Search Results

The Philips iCT CT systems 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 iCT 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 Philips iCT CT System is a whole-body computed tomography (CT) X-ray system designed for diagnostic imaging. It features a continuously rotating X-ray tube and multi-slice detector gantry, enabling the acquisition of X-ray transmission data from multiple angles and planes. The system reconstructs these data into cross-sectional images using advanced image reconstruction algorithms, supporting a wide range of clinical applications.

The system consists of a gantry, which houses the rotating X-ray tube, detector array, and key imaging subsystems; a patient support couch, which moves the patient through the gantry bore in synchronization with the scan and is available in multiple configurations; an operator console, which serves as the primary user interface for system controls, image processing, and data management; and a Data Measurement System (DMS), which captures X-ray attenuation data to support high-quality image reconstruction.

The provided FDA 510(k) clearance letter for the Philips iCT CT System (K250648) focuses on demonstrating substantial equivalence to a predicate device (K162838) based on hardware and software enhancements.

However, there is no information within this document that describes specific acceptance criteria in terms of algorithm performance metrics (e.g., sensitivity, specificity, AUC) for an AI/ML-driven diagnostic task, nor does it detail a study proving the device meets such criteria in a clinical context.

The document primarily addresses:

• Physical and technical characteristics of the CT system (e.g., spatial resolution, low contrast resolution, noise, scan speeds).
• Safety and performance of system modifications (e.g., OS upgrade, cybersecurity enhancements, new phantom kit) through non-clinical verification and validation activities.
• Substantial equivalence to a predicate device based on these engineering and system-level tests.

The mention of "low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer" refers to a general indication for the CT system itself, not a specific AI/ML diagnostic algorithm for nodule detection or characterization within the system. The note to "refer to clinical literature, including the results of the National Lung Screening Trial" further supports that the clinical efficacy of CT for lung screening is established and not being re-proven by this submission for a new AI feature.

Therefore, I cannot populate the requested table or answer the specific questions about AI/ML study design directly from the provided text, as this information is not present. The document focuses on the CT scanner as the device, not a specific AI-powered diagnostic algorithm within it that would require the detailed studies outlined in your request.

If the "Philips iCT CT System" were to include an AI component with an explicit diagnostic function beyond general image acquisition and display, the FDA submission would typically contain a dedicated section on its performance evaluation, including the types of studies you are asking about. This document does not describe such an AI component or its associated clinical performance study.

Ask a specific question about this device

The Alinity ci-series is intended for in vitro diagnostic use only.

The Alinity ci-series is a System comprised of inity i or Alinity c analyzers/processing modules that may be arranged into individual or multimodule configurations including up to four Alinity i processing modules, up to four Alinity c processing modules, or a combination of up to four of Alinity i and Alinity c processing modules with a shared system control module to form a single workstation.

The Alinity c System is a fully automated, random/continuous access, clinical chemistry analyzer intended for the in vitro determination of analytes in body fluids.

The Alinity i System is a fully automated analyzer allowing random and continuous access, as well as priority and automated retest processing using chemiluminescent microparticle immunoassay (CMIA) technology is used to determine the presence of antigens, antibodies, and analytes in samples.

The Alinity c ICT (Integrated Chip Technology) is used for the quantitation of sodium, and chloride in human serum, plasma, or urine on the Alinity c analyzer.

Sodium measurements are used in the diagnosis and treatment of aldosteronism (excessive secretion of the hormone aldosterone), diabetes insipidus (chronic excretion of large amounts of dilute urine, accompanied by extreme thirst), adrenal hypertension. Addison's disease (caused by destruction of the adrenal glands), dehydration, inappropriate antidiuretic hormone secretion, or other diseases involving electrolyte imbalance.

Potassium measurements are used to monitor electrolyte balance in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels.

Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.

The Alinity c Glucose Reagent Kit is used for the quantitation of glucose in human serum, plasma, urine, or cerebrospinal fluid (CSF) on the Alinity c analyzer. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.

The Alinity i Total B-hCG assay is a chemiluminescent microparticle immunoassay (CMIA) used for the quantitative and qualitative determination of beta-human chorionic gonadotropin (B-hCG) in human serum and plasma for the early detection of pregnancy on the Alinity i analyzer.

The Alinity ci-series is comprised of individual Alinity i or Alinity c analyzers/processing modules that may be arranged into individual or multimodule configurations which include either multiple Alinity i processing modules, multiple Alinity c processing modules, or a combination of up to four of both Alinity i and Alinity c processing modules with a shared system control module (SCM). The SCM includes the reagent and sample manager (RSM). The multimodule configurations do not have a separate device label or list number. In a multimodule configuration, each processing module retains its original unique identification label.

