied by compliance with NEMA MS 14-2019) |
  | Clinical Image Quality for Diagnostic Use | "No issues with the clinical image quality was seen and images were considered have sufficient quality for diagnostic use." |
  | Biocompatibility | Biocompatibility testing against internal specifications and ISO10993-1 performed. "The safety of PC and PU has been proved in the biocompatibility report." |
  | Risk Management | "all risks are sufficiently mitigated, that no new risks are" (sentence incomplete in document, but implies compliance/mitigation) |
  | Substantial Equivalence | "considered substantially equivalent to the currently marketed and predicate devices" |

Study Information (based on provided text):

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

   • Test set sample size: Not explicitly stated as a distinct "test set" for performance evaluation in the context of an AI/ML algorithm (which is not this device). However, the document mentions "All clinical images on the proposed coils Smart Fit TorsoCardiac 1.5T and Smart Fit Shoulder 1.5T were evaluated by qualified radiologists." This implies a set of clinical images used for evaluation. The number of images or patients is not provided.
   • Data Provenance: Not specified (e.g., country of origin). The study is descriptive, focusing on demonstrating equivalence to predicates via technical characteristics, standards compliance, and subjective review of image quality rather than analyzing data from a specific patient cohort. The clinical image evaluation mentioned is a retrospective review of images generated by the new coils.

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

   • Number of experts: Not specified beyond "qualified radiologists".
   • Qualifications: "qualified radiologists". No specific years of experience or board certifications are detailed in this summary.
   • Note: This is not an AI/ML device that generates a "ground truth" for classification or detection. The radiologists are evaluating the diagnostic quality of the images produced by the new coils.

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

   • Not specified. The document only states that images "were evaluated by qualified radiologists." It does not detail any consensus or adjudication process for image quality assessment.

4. If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done:

   • No, an MRMC study was NOT done. The document explicitly states: "The proposed Smart Fit TorsoCardiac 1.5T and Smart Fit Shoulder 1.5T did not require clinical study since substantial equivalence to the legally marketed predicate device was proven in the comparison in terms of safety and effectiveness." MRMC studies are typically performed for AI/ML devices to assess reader performance with and without AI assistance; this device is an MRI coil, not an AI/ML algorithm.
   • Effect size of human readers improvement with AI vs. without AI assistance: Not applicable, as no AI assistance is involved with these MRI coils, and no such study was performed.

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

   • Not applicable. This device is an MRI coil, which is a hardware component, not a standalone algorithm.

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

   • Not applicable in the context of an AI/ML algorithm generating diagnostic output. For this device (an MRI coil), the "ground truth" is implicitly tied to the expectation that the images produced are of sufficient diagnostic quality as determined by "qualified radiologists" (expert opinion on image quality) and meet established technical performance standards (NEMA, IEC, AAMI). There's no disease pathology ground truth being established/compared for an AI model.

7. The sample size for the training set:

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

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

   • Not applicable. This is not an AI/ML device.

