Search Results

The FUJIFILM Bronchoscope Model EB-530P is intended for the observation, diagnosis, and endoscopic treatment of the trachea and bronchial tree.

The FUJIFILM Bronchoscope Model EB-530P is comprised of three general sections: a control/ operating section, an insertion and an umbilicus. The control/operating section controls the angulation (up/down) of the distal end of the endoscope. The insertion portion contains glass fiber bundles, several channels and a complementary charged coupled device (CCD) image sensor in its distal end. The channels in the insertion portion assist in delivering air/suction as well as endoscope accessories, such as forceps. The glass fiber bundles allow light to travel through the endoscope and emit light from the tip of the insertion to illuminate the body cavity. This provides enough light to the CCD image sensor to capture an image and display it on the monitor. The umbilicus consists of electronic components needed to operate the endoscope when plugged in to the video processor and the light source.

The subject device is used in combination with FUJIFILM's video processors, light sources and peripheral devices such as monitor, printer, foot switch, and cart. All of these combinations were previously cleared in K122535.

The provided document is a 510(k) premarket notification for a medical device, the FUJIFILM Bronchoscope Model EB-530P. This type of submission aims to demonstrate substantial equivalence to a legally marketed predicate device, rather than proving the device meets specific performance acceptance criteria for a new clinical indication.

The document does not describe acceptance criteria in the way one would typically find for a medical device that uses artificial intelligence (AI) or requires a clinical performance study with defined metrics like sensitivity, specificity, or accuracy. It's a bronchoscope, which is a physical instrument for observation, diagnosis, and endoscopic treatment.

Therefore, many of the requested bullet points, such as those related to AI performance, ground truth, expert adjudication, and MRMC studies, are not applicable to this type of device submission.

However, I can extract information related to performance testing and comparison to the predicate device, which serves as the basis for the FDA's substantial equivalence determination.

Based on the provided document, here's what can be extracted and what cannot:

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

   • Acceptance Criteria: Not explicitly stated as pass/fail thresholds in the typical sense of clinical performance metrics. Instead, the "acceptance" is implicitly that the device performs functionally as intended and safely, similar to or better than the predicate device.
   • Reported Device Performance: The document lists several characteristics and states implicitly that the device "met performance specifications" or "has substantially equivalent performance" to the predicate. The "Performance Data" section (page 4) lists the types of tests conducted:
     • Electrical safety
     • Biocompatibility
     • Cleaning, high-level disinfection, and EO sterilization reprocessing validation
     • Endoscope specific testing (ISO standards)
     • Additional testing: Field of view, Bending capability, Rate of suction, Working length, Diameter of forceps channel, Viewing direction, LG Output.

   Table (Reconstructed from "Performance Data" and "Table 7.1: Comparison"):

   Acceptance Criteria Category/Characteristic	Device Performance (How it meets "acceptance")	Unclear if specific quantitative thresholds were used beyond "met specifications" or "comparable to predicate."
   Electrical Safety	Evaluated using ANSI/AAMI ES 60601-1:2012, IEC 60601-1-2:2007, IEC 60601-1-6:2013, and IEC 60601-2-18:2009.	Implied "met standards."
   Biocompatibility	Evaluated using ISO 10993-1:2009, ISO 10993-5:2009, and ISO 10993-10:2010.	Implied "met standards" and "material changes...raise no new concerns."
   Reprocessing Validation	Cleaning, high-level disinfection, and EO sterilization were performed.	Implied "validated reprocessing instructions."
   Endoscope Specific Testing	Conducted using ISO 8600-1:2015, ISO 8600-3:1997, and ISO 8600-4:2014.	Implied "met standards."
   Field of View	120 degrees (Same as predicate)	Implicitly, "Same as predicate device" means it meets performance.
   Bending Capability (Up)	180 degrees (Same as predicate)	Implicitly, "Same as predicate device" means it meets performance.
   Bending Capability (Down)	130 degrees (Same as predicate)	Implicitly, "Same as predicate device" means it meets performance.
   Rate of Suction	"Met performance specifications"	Not quantified in document.
   Working Length	600mm (Same as predicate)	Implicitly, "Same as predicate device" means it meets performance.
   Diameter of Forceps Channel	1.2mm (Predicate: 2.0mm)	Although different, implied "met performance specifications" for the new design without raising safety/effectiveness issues.
   Viewing Direction	Forward/ 0 degree (Same as predicate)	Implicitly, "Same as predicate device" means it meets performance.
   LG Output	"Met performance specifications"	Not quantified in document.
   Distal End Diameter	3.8mm (Predicate: 4.9mm)	Different, but considered "minor dimensional differences" that "raise no new issues of safety or effectiveness."
   Flexible Portion Diameter	3.8mm (Same as predicate for proposed, but 4.9mm for predicate)	Different, but considered "minor dimensional differences."
   Maximum Insertion Diameter	4.2mm (Predicate: 5.9mm)	Different, but considered "minor dimensional differences."
   Total Length	890mm (Predicate: 870mm)	Different, but considered "minor dimensional differences."

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

   • Sample Size: Not specified quantitatively for any of the performance tests (e.g., how many bronchoscopes were tested for bending capability). These are likely bench tests of physical characteristics.
   • Data Provenance: The tests are "bench testing data" (page 7), implying laboratory testing of the device itself, not clinical data from patients. No country of origin for data is specified, as it's not typical patient data. The tests are prospective as they are conducted for the specific submission.

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. This is a physical bronchoscope, not an AI or diagnostic imaging device that requires expert ground truth establishment for clinical performance. The "ground truth" for its physical specifications comes from engineering measurements and adherence to international standards.

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

   • Not Applicable. No human adjudication of results in the sense of clinical interpretation is described. Physical and electrical tests are verified against defined standards and specifications.

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 is not an AI device or a diagnostic device where human perception is assisted by AI.

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

   • Not Applicable. There is no algorithm mentioned in this submission.