The document describes the non-clinical performance evaluation of the Alinity ci-series system, Alinity i Total ß-hCG Reagent Kit, Alinity c Glucose Reagent Kit, and Alinity c ICT Sample Diluent. The study focuses on demonstrating equivalent performance between the original single-module configurations and the new multi-module configurations.

Here's an breakdown of the information requested:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly based on demonstrating "equivalent performance" between the investigational multimodule system and the previously cleared single-module predicate devices. The reported performance metrics are precision (%CV) and method comparison parameters (slope and correlation coefficient). The document doesn't explicitly state numerical acceptance criteria thresholds, but rather implies that the observed results were within an acceptable range for "equivalent performance."

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

The document does not explicitly state the exact sample sizes (number of patient samples) for the precision and method comparison studies. It provides ranges of analyte concentrations, implying that multiple samples spanning these ranges were tested.

• Precision Studies: Samples across various concentration ranges (e.g., 5.25 to 12,850 mIU/mL for ß-hCG, 7 to 688 mg/dL for glucose serum, etc.) were used. The term "5-day precision" suggests a study design where samples are run over 5 days to assess within-laboratory variability.
• Method Comparison Studies: Samples across various concentration ranges were used (e.g., 2.74 to 14,998.60 mIU/mL for ß-hCG, 14 to 659 mg/dL for glucose serum, etc.).

Data Provenance: The document does not specify the country of origin of the data or whether the studies were retrospective or prospective. Given that it's a pre-market submission to the FDA, the studies are typically prospective and conducted by the manufacturer, often at their own facilities or clinical study sites.

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

Not applicable for this type of device. The ground truth for quantitative laboratory assays is typically established by reference methods or the performance of a cleared predicate device, not by expert consensus or physician review in the way it would be for imaging diagnostics. The "ground truth" here is the measurement obtained from the previously cleared single-module systems.

4. Adjudication method for the test set

Not applicable for this type of device. Adjudication methods (like 2+1, 3+1) are typically used in studies involving subjective interpretation (e.g., radiology reads) to resolve discrepancies among multiple expert reviewers. Here, the comparison is against quantitative measurements from a reference or predicate system.

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 submission is for an in vitro diagnostic (IVD) system that performs automated quantitative measurements, not an AI-assisted diagnostic imaging device that involves human readers.

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

This refers to the performance of the automated Alinity ci-series system. The studies described (precision and method comparison) are essentially standalone performance evaluations comparing the new multimodule system to the existing single-module systems. There is no "human-in-the-loop" component in the sense of an operator making diagnostic interpretations based on the output. Operators load samples and reagents and manage the system, but the analytical measurement itself is automated.

7. The type of ground truth used

The ground truth used for comparison in these non-clinical studies is the performance of the predicate devices (Alinity i System for Alinity i Total ß-hCG, and Alinity c System for Alinity c Glucose and ICT assays) in their single-module configurations. The goal was to demonstrate "equivalent performance" of the new multimodule configurations to these already cleared systems. This is a form of comparative effectiveness against a legally marketed predicate device.

8. The sample size for the training set

Not applicable. This document describes the validation of a laboratory instrument system and reagent kits through non-clinical performance studies (precision, method comparison), not an AI/machine learning model that requires a distinct "training set." The methodology involves biochemical reactions and optical/potentiometric detection, which are established principles, not learned from a dataset.

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

Not applicable, as there is no "training set" in the context of an AI/ML model for this device.

Ask a specific question about this device

EFAI Intelligent Cardiothoracic Ratio Assessment System (or iCTR) is a software for use by hospital and clinics to automatically assess the cardiothoracic ratio (CTR) of a chest X-ray image from the X-ray imager subject. The iCTR is designed to measure the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity and calculate the CTR of a chest X-ray image in posterior (PA) chest view using an artificial intelligence algorithm.

Intended users of the software are aimed to the physicians or other licensed practitioners in the healthcare institutions, such as clinics, hospitals, healthcare facilities, residential care facilities and long-term care services. The system is suitable for adults between 20 - 80 years of age.

Its results are not intended to be used on a stand-alone basis for clinical-decision making or otherwise preclude clinical assessment of cardiothoracic ratio (CTR) cases.

The iCTR is a non-invasive software medical device designed to be installed on the computer with specific system requirements. It is a radiological computer-assisted software system that automatically analyzes DICOM chest X-ray images in PA view and outputs the CTR through an artificial intelligence algorithm. The structure report includes a preview of the compressed chest X-ray image with the automatically-derived CTR result and annotation line, indicating the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity, and the trajectory of CTR records. The trajectory of CTR does not implement a predictive or prognostic feature.