Ask a specific question about this device

The Philips CT 3500 is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of X-Ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipments and accessories. The Philips CT 3500 is indicated for head, whole body, cardiac (Cardiac Calcium Scoring) and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The proposed Philips CT 3500 is a whole-body computed tomography (CT) X-Ray System featuring a continuously rotating x-ray tube, detectors, and gantry with multi-slice capability. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body taken at different angles and planes. This system also includes signal analvsis and display equipment, patient and equipment supports, components, and accessories. The Philips CT 3500 has a 72cm bore and includes a detector array that provides 50cm scan field of view (FOV). Besides installed in hospital, the proposed Philips CT 3500 may also be installed on trailer and be transported to designed locations for use. And Philips CT 3500 installed on trailer has the same intended use as installed in hospital. The key components that are used in the proposed Philips CT 3500 have the same fundamental design characteristics and are based on comparable technologies as the current market predicate Philips Incisive CT (K212441 - April 27, 2022). CT on Trailer Kit that is used in the proposed Philips CT 3500 to install and secure the CT system on trailers have the same fundamental design characteristics and are based on comparable technologies as the current market predicate Philips Incisive CT on trailer (K211168 - November 22, 2021). Trailers are provided by trailer manufactures and are not components of the proposed Philips CT 3500. The key system modules and functionalities are: 1. Gantry. The Gantry consists of 4 main internal units: a) X-Ray Tube – produce X-ray necessary for scanning. b) High voltage generator - produce high voltage power supply to X-ray tube. consists of system Interface Unit, Power Block Unit and Anode Drive Unit. c) A-plane: adjust the slice thickness during axial scan and monitors the changes of X-ray d) DMS (Data Measurement System) – absorb X-ray radiation by detectors and convert it to digital readout. 2. Patient Table (Couch) Couch is used to position the patient. Carries the patient in and out through the Gantry bore synchronized with the scan. 3. Console It is used to operate the system and monitor the scan. The Operator console includes computer, monitor and CTBOX. 4. CT on Trailer Kit Philips CT 3500 installed and secured on trailer requires locking motion parts during trailer transportation and unlocking motion parts before CT operations. CT on Trailer Kit is used to install and secure the CT system on trailers, trailers are provided by trailer manufactures and are not components of the proposed Philips CT 3500. In addition to the above components and the software operating them, each system includes hardware and software for data acquisition, display, manipulation, storage and filming as well as post-processing into views other than the original axial images.

It appears there might be a misunderstanding of the provided text. The document is an FDA 510(k) clearance letter for the Philips CT 3500. This type of document declares a device substantially equivalent to a predicate device, based on non-clinical performance data (e.g., adherence to standards, design verification and validation), rather than a clinical study with specific acceptance criteria related to AI performance, human reader improvement, or detailed ground truth establishment for a test set.

The document does not describe an AI/algorithm-driven device requiring a study with acceptance criteria of the type typically seen for CADe/CADx devices (e.g., sensitivity, specificity, FROC analysis, MRMC studies). Instead, it's for a Computed Tomography X-Ray System (a hardware device), where "acceptance criteria" are related to its physical performance, safety, and adherence to established regulatory standards, demonstrating substantial equivalence to a previously cleared CT system.

Therefore, most of the requested information (e.g., acceptance criteria for AI performance, sample sizes for AI test sets, number of experts for AI ground truth, MRMC study effect size) is not present in the provided text because it's not relevant to this type of device clearance.

However, I can extract the information that is relevant to the device clearance as described in the document, framed in the context of "acceptance criteria" through compliance with standards and a comparison with a predicate device.

Here's an interpretation based on the provided document:

Device: Philips CT 3500 (Computed Tomography X-Ray System)

Purpose of the Study (for 510(k) Clearance): To demonstrate substantial equivalence of the Philips CT 3500 to a legally marketed predicate device (Philips Incisive CT - K212441, K211168) through non-clinical performance data (design verification, design validation, and adherence to consensus standards).

Acceptance Criteria and Reported Device Performance (Non-Clinical)

The document primarily relies on demonstrating equivalence to predicate devices and compliance with recognized standards. There isn't a direct table of "acceptance criteria" and "reported performance" as one might see for AI algorithm metrics. Instead, the acceptance is based on meeting the criteria set by these standards and showing comparable characteristics to the predicate device.

Study Information (Based on 510(k) Non-Clinical Data Submission):

1. Sample size used for the test set and the data provenance: Not applicable in the context of a "test set" for an AI algorithm. The validation was a non-clinical evaluation comparing the device to a predicate and established standards. The data provenance would be internal performance testing data and compliance documentation. The document doesn't specify a "test set" size or data origin in the sense of clinical images for an AI study.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI algorithm is not established in this type of 510(k) for a CT system itself, as it is a hardware device. The "ground truth" for the clearance is compliance with engineering specifications, safety standards, and performance benchmarks compared to an existing device.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
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 was done, as this is a CT scanner, not an AI-assisted diagnostic software. The document explicitly states: "The proposed Philips CT 3500 did not require clinical study since substantial equivalence to the legally marketed predicate device was proven with the verification/validation testing."
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is a medical imaging system, not an AI algorithm.
6. The type of ground truth used: The "ground truth" for this clearance is defined by:
   • Consensus Standards: Compliance with dozens of established national and international standards for medical electrical equipment, radiation protection, software, risk management, etc. (e.g., IEC 60601 series, ISO 14971, NEMA XR series).
   • Predicate Device Performance: Direct comparison of fundamental design characteristics, key components, features, and technical specifications with the legally marketed Philips Incisive CT (K212441, K211168).
   • Internal Verification and Validation: System verification against system requirement specifications (SRS) and validation testing covering intended use and commercial claims, including workflow validation.
7. The sample size for the training set: Not applicable. This is not an AI algorithm clearance.
8. How the ground truth for the training set was established: Not applicable. This is not an AI algorithm clearance.

