Search Results

Processor VP-7000

The VP-7000 unit is used for endoscopic observation, diagnosis, treatment, and image recording.

It is intended to process electronic signals transmitted from a video endoscope (a video camera in an endoscope). This product may be used on all patients requiring endoscopic examination and when using a Fujinon/FUJIFILM medical endoscope and light source together with monitor, recorder and various peripheral devices.

BLI (Blue Light Imaging), LCI (Linked Color Imaging) and FICE (Flexible spectral-Imaging Color Enhancement) are adjunctive tools for gastrointestinal endoscopic examination which can be used to supplement Fujifilm white light endoscopy.

BLI, LCI and FICE are not intended to replace histopathological sampling as a means of diagnosis.

Light Source BL-7000

The BL-7000 Light Source is used for endoscopic observation, diagnosis, treatment, and image recording, If is intended to provide illumination to an endoscope.

The light source also functions as a pump to supply air through the endoscope while inside the obtaining clear visualization to facilitate diagnostic examination.

This product may be used on all patients requiring endoscopic examination and when using a Fujinon/FUJIFILM medical endoscope and video processor together with monitor, recorder and various peripheral devices.

VP-7000 and BL-7000 are intended to be used in conjunction with Fujinon/FUJIFILM endoscopes for endoscopic observation, diagnosis, treatment, and image recording. The description for each of the components of the subject device is below:

The VP-7000 Video Processor:

The Processor relays the image from the endoscope to a video monitor. Projection can be either analog or digital at the user's preference. The Processor incorporates internal digital storage capacity. The Processor also controls the light projected to the body cavity. The Processor provides for optional structural enhancement through user modes FICE. BLI. BLI-bright and LCI. Spectral and structural enhancements are achieved through proprietary software. The device is AC operated at a power setting of 100-240V/50-60Hz/0.8-0.5A. The Processor is housed in a steelpolycarbonate case measuring 390x110x485mm.

The DK-7000E Keyboard is a standard accessory of VP-7000. It is used to enter pertinent procedural information (patient, physician, date, etc.) for display on the video monitor and digital/analog storage systems. The Keyboard is also used to control operational features of the VP-7000 Processor. The Keyboard resembles a standard computer keyboard, and is provided with an instruction label attached to it.

The BL-7000 Light Source:

The Fujinon/FUJIFILM endoscope employs fiber bundles to transmit light from the light source and subsequently to the body cavity. The Light Source employs 79.2W 4 LED lamps. Brightness control is performed by the user. The device is AC operated at a power setting of 100-240V/50-60Hz/1.2-0.7A. The Light Source is housed in a steel-polycarbonate case measuring 390x155x485mm.

The provided document describes the FUJIFILM Processor VP-7000 and Light Source BL-7000 and its substantial equivalence to predicate devices, particularly focusing on the performance data for its new imaging features (BLI and BLI-bright).

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with quantitative metrics for the clinical performance of the device's enhanced imaging modes (BLI, BLI-bright). Instead, it states that "All testing criteria were met" for non-clinical functional tests and for clinical evaluation, "The clinical study established that BLI and BLI-bright demonstrated substantial equivalence of diagnostic visualization (e.g. image quality) to the predicate FICE."

The primary goal of the clinical study was to demonstrate substantial equivalence of diagnostic visualization (image quality) compared to the FICE predicate. While a specific numerical acceptance criterion isn't given, the statement implies that the image quality was not worse than FICE, which was already a cleared device.

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

• Sample Size: The document does not specify the exact number of subjects (patients) or images in the clinical study's test set. It mentions each subject underwent an endoscopic examination using the VP-7000, BL-7000, and FUJIFILM's video endoscopes.
• Data Provenance: The study was a "prospective clinical trial." The country of origin for the data is not explicitly stated, but given the FDA filing, it is likely that parts, if not all, of the data were collected in the United States or under similar clinical standards.