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

   • Not Applicable. For a physical device like a bronchoscope, the "ground truth" for performance is based on engineering specifications, physical measurements, and adherence to established international standards (e.g., ISO, IEC).

8. The sample size for the training set:

   • Not Applicable. This device does not involve a "training set" in the context of machine learning or AI.

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

   • Not Applicable. As above, no training set for an AI/ML algorithm is involved.

Ask a specific question about this device

SP-900:

The FUJIFILM Ultrasonic Processor SP-900 is intended to be used in combination with FUJIFILM Ultrasonic Probe, video processor, light source, monitor, recorder, and various peripheral devices. The product is intended to provide ultrasonic images of the gastrointestinal tract, biliary and pancreatic ducts and surrounding organs, airways and tracheobronchial tree for observation, recording and to aid in diagnosis during endoscopic evaluation.

PB2020-M:

This product is a medical ultrasonic probe. It is intended for the observation and diagnosis of the gastrointestinal tract, biliary and pancreatic ducts and surrounding organs, airways and tracheobronchial tree under the management of physicians at medical facilities.

The FUJIFILM Ultrasonic Processor SP-900 and Ultrasonic Probe PB2020-M consists of five components: 1) processor (SP-900), 2) probe (PB2020-M), 3) control pad (CP-900), 4) scanner (RS-900), and 5) power cord. The SP-900 generates ultrasound waves into the body cavity by driving the ultrasonic transducer installed in the PB2020-M, which is inserted through the forceps channel of an endoscope. The SP-900 processes the reflected ultrasound signals which the PB2020-M receives in the body cavity and further converts the processed electrical signals into video signals to relay to a monitoring system. The SP-900 can acquire and display real-time ultrasound data in B-mode. The CP-900 is used to control operational features of the RS-900 provides the mechanical scanning for acquiring a two-dimensional image. The power cord supplies power to the SP-900.

The provided document is a 510(k) summary for the FUJIFILM Ultrasonic Processor SP-900 and Ultrasonic Probe PB2020-M. It primarily focuses on demonstrating substantial equivalence to a predicate device, rather than proving that the device meets specific acceptance criteria through a clinical study or performance efficacy study with a test set, ground truth, or expert readers.

Therefore, many of the requested details about acceptance criteria, study design, sample sizes for test/training sets, expert involvement, and ground truth establishment are not present in this document. The document outlines bench testing to ensure the device functions as intended and meets established specifications, particularly regarding image quality and performance, but it does not describe a study involving human readers or a defined set of diagnostic tasks.

Based on the information provided, here's what can be extracted and what is missing:

Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in terms of specific performance metrics for diagnostic accuracy (e.g., sensitivity, specificity) against a ground truth. Instead, it focuses on demonstrating substantial equivalence to an existing predicate device (Olympus EU-ME2 and UM-S20-17S). The "performance" reported is primarily the device's conformance to safety and performance standards, and its ability to produce images and function as intended during bench testing.

Table of Acceptance Criteria and Reported Device Performance:

Study Details (Based on available information):

1. Sample size used for the test set and the data provenance:
   This document describes bench testing and software validation, not a clinical or performance study with a "test set" of patient data in the typical sense for evaluating diagnostic accuracy. No sample size for a patient data test set is mentioned. The data provenance is not applicable in the context of device function testing rather than diagnostic performance evaluation.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
   Not applicable. No "ground truth" establishment for diagnostic accuracy is described, as the evaluation was of device functionality and safety, not diagnostic performance on patient cases.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
   Not applicable. There was no test set requiring expert adjudication for diagnostic ground truth.

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. This document does not mention any MRMC study or AI assistance. The device is an ultrasonic processor and probe, not an AI-powered diagnostic tool requiring human-in-the-loop performance studies.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
   Not applicable. The device is hardware (ultrasonic processor and probe), not an algorithm that performs standalone diagnostic functions. Its performance was tested as a system.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
   Not applicable. No ground truth for diagnostic accuracy was used. The "ground truth" for the engineering tests would be the established performance specifications and safety standards defined in the relevant IEC and ISO standards (e.g., acoustic output limits, electromagnetic compatibility, software integrity).

7. The sample size for the training set:
   Not applicable. There is no mention of machine learning or an AI model requiring a training set.

8. How the ground truth for the training set was established:
   Not applicable, as there was no training set for an AI/ML model.

In summary: This 510(k) summary focuses on demonstrating the substantial equivalence of a new ultrasonic imaging device to existing legally marketed devices, primarily through engineering and safety testing. It attests that the device meets relevant performance and safety standards and its functionality is comparable to its predicate. It does not include details about clinical performance studies, diagnostic accuracy, or human reader involvement, as these types of studies are typically required for devices with more subjective or interpretative outputs, or for AI-based diagnostic tools.

Ask a specific question about this device

The Fujifilm Digital Mammography System, ASPIRE Cristalle (FDR MS-3500) generates full-field digital mammography images that can, as other full-field digital mammography systems, be used for screening and diagnosis of breast cancer and is intended for use in the same clinical applications as traditional screen-film mammography systems.

The ASPIRE Cristalle (K133972) (FDR MS-3500) is an integrated FFDM system combining an X-ray system made by Fujifilm with Fujifilm's a-Se detector and FDR-AWS3000 acquisition workstation (AWS). The system creates digital mammography images by direct capture of x-ray energy using a detector of Fujifilm design utilizing an a-Se photo-conversion layer with TFT readout circuitry to acquire image data and transfer images to the AWS for automated post processing, technologists' preview and QC, and subsequent transmission to hard copy printers, diagnostic workstations and archiving systems. The ASPIRE Cristalle provides powered compression and AEC modes.

The subject of this premarket notification is a software upgrade to the predicate device. The hardware is unchanged. The software is unchanged with the exception that the subject device incorporates improved grayscale and frequency processing software named Dynamic Visualization II for Mammography (DVIIm) in the FDR-AWS3000 image acquisition software.

DVIIm image processing consists of EDR2m and MFP2 image processing.