In summary, the provided document details a 510(k) clearance for a CT imaging system, which is a hardware device. The "study" proving it meets "acceptance criteria" primarily involved non-clinical engineering and performance testing to demonstrate safety, effectiveness, and substantial equivalence to existing predicate devices and compliance with regulatory standards, rather than clinical studies of an AI algorithm's diagnostic performance.

Ask a specific question about this device

The Incisive CT is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipment supports, components and accessories. The Incisive CT is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The proposed Philips Incisive CT is a whole-body computed tomography (CT) X-Ray System featuring a continuously rotating x-ray tube, detectors, and gantry with multi-slice capability. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body taken at different angles and planes. This system also includes signal analysis and display equipment, patient and equipment supports, components, and accessories. The Philips Incisive CT has a 72cm bore and includes a detector array that provides 50cm scan field of view (FOV).

The main components (detection system, the reconstruction algorithm, and the x-ray system) that are used in the proposed Philips Incisive CT have the same fundamental design characteristics and are based on comparable technologies as the current market predicate Philips Ingenuity CT (K160743, 08/08/2016).

The main system modules and functionalities are:

1. Gantry. The Gantry consists of 4 main internal units:
   a. Stator - a fixed mechanical frame that carries HW and SW
   b. Rotor - A rotating circular stiff frame that is mounted in and supported by the stator.
   c. X-Ray Tube (XRT) and Generator, - fixed to the Rotor frame
   d. Data Measurement System (DMS) – a detectors array, fixed to the Rotor frame
2. Patient Support (Couch) - carries the patient in and out through the Gantry bore synchronized with the scan
3. Console - Containing a Host computer and display that is the primary user interface.

In addition to the above components and the software operating them, each system includes hardware and software for data acquisition, display, manipulation, storage and filming as well as post-processing into views other than the original axial images. Patient supports (positioning aids) are used to position the patient.

The provided text is a 510(k) Summary of Safety and Effectiveness for the Philips Incisive CT, a computed tomography x-ray system. The document focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and performance data for an AI/CADe device.

Therefore, the information required to fully answer your request regarding acceptance criteria and a study proving an AI device meets those criteria (especially points 3, 4, 5, 7, 8, 9) is largely missing from this specific document. The document describes a traditional CT scanner, not an AI feature or independent AI device.

However, I can extract the relevant information that is present and note the missing parts:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria here are based on demonstrating substantial equivalence to predicate devices in terms of technical characteristics and imaging features. The "performance" is implicitly the device meeting, matching, or improving upon these characteristics without raising new questions of safety or effectiveness.

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

The document states: "The proposed Philips Incisive CT did not require clinical study since substantial equivalence to the legally marketed predicate device was proven with the verification/validation testing."

This means there was no dedicated clinical test set in the traditional sense of patient data used for performance claims. The "testing" appears to be primarily engineering verification and validation against design specifications and industry standards, and comparison to the technical specifications of a predicate device. Therefore, no specific sample size, country of origin, or retrospective/prospective nature of a clinical test set is provided.

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

As there was no clinical study and no clinical test set for independent performance evaluation (rather, it was a substantial equivalence submission based on technical and functional comparison), this information is not applicable/provided. Ground truth establishment by experts for specific clinical findings is not described.

4. Adjudication method for the test set

Not applicable as no clinical test set and ground truth establishment by experts are described.

