Search Results

The Philips CT Big Bore 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. These systems are indicated for head and whole body X-ray Computed Tomography applications in oncology, vascular and cardiology, for 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 Philips CT Big Bore is currently available in two system configurations, the Oncology configuration and the Radiology (Base) configuration.

The main components (detection system, the reconstruction algorithm, and the x-ray system) that are used in the Philips CT Big Bore have the same fundamental design characteristics and are based on comparable technologies as the predicate.

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 detector 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 A two part subsystem containing a Host computer and display that is the primary user interface and the Common Image Reconstruction System (CIRS) - a dedicated, powerful image reconstruction computer

In addition to the above components and the software operating them, each system includes workstation 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.

This document describes the Philips CT Big Bore, a Computed Tomography X-Ray System. The submission focuses on demonstrating substantial equivalence to a predicate device rather than a standalone clinical efficacy study with acceptance criteria in the typical sense of a diagnostic AI product. Therefore, much of the requested information regarding clinical studies and expert review for ground truth is not directly applicable in the same way.

However, based on the provided text, we can infer and extract the following:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are framed in terms of achieving similar or improved performance compared to the predicate device and meeting established industry standards for CT systems. The reported device performance is primarily a comparison to the predicate device's specifications and measurements on phantoms.

2. Sample Size for Test Set and Data Provenance

The document does not explicitly state a "test set" in the context of an AI/algorithm-driven diagnostic study. Instead, it refers to "bench testing included basic CT performance tests on phantoms" and "Sample clinical images were provided with this submission, which were reviewed and evaluated by radiologists."

• Sample Size for Test Set: Not specified for clinical images. For bench testing, it refers to "phantoms."
• Data Provenance: Not specified for the "sample clinical images." Given the context of a 510(k) for a hardware device, it's highly likely these were internal and possibly from a variety of sources. It's not stated whether they were retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: "radiologists" (plural, but exact number not specified).
• Qualifications of Experts: Only "radiologists" are mentioned. No details on years of experience or subspecialty.

4. Adjudication Method for Test Set

• Adjudication Method: Not specified. The document states, "All images were evaluated to have good image quality," suggesting a qualitative assessment rather than a structured adjudication process for a specific diagnostic task.

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

• MRMC Study: No, a typical MRMC comparative effectiveness study was not performed as described. This submission is for a CT scanner itself, not an AI-assisted interpretation tool where human readers' performance with and without AI would be compared.
• Effect Size of Human Readers with AI vs. without AI: Not applicable, as this was not an AI-assistance study.

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: No, this was not a standalone algorithm performance study. The submission is for a complete CT imaging system. The performance metrics reported are for the overall system, not an isolated algorithm. The document mentions "optional software algorithm called WARP or DAS" for increasing slice count, and features like "iDose4" (an extension of DoseRight) and "FDOM, 3D-DOM" for dose modulation, but their standalone performance is not detailed in terms of a clinical study.

7. Type of Ground Truth Used

• Type of Ground Truth: For the "sample clinical images," the ground truth seems to be expert opinion / qualitative assessment by radiologists that the image quality was "good." For the technical performance parameters (MTF, CTDIvol, CT number accuracy, Noise, Slice Thickness), the ground truth was derived from physical phantom measurements against established technical specifications.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. This document describes a CT scanner (hardware and embedded software), not a machine learning model that would have a separate "training set" in the conventional sense. The "training" for the system's development would be through engineering design, iterative testing, and adherence to established physical and software engineering principles.

9. How Ground Truth for the Training Set Was Established

• How Ground Truth for Training Set Was Established: Not applicable. (See point 8). The development of the CT system likely involved extensive engineering design, simulations, and validation against known physical principles and performance targets, which are fundamentally different from establishing ground truth for a machine learning training set.

Ask a specific question about this device

This device is a diagnostic imaging system for that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT) systems. The CT subsystem produces cross-sectional images of the body by computer reconstruction of x-ray transmission data. The PET subsystem produces images of the distribution of PET radiopharmaceuticals in the patient body (specific radiopharmaceuticals are used for whole body, brain, heart and other organ imaging). CT data is applied to the PET data for attenuation correction. The PET subsystem also provides for list mode, dynamic, and gated acquisitions. This system is intended for patients of all ages.

Image processing and display workstations provide software applications to process, analyze, display, quantify and interpret medical images/data.

The PET and CT images may be registered and displayed in a "fused" (overlaid in the same spatial orientation) format to provide combined metabolic and anatomical data at different angles. Trained professionals use the images in:
· The evaluation, detection and diagnosis of lesions, disease and organ function such as but not limited to cancer, cardiovascular disease, and neurological disorders.
· The detection, localization, and staging of tumors and diagnosing cancer patients.
· Radiation therapy treatment planning and interventional radiology procedures.