• . Exposure Data Recognition 2 for mammography (EDR2m) = the EDR2m algorithm analyzes image data and identifies various anatomic structures using a statistical estimation method as opposed to original EDR's histogram analysis method. EDR2m determines the parameters to optimize brightness and contrast of the image based on the analysis result.
• . Multi-Object Frequency Processing 2 (MFP2) - MFP2 optimizes the brightness, contrast and sharpness of the image using parameters determined by the EDR2m processing. MFP2 uses additional low frequency tables and a combination of automatic and preset dynamic range control operations.

DVIIm takes full advantage of the wide range of image data acquired with the high sensitivity of Fujifilm's advanced detector technologies. DVIIm provides improved contrast and density stability throughout the entire exposure region and achieves improved visibility across a wide range of breast compositions including the presence of implants.

Here's an analysis of the provided text regarding the ASPIRE Cristalle device, focusing on acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes a software upgrade to an existing device (ASPIRE Cristalle with DVIIm image processing). The "acceptance criteria" here are framed within the context of demonstrating substantial equivalence to the predicate device and meeting regulatory guidance for Full-Field Digital Mammography (FFDM) systems. The reported performance refers to the outcomes of the clinical image attribute review.

• Phantom Testing (Section 8 Physical Laboratory Testing) | Applicable phantom testing results have been provided in accordance with the guidance. (Specific numerical acceptance criteria for phantom testing are not detailed in this summary, but the general statement indicates compliance). Additionally, "ASPIRE Cristalle maintains the confidentiality, integrity and availability in accordance with Section 6 of the Content of Premarket Submissions for Management of Cybersecurity in Medical Devices". |
  | Premarket Notification Guidance for FFDM Systems (March 27, 2012):
• Clinical Image Attribute Review (Section 6)
  Implicit Criterion: Provide sufficiently acceptable image quality for mammographic use across various breast compositions and exposure modes. | A clinical image attribute review was conducted by independent mammographic radiologists.
  Conclusion: "The ASPIRE Cristalle provides sufficiently acceptable image quality for mammographic use."
  Specifically, DVIIm "provides improved contrast and density stability throughout the entire exposure region and achieves improved visibility across a wide range of breast compositions including the presence of implants." |
  | General Safety and Performance Standards (e.g., IEC 60601 series, IEC 62304, DICOM v3):
• Compliance with relevant medical electrical equipment, software, and imaging communication standards. | The ASPIRE Cristalle meets the applicable basic safety and essential performance requirements for Medical Electrical Equipment, including IEC 60601-1, IEC 60601-1-2, IEC 60601-1-3, IEC 60601-2-45, IEC 62304, and DICOM Version 3.
  Hazard Analysis: Indicates the device is of moderate concern, consistent with guidance, and introduces "no new safety or efficacy issues other than those already identified with the predicate device." |
  | Software Development Lifecycle (Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices):
• Comprehensive software development, verification, and validation activities. | Software verification and validation have been performed by unit, integration, and system tests throughout design verification and validation phases. (This implies adherence to established software quality processes, which are an acceptance criterion for software-driven medical devices). |
  | Substantial Equivalence:
• Same Indications for Use (IFU) as the predicate device. | The predicate and proposed devices have the same indications for use (IFU). (Explicitly stated). |

Note: The FDA 510(k) process primarily evaluates "substantial equivalence" to a legally marketed predicate device, rather than setting distinct, quantitative "acceptance criteria" for novel performance. The acceptance criteria here are derived from the regulatory guidance documents referenced and the conclusion of equivalence based on the provided data.

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

• Sample Size for Test Set: Six (6) image sets of screening and diagnostic cases.
• Data Provenance: Not explicitly stated regarding country of origin or whether it was retrospective or prospective. The cases were reviewed by independent mammographic radiologists, implying they were existing or newly acquired images for the purpose of the review.

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

• Number of Experts: Not explicitly stated as a specific number. The document mentions "independent mammographic radiologists" in the plural, so it was more than one.

• Qualifications of Experts: "Independent mammographic radiologists." Specific experience levels (e.g., "10 years of experience") are not provided.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). It states that the review was conducted by "independent mammographic radiologists" who concluded that the image quality was "sufficiently acceptable for mammographic use." This suggests a consensus or independent evaluation without a formal multi-reader adjudication process detailed here.

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

• No, a formal MRMC comparative effectiveness study that quantitatively measures "how much human readers improve with AI vs without AI assistance" was not described.
• The study was a clinical image attribute review assessing the quality of images produced by the device, not a reader study evaluating diagnostic performance with or without an AI assist. While it mentions "improved visibility" across breast compositions, this is a qualitative claim based on the image attribute review, not a quantitative measure of reader improvement.

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

• Yes, implicitly. The DVIIm software is an "image processing" algorithm. The clinical image attribute review assessed the output of this algorithm (the images themselves) in terms of their quality for mammographic use. While radiologists were involved in evaluating the images, the study was not testing the algorithm as a diagnostic assist to the radiologists' decision-making. It was assessing the quality of the image produced by the algorithm.
• The "performance testing - bench: Applicable phantom testing results..." also represents a form of standalone testing of the system/algorithm's physical output and processing capabilities without human diagnostic interaction.

7. The Type of Ground Truth Used

• For the clinical image attribute review, the "ground truth" was expert consensus/opinion by "independent mammographic radiologists" regarding the acceptability of image quality for mammographic use.
• It's important to note this is not ground truth for disease diagnosis (e.g., pathology-confirmed cancer) but rather ground truth for the quality and suitability of the image for interpretation.

8. The Sample Size for the Training Set

The document does not provide information regarding the sample size used for the training set of the DVIIm image processing software. It mentions that DVIIm image processing consists of EDR2m and MFP2, and describes their functions, but does not detail their development data.