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

Not applicable. The submission is for a CT scanner itself, not an AI-assisted reading tool. While some newer "Precise" features mention deep learning (e.g., "Precise image reconstruction"), the document explicitly states these are "Different" and refers to other 510(k) clearances (K210760, K203020, K203514) for their safety and effectiveness. This document does not contain the MRMC study details for those specific AI features.

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

Not applicable for the CT scanner itself. For the "Precise" features that hint at AI, the performance data is referenced in other submissions, not detailed here.

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

Not applicable for this submission's stated "verification/validation testing" which focuses on technical specifications and functional equivalence to predicates.

8. The sample size for the training set

Not applicable, as this document does not describe the development or training of an AI model.

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

Not applicable, as this document does not describe the development or training of an AI model.

Summary of what the document does provide:

The document describes the Philips Incisive CT as a Computed Tomography X-Ray System. Its acceptance criteria and proving methodology revolve around demonstrating substantial equivalence to existing, legally marketed predicate CT devices (Philips Ingenuity CT K160743 and Philips Incisive CT K180015). This is achieved through:

• Comparison of technical specifications: Scan characteristics (slices, scan modes, scan time, resolution, noise, slice thickness, FOV, image matrix, display, infrastructure, communication, dose reporting).
• Comparison of imaging features/functionalities: A comprehensive list of features like 2D Viewer, MPR, 3D, O-MAR, Dose Modulation, Bolus Tracking, various analysis applications (Lung Nodule, Cardiac Artery, etc.), and others.
• Compliance with recognized consensus standards: A list of international and FDA-recognized standards (e.g., IEC 60601 series, IEC 62304, ISO 14971, NEMA XR standards) which the device is stated to comply with.
• Non-clinical design verification and validation testing: The document briefly states that "The systems pass the design verification, design validation and consensus standards test as nonclinical tests. The system verification is conducted against the system requirement specifications (SRS). ... Non-Clinical design validation testing covered the intended use and commercial claims. Validation testing included workflow validation."

The core assertion for the Philips Incisive CT's acceptance is that its design, intended use, technology, and principal technological components are substantially equivalent to the predicate devices, and that the product's differences do not raise new questions of safety or effectiveness. For specific features that appear to involve AI (like "Precise image reconstruction"), the document explicitly points to other 510(k) submissions, indicating that their clinical performance and acceptance would be detailed there.

Ask a specific question about this device

The Magnetic Resonance (MR) coil is used with a Philips 1.5T MR scanner. A trained physician interprets the diagnostic images (of the anatomy of interest) produced.

The proposed dS TorsoCardiac 1.5T, dS MSK S 1.5T and dS MSK M 1.5T are designed to be used in conjunction with MR Scanner to produce diagnostic images of the anatomy of interest that can be interpreted by a trained physician.

The proposed dS TorsoCardiac 1.5T is a phased array receive-only coil for high resolution diagnostic imaging of torso, cardiac, and neck. The coil foam is composed of PU foil, flexible PCB and EVA to provide sufficient flexibility along Left-Right direction for patient body scan. The layers from outside to patient side are: PU foil (outer surface), EVA30 foam, PCBA of the coil and PU foil (inner surface). The foam looks flat at the top surface. A few parts, two feed-board boxes, cable housing and a small connector placed across the central Head-Feet axis are also at the top surface. Inner surface is naturally flat and is bendable along slots to fit well to the patient body.

The proposed dS MSK S 1.5T is a phased array receive-only coil for high resolution diagnostic imaging of wrist, foot-ankle, and elbow. The coil foam is composed of PU foil, flexible PCB and EVA to provide sufficient flexibility along Left-Right direction for patient body scan. The layers from outside to patient side are: PU foil (outer surface), EVA30 foam, PCBA of the coil, EVA 30 foam, and PU foil (inner surface). A few parts, feed-board boxes, cable housing and a small connector placed across the central Head-Feet axis are also at the top surface. Inner surface is naturally flat and is bendable along slots to fit well to the patient body.