The system includes software that provides a quantified analysis of regional cerebral activity from PET images.

Cardiac imaging software provides functionality for the quantification of cardiology images and data sets including but not limited to myocardial perfusion for the display of wall motion and quantification of left-ventricular function parameters from gated myocardial perfusion studies and for the 3D alignment of coronary artery images from CT coronary angiography onto the myocardium.

Both subsystems (PET and CT) can also be operated independently as fully functional, diagnostic imaging systems including application of the CT scanner as a radiation therapy simulation scanner.

This scanner is also 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 Ingenuity TF is an integrated diagnostic imaging system that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT). PET uses radiopharmaceuticals to obtain images by measuring the internal distribution of radioactivity within head, body and total body. PET technology enables the practitioner to reconstruct high-resolution, three-dimensional images of biochemical and metabolic processes of organs within the body. The Ingenuity TF utilized Time-of-Flight (ToF) technology for the PET reconstruction. CT is a medical imaging technique that uses Xrays to obtain cross-sectional images of the head or body. The system utilizes the CT technology to obtain anatomic images of the human body and PET technology to obtain functional images of the human body. The CT component can be utilized by clinicians for lung cancer screening. As such, lung cancer screening has been added to the Ingenuity TF intended use. The integration of the anatomical data from CT with the metabolic data from PET gives clinicians the visual information necessary to define the severity, as well as the extent, of the disease. The major subsystems of the PET/CT include the PET image reconstruction subsystem, the PET Data Acquisition subsystem, the CT Image reconstruction subsystem, the CT acquisition subsystem, the PET Gantry, the CT Gantry and the patient table. The system is suitable for all patients, infant through adult.

Here's a summary of the acceptance criteria and study information for the Ingenuity TF device based on the provided text, focusing on what is and isn't available for each point:

1. Table of Acceptance Criteria and Reported Device Performance

The provided FDA 510(k) summary does not include a direct table of specific acceptance criteria (performance metrics with pass/fail thresholds) and corresponding reported performance for the Ingenuity TF. Instead, it states that:

• Acceptance Criteria (Implicit): The device was designed to meet "established design input requirements," "user needs and intended use," and comply with "FDA recognized consensus standards."
• Reported Performance (General): Design Verification activities "demonstrate the Ingenuity TF meets the established design input requirements." "Design Validation of user needs and intended use was conducted via simulated use testing." "Traceability from requirements to test plans to test results confirmed... that design requirements were met."

The document focuses on demonstrating substantial equivalence to a predicate device rather than providing quantitative performance against specific acceptance criteria for standalone performance.

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

This information is not provided in the document. The text mentions "simulated use testing" and "clinical workflow validation," but does not specify the sample size of cases or the provenance (country, retrospective/prospective) of any test data.

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

This information is not provided. If an expert panel was used for simulated use testing or clinical workflow validation, their number and qualifications are not detailed.

4. Adjudication Method for the Test Set

This information is not provided.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted for the Ingenuity TF. The document explicitly states: "The Ingenuity TF did not require clinical study since substantial equivalence to the primary currently marketed and predicate device was demonstrated with the following attributes: Intended Use; Technological characteristics; Non-clinical performance testing; and Safety and effectiveness." Therefore, an effect size of human readers' improvement with AI vs. without AI assistance is not reported.

6. Standalone Performance Study

A standalone performance study (i.e., algorithm only without human-in-the-loop performance) was not explicitly detailed as a separate clinical study. The device itself is a diagnostic imaging system (a PET/CT scanner), not an AI algorithm intended for standalone interpretation. Performance was assessed through non-clinical testing and comparison to a predicate device. The "Image Quality verification" mentioned under non-clinical testing would involve evaluating the image output itself, which is a form of standalone evaluation of the device's output quality.

7. Type of Ground Truth Used

For the non-clinical and simulated use testing mentioned, the type of "ground truth" would likely involve:

• Established Design Input Requirements: Compliance with specified technical and functional requirements.
• User Needs and Intended Use: Verified through simulated use.
• Consensus Standards: Compliance with international safety and performance standards (e.g., NEMA NU 2:2012 for PET performance, IEC 60601 series).

For any "Image Quality verification," ground truth might be derived from phantom studies with known properties or comparison against highly detailed reference images, but this is not explicitly stated. The document doesn't mention pathology, expert consensus on clinical cases, or outcomes data as direct ground truth for device acceptance.