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

The document does not provide information on how ground truth was established for the training set (if any) used for developing the DVIIm image processing software. It describes the algorithms (EDR2m and MFP2) but doesn't detail their training methodology or data. Image processing algorithms often rely on various image characteristics and properties rather than diagnostic "ground truth" derived from patient outcomes or pathology, but the specific methods are not mentioned here.

Ask a specific question about this device

ASPIRE Bellus II is medical imaging software that is intended to provide trained medical imaging professionals, including Physicians and Radiologists, with tools to aid them in reading, interpreting, reporting. This product accepts DICOM compliant medical images acquired from a variety of imaging devices including, MG, CT, PT, MR, CR, DX, and US, etc. This product also provides general 2D/3D viewing and general image processing, measurements, annotations, reporting, printing, storing, and general image administration tools, etc.

This product does not accept lossy compressed mammographic images, which should not be used for primary diagnostic interpretation. Display monitors connected to this product for diagnostic interpretation of mammographic images must be approved for use in digital mammography. All images sent to or imported into this product must conform to regulatory requirements. Image quality must conform to applicable quality guidelines.

ASPIRE Bellus II is medical application software with speedy image display and intelligent functions by image processing technologies. This application can support user to efficiently perform interpretation of examination images and make a diagnosis using various modality images and generate Mammography reports for diagnostic/screening purposes. ASPIRE Bellus II can receive various diagnostic images directly from image acquisition systems or PACS via network using DICOM protocol. Images are displayed on viewer monitors for doctors' review.

The provided document is a 510(k) premarket notification for the ASPIRE Bellus II device. It describes the device, its indications for use, comparison with predicate devices, and safety information. However, it explicitly states:

"The subject of this 510(k) notification, ASPIRE Bellus II did not require clinical studies to support safety and effectiveness of the software."

Therefore, the document does not contain any information regarding clinical studies, acceptance criteria, or reported device performance in the context of clinical outcomes or a specific task aided by AI. The notification focuses on demonstrating substantial equivalence to predicate devices for regulatory clearance as a medical imaging software (PACS).

As a result, I cannot provide the requested table and information based on the given document because a study demonstrating the device meets acceptance criteria for a specific clinical task or AI performance was not conducted or reported in this 510(k) submission.

Ask a specific question about this device

The Fujifilm Duodenoscope Model ED-530XT is intended for the visualization of the duodenum and upper digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the esophagus, stomach, and duodenum.

The Fujifilm Duodenoscope Model ED-530XT is comprised of three main sections: an operation section, an insertion portion, and an umbilicus. The operation section controls the angulation (up/down/left/right) of the distal end of the endoscope. The insertion portion contains glass fiber bundles, several channels and a CCD image sensor. The glass fiber bundles allow light to travel through the endoscope and emit light from the tip of the insertion portion to illuminate the body cavity. This provides enough light to the CCD sensor to capture an image and display it on the monitor. The endoscope also contains several channels to deliver air/water and provide suction, as well as a forceps channel. The forceps channel is used to introduce endoscope accessories such as biopsy forceps during the procedure. The umbilicus section consists of electronic components needed to operate the endoscope when plugged in to the video processor and the light source.

The provided text is a 510(k) summary for a medical device called the Fujifilm Duodenoscope Model ED-530XT. It primarily focuses on demonstrating substantial equivalence to a predicate device (Fujinon G5 Duodenoscope ED-450XT5 / ED-250XT5) rather than detailing specific acceptance criteria and a study proving device performance against those criteria in a typical clinical or AI context.

Therefore, many of the requested categories (like sample sizes for test/training sets, expert qualifications, adjudication methods, MRMC studies, standalone performance with AI, and specific ground truth types) are not applicable or not explicitly detailed in this document, as the submission relies on bench testing and comparison to an existing predicate device rather than a clinical trial demonstrating new performance metrics against specific acceptance thresholds.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a formal table of specific acceptance criteria with quantifiable metrics (e.g., sensitivity, specificity, accuracy) that are typically seen for diagnostic devices or AI algorithms. Instead, the performance is demonstrated through various engineering and safety tests, with the implied "acceptance criterion" being that the device meets the standards and performs comparably to the predicate.

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

• Sample Size: Not specified. The performance data described are primarily from bench testing of the device itself and its components, rather than a "test set" of patient data or clinical cases.
• Data Provenance: Not applicable in the context of clinical data. The tests are lab-based, engineering performance tests.

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

• Not applicable. The ground truth for these engineering and safety tests is established by adherence to industry standards, measurement protocols, and physical testing, not by expert medical interpretation of images or clinical outcomes.

4. Adjudication Method for the Test Set

• Not applicable. This concept is relevant for studies involving human interpretation or clinical endpoints, not for bench testing of physical device performance.

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 reported. This type of study is typically done for diagnostic aids or AI algorithms where human reader performance is a key outcome. This 510(k) submission focuses on the safety and functional equivalence of an endoscope.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Not applicable. This device is an endoscope, which is a physical medical instrument, not an AI algorithm. Therefore, "standalone" performance in the AI sense is not relevant.

7. The Type of Ground Truth Used

• The "ground truth" for the tests described is based on engineering specifications, established consensus standards (e.g., ISO, AAMI, IEC), and documented test methods for device performance, safety, and biocompatibility.

8. The Sample Size for the Training Set

• Not applicable. This device is not an AI algorithm that undergoes "training."

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

• Not applicable, as there is no training set for this type of device submission.

Ask a specific question about this device

Dynamic Visualization II Image Processing is an optional software for the FDX Console, intended to provide optimized image quality over a wide range of patient thicknesses, especially for bariatric imaging. The device is not intended for mammography use.

Fujifilm's FDR D-EVO Flat Panel Detector System (DR-ID600) is a portable digital detector system that interfaces with, and acquires and digitizes x-ray exposures, from standard radiographic svstems. The FDR D-EVO is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults, pediatrics and neonates. The detector models support both wireless and wired/tethered data communication between the detector and the system. Detectors can be placed in a wall bucky for upright exams, a table bucky for recumbent exams, or removed from the bucky for non-grid exams. The Acquisition Workstation for the DR-ID600 is the FDX Console. Dynamic Visualization II Image Processing (DVII) is optional software included in v9.0 of the FDX Console. The FDX Console and Dynamic Visualization II software may be used with Fujifilm DR and CR X-ray systems.