The proposed dS MSK M 1.5T is a phased array receive-only coil for high resolution diagnostic imaging of shoulder, knee, hip, foot, and elbow. The coil foam is composed of PU foil, flexible PCB and EVA to provide sufficient flexibility along Left-Right direction for patient body scan. The layers from outside to patient side are: PU foil (outer surface), EVA30 foam, PCBA of the coil, EVA30 foam, and PU foil (inner surface). A few parts, feed-board boxes, cable housing and a small connector placed across the central Head-Feet axis are also at the top surface. Inner surface is naturally flat and is bendable along slots to fit well to the patient body.

The proposed dS TorsoCardiac 1.5T, dS MSK S 1.5T and dS MSK M 1.5T are designed to be used with the Philips 1.5T MRI Scanners.

The provided text is a 510(k) summary for Philips Healthcare's MR coils. It focuses on demonstrating substantial equivalence to predicate devices based on non-clinical performance data and fundamental scientific technology. The document explicitly states that no clinical study was required for this submission.

Therefore, I cannot provide the requested information regarding acceptance criteria, study details, sample sizes, expert involvement, adjudication methods, MRMC studies, standalone performance, or ground truth establishment concerning clinical data. The document indicates that safety and performance were evaluated through non-clinical testing and compliance with various standards.

Here's a breakdown of what the document does contain regarding performance and equivalence:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't present a table of specific acceptance criteria in the sense of quantitative performance metrics for a clinical study with corresponding reported device performance values. Instead, it describes compliance with recognized standards and similarity to predicate devices as the basis for substantial equivalence.

The "performance" is demonstrated through compliance with the following non-clinical testing standards:

The document confirms: "The results of these tests demonstrate that dS TorsoCardiac 1.5T, dS MSK S 1.5T and dS MSK M 1.5T met the acceptance criteria and are adequate for this intended use."

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

• Not applicable. This submission relies on non-clinical performance testing and substantial equivalence to predicate devices, not a clinical test set with patient data.

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

• Not applicable. As no clinical testing/test set was required, there was no need for expert ground truth establishment in this context. The document mentions "A trained physician interprets the diagnostic images (of the anatomy of interest) produced" as part of the Indications for Use, which is standard for MR devices.

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

• Not applicable. No clinical test set data requiring adjudication was generated for this submission.

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

• Not applicable. This device is an MR coil, which is a hardware component for imaging, not an AI software algorithm. No MRMC study was performed as it's not relevant to this device's function or the nature of this 510(k) submission.

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

• Not applicable. This is a hardware device (MR coil), not an algorithm.

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

• Not applicable. As there was no clinical study evaluating diagnostic performance, no "ground truth" of this nature was established for the purpose of this submission. Device performance was assessed via compliance with engineering and safety standards.

8. The sample size for the training set:

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

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

• Not applicable. This is not an AI/machine learning device.

In summary: The K212864 submission for Philips Healthcare's dS TorsoCardiac 1.5T, dS MSK S 1.5T, and dS MSK M 1.5T MR coils was cleared based on demonstrating substantial equivalence to legally marketed predicate devices. This equivalence was supported by extensive non-clinical performance testing and compliance with various international and FDA-recognized consensus standards for medical electrical equipment, magnetic resonance equipment, electromagnetic compatibility, risk management, biological evaluation, usability, and specific MRI performance characteristics (SNR, uniformity, coil characterization, RF heating). The FDA letter and the 510(k) summary explicitly state that no clinical study was required to prove safety and effectiveness for these devices.

Ask a specific question about this device

The Incisive CT is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipments and accessories. The Incisive CT is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

Besides installed in hospital, the proposed Philips Incisive CT may also be installed on trailer and be transported to designated locations for use. And Incisive CT installed on trailer has the same intended use as installed in hospital.

The proposed Philips Incisive CT on Trailer is a whole-body computed tomography (CT) X-Ray System featuring a continuously rotating x-ray tube, detectors, and gantry with multi-slice capability. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body taken at different angles and planes. This system also includes signal analysis and display equipment, patient and equipment support, components, and accessories. The Philips Incisive CT has a 72cm bore and includes a detector array that provides 50cm scan field of view (FOV).

Besides installed in hospital, Philips Incisive CT can also be installed on trailer and be transported to designated locations.

The main components (detection system, the reconstruction algorithm, and the x-ray system) that are used in the proposed Philips Incisive CT on trailer are identical to the currently marketed and predicate Philips Incisive CT (K180015, 20/March/2018).