8. Sample Size for the Training Set

The document does not mention a training set sample size. This device is a PET/CT scanner, not an AI model that undergoes a typical training phase with a dedicated dataset. While it incorporates "software that provides a quantified analysis," the development of this software (its training, if any, for specific analytical tasks) is not detailed.

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

Since there is no mention of a training set for the device itself (as it's a hardware imaging system with integrated software), the method for establishing ground truth for a training set is not applicable/not provided.

Ask a specific question about this device

The NL4000 BodyTom Elite CT system is intended to be used for x-ray computed tomography applications for anatomy that can be imaged in the 85cm aperture.

The CT system is intended to be used for both pediatric and adult imaging and as such has preset dose settings based upon weight and age. The CT images can be obtained either with or without contrast.

BodyTom Elite CT system can be used for low dose lung cancer screening. The screening must be performed in compliance with the approved and established protocols as defined by professional medical societies.

*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 BodyTom Elite is an improved version of BodyTom computed tomography (CT) system providing enhanced functionality. It still has the same high resolution, multi row, 85cm bore and 60cm field of view. The lightweight translating gantry consists of a rotating disk with a solid state x-ray generator, solid state detector array, collimator, control computer, communications link, power slip-ring, data acquisition system, reconstruction computer, power system, brushless DC servo drive system (disk rotation) and stepper drive system (translation). The power system consists of batteries which provide system power while unplugged from the charging outlet. The system has the necessary safety features such as the emergency stop switch, x-ray indicators, interlocks, patient alignment laser and 110% x-ray timer. The gantry has retractable rotating caster wheels and electrical drive system so the system can be moved easily to different locations.

Here's an analysis of the acceptance criteria and study information provided, structured as requested:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document primarily focuses on demonstrating substantial equivalence to a predicate device rather than explicitly stating acceptance criteria and their corresponding performance values in a direct numerical table for the entire device. However, it does list several image quality parameters that are important for Low Dose CT Lung Cancer Screening (LDCT LCS) and the general use of CT, along with reasons for their inclusion. The performance is stated as meeting all image quality criteria used for testing the predicate device.

Image Quality Parameters Relevant to LDCT LCS and General CT Use (Implicit Acceptance Criteria)

Ask a specific question about this device

The IQon Spectral CT is a Computed Tomography X-Ray System intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes. This device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories. The IQon Spectral CT system acquires one CT dataset - composed of data from a higher-energy detected x-ray spectrum and a lower- energy detected x-ray spectra may be used to analyze the differences in the energy dependence of the attenuation coefficient of different materials. This allows for the generation of images at energies selected from the available spectrum and to provide information about the chemical composition of the body materials and/or contrast agents. Additionally, materials analysis provides for the quantification and graphical display of attenuation, material density, and effective atomic number.

This information may be used by a trained healthcare professional as a diagnostic tool for the visualization and analysis of anatomical and pathological structures.

The system is also intended to be used 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 IQon Spectral CT is a whole-body computed tomography (CT) X-Ray System featuring a continuously rotating x-ray tube and detectors gantry and multi-slice capability. The acquired xray transmission data is reconstructed by computer into crosssectional images of the body taken at different angles and planes. This device also includes signal analysis and display equipment; patient and equipment supports; components; and accessories. The IQon Spectral CT includes the detector array previously described in K133674 "Philips IQon Spectral CT".

The IQon Spectral CT consists of three main components - a scanner system that includes a rotating gantry, a movable patient couch, and an operator console for control and image reconstruction; a Spectral Reconstruction System; and a Spectral CT Viewer. On the gantry, the main active components are the x-ray high voltage (HV) power supply, the x-ray tube, and the detection system.

In addition to the above components and the software operating them, the system includes workstation hardware and software for data acquisition; and image 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.

This document, a 510(k) Pre-Market Notification for the Philips IQon Spectral CT (K163711), indicates that no new clinical study was required to demonstrate substantial equivalence for the core device to its predicate (K133674). The addition of "Low Dose CT Lung Cancer Screening" to the Indications for Use was supported by a comparative assessment to another cleared device (K153444), rather than a de novo clinical study for the IQon Spectral CT itself.

Therefore, much of the requested information about acceptance criteria for a specific study conducted for this device, sample sizes for test sets, ground truth establishment, expert qualifications, and MRMC studies, is not present in this document as it pertains to this specific 510(k) submission for the IQon Spectral CT. The document relies heavily on the substantial equivalence to previously cleared devices.

However, I can extract information related to the general acceptance of the device based on non-clinical testing and its reliance on previously cleared predicate devices.