Dynamic Visualization II is an enhanced version of Fujifilm's Dynamic Visualization™ (DV) image processing software. The enhancements made to DVII are designed to provide optimized image quality over a wide range of patient thicknesses, and can be particularly useful when imaging bariatric patients.

DVII uses the same image processing sequence as the predicate DV, but the EDR (Exposure Data Recognition) and MFP (Multi-objective Frequency Processing) algorithms have been modified. When compared to the current EDR and MFP algorithms, the corresponding new algorithms (EDR2, MFP2) have been modified as follows:

EDR2 - to identify and optimize various anatomic structures in an acquired image prior to the subsequent application of contrast and sharpness image processing steps, EDR2 uses a feature recognition method as opposed to conventional EDR's histogram analysis method.

MFP2 - similar to MFP, MFP2 sharpens and balances contrast in anatomic structures in an image after being subject to Exposure Data Recognition. MFP2 uses additional low frequency tables and a combination of automatic and preset dynamic range control operations.

Here's an analysis of the provided information regarding the acceptance criteria and study for the Dynamic Visualization II Image Processing Option:

Acceptance Criteria and Device Performance

The document does not explicitly present a table of acceptance criteria with numerical targets. Instead, the "acceptance criteria" are implied by the comparative image quality evaluation, which aimed to show that the new processing option (DV2) optimizes image quality relative to the predicate (DV), especially for bariatric patients.

Implied Acceptance Criteria and Reported Device Performance:

Study Details:

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

   • Sample Size: The document states that "Raw clinical images were processed" and "Randomized image pairs (DV vs. DV2) were then evaluated." However, the exact number of images in the test set is not specified.
   • Data Provenance: The data consisted of "Raw clinical images," but the country of origin is not specified. It is stated that "Slightly more than half of the images were of bariatric patients," indicating a focus on a specific patient demographic relevant to the device's indications for use. The study is retrospective as it used "Raw clinical images" that were then processed by both the predicate and proposed algorithms.

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

   • Number of Experts: Three readers evaluated the randomized image pairs.
   • Qualifications of Experts: The qualifications of these readers are not specified. It is only mentioned that they were "readers," implying they are likely medical professionals, but their specific specialty (e.g., radiologist) and experience level are not provided.

3. Adjudication method for the test set:

   • The document states that "Randomized image pairs (DV vs. DV2) were then evaluated by three readers." It does not specify an explicit adjudication method like 2+1 or 3+1. The phrasing suggests individual evaluations by each reader rather than a consensus-building process with formal adjudication rules.

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:

   • A comparative effectiveness study was performed, focusing on the image processing algorithms (DV vs. DV2) rather than direct AI assistance to human readers. The study compared images processed by the predicate algorithm to images processed by the new algorithm. It was a "comparative image quality evaluation" where "Randomized image pairs (DV vs. DV2) were then evaluated by three readers."
   • This was not an MRMC study comparing human readers with vs. without AI assistance. It was a comparison of two different image processing algorithms applied to images, and human readers then evaluated the quality differences between the outputs of these algorithms. Therefore, an effect size of human readers improving with/without AI assistance is not applicable in this context. The study aimed to show the new algorithm itself produces better images.

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

   • The study implicitly involves a standalone performance aspect if you consider the algorithms' ability to process images. The output of the algorithms (processed images) was then directly evaluated by human readers. However, the direct performance of the algorithm without human evaluation is not specifically detailed or presented (e.g., objective metrics of image quality without human perception). The evaluation method involved human readers assessing the output.

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

   • The ground truth for the "image quality optimization" was based on the evaluation of three readers (experts). There's no mention of pathology, outcomes data, or a formal expert consensus process to establish ground truth in the sense of a definitive diagnostic label. The evaluation was relative: which processed image (DV or DV2) looked "better" or "optimized."

7. The sample size for the training set:

   • The document does not specify the sample size for any training set. The device is described as an enhanced image processing software (Dynamic Visualization II) with modified algorithms (EDR2, MFP2) from a predicate (Dynamic Visualization), not necessarily a machine learning model that requires a distinct training set. While these algorithms were "modified," the process of their development or any explicit "training" of a machine learning model with a defined training set size is not detailed.

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

   • As no training set is explicitly mentioned or detailed, the method for establishing its ground truth is not provided. The changes are described as modifications to existing image processing algorithms (EDR and MFP), suggesting an engineering or algorithmic refinement process rather than, for example, supervised machine learning requiring labeled training data.

Ask a specific question about this device

The FUJIFILM Hood Models DH-28GR, DH-29CR and DH-30CR are intended to be used in combination with compatible endoscopes to maintain the field of view during endoscopic procedures such as mucosal resection.

FUJIFILM Hood Models DH-28GR, DH-29CR and DH-30CR are intended to be used in combination with compatible endoscopes to maintain the field of view during endscopic procedures such as mucosal resection.

The FUJIFILM Hood Models DH-28GR, DH-29CR and DH-30CR are comprised of three main sections: an attaching portion, a distal portion, and a drain portion. The attaching portion is a wider diameter opening which is used to connect the hood to an applicable endoscope; a distal portion is the ending portion of the hood which tapers into narrower diameter opening, the drain slits on the distal portion form drain portion which prevent the fluids lodging on the surface of the endoscope.

The subject devices are used in combination with their respective applicable Fujifilm's endoscopes as shown in the table 7.1. All the applicable endoscopes marketed in USA are cleared under respective 510(k) notices.

The provided document is a 510(k) premarket notification for FUJIFILM Hood Models DH-28GR, DH-29CR, and DH-30CR. It primarily focuses on demonstrating substantial equivalence to a predicate device, FUJIFILM Hood Model DH-17EN (K143556), rather than outlining specific acceptance criteria in the context of device performance metrics and a detailed study proving performance against those metrics in the way one might typically see for AI/ML devices.