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

• Number of Experts: The clinical study involved "multiple blinded investigators." The exact number is not specified.
• Qualifications of Experts: The qualifications of these "investigators" are not detailed in the provided text. It can be inferred they are medical professionals qualified to interpret endoscopic images, but specific credentials (e.g., gastroenterologists, radiologists) or years of experience are not mentioned.

4. Adjudication Method for the Test Set

• The study design was a "reader concurrence study." Images were "analyzed independently by multiple blinded investigators." It is not explicitly stated how discrepancies among readers were resolved or if a formal adjudication process (e.g., 2+1, 3+1) was used to establish a final ground truth for each image, beyond simply analyzing reader agreement (concurrence).

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

• An MRMC-like study was performed in the sense that multiple readers evaluated multiple cases. However, this study was not a comparative effectiveness study designed to assess how much human readers improve with AI vs. without AI assistance.
• The BLI, LCI, and FICE features are described as "adjunctive tools for gastrointestinal endoscopic examination which can be used to supplement Fujifilm white light endoscopy." They are image processing features, not necessarily "AI" in the modern sense (e.g., providing diagnostic suggestions).
• The study's goal was to establish "substantial equivalence of diagnostic visualization (e.g. image quality) to the predicate FICE," not an improvement in human reader performance or diagnostic accuracy per se. Therefore, no effect size for human reader improvement with AI assistance is reported.

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

• No standalone performance was reported in this document. The BLI, LCI, and FICE features are image processing enhancements intended to be used by a "licensed medical practitioner (user)" as "adjunctive tools" to "supplement" white light endoscopy. They are not presenting a standalone diagnostic output that would require a separate "algorithm only" performance evaluation.

7. The Type of Ground Truth Used

• The document states that the clinical study evaluated "overall image quality" and "diagnostic visualization."
• The images were analyzed independently by multiple blinded investigators using a "4-point Likert scale." This suggests that the ground truth for image quality/diagnostic visualization was established through expert consensus/opinion based on their scoring.
• The document explicitly states: "BLI, LCI and FICE are not intended to replace histopathological sampling as a means of diagnosis." This indicates that histopathology was not the ground truth against which the image enhancements were directly evaluated for diagnostic accuracy outcomes.

8. The Sample Size for the Training Set

• The document does not specify a separate training set. The BLI, LCI, and FICE enhancements are described as "achieved through proprietary software" and based on "signal processing" and manipulation of LED light intensity ratios. This suggests these are pre-defined image processing algorithms rather than machine learning models that require a distinct training set in the typical sense of AI development.

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

• As no explicit training set for a machine learning model is mentioned, the concept of "ground truth for the training set" does not directly apply in the context of the information provided for these specific image processing features. The development of these enhancements would likely have involved engineering and optical principles to achieve desired visual effects, rather than a data-driven training process with established clinical ground truth labels.

Ask a specific question about this device

The Fujifilm ultrasonic processors SU-1 PLATINUM and SU-1 are intended to be used in combination with Fujifilm ultrasonic endoscope, video processor, light source, monitor, recorder, and various peripheral devices. The product is intended to provide ultrasonic images of the trachea, bronchial tree and surrounding organs, or submucosal and peripheral organs of the upper gastrointestinal tract for observation, recording and in diagnosis during endoscopic evaluation.

The Fujifilm ultrasonic processors SU-1 PLATINUM and SU-1 are used with previously cleared ultrasonic endoscopes, EG-530UR2 & EG-530UT2 (K120446) and EB-530US (K121035) to provide ultrasonic images of the trachea, bronchial tree, and surrounding organs, or submucosal and peripheral organs of the upper gastrointestinal tract for observation, recording and to aid in diagnosis during endoscopic evaluation.