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

Device Name: EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document does not explicitly present a formal "acceptance criteria" table with thresholds. Instead, it describes performance metrics that were achieved and deemed "met" or "greater than" a certain level. For clarity, I've inferenced the acceptance criteria based on these reported performance numbers.

Ask a specific question about this device

iCTmotor (WL-1) is intended for use in dental surgery and implantology. The main control unit is designed to operate a specific dental micro motor that drives dental handpieces to cut hard and soft tissues in the mouth and screw dental implants. iCTmotor (WL-1) is compatible with a handpiece equipped with connection according to ISO 3964.

iCTmotor (WL-1) is a software based driving engine that controls the speed of a specific dental micromotor. This device is optimized for dental implant procedures and user programmable parameters operate and control a dental handpiece for dental implant surgery. iCTmotor (WL-1) consists of a main controller unit, a charger, a foot controller, micro motor, cable, a water holder, tube holder, and micro motor holder. The main control unit operates the speed and torque of a dental micromotor that drives dental handpiece to cut tissues in the mouth and to screw dental implants. The main control unit is operated via a wireless foot pedal. The holders are used for placement of a water bag, a micro motor and a handpiece. The power cord delivers electric power to the main control unit.

The provided text is a 510(k) summary for the iCTmotor (WL-1), a dental device. It does not describe an AI/ML-based medical device or a study involving human readers or AI assistance. Therefore, it's not possible to provide acceptance criteria or a study description related to AI/ML device performance from this document.

The document focuses on demonstrating substantial equivalence to a predicate device (MASTERsurg / EXPERTsurg) through non-clinical performance testing. It highlights the device's intended use in dental surgery and implantology, specifically controlling a dental micromotor for cutting tissues and screwing dental implants.

The non-clinical tests performed are related to the physical and electrical characteristics of the device, as well as software validation for its control functions.

Key points from the document relevant to non-clinical performance testing (not AI/ML):

• Acceptance Criteria & Performance: The document states that "Performance testing was conducted according to ISO 14457:2012 to show that the device meets its design requirements and performs as intended." The specifications for the following parameters were met:

  • Rotating speed of micromotor
  • Torque of micromotor
  • Stop of micromotor
  • Rotating direction of micromotor
  • Irrigation amount

  The exact numerical acceptance criteria and the reported numerical performance for these parameters are not explicitly detailed in a table format within this summary, but the general claim is that they were "met." For example, under "Electrical Specification Motor (Speed)," the iCTmotor (WL-1) has a speed of "400- 40,000rpm," and the predicate has "300 - 40,000 rpm." While these are performance specs, the document doesn't present them as formal "acceptance criteria" vs. "reported performance" in a dedicated test. Instead, it asserts compliance with ISO 14457:2012.

• Sample Size and Data Provenance: Not applicable for an AI/ML context. For the non-clinical tests, the sample size would refer to the number of units tested, which is not specified but is typically a small engineering sample or a representative batch. The data provenance is from the manufacturer's internal testing.

• Experts and Ground Truth: Not applicable in the context of AI/ML interpretation. The "ground truth" for these performance tests is the engineering specification for each parameter (e.g., a specific RPM range, torque value).

• Adjudication Method: Not applicable. Performance testing of physical devices is typically a direct measurement against a specification.

• MRMC Comparative Effectiveness Study: Not applicable. This study focuses on a hardware device, not an AI/ML algorithm.

• Standalone Performance: The "performance testing" described (rotating speed, torque, etc.) represents the standalone performance of the device's control system and motor.

• Type of Ground Truth: The ground truth for this device's performance testing is based on engineering specifications and established international standards (ISO 14457:2012) for dental handpieces/micromotors.

• Training Set Sample Size: Not applicable. This is a hardware device with software control, not an AI/ML model that requires training data. The software was subjected to verification and validation as per FDA guidance for software in medical devices, but this is distinct from AI/ML model training.

• Ground Truth for Training Set: Not applicable, as there is no AI/ML training set in this context. Software "ground truth" for verification and validation typically means that the software functions as designed according to its requirements specification.

In summary, this document is a 510(k) premarket notification for a traditional medical device (iCTmotor (WL-1)) and does not contain information about AI/ML acceptance criteria or a study proving an AI/ML device meets such criteria.

Ask a specific question about this device

The Alinity c ICT (Integrated Chip Technology) is used for the quantitation of sodium, potassium, and chloride in human serum, plasma, or urine on the Alinity c analyzer.

Sodium measurements are used in the diagnosis and treatment of aldosteronism (excessive secretion of the hormone aldosterone), diabetes insipidus (chronic excretion of large amounts of dilute urine, accompanied by extreme thirst), adrenal hypertension, Addison's disease (caused by destruction of the adrenal glands), dehydration, inappropriate antidiuretic hormone secretion, or other diseases involving electrolyte imbalance.