Instead, the document details performance data that supports the substantial equivalence, particularly concerning changes in dimensions, material, and sterility status compared to the predicate device.

Here's an analysis based on the information provided, framed to address your requested points where applicable, and highlighting what is not present (which is most of the detailed information expected for an AI/ML device performance study):

1. Table of Acceptance Criteria and Reported Device Performance

The term "acceptance criteria" is not used in the document for specific performance thresholds. Instead, the document discusses meeting "performance specifications" or demonstrating "substantially equivalent performance" to the predicate device. The performance data presented focuses on verifying that changes to the device (dimensions, material, sterility) do not negatively impact its safety and effectiveness compared to the predicate.

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

This information is not provided in the document. The testing described appears to be bench testing or in vitro assessments of device properties rather than a clinical study with patient data.

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

This information is not applicable and not provided as this is not a study involving expert review for ground truth establishment. The performance data relates to physical and material properties and compliance with engineering and sterilization standards.

4. Adjudication Method for the Test Set

This information is not applicable as there is no mention of a test set requiring adjudication by experts.

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

This information is not applicable and not provided. This device is an accessory for endoscopes, not an AI-assisted diagnostic tool.

6. Standalone (Algorithm Only) Performance

This information is not applicable and not provided. This is a physical medical device, not an algorithm.

7. Type of Ground Truth Used

The concept of "ground truth" as it applies to AI/ML device performance (e.g., expert consensus, pathology, outcomes data) is not relevant to this 510(k) submission. The "ground truth" in this context would be the established engineering specifications, material properties, and regulatory standards.

8. Sample Size for the Training Set

This information is not applicable and not provided. This is not an AI/ML device requiring a training set.

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

This information is not applicable and not provided.

Summary of the Study (as described in the document):

The "study" described in the 510(k) submission is a series of bench tests and evaluations aimed at demonstrating that the new FUJIFILM Hood Models DH-28GR, DH-29CR, and DH-30CR are substantially equivalent to the predicate device, FUJIFILM Hood Model DH-17EN. The focus is on showing that changes in dimensions, material composition, and the introduction of a sterile presentation do not introduce new questions of safety or effectiveness.

The performance data included:

• Biocompatibility testing according to ISO 10993 standards.
• Sterilization validation according to ISO 11135 and ASTM F1980.
• Endoscope-specific testing according to ISO 8600 standards.
• Verification of specific dimensions (outer diameter, max diameter of attaching endoscope, inner diameter of distal end, inner diameter of attaching portion, distance from the tip) against performance specifications.

The document concludes that these tests demonstrated substantially equivalent performance to the predicate device, supporting the claim that the new device models are as safe and effective as the previously cleared device.

Ask a specific question about this device

Diathermic Slitter (FlushKnife) DK2618J and DK2623J are intended to be used with specified endoscopes to cut tissue using high-frequency current within the digestive tract. The devices are indicated for ablation, incision, dissection, avulsion, coagulation and hemostasis of tissue within the digestive tract.

Diathermic Slitter (FlushKnife) is sterile and intended for single used electrosurgical instruments that remove tissue and control bleeding by use of high-frequency ("HF") electrical current. The device is comprised of a proximal handle with slider that is connected to a flexible resin tube. The flexible resin tube covers and insulates the operation wire and slitter (when retracted). The operation wire controls the mechanical function of and delivers high frequency (HF) electrical current to the slitter. The proximal end of the operation wire is connected to the slider, which allows the operator to manually control the extension and retraction of the distal end of the operation wire connects to the slitter, which is located at the distal tip of the device. The device connects to a HF electrosurgical power supply unit by an active cord ("A-Cord") connector. HF electrical current generated by a HF electrosurgical power supply unit flows to the slitter from the HF electrosurgical power supply unit via the A-cord, the A-cord connector, and the operation wire. The distal tip of the device is inserted through the forceps channel of the specified endoscope. Once inserted, the operator can extend the slitter from the tip of the endoscope using the slitter is extended to the target site of a patient. Cleavage, resection, incision, ablation, hemostasis, coagulation, or excision of tissue is achieved by delivering HF current to the target tissue through the slitter. The device is provided sterile for single-use only. The device can supply sterile water or fluids to its distal end target site via a water/fluid supply channel. The port for the water/fluid supply channel is located on the handle at the proximal end of the device. The sterile water or fluid also aids in the removal of debris, blood and extraneous material from the distal end of the device or a target site. To supply sterile water or fluid to the distal end target site, a syringe filled with water or fluid is connected to the water/fluid inlet at the proximal handle. Besides a syringe, alternate delivery methods can also be used to supply sterile water or fluid to the distal end target site of the device.

The provided text describes a 510(k) submission for a medical device called the "Fujifilm Diathermic Slitter (FlushKnife)," which is a modified version of a previously cleared device. The submission focuses on demonstrating substantial equivalence to the predicate device, especially regarding a minor modification: the addition of compatible sterile fluids and alternate delivery systems.

Here's an analysis of the acceptance criteria and study information provided, focusing on what's explicitly stated and what is not:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a detailed table with specific numerical acceptance criteria and a corresponding reported performance for each criterion. It mentions categories of performance testing but does not quantify them.

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

This information is not provided in the document. The text states "Fujifilm conducted the following performance testing," but no details about sample sizes or the origin of the test data (e.g., country of origin, retrospective/prospective) are mentioned.

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

This information is not applicable/provided. The performance testing described (fluid supply, temperature rise, dielectric voltage, durability) are engineering/functional tests, not tests that require expert-established ground truth related to clinical outcomes or interpretations.

4. Adjudication Method for the Test Set

This information is not applicable/provided. As above, the tests mentioned are functional performance tests, not clinical evaluations requiring adjudication.