The Fujifilm ultrasonic processors SU-1 PLATINUM and SU-1 consist of two components, Processor and Keyboard, which are used in conjunction with one another. The SU-1 PLATINUM or SU-1 ultrasonic processors connect to an ultrasonic endoscope and transmit ultrasound waves into the body cavity by driving the transducer installed on the ultrasonic endoscope. The SU-1 PLATINUM or SU-1 ultrasonic processors process the reflected ultrasound signals received by the ultrasonic transducer in the body cavity and convert the electrical signals into image or video signals. The signals are displayed on the monitor or printer as ultrasonic images. The Keyboard, CP-1, is used to control operational features of the SU-1 PLATINUM or SU-1 ultrasonic processor.

The Fuifilm ultrasonic processor SU-1 PLATINUM and SU-1 can acquire and display real-time ultrasound data in different modes such as M, B, Color Doppler, Pulse Doppler, Duplex and Triplex. Additionally. SU-1 PLATINUM offers a feature/mode known as Elastrography, which is a medical imaging modality that maps the elastic properties of the target organs. Relative stiffness of the tissue is visualized as a color distribution map by a way of calculating the distortion of the tissue caused by external compression of inner vibration, and displaying disparities in stiffness levels as different colors.

This is a device that processes ultrasound images, not an AI / ML device. Hence most of the questions are not applicable to the context.

Here's an analysis of the provided text in relation to your request about acceptance criteria and a study proving device conformance:

The document describes a medical device submission (K153206) for Fujifilm Ultrasonic Processors SU-1 PLATINUM and SU-1. It is a 510(k) submission, meaning the device is seeking clearance by demonstrating substantial equivalence to a legally marketed predicate device, not by proving efficacy through a comprehensive clinical trial.

Therefore, there is no mention of "acceptance criteria," "device performance," "sample size for test set," "data provenance," "number of experts," "adjudication method," "MRMC comparative effectiveness study," "standalone performance," "type of ground truth," "sample size for training set," or "how ground truth for training set was established" in the context of an AI/ML device or a traditional clinical study with outcome-based performance metrics.

Instead, the document focuses on demonstrating substantial equivalence through:

• Comparing technological characteristics.
• Compliance with recognized performance and safety standards.
• Bench testing.

Here's an attempt to extract relevant information given the nature of the document:

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

The document does not present acceptance criteria in a typical AI/ML or clinical study format (e.g., target sensitivity/specificity). Instead, equivalence is demonstrated by meeting technical specifications and safety standards.

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

• Sample Size: Not applicable in the context of clinical data for performance evaluation. The "Performance Data" section refers to software validation and EMC safety/performance testing. These are engineering/device-level tests, not imaging-data-based performance studies with a "test set" of patient data.
• Data Provenance: Not applicable. The "Performance Data" section describes engineering and safety testing of the device hardware and software.

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 not a study involving expert readers and establishing ground truth for diagnostic accuracy.

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

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

Not applicable. This device is an ultrasonic processor, not an AI-assisted diagnostic tool.

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

Not applicable. This is not an algorithm, but a hardware device with embedded software for image processing.

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

Not applicable. The "ground truth" here pertains to the device meeting engineering specifications and safety standards, confirmed through various tests (e.g., electrical safety, electromagnetic compatibility, software validation).

8. The sample size for the training set

Not applicable. This is not an AI/ML device that undergoes training on a dataset.

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

Not applicable.

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, cauterization, coagulation and hemostasis of tissue within the digestive tract.

Diathermic Slitter (ClutchCutter) DP2618DT is intended to be used with specified endoscopes to cut tissue using high-frequency current within the digestive tract. The device is indicated for ablation, incision, dissection, avulsion, cauterization, coagulation and hemostasis of tissue within the digestive tract.