Acceptance Criteria and Device Performance (Based on Non-Clinical Data and Substantial Equivalence)

• IEC 60601-1:2005+A1:2012
• IEC 60601-1-2:2007
• IEC 60601-1-3 Edition 2.0:2008
• IEC 60601-1-6:2010
• IEC 60601-2-44:2009
• ISO 14971:2007 (Application of risk management to medical devices) |
  | Compliance with FDA device-specific guidance documents | The IQon Spectral CT System complies with:
• Guidance for Industry and FDA Staff – "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005)
• Content of Premarket Submissions for Management of Cybersecurity in Medical Devices (Oct 2, 2014) |
  | Adequacy for intended use | "Non-Clinical verification and or validation tests have been performed with regards to the intended use, the technical claims, the requirement specifications and the risk management results."
  "The results of these tests demonstrate that the IQon Spectral CT System met the acceptance criteria and is adequate for its intended use." |
  | Image Quality and Technological Characteristics (for LDCT) | "The addition of lung cancer screening to the IFU statement was supported with a comparative assessment of image quality and technological characteristics to the devices cleared for this use in K153444 [Philips Multislice CT System with Low Dose CT Lung Cancer Screening]." (This implies that the IQon Spectral CT's performance for LDCT was deemed comparable to a previously cleared device for that specific indication, but specific metrics are not detailed in this document). |
  | Safety and Effectiveness | "The IQon Spectral CT System is substantially equivalent to the currently marketed and predicate device, Philips IQon Spectral CT (K133674, Nov. 21, 2014) in terms of safety and effectiveness." |

Study Details (as inferable from the document):

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

   • This 510(k) relies on non-clinical verification and validation testing, and comparative assessment to predicate devices, rather than a new clinical study. Therefore, there is no "test set" in the context of a new prospective or retrospective clinical study of patients, or information on data provenance, within this specific submission. The non-clinical tests would have involved phantom or laboratory testing.

2. 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 new clinical test set requiring expert ground truth establishment is described in this 510(k). The "ground truth" for compliance testing would be defined by the standards and technical specifications being verified.

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

   • Not applicable, as no new clinical test set is described.

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

   • No MRMC study is mentioned or appears to have been conducted for this 510(k) submission. The device is a CT scanner, not an AI-assisted diagnostic tool in the typical sense that would necessitate an MRMC study for improved reader performance for this submission. The "minor improvements to some spectral algorithms" are internal technical refinements, not standalone AI algorithms for interpretation.

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

   • Not applicable. The IQon Spectral CT is a medical imaging device. Its function involves acquiring and processing images for interpretation by a human healthcare professional. There isn't a standalone algorithm performance evaluation described independent of the imaging system. The modifications mentioned ("minor improvements to some spectral algorithms") are part of the image generation/processing pipeline, not a separate diagnostic algorithm.

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

   • For the non-clinical performance data, the ground truth would be the established specifications and requirements defined by the international and FDA-recognized consensus standards (e.g., image quality metrics, dose measurements in phantoms, electrical safety parameters) and the technical design requirements of the device.
   • For the Low Dose CT Lung Cancer Screening indication, the ground for clinical validity would stem from the clinical literature referenced (e.g., National Lung Screening Trial) and the established inclusion criteria/protocols of governmental/professional medical societies, which inherently rely on outcomes data and pathology for nodule malignancy. The IQon Spectral CT's role is to provide the imaging data.

7. The sample size for the training set:

   • Not applicable. This document describes a medical device clearance based on substantial equivalence and non-clinical testing, not a machine learning model requiring a training set. The "spectral algorithms" receiving "minor improvements" are likely image reconstruction and processing algorithms that have been refined based on engineering principles and potentially internal validation, not AI models trained on large datasets.

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

   • Not applicable, as no training set for a machine learning model is described in this 510(k) submission.

Ask a specific question about this device

The Lung Nodule Assessment and Comparison Option is intended for use as a diagnostic patient-imaging tool. It is intended for the review and analysis of thoracic CT images, providing quantitative and characterizing information about nodules in the lung in a single study, or over the time course of several thoracic studies. Characterizations include diameter, volume and volume over time. The system automatically performs the measurements, allowing lung nodules and measurements to be displayed.

The Lung Nodule Assessment and Comparison Option application is intended for use as a diagnostic patient-imaging tool. It is intended for the review and analysis of thoracic CT images, providing quantitative and characterizing information about nodules in the lung in a single study, or over the time course of several thoracic studies. The system automatically performs the measurements, allowing lung nodules and measurements to be displayed. The user interface and automated tools help to determine growth patterns and compose comparative reviews. The Lung Nodule Assessment and Comparison Option application requires the user to identify a nodule and to determine the type of nodule in order to use the appropriate characterization tool. Lung Nodule Assessment and Comparison Option may be utilized in both diagnostic and screening evaluations supporting Low Dose CT Lung Cancer Screening*.