Potassium measurements are used to monitor electrolyte balance in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels.

Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.

The Alinity c ICT Sample Diluent is a reagent kit containing Reagent 1 (Buffer). It is used with the Alinity c ICT Serum Calibrator and Alinity c ICT Urine Calibrator on the Alinity c analyzer. The system utilizes ion-selective electrodes (ISE) for sodium, potassium, and chloride, which develop an electrical potential across membranes selective to each ion. This voltage is compared to calibrator voltages and converted into ion concentration. The methodology is Ion-selective electrode diluted (Indirect) and the detection is Potentiometric.

The provided document describes the Alinity c ICT Sample Diluent, a device used for the quantitation of sodium, potassium, and chloride in human serum, plasma, or urine. The document mainly focuses on non-clinical performance studies to demonstrate substantial equivalence to a predicate device, rather than a clinical study with acceptance criteria in the traditional sense of diagnostic accuracy or reader performance.

Here's an analysis of the provided information based on your requested criteria:

The studies presented are primarily analytical performance studies (precision, linearity, interference, method comparison, and tube type equivalency) to demonstrate the device's accuracy and reliability compared to a predicate device. The acceptance criteria are internal, predefined thresholds for these analytical performance characteristics.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the country of origin for the data or whether the studies were retrospective or prospective, for patient samples. The studies are described as "Within-Laboratory Precision" and "Method Comparison," implying they were conducted in a controlled laboratory setting.

• Precision Studies (Test Set):
  • Serum Samples: For Sodium, Potassium, and Chloride assays, each control level (3 levels) typically had n=243 to n=252 measurements per control lot. For patient panels, n=485 to n=498 measurements were performed.
  • Urine Samples: For Sodium, Potassium, and Chloride assays, each control level (2 levels) typically had n=240 measurements per control lot. For patient panels, n=479 to n=480 measurements were performed.
• Method Comparison (Test Set):
  • Sodium (Serum): n=141
  • Sodium (Urine): n=101
  • Potassium (Serum): n=122
  • Potassium (Urine): n=107
  • Chloride (Serum): n=120
  • Chloride (Urine): n=112
  • Data Provenance: "Human serum and urine specimens that spanned the measuring interval of the assay were evaluated." The specific origin (e.g., country) is not mentioned. These are likely prospective samples collected for testing.
• Interference Studies (Test Set): Not explicitly stated, but typically these studies use spiked samples or samples with naturally elevated interferents.
• Tube Type Equivalency (Test Set): Samples were collected from a minimum of 40 donors.

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

This type of device (in-vitro diagnostic for electrolyte measurement) does not typically involve human experts establishing ground truth in the way medical imaging or pathology devices do. The "ground truth" for these analytical studies is established by:

• Reference Methods: For calibrator concentrations, "flame photometry calibrated against NIST Standard Reference Material" and "titration with silver calibrated against NIST Standard Reference Material" were used.
• Predicate Device: For method comparison, the "ARCHITECT ICT Sample Diluent Sodium, Potassium, and Chloride" is used as the comparator method, implying its results are considered the established values for comparison.
• Known Concentrations: For precision, linearity, and interference studies, samples are often prepared with known concentrations or spiked with specific substances.

Therefore, the concept of "experts establishing ground truth" as in qualitative diagnostic interpretation is not applicable here.

4. Adjudication Method for the Test Set

Not applicable for this type of analytical performance study. Adjudication methods like 2+1 or 3+1 are used for qualitative assessments, typically when human interpretations are being compared, or when there's disagreement among experts on a ground truth.

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

No. This is an analytical performance study for an in-vitro diagnostic instrument component, not a diagnostic imaging or AI-driven interpretive device. Therefore, a MRMC comparative effectiveness study involving human readers with and without AI assistance is not relevant.

6. Standalone (Algorithm Only) Performance Study

Yes, implicitly. The entirety of the reported Nonclinical Performance (precision, linearity, interference, method comparison, and tube type equivalency) represents the standalone performance of the Alinity c ICT Sample Diluent device on the Alinity c analyzer. There is no "human-in-the-loop" aspect to the measurement of electrolyte concentrations by this automated system.

7. Type of Ground Truth Used

• Reference Methods: NIST Standard Reference Materials, flame photometry, and titration with silver were used to establish the ground truth for calibrator concentrations.
• Comparator (Predicate) Device: The ARCHITECT ICT Sample Diluent was used as the comparator for method comparison studies.
• Known Concentrations/Spiked Samples: For precision, linearity, and interference studies, samples with known or precisely prepared concentrations were used.

8. Sample Size for the Training Set

This document does not describe the development of an algorithm that would require a separate "training set" in the context of machine learning. The device is an in-vitro diagnostic reagent and system based on established ion-selective electrode technology. Its performance is evaluated through analytical studies, not by training a model on a dataset.