The Fujifilm Diathermic Slitter (FlushKnife) and Diathermic Slitter) (the "devices") are electrosurgical instruments that remove tissue and control bleeding by use of high-frequency ("HF") electrical current. The devices are provided sterile for single-use only. The devices are provided in various models (described below), but each is comprised of the following major components:

The FlushKnife and ClutchCutter consist of the following major components:

• · Slitter Electrode at distal tip of the device that performs ablation, incision, dissection, avulsion, cauterization, coagulation, and hemostasis of tissue via delivery of HF electrical current.
• Operation wire Inner wire of the device that connects the handle and slider control to the slitter, facilitates manual control of slitter position, and delivers the HF electrical current to the slitter.
• · Tube Flexible resin tube that is inserted into body cavities and insulates operation wire carrying the HF electrical current.
• Slider Portion of handle that extends and retracts the slitter portion from the distal end of the tube (FlushKnife) or opens and closes slitter jaws (ClutchCutter) by means of the operation wire.
• · Handle Proximal end of the device that provides for user control.
• · Active Cord ("A-Cord") Connector Used to connect the device to the electrosurgical power supply unit via an A-cord.

The devices are 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 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 of the slitter (for the FlushKnife) or open and close (ClutchCutter) of the slitter Jaws. The distal end of the operation wire connects to the slitter, which is located at the distal tip of the device.

The devices connect to a HF electrosurgical power supply unit by an active cord ("A-Cord") connector. HF electrical current generated by HF electrosurgical power supply unit flows to the slitter from the HF electrosurgical power supply unit via 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 (FlushKnife) or opens and closes slitter jaws (ClutchCutter) 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 provided text describes a 510(k) premarket notification for electrosurgical instruments (Fujifilm Diathermic Slitter FlushKnife and ClutchCutter). This type of submission focuses on demonstrating substantial equivalence to a predicate device, rather than proving a device meets specific acceptance criteria based on performance studies with human-in-the-loop or standalone AI.

Therefore, the document does not contain the information requested regarding acceptance criteria and a study proving a device meets them in the context of an AI/human comparative effectiveness study.

The performance data mentioned in the document are related to safety and effectiveness through compliance with recognized consensus standards (biocompatibility, sterilization, EMC, electrical safety, as well as standards related to packaging and shelf life) and bench testing, primarily to demonstrate that the new device is as safe and effective as the predicate devices.

Here's why the requested information cannot be extracted:

• Acceptance Criteria & Reported Device Performance (Table 1): The document does not define specific performance metrics (e.g., sensitivity, specificity, accuracy, or other clinical outcomes) as acceptance criteria for the device's function that would typically be evaluated in an AI-related study. Instead, it compares the technological characteristics of the subject device to predicate devices to establish substantial equivalence.
• Sample Size for Test Set & Data Provenance: This information is not explicitly provided because the studies conducted are primarily bench tests and compliance assessments against standards, not clinical performance studies with a "test set" of patient data.
• Number of Experts & Qualifications / Adjudication Method: These points are relevant for studies determining ground truth in diagnostic or AI applications. The document describes electrosurgical instruments, not a diagnostic or AI device that requires expert review for ground truth.
• Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: There is no indication that such a study was performed. The device is an electrosurgical tool, not an AI-assisted diagnostic system where human readers would be evaluated with and without AI assistance.
• Standalone Performance (Algorithm Only): The device is a physical electrosurgical instrument; there is no mention of an associated algorithm or AI component that would have standalone performance.
• Type of Ground Truth Used: "Ground truth" in the context of this document is related to the physical and electrical safety and performance of the instrument as measured by engineering and material standards, not clinical ground truth derived from expert consensus, pathology, or outcomes data in a diagnostic sense.
• Sample Size for Training Set & How Ground Truth for Training Set was Established: These concepts are entirely absent as the device is not an AI/machine learning product.

In summary, the provided text describes a submission for an electrosurgical instrument, not a device involving AI or complex clinical diagnostic performance metrics as typically seen in AI/ML medical device submissions.

Ask a specific question about this device

The FDR D-EVO GL flat panel detector system is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications including pediatic exams wherever conventional film/screen or CR systems may be used. This device is used to capture anatomic regions that are too large for conventional CR/DR format sizes. FDR D-EVO GL is not intended for mammography, fluoroscopy, tomography, and angiography applications.