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

No, an MRMC comparative effectiveness study was not done. The device is an electrosurgical instrument for cutting tissue, not an imaging or diagnostic device that would typically involve human readers interpreting cases.

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

The concept of "standalone performance" for an algorithm does not apply to this device. This is a physical electrosurgical instrument, not an AI or algorithmic device. The performance tests described (fluid supply, temperature rise, dielectric voltage, durability) are inherent to the device's physical function.

7. The Type of Ground Truth Used

The ground truth for the performance tests would be established through engineering specifications and standards relevant to medical device safety and performance. For example:

• Fluid supply: Met predefined flow rates or delivery volumes.
• Temperature rise: Stayed within safe operating temperature limits.
• Dielectric voltage: Withstood specified voltage without breakdown.
• Durability: Maintained functional integrity after a specified number of uses or cycles.

These are not "expert consensus," "pathology," or "outcomes data" in the typical clinical sense, but rather objective measurements against established engineering benchmarks.

8. The Sample Size for the Training Set

This information is not applicable/provided. As this is a physical medical instrument and not an AI or machine learning device, there is no "training set."

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

This information is not applicable/provided for the same reason as point 8.

Ask a specific question about this device

The FDR AQRO (DR-XD 1000) is a digital mobile X-ray system intended for use in general purpose radiography for generating radiographic images of human anatomy, including adult, pediatric, and neonatal exams. The FDR AORO is not intended for mammography.

FUJIFILM's FDR AQRO (DR-XD1000) is a compact, economical, lightweight, nonmotorized, low power (2.5 kW), mobile X-ray system designed to work with FUJIFILM's GOS and Csl scintillator FDR D-EVO2 (DR-ID 12XXSE) family of digital X-ray detectors coupled. The D-EVO2 detectors received clearance on 7/23/2014 via 510(k) K142003. The FDR AQRO includes a built-in operation console. The AQRO's console uses Version 10.0 of Fujifilm's FDX Console Software. This software received 510(k) clearance via K170451 on 3/16/2017. The console software includes Virtual Grid 2 (VG2) Image Processing functionality. The VG2 function allows using the mobile X-ray system without a physical grid, resulting in a dose reduction of up to 50% (when compared to using a physical grid). The Virtual Grid 2 Image Processing software received clearance on 4/8/2016 via K153464. The reduction in the external dimensions of FDR AQRO enables smooth movement in the hospital and at the bedside because of an integrated X-ray tube and high-voltage generator (mono-block) that eliminates the need for High Voltage cables and utilizes less space. A high performance Li-ion battery provides up to twelve (12) hours of continuous use (at ~20 exposures/hour) with a quick full charge in four hours. A quick charge of 15 minutes provides one hour of usage. Exposure may also be made when the AC power cord is plugged in.

This document describes the 510(k) premarket notification for the Fujifilm FDR AQRO (DR-XD1000) Mobile X-ray System. As such, it primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study with specific acceptance criteria, comprehensive performance metrics, and a full statistical plan often found in PMA applications or de novo submissions for novel AI/ML devices.

Therefore, many of the typical elements requested in your prompt regarding acceptance criteria and performance studies (e.g., number of experts for ground truth, adjudication methods, MRMC studies, effect sizes, training set details) are not explicitly provided or applicable in this 510(k) summary for a mobile X-ray system. The performance is assessed primarily through non-clinical (phantom images, compliance with standards) and limited clinical data (sample clinical images) to demonstrate that the device is as safe and effective as the predicate.

However, I can extract the information that is present and explain why certain details are missing based on the nature of this submission.

Here's the breakdown based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document does not present "acceptance criteria" in the sense of specific quantitative thresholds for clinical performance (e.g., sensitivity, specificity, AUC) that a novel diagnostic AI algorithm would typically undergo. Instead, the "performance" is demonstrated through:

• Compliance with recognized standards: This serves as a primary form of "acceptance criteria" for safety and basic performance of X-ray systems.
• Comparison to a predicate device: The core argument is substantial equivalence, meaning the new device performs "as safe and effective as" the legally marketed predicate.
• Image Quality: Assessed via sample phantom and clinical images, which are qualitatively evaluated rather than against quantitative metrics in this summary.
• Technical Specifications: Comparison of technical specs to the predicate.

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

• Test Set Sample Size: The document does not specify a quantitative "test set" sample size in terms of number of cases for a clinical performance study. The evaluation appears to involve "sample phantom images" and "sample clinical images" for qualitative assessment. This is typical for a 510(k) for an X-ray system, which focuses on device safety and basic image generation capabilities, rather than a diagnostic algorithm that analyzes images for specific findings.
• Data Provenance: Not specified within this summary. It's likely general radiography data, but no country of origin or whether it's retrospective/prospective is mentioned.

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

• Not Applicable/Not Specified: For a 510(k) submission of an X-ray system, the "ground truth" is typically the physical output and image quality of the device (compared to a predicate and standards), not a diagnostic finding that requires expert interpretation to establish a gold standard. Without a diagnostic study quantifying performance against a true disease state, there's no mention of experts establishing ground truth for a test set.

4. Adjudication Method for the Test Set

• Not Applicable/Not Specified: As there isn't a stated clinical study with a test set requiring interpretation for specific findings, there is no adjudication method described.

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

• No: The document does not mention an MRMC study comparing human readers with and without AI assistance. This device is an X-ray system, not an AI software for diagnosis. While it includes "Virtual Grid 2" software, its clearance (K153464) and functionality relate to image processing affecting dose and image appearance, not to diagnostic AI assistance for readers that would warrant an MRMC study.

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

• No: This is a physical X-ray system. While it contains software components (FDX Console Software and Virtual Grid 2), the "standalone performance" refers to the system as a whole in generating images, not an AI algorithm analyzing images independently. The performance data is primarily demonstrated through technical specifications, compliance with standards, and visual assessment of sample images.