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

Not applicable. As explained in point 8, there is no "training set" in the machine learning sense for this device.

Ask a specific question about this device

The Philips iCT CT System 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 iCT 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 Philips iCT is currently available in two system configurations, iCT and iCT SP. Identical to the predicate, the Philips iCT CT System produces cross-sectional images of the body head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. The main components (detection system, the reconstruction algorithm, and the x-ray system) that are used in the Philips iCT 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 has an aperture of 700mm and consists of the following internal units:
   a. Stator a fixed mechanical frame that carries hardware and software.
   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. The generator has a power rating of 100kW with optional 120kW.
   d. Data Measurement System (DMS) a detectors array, fixed to the rotor frame. The DMS provides 8cm of coverage (4cm for the iCT SP configuration) and up to 256 slices (128 slices for the iCT SP configuration).The gantry offers 0.3 second rotation time (with optional 0.27s rotation).
2. Patient Table (aka Couch or Support) carries the patient in and out through the Gantry bore synchronized with the scan. There are three available patient supports:
   a. Standard Table provides maximum scannable range of 1750mm, longitudinal speed of 0.5mm/s-185mm/s and a maximum load capacity of 450 lbs.(204kg)
   b. Bariatric Table provides maximum scannable range of 1750mm, longitudinal speed of 0.5mm/s-185mm/s and a maximum load capacity of 650 lbs.(295kg)
   c. Extended Table provides maximum scannable range of 2100mm, longitudinal speed of 0.5mm/s-185mm/s and a maximum load capacity of 450 lbs.(204kg)
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.
4. Monitors
5. Software features to view and analyze images.

This document is a 510(k) premarket notification for the Philips iCT CT System, which is a Computed Tomography X-Ray System. The document details the device's indications for use, description, and a comparison with a predicate device (Philips Brilliance Volume) to establish substantial equivalence.

Based on the provided text, the Philips iCT CT System is a Computed Tomography (CT) X-Ray System. The document outlines that the system is intended to produce images of the head and body by computer reconstruction of x-ray transmission data. It also explicitly states its indication for "low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer."

Regarding acceptance criteria and the study proving the device meets these criteria:

The document focuses on demonstrating substantial equivalence to a predicate device (Philips Brilliance Volume) rather than presenting a performance study with explicit acceptance criteria for a novel AI/ML-driven diagnostic device. This means the 510(k) submission primarily relies on comparing the design, technology, and specified performance parameters of the new device to an already legally marketed device, and showing that any differences do not raise new questions of safety or effectiveness.

Therefore, many of the requested elements for an AI/ML diagnostic device study (like sample size for test sets, expert adjudication, MRMC studies, standalone performance with specific metrics like sensitivity/specificity, or ground truth establishment for novel findings) are not detailed or applicable in the traditional sense for this 510(k) submission. This submission is for hardware (CT scanner) with associated software for image reconstruction, not primarily a sophisticated AI/ML diagnostic algorithm operating on those images for making clinical decisions beyond image acquisition and display.

Here's an attempt to address the requested information based on the provided document:

1. Table of acceptance criteria and the reported device performance:

Since this is a 510(k) for a CT system demonstrating substantial equivalence, the "acceptance criteria" are implicitly met by showing that the proposed device's characteristics are either identical to or comparable to the predicate device, and any changes do not adversely affect safety or effectiveness. The document presents a comparative table, not a table of specific numerical performance acceptance criteria for a diagnostic algorithm.

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

The document mentions "Design Verification planning and testing was conducted at the sub-system and at the system level." It also states "Design validation of user needs and intended use was conducted via simulated use testing with production equivalent Philips iCT CT Systems."

• Test Set Sample Size: Not specified in terms of patient data or clinical cases for diagnostic performance. The document refers to "system and sub-system level verification" and "simulated use testing." This suggests engineering and functional testing rather than a large-scale clinical performance study on a specific number of patient scans.
• Data Provenance: Not specified. Given it's a Philips product for a global market, the data provenance for engineering/simulated testing is likely internal R&D, not necessarily specific patient data sets from particular countries. "Retrospective or prospective" is not applicable in the context of hardware/software functional testing described.

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

Not applicable. This 510(k) is not for an AI/ML diagnostic algorithm that requires expert-established ground truth on clinical images for its performance evaluation. The "ground truth" for a CT system's performance in this context would be its physical specifications, image quality metrics (like spatial resolution, contrast resolution, noise), and safety parameters (radiation dose). These are typically verified against engineering specifications, phantoms, and regulatory standards, not clinical ground truth established by experts.

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

Not applicable. No clinical image or diagnostic performance adjudication is described.