The components of the proposed Philips Incisive CT on trailer include the following:

1. Gantry. The Gantry consists of 4 main internal units:
   a. Stator – a fixed mechanical frame that carries HW and SW
   b. Rotor – A rotating circular stiff frame that is mounted in and supported by the stator
   c. X-Ray Tube (XRT) and Generator, - fixed to the Rotor frame
   d. Data Measurement System (DMS) - a detectors array, fixed to the Rotor frame
2. Patient Support (Couch) - carries the patient in and out through the Gantry bore synchronized with the scan.
3. Console - Containing a Host computer and display that is the primary user interface.
4. CT on Trailer Kit - Modified Incisive CT installed and secured on trailer requires locking motion parts during trailer transportation and unlocking motion parts before CT operations.

In addition to the above components and the software operating them, each system includes hardware and software for data acquisition, display, manipulation, storage and filming as well as post-processing into views other than the original axial images. Patient supports (positioning aids) are used to position the patient.

The provided document is a 510(k) premarket notification for the Philips Incisive CT on Trailer. It seeks to demonstrate substantial equivalence to a predicate device, the Philips Incisive CT (K180015). This type of submission focuses on showing that the new device is as safe and effective as a legally marketed predicate device, rather than on providing extensive clinical performance data for an AI algorithm.

Therefore, the document does not contain the detailed information necessary to answer all parts of your request, especially those pertaining to AI/algorithm-specific studies. The device described is a CT scanner, not an AI algorithm for image analysis.

However, I can extract the relevant information regarding the device's performance criteria based on the context provided for a traditional 510(k) submission for an imaging device.

Here's an analysis based on the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document details that the "Philips Incisive CT on Trailer" is essentially the predicate "Philips Incisive CT" (K180015) installed on a trailer. The justification for substantial equivalence relies heavily on the fact that the core CT system (detection system, reconstruction algorithm, x-ray system) is identical to the predicate.

The primary performance evaluation mentioned, specifically for the "on Trailer" aspect, relates to robustness and image quality after transportation.

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

• Test Set Sample Size: Not explicitly stated as a number of patient cases. The "test set" in this context refers to the physical device undergoing vibration and QA tests. The tests were performed on "the proposed Philips Incisive CT on Trailer." This likely refers to one or more physical units of the device.
• Data Provenance: The testing was conducted by Philips Healthcare (Suzhou) Co., Ltd. within their development/validation process in China. The data is prospective in the sense that it's generated from testing the new "on Trailer" configuration.

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

• This question is not applicable in the context of this 510(k) submission. This filing is for a physical CT device (mobile CT scanner) and its ability to maintain performance after transport, not for an AI algorithm that generates a "ground truth" often established by expert readers. The "ground truth" here is the physical performance of the CT scanner measured by established imaging quality metrics.

4. Adjudication Method for the Test Set

• Not applicable for this type of device submission. Adjudication generally refers to expert consensus in interpreting medical images or data. The performance of the CT scanner is measured objectively (e.g., noise levels, spatial resolution) against pre-defined engineering and image quality specifications.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size

• No, an MRMC study was not done. This type of study is relevant for AI algorithms intended to assist human readers in diagnostic tasks. The device in focus is the CT scanner itself, not an AI software for image interpretation.

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

• No, a standalone AI algorithm performance study was not done. This 510(k) is for the CT imaging system, not an AI diagnostic algorithm.

7. The Type of Ground Truth Used

• For the physical performance of the CT scanner (MeanCT, Uniformity, Noise, Spatial Resolution, Slice Thickness, Linearity, Low Contrast Resolution), the "ground truth" is established by engineering specifications and phantoms/test objects yielding objective physical measurements, rather than clinical outcomes or expert consensus on patient images. The claim is that these measurements are "same as the predicate device," implying the predicate's performance serves as the benchmark.

8. The Sample Size for the Training Set

• Not applicable. This document is for a CT scanner hardware device (with integrated software for image acquisition and reconstruction), not a machine learning model that requires a "training set" of data.

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

• Not applicable. See point 8.