7. The Type of Ground Truth Used

• Technical Specifications & Compliance Standards/Predicate Comparison: The "ground truth" used for this device is effectively its ability to generate radiographic images safely and effectively, achieving comparable technical performance metrics (e.g., DQE, MTF, tube characteristics, radiation control) to a legally marketed predicate device, and compliance with relevant industry and medical device standards. Qualitative visual assessment of sample phantom and clinical images also contributes.

8. The Sample Size for the Training Set

• Not Applicable/Not Specified: This is not an AI/ML device that learns from a "training set" of images in the conventional sense. It's an X-ray system. The software components like FDX Console and Virtual Grid 2 would have been developed and tested through software validation processes (IEC 62304 compliance is noted), but this does not involve a "training set" of patient images in the way an AI diagnostic algorithm would.

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

• Not Applicable/Not Specified: Since there is no "training set" for an AI/ML model described, there is no ground truth established in this context. Device performance is evaluated against engineering specifications, safety standards, and equivalence to a predicate.

Ask a specific question about this device

Synapse 3D Perfusion Analysis is medical imaging software used with Synapse 3D Base Tools that is intended to provide trained medical professionals, with tools to aid them in reading, interpreting, and treatment planning. Synapse 3D Perfusion Analysis accepts DICOM compliant medical images acquired from CT and MR. This product is not intended for use with or for the primary diagnostic interpretation of Mammography images.

Addition to Synapse 3D Base Tools, Synapse 3D Perfusion Analysis provides the parameter images by post-processing of dynamic scanned CT arteriography and magnetic resonance (MR) images acquired with contrast agents to aid the assessment of cerebral (CT and MR), myocardial (CT) and abdomen (CT) blood flows. The parameter images are Blood Volume (BV), Blood Flow (BF), Mean Transit Time (MTT), and Time To Peak (TTP),

Synapse 3D Perfusion Analysis is medical device software for Perfusion Analysis that provides the parameter images by post-processing of dynamic scanned CT arteriography and MR images acquired with contrast agents to aid the assessment of cerebral (CT and MR), myocardial (CT) and abdomen (CT) blood flows. The parameter images are Blood Volume (BV), Blood Flow (BF), Mean Transit Time (MTT), and Time to Peak (TTP). The perfusion parameter images can be presented to the trained medical professionals as the time-density curves (TDC) and perfusion characteristics maps (in parametric and summary) to assist them in assessing the blood flows. Synapse 3D Perfusion Analysis includes the following perfusion analysis applications.

• (1) Brain Perfusion (CT and MR) (unchanged from the FDA-cleared version K120637) is an application that analyzes the cerebral blood flow using the contrast-enhanced dynamic scanned CT and MR cerebral arteriography images. The Brain Perfusion post-processes the cerebral arteriography CT and MR images, and generates the parameter images of Cerebral Blood Volume (CBV), Cerebral Blood Flow (CBF), MTT, and TTP.
• (2) 4D Perfusion (CT) is an application that analyzes the changes in the cerebral blood flow over time (in 4D) using the contrast-enhanced multi-phase 3D whole-brain images. The 4D Perfusion post-processes the cerebral arteriography CT and MR images, and generates the 4D (over time) parameter images of CBV, CBF, MTT, and TTP.
• (3) Abdominal Perfusion (CT) is an application that analyzes the blood flow of abdominal organs over time (in 4D) using the contrast-enhanced multi-phase 3D abdomen images. The Abdominal Perfusion post-processes the abdominal CT images, and generates the parameter images of Tissue Blood Volume (TBV), Tissue Blood Flow (TBF), MTT, and TTP.
• (4) Cardiac Perfusion (CT) is an application that analyzes the myocardial blood flow using the multi-phase 3D heart images. The Cardiac Perfusion post-processes the contrast-enhanced Myocardial CT images, and generates the parameter images of Myocardial Blood Volume (MBV), Myocardial Blood Flow (MBF), MTT, and TTP.

Synapse 3D Perfusion Analysis runs on Windows standalone and server/client configuration installed on a commercial general-purpose Windows-compatible computer. Synapse 3D Perfusion Analysis is an optional software module that works with Synapse 3D Base Tools (cleared by CDRH via K120361 on 04/06/2012) which is connected through DICOM standard to medical devices such as CT, MR, CR, US, NM, PT, XA, etc. and to a PACS system storing data generated by these medical devices, and it retrieves image data via network communication based on the DICOM standard. The retrieved image data are stored on the local disk managed by Synapse 3D Base Tools, and the associated image-related information of the image data is registered in the database and is used for display, image processing, analysis, etc. The software can display the images on a display monitor, or printed them on a hardcopy using a DICOM printer or a Windows printer.

The provided text describes the Fujifilm Synapse 3D Perfusion Analysis device and its 510(k) submission. Here's a breakdown of the acceptance criteria and the study information:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not explicitly stated as a number of cases or patients. The document refers to "all of the test cases" but does not quantify them.
• Data Provenance: "actual clinical images" were used for benchmark performance testing. No specific country of origin or whether it was retrospective or prospective is mentioned.

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

Not explicitly stated. The ground truth ("Reference data (Pt)") was derived from a perfusion calculation model using arbitrary CT signal values, not directly from expert consensus on clinical images in the performance testing section.

4. Adjudication method for the test set

Not applicable. The ground truth for performance testing was established computationally through a perfusion calculation model, not through expert adjudication of cases.

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 comparative effectiveness study is mentioned. The submission focuses on the performance of the algorithm itself.

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

Yes, a standalone performance test was done. The "benchmark performance testing" calculated the "Result data (Pc)" by Synapse 3D Perfusion Analysis using input data (Pi) and compared it to "Reference data (Pt)" derived from a perfusion calculation model. This evaluates the algorithm's accuracy in isolation.

7. The type of ground truth used

For the benchmark performance testing, the ground truth (Reference data (Pt)) was derived from a perfusion calculation model using input data (Pi: an image created using an arbitrary CT signal value).

8. The sample size for the training set

Not mentioned in the provided text.

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

Not mentioned in the provided text.

Ask a specific question about this device