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

Not applicable. This submission is for a CT hardware system, not an AI-assisted diagnostic tool that integrates with human readers. The "low dose CT lung cancer screening" indication refers to the capability of the scanner, and refers to existing clinical literature (National Lung Screening Trial) as evidence for the efficacy of low-dose CT screening in general, not specific AI augmentation.

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

Not applicable for a diagnostic algorithm. The device, the Philips iCT CT System, is the standalone imaging system for image acquisition and reconstruction. Its performance is evaluated against engineering specifications and industry standards.

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

The "ground truth" for the device's technical performance (e.g., image quality, scan range, rotation times) would be established by:

• Engineering specifications: The designed parameters of the CT system components.
• Physical phantoms: Standardized objects used to measure image quality characteristics (e.g., spatial resolution, contrast-to-noise ratio, slice thickness accuracy).
• Calibration procedures: Ensuring the system's measurements are accurate.
• Compliance with international standards: (e.g., IEC 60601 series for medical electrical equipment safety and performance).

For the lung cancer screening indication, the document refers to "clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature." This means the ground truth for the clinical utility of low-dose CT screening, in general, is based on outcomes data from large clinical trials. The device's "acceptance" for this indication is based on its capability to perform scans at low dose within established protocols, implying it meets the technical requirements to participate in such screening programs.

8. The sample size for the training set:

Not applicable. This is not for a machine learning model that requires a "training set" of clinical data in the typical sense.

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

Not applicable. No machine learning training set is described.

In summary: This 510(k) document is a regulatory submission for a general-purpose CT scanner. Its "acceptance criteria" and "proof" primarily revolve around demonstrating that its technical specifications, design, and functionality are substantially equivalent to a previously cleared predicate device, and that any modifications (like extended scan range, increased slices, or removal of gantry tilt) do not compromise safety or effectiveness. The inclusion of "low dose CT lung cancer screening" as an indication relies on the device's ability to perform scans compatible with established clinical guidelines, rather than presenting novel AI performance data for nodule detection or characterization.

Ask a specific question about this device

The "Brilliance iCT" 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, components, and accessories.

The Brilliance iCT 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 x-ray transmission data is reconstructed by computer into cross-sectional 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 submitted text describes a 510(k) summary for the Brilliance iCT, a Computed Tomography (CT) X-Ray System. The summary focuses on demonstrating the substantial equivalence of a modified version of the Brilliance iCT to its predicate device, "Brilliance Volume," by highlighting technical characteristics and performance data.

Here's an analysis of the provided information, structured to address your specific questions. It's important to note that the document is a 510(k) summary for a CT scanner, not necessarily an AI-powered diagnostic device in the modern sense. Therefore, many of your questions related to AI-specific studies (like MRMC, training sets, ground truth for AI, etc.) are not directly applicable or detailed in this type of submission for a CT hardware modification.

Acceptance Criteria and Device Performance

The study primarily focuses on demonstrating that the modified Brilliance iCT continues to meet established performance standards for CT systems, particularly IEC 61223-3-5:2004. The acceptance criteria are implicit in compliance with this standard, which outlines specific acceptance tests for the imaging performance of CT X-ray equipment.

Table of Acceptance Criteria and Reported Device Performance:

Detailed Responses to Specific Questions:

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

   • See the table above. The acceptance criteria are based on compliance with IEC 61223-3-5:2004, and the performance is stated as meeting this standard for each listed measurement. A clinical evaluation also confirmed diagnostic image quality.

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

   • The document mentions "bench tests" for the technical performance measurements. These typically involve phantoms and laboratory setups, not human patient data in the sense of a clinical trial.
   • For the "Clinical evaluation," the sample size of cases/images is not specified.
   • The data provenance (country of origin, retrospective/prospective) is not mentioned for either bench tests or clinical evaluation.

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):

   • For the technical performance measurements (CT Number, Noise, Resolution, etc.), the "ground truth" is established by physical measurement standards and the test methodology dictated by IEC 61223-3-5:2004, not by human experts.
   • For the "Clinical evaluation," it states "images... have been evaluated by a radiologist as being of diagnostic quality." The number is one radiologist, and their specific qualifications (e.g., years of experience) are not provided.

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

   • Given that only "a radiologist" is mentioned for the clinical evaluation, it implies no multi-reader adjudication method was used. For the technical bench tests, adjudication by human experts 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:

   • No MRMC study was done or reported. This submission pertains to a modification of a CT scanner's hardware (detection array and supporting software), not an AI-powered diagnostic tool in the sense of one that assists human readers. The clinical evaluation mentioned is a basic check for diagnostic quality of the reconstructed images.