Fujifilm's FDR D-EVO GL FPD System (DR-ID1300) is a digital detector system that interfaces with, and acquires and digitizes x-ray exposures from, standard radiographic systems. The DR-ID1300 is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults and pediatrics including longlength exams where anatomic regions that are too large for conventional CR/DR format sizes, such as the entire spine or lower extremities, can be captured. The DR-ID1300 employs a new DR detector with a large exposure area size of ~ 17 x 49 inches. The detector can be placed in an appropriate stand for upright exams.

The provided text contains information about the FDR D-EVO GL Flat Panel Detector System (DR-ID1300) and its 510(k) submission. However, it explicitly states:

"Clinical Performance Data: No clinical study has been performed. The substantial equivalence has been demonstrated by non-clinical studies."

Therefore, I cannot provide details on acceptance criteria and a study proving the device meets those criteria from a clinical perspective because such a study was not performed. The substantial equivalence was demonstrated through non-clinical studies and comparisons to predicate devices.

The document mentions that the device conforms to voluntary standards (e.g., AAMI/ANSI ES60601-1, IEC 60601-1, IEC 60601-1-2, IEC 62304, IEC 62366, IEC 62494-1, and DICOM) and followed FDA guidance documents for solid-state X-ray imaging devices, software, and cybersecurity. These standards and guidances implicitly define performance requirements, but specific acceptance criteria and detailed performance metrics are not explicitly presented in a table format suitable for your request.

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

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

• Cannot be provided as clinical performance data was not generated. The document only states that "All the major detector characteristics that may affect the image quality are substantially equivalent to the legally marketed DR-ID1201SE detector in K142003." and "The difference in MTF measurements is negligible, and the difference in DQE (Detective Quantum Efficiency) measurement is insignificant." These are comparative statements rather than specific acceptance criteria and reported performance values.

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

• Not applicable / Not provided. No clinical test set was used for performance evaluation as no clinical study was performed. Non-clinical bench testing was "conducted to evaluate the long view attributes that are unique to the DR-ID1300 system," but details on sample size or data provenance for these non-clinical tests are not given.

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. No clinical ground truth was established as no clinical study was performed.

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

• Not applicable. No clinical test set data was created that would require adjudication.

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. The document explicitly states "No clinical study has been performed." Additionally, this device is a flat panel detector system, not an AI-based diagnostic tool, so an MRMC study comparing human readers with and without AI assistance would not be relevant.

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

• Not applicable/Not provided. This is a hardware device (flat panel detector) that captures images, not an algorithm being evaluated for standalone performance. The "non-clinical studies" focused on validating its characteristics against a predicate device.

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

• Not applicable. No clinical ground truth was established. The "ground truth" for the non-clinical studies would be instrument specifications, physics measurements, and comparisons to the predicate device's measured characteristics.

8. The sample size for the training set:

• Not applicable/Not provided. This device is a flat panel detector system, not a machine learning algorithm that requires a training set.

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

• Not applicable/Not provided. See above.

In summary, the provided document describes a 510(k) submission for a new flat panel detector system where substantial equivalence was demonstrated through non-clinical studies and comparisons to predicate devices, rather than through clinical performance data.

Ask a specific question about this device

The EPX-4400 and EPX-4400HD Digital Video Processors with FICE are used for endoscopic observation, diagnosis, treatment, and image recording. The devices are intended to process electronic signals transmitted from a video endoscope (a video camera in an endoscope). The devices may be used on all patients requiring endoscopic examination and when using a Fujinon/FUJIFILM medical endoscope, light source, monitor, recorder and various peripheral devices. FICE is an adjunctive tool for gastrointestinal endoscopic examination which can be used to supplement FUJIFILM white light endoscopy. FICE is not intended to replace histopathological sampling as a means of diagnosis.