Ask a specific question about this device

The Precise Position is intended for use with Philips Incisive CT systems. The following guided workflow.

• Patient orientation identification
• Surview range recommendation
• Automatic centering the patient anatomy
• Provide visual images of patient on the table

Precise position is indicated for use for CT imaging of the head, chest, abdomen, pelvis, and combination of those anatomies.

Patient population limitation: Patient younger than 16 years are not supported.

Precise Position is an optional feature to assist user for position the patient before the body examination such as CT scan. The purpose of this feature is to reduce the patient position time via the camera detection and calculation result. It includes automatic detect patient orientation, patient anatomy scan range and center of patient anatomy.

Precise Position including a camera with both color and depth function is installed in the ceiling of the scan room, in such a way to cover the entire patient on the patient table. The camera control and image data transmit via the high speed fiber and copper hybrid USB cable. The power supply of the camera is from the gantry. Precise position adopts the AI algorithm (Convolution Neural Network) to detect the joints of the patient body, and then identify surview start/end position and patient orientation. The algorithm can also support detect center of patient anatomy.

Limitation for Precise Position
There is no limitation for Precise Position except below items:
• Patients below the age of 16 are not supported.
• Decubitus orientations are not supported.

The Precise Position display results may get affected by the following conditions:
• When the patient is covered by sheet, blanket etc.,
• When the patient is not completely covered by the ceiling camera view, e.g. blocked by the gantry or out of camera's FOV etc.
• When the patient is wearing clothes that reflects light, e.g. plastic-like clothes.
• When the patient is wearing black clothes.
• When the patient is wearing thick clothes.
• When there are other people around the patient.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Total 80 clinical scan positions.
  • 40 cases used with Precise Position.
  • 40 cases without the usage of Precise Position.
• Data Provenance: The document does not explicitly state the country of origin for the data or if it was retrospective or prospective. However, it mentions a "clinical evaluation… done by 5 Clinical experts" and volunteers not receiving radiation, implying a prospective study conducted for the purpose of this evaluation. The manufacturer is Philips Healthcare (Suzhou) Co., Ltd., which suggests the study likely occurred in China.

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

• Number of Experts: 5 Clinical experts.
• Qualifications: The specific qualifications (e.g., number of years of experience, specific specialty like "radiologist") are not explicitly stated beyond "Clinical experts."

4. Adjudication Method for the Test Set

• The document does not specify an explicit adjudication method (e.g., 2+1, 3+1). It states that the "thorough clinical evaluation of this feature is done by 5 Clinical experts," implying they collectively contributed to the evaluation, but the exact consensus or adjudication process is not detailed.

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

• This was not a typical MRMC comparative effectiveness study in the sense of multiple readers interpreting cases with and without AI.
• Instead, it was a comparative study on operational efficiency and positioning accuracy. It compared:
  • Time taken for patient positioning by users with and without the Precise Position feature.
  • Accuracy of vertical (iso)center positioning by users with and without the Precise Position feature.
  • Consistency (standard deviation) of positioning by users with and without the Precise Position feature.
• Effect Size (Human Improvement with AI):
  • Time Reduction: Users achieved up to 23% time reduction in patient positioning with the "Precise Positioning workflow" (which includes the AI).
  • Vertical Position Accuracy: Users achieved an increase of up to 50% in vertical position accuracy with "Precise Position."
  • Positioning Consistency (Vertical and Horizontal): Users achieved an increase of up to 70% in consistency with "Precise Position."
    These metrics indicate the improvement in human operators' performance when assisted by the AI-powered Precise Position device.

6. If a Standalone (Algorithm Only) Performance Study Was Done

• The document does not explicitly state whether a standalone (algorithm only, without human-in-the-loop) performance study was conducted for the AI component of the Precise Position device. The clinical evaluation focuses on the human-with-AI system performance. The AI algorithm (Convolution Neural Network) is described as being used to detect joints and then determine positioning parameters, suggesting its performance is evaluated as part of the overall integrated system.