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

   • This question is not applicable in the context of this device. The Brilliance iCT is a CT scanner, which provides images for human interpretation, not an algorithm providing a standalone diagnostic output. The "algorithm only" performance refers to the image reconstruction algorithm's output, which is then clinically evaluated by a radiologist. The technical bench tests assess the fundamental image quality parameters, which are (in a way) "standalone" performance metrics of the hardware and reconstruction.

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

   • For the technical performance measurements, the "ground truth" is based on the physical properties of phantoms and measurement standards defined by IEC 61223-3-5:2004.
   • For the clinical evaluation, the ground truth for "diagnostic quality" appears to be the subjective assessment of a single radiologist. This is not equivalent to pathology or outcomes data.

8. The sample size for the training set:

   • Not applicable / Not mentioned. This document describes the modification of a CT scanner hardware and its performance, not an AI algorithm that would typically require a training set in the sense of machine learning. The "supporting software" mentioned would be for image reconstruction and system control, not a learned model.

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

   • Not applicable / Not mentioned for the same reasons as point 8.

Ask a specific question about this device

The iCT device with sliding gantry is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from either the same axial plane taken at different angles or spiral planes* taken at different angles.

(*spiral plane: the axial planes resulted from the continuous rotation of detectors and x-ray tube, and the simultaneous translation of the sliding gantry).

iCT is a whole body x-ray computed tomography (CT) scanner. It combines a standard CT gantry with a ceiling mounted suspension and drive mechanism to move the gantry horizontally during image acquisition. The standard CT gantry features a continuously rotating tub-detector system and functions according to the fan beam principle. The ceiling mounted suspension and drive mechanism allows iCT to be moved along rails for storage or to share the iCT between multiple rooms. The ceiling mounted system also provides precise horizontal movement that is integrated with the CT scan control. During image acquisition, the iCT drive mechanism translates the CT gantry while the patient table remains stationary. Moving the gantry allows the patient to remain stationary instead of translating the patient relative to the gantry as is required with fixed gantry systems. iCT may be used with commercially available patient tables, including surgical tables, that meet the appropriate size and x-ray transmission characteristic requirements.

iCT leverages the previously cleared SOMATOM Definition, Model AS/AS+ (K081022) gantry, power supply and operator console components, including the syngo software platform and compatible syngo applications. iCT produces CT images in DICOM format. The syngo platform is able to run optional postprocessing applications.

Here's a breakdown of the acceptance criteria and study information for the iCT device, 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: The document explicitly states that "sample clinical images are unnecessary to support substantial equivalence in this case and instead testing relied on laboratory studies." This implies that clinical images were NOT used as a test set. The testing was done using "high precision phantoms." The specific number of phantoms or scans performed is not provided.
• Data Provenance: Not applicable, as clinical data was not used for the test set.

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

• Not applicable as the testing was conducted using "high precision phantoms" and laboratory studies, not clinical data and expert interpretation.

4. Adjudication Method for the Test Set

• Not applicable, as the testing was conducted using "high precision phantoms" and laboratory studies, not human evaluation of clinical data.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document states that "sample clinical images are unnecessary to support substantial equivalence in this case and instead testing relied on laboratory studies." This indicates the evaluation was technical and mechanical, not clinical or involving human readers.

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

• Yes, the primary evaluation was a standalone technical/mechanical evaluation of the iCT system's performance metrics (image quality, z-axis accuracy, gantry stability) against the specifications of the predicate device using phantoms. This is effectively a "standalone" assessment of the device's physical and image acquisition capabilities without human interpretation of clinical images.

7. The Type of Ground Truth Used

• The ground truth was established by the specifications and performance characteristics of the predicate device, specifically the SOMATOM Definition, Model AS/AS+ with the sliding gantry package. The iCT's performance was measured against these established technical benchmarks using "high precision phantoms."

8. The Sample Size for the Training Set

• Not applicable. The iCT is leveraging a previously cleared CT gantry, power supply and operator console components (SOMATOM Definition, Model AS/AS+), including its syngo software platform and compatible syngo applications. The iCT itself is primarily a modification concerning the physical mounting and movement of this existing CT technology (ceiling rails vs. floor rails). Therefore, it doesn't appear to involve its own separate "training set" in the context of an AI/algorithm. The core imaging algorithms are assumed to be from the predicate device.

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

• Not applicable, as a separate training set for the iCT's distinct features (ceiling mounted gantry movement) is not described, and the core imaging software/algorithms are inherited from the cleared predicate device. The information provided focuses on the physical and technical performance of the modified gantry system.

Ask a specific question about this device

The ICTA software is intended as a review tool to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings (surface or intracranial) that may correspond to electrographic seizures, in order to assist qualified clinical practitioners, who will exercise professional judgment in using the information, in the assessment of EEG traces.