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

Device Name: Lung Nodule Assessment and Comparison Option (LNA)

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary does not explicitly list quantified acceptance criteria with numerical targets. Instead, it indicates that the device was tested against its defined functional requirements and performance claims, and that it "meets the acceptance criteria and is adequate for its intended use and specifications." The "acceptance criteria" are implied by the verification and validation tests performed to ensure the device's design meets user needs and intended use, and that its technological characteristics claims are met.

However, based on the description of the device's capabilities, we can infer some key performance areas that would have been subject to acceptance criteria:

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

• Test Set Sample Size: The document does not specify a numerical sample size for the internal validation studies conducted by Philips for the LNA application. It states that the LNA application was validated "using real recorded clinical data cases in order to simulate the actual use of the software."
• Data Provenance for Philips' Internal Tests: The text implicitly suggests the data was retrospective, as it refers to "real recorded clinical data cases." The country of origin for these internal test cases is not specified.
• Data Provenance for the Risk Calculator (McWilliams et al. study):
  • Development Data Set: Participants from the Pan-Canadian Early Detection of Lung Cancer Study (PanCan).
  • Validation Data Set: Participants from chemoprevention trials at the British Columbia Cancer Agency (BCCA), sponsored by the U.S. National Cancer Institute.
  • This indicates the data was from Canada (PanCan, BCCA in British Columbia) and supported by the U.S. National Cancer Institute. Both were prospective population-based studies.

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

The document does not specify the number of experts or their qualifications for establishing ground truth specifically for Philips' internal V&V test set. It mentions the LNA application was validated to address "user needs" and simulate "actual use of the software," which implies expert input, but no details are provided.

For the Risk Calculator, the ground truth for malignancy in the McWilliams et al. study was established through tracking the final outcomes of all detected nodules. This likely involved pathology reports and clinical follow-up, adjudicated by clinical experts, but the exact number and qualifications of these experts are not detailed in this summary.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1) for Philips' internal V&V test set. The validation process involved evaluating each test case for the complete clinical workflow and ensuring the design meets user needs, which might involve expert review, but the formal adjudication protocol is not elaborated upon in this summary.

For the Risk Calculator's underlying study (McWilliams et al.), the "final outcomes of all nodules" suggests a definitive ground truth based on pathology or long-term clinical stability/progression, but the adjudication method for these biological outcomes is not specified within this document.

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

The document does not report an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The studies described focus on the standalone performance and validation of the LNA application's features and the underlying model for the risk calculator.

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

Yes, standalone performance was evaluated for various features of the LNA application:

• The automatic segmentation capabilities (lungs, lobes, nodules) were validated to be "adequate."
• The automatic measurement calculations (diameters, volume, mean HU) were tested to comply with "defined functionality requirements and performance claims."
• The comparison and matching functionality and "Prefill functionality for the Lung RADS score and the risk prediction" were assured to be "adequate."
• The Risk Calculator tool itself (based on McWilliams et al.) demonstrated standalone predictive performance with "excellent discrimination and calibration, with areas under the receiver-operating-characteristic curve of more than 0.90." This indicates strong standalone performance of the algorithm in predicting malignancy.

7. The Type of Ground Truth Used

• For Philips' Internal V&V: The ground truth appears to be based on "real recorded clinical data cases," implying clinical diagnoses, measurements, and potentially pathology results where applicable, as evaluated against the software's specified functionality and user needs. The specific hierarchy or gold standard used for each feature's ground truth (e.g., expert consensus for segmentation, pathology for nodule type) is not explicitly detailed.
• For the Risk Calculator (McWilliams et al. study): The ground truth for malignancy was established by tracking "the final outcomes of all nodules," which would primarily be pathology results for cancerous nodules and long-term clinical outcome data (stability or benign diagnosis) for non-cancerous ones.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set used for the LNA application's algorithms, including the segmentation, measurement, and comparison features.

For the Risk Calculator's underlying model (McWilliams et al.):

• The "development data set" (training set) included participants from the Pan-Canadian Early Detection of Lung Cancer Study (PanCan). The exact number of participants or nodules is not provided in this summary but the PanCan study is a large, population-based study.

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

For the Risk Calculator's underlying model (McWilliams et al.):

• The ground truth for the development data set (PanCan study) was established by tracking "the final outcomes of all nodules of any size that were detected on baseline low-dose CT scans." This indicates that the ground truth for malignancy was based on definitive pathological diagnosis or long-term clinical follow-up confirming benignity or stability.

Ask a specific question about this device