7. The Type of Ground Truth Used

• For the clinical evaluation, the ground truth for measuring time, accuracy, and consistency appears to be based on:
  • Direct measurements of time taken for positioning.
  • Measurements of offset in mm for vertical (iso) center position.
  • Standard deviation calculations for vertical (iso)center positioning and surview (horizontal) start position.
  • These measurements were likely compared against an ideal or intended positioning, which would be implicitly defined by the CT system's requirements and presumably verified by the clinical experts. It's not "pathology," "outcomes data," or a direct "expert consensus" on disease presence/absence, but rather a consensus on the correctness and optimal nature of the patient positioning parameters established by the device.

8. The Sample Size for the Training Set

• The document does not provide the sample size for the training set used for the AI algorithm (Convolution Neural Network). It only discusses the test set used for validating the combined human-AI system.

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

• The document does not describe how the ground truth for the training set of the AI algorithm was established. It only mentions that the AI algorithm (Convolution Neural Network) is used to detect "joints of the patient body" to then identify surview start/end position and patient orientation, and support detection of the center of patient anatomy. This implies annotation of patient body parts and anatomical landmarks in imaging data for training purposes, but specific details on its establishment are not provided.

Ask a specific question about this device

The DuraDiagnost is intended for use in generating radiographic images of human anatomy by qualified/trained doctor or technician. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. This device is not intended for mammographic applications.

The DuraDiagnost is a flexible digital radiography (DR) system that is designed to provide fast and smooth radiography examinations of sitting, standing or lying patients.
The DuraDiagnost consist of the following components: Tube column with X-ray assembly, wall stand with detector carrier, patient table with detector carrier and floating table top, high voltage generator, and acquisition and reviewing workstation for post-processing, storage and viewing of images. Images may be transferred via a DICOM network for printing, storage and detailed review.

The provided text describes a 510(k) premarket notification for the Philips DuraDiagnost, an X-ray system. The submission focuses on demonstrating substantial equivalence to a predicate device (DuraDiagnost K141381), rather than proving the performance of a novel AI algorithm. Therefore, many of the requested details, such as acceptance criteria for AI performance metrics, sample sizes for test sets, expert adjudication methods for AI ground truth, MRMC studies, standalone AI performance, and AI training set details, are not applicable to this submission.

The document primarily evaluates the DuraDiagnost against safety and effectiveness standards applicable to X-ray systems and its equivalence to a previous version of the device.

Here's the information that can be extracted, and an explanation of why other requested information is not present:

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

The document does not provide specific quantitative acceptance criteria for image quality or clinical performance metrics in a readily extractable table format for human or AI performance. Instead, it states that the device meets acceptance criteria by:

• Complying with international and FDA-recognized consensus standards.
• Demonstrating substantial equivalence to its predicate device in terms of design, technology, indications for use, safety, and effectiveness.

The "performance" is reported as compliance with the following standards and internal tests:

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

This information is not provided in the document as it is a 510(k) submission based on comparison to a predicate device and compliance with general safety and performance standards for X-ray systems, not specific clinical performance studies with AI. The non-clinical verification/validation tests performed would typically use test phantoms or specific equipment testing, not a "test set" of patient data in the way an AI algorithm would.

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

This is not applicable as the submission is not for an AI algorithm requiring clinical ground truth established by experts.

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

This is not applicable.

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 is not applicable. The device is an X-ray system, not an AI-powered diagnostic aide. The document explicitly states: "The DuraDiagnost does not require clinical study since substantial equivalence to the primary currently marketed and predicate device was demonstrated..." (Page 15).

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

This is not applicable. The device includes image processing software (UNIQUE 2 and SkyFlow), listed as comparable or updated versions of software present in predicate/reference devices, but it is not presented as a standalone AI diagnostic algorithm.

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

This is not applicable in the context of an AI study. The "ground truth" for this submission refers to the established safety standards and the performance characteristics of the predicate device, against which the new device (DuraDiagnost) is compared. Compliance with engineering standards and performance specifications (e.g., tube voltage, focal spot size, image matrix, pixel size) serves as the "ground truth" for the device's equivalent performance to what is already on the market.

8. The sample size for the training set

This is not applicable. The document does not describe the development or training of a new AI algorithm.

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

This is not applicable.

Ask a specific question about this device