• Surface recordings must be obtained with full montage according to the standard 10/20 . system.
• Intracranial recordings must be obtained with depth electrodes (strips and/or grids). .
  This device does not provide any diagnostic conclusion about the patient's condition to the user.

ICTA is a software only product. It runs on a personal computer and requires no specialized hardware. It identifies electroencephalographic activity that might correspond to seizures (referred as "events"). These events are then reviewed, accepted, modified and/or deleted by the qualified medical practitioner. The software does not make any final decisions that result in any automatic diagnosis or treatment. The EEG input is read from a file on the personal computer (or available across the network).
ICTA employs Bayesian formulation to provide a detection variable based on the probabilities that a given section of EEG contains a seizure-like activity. The a priori probabilities that a certain set of features represent seizure or non-seizure data were computed from the training data set. These probabilities are used by the detection method for all seizure detections.
The software has two components: ICTA-S for analysis of surface EEG recordings and ICTA-D for analysis of intracranial recordings. Whether a particular module is active is determined by the user. The user also determines parameters that are needed for the algorithm to perform its intended task. None of the components is responsible for data acquisition, review or any other function different from analysis.

Here's a breakdown of the acceptance criteria and study details for the ICTA device, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for ICTA were established through a comparison with a predicate device (NeuroWorks Seizure Detector, K090019) and the "gold standard" of expert neurophysiologists. The key performance metrics are Positive Percent Agreement (PPA) and False Detection Rate (FDR).

Note: The document states "Equivalent" for both metrics when comparing to the predicate, even though the FDRs are numerically different. This suggests the FDA considers these values acceptable within the context of seizure detection assistance tools.

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

• ICTA-S (Surface EEG):
  • Number of Seizures: 615
  • Total Number of Patients: 102
  • Total Number of Hours: 395
  • Data Provenance: Retrospective, patients with medically refractory seizures admitted to an Epilepsy Monitoring Unit. The specific country of origin is not explicitly stated, but Natus Medical Incorporated DBA Excel-Tech Ltd. is based in Oakville, Ontario, Canada.
• ICTA-D (Intracranial EEG):
  • Number of Seizures: 429
  • Total Number of Patients: 93 (57 Male, 36 Female)
  • Total Number of Hours: 619 hours
  • Data Provenance: Retrospective, adult patients seen for routine clinical evaluation at Epilepsy Monitoring Units of Toronto Western General Hospital (Canada) and NewYork-Presbyterian Hospital (USA).

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

• Number of Experts: Three independent, blinded EEG experts were used for both ICTA-S and ICTA-D studies.
• Qualifications: All experts were board-certified Neurophysiologists (or neurologists/epileptologists). The document does not specify their years of experience.

4. Adjudication Method for the Test Set

• Adjudication Method: A "majority rule (at least 2 out of 3)" was applied. This means that for a seizure to be considered a "true" electrographic seizure (ground truth), at least two of the three independent experts had to agree on its presence.

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

• The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The study focuses on evaluating the standalone performance of the ICTA algorithm against a human-established ground truth and comparing it to a predicate device's reported performance.

6. Standalone Performance Study

• Yes, a standalone (algorithm only without human-in-the-loop performance) study was done. The entire clinical testing section describes the evaluation of the ICTA-S and ICTA-D algorithms' performance (PPA and FDR) independently against the ground truth established by the expert panel. The results presented in the tables (e.g., PPA 75% / FDR 2.0 FP/h for ICTA-S) are for the algorithm in standalone mode.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus. Specifically, electrographic seizures identified by a panel of three board-certified Neurophysiologists, with a majority rule for final determination.

8. Sample Size for the Training Set

• The document states that Bayesian formulation was used, and "The a priori probabilities that a certain set of features represent seizure or non-seizure data were computed from the training data set."
• However, the specific sample size for the training set is not provided in the summary.

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

• The document states that probabilities were computed from the "training data set." It does not explicitly detail the method for establishing ground truth for this training set. However, given the nature of the device and the methods described for the test set, it is highly probable that the ground truth for the training set was also established through expert review and annotation of EEG recordings, likely by qualified medical practitioners. The summary implies that this training data was used to establish the "a priori probabilities" for the Bayesian model.

Ask a specific question about this device

Infrared Ear Thermometer (Dr. Schven ICT-1000) is intended for an electronic clinical thermometer using an infrared sensor to detect body temperature from the auditory canal in the neonatal, pediatric and adult population.

Not Found

The provided text is a 510(k) premarket notification letter from the FDA regarding an Infrared Ear Thermometer (Dr. Schven ICT-1000). It makes a "substantial equivalence" determination but does not contain any information about acceptance criteria, device performance studies, sample sizes, expert qualifications, or ground truth methods.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study proving the device meets them based on the provided input.

Ask a specific question about this device