The EPX-4400 and EPX-4400HD Digital Video Processor with FICE and light source consist of three components used in conjunction with one another: The VP-4400/4400HD Video Processor, The XL-4400/4400HD Light Source, and The DK-4400E Keyboard. The Processor relays the image from the endoscope to a video monitor. Projection can be either analog or digital at the user's preference. The Processor incorporates internal or external digital storage capacity. The Processor also controls the light projected to the body cavity. The Processor provides for optional structural enhancement at the user's option. Spectral and structural enhancements are achieved through proprietary software. The Light Source employs a 300W Xenon lamp with a 75W emergency back-up Halogen lamp. Brightness control is performed by the user. The Keyboard is used to enter pertinent procedural information (patient, physician, date, etc.) for display on the video monitor and digital/analog storage systems. The Keyboard is also used to control operational features of the VP-4400/4400HD Processor. Both EPX-4400 and EPX-4400HD contain FICE which is an image processing technology.

The provided text is a 510(k) summary for the FUJIFILM EPX-4400 and EPX-4400 HD with FICE. It describes the device, its intended use, and substantial equivalence to a predicate device. However, it does not contain the detailed information required to answer your questions about specific acceptance criteria, study details, sample sizes, ground truth establishment, or expert involvement for a comparative effectiveness study or a standalone performance study of FICE's diagnostic capabilities.

The document primarily focuses on demonstrating substantial equivalence in terms of safety and technical characteristics consistent with an endoscopic video processor, rather than a clinical diagnostic AI.

Here's a breakdown of what can be extracted and what cannot:

Information that can be extracted from the provided text:

• 1. A table of acceptance criteria and the reported device performance: This specific detail is not present. The document mentions that "All predetermined testing criteria were met, and in all instances the device functioned as intended" for the performance tests listed below, but it does not specify the actual criteria or the quantitative results against those criteria.
  • Performance Tests listed:
    • Contrast Enhancement
    • Resolution
    • Noise
    • Artifact
    • Color Reproduction
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document states, "FUJIFILM has performed the same testing that was used to fully characterize the FICE feature as part of clearance with use with the EPX-4440HD system in K140149." The listed tests (Contrast Enhancement, Resolution, Noise, Artifact, Color Reproduction) are technical performance evaluations, which can be seen as a form of standalone performance assessment of the image processing itself. However, this is not a diagnostic standalone performance study measuring clinical endpoints like sensitivity/specificity.

Information that cannot be extracted from the provided text:

• 2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not mentioned. The testing described is technical characteristic validation, not a clinical trial with a test set of patient data.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience): Not mentioned. Ground truth for clinical diagnostic outcomes is not discussed.
• 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
• 5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: An MRMC comparative effectiveness study is not mentioned. The document describes FICE as an "adjunctive tool" and states it "is not intended to replace histopathological sampling as a means of diagnosis," which suggests it's a visualization aid rather than a primary diagnostic AI that would typically undergo MRMC studies for diagnostic improvement.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the technical performance tests, the "ground truth" would be the expected technical specifications or ideal image characteristics, but this is not defined in terms of clinical ground truth like pathology.
• 8. The sample size for the training set: The document discusses software validation and technical performance; it does not mention a "training set" in the context of machine learning or AI that learns from data.
• 9. How the ground truth for the training set was established: As no training set is discussed, this information is not present.

In summary:

This 510(k) pertains to the EPX-4400 and EPX-4400 HD with FICE as an endoscopic video processor and image processing technology to enhance visualization. The performance data provided are technical validations (software, electrical safety, contrast, resolution, noise, artifact, color reproduction) to ensure the device performs as intended and is safe, rather than clinical performance studies demonstrating diagnostic accuracy or improvement in human reader performance. The device is explicitly stated to be an "adjunctive tool" and "not intended to replace histopathological sampling."

Ask a specific question about this device

The Fujifilm Endoscopes: EG-530CT, EG-530D, EC-530DL, and ES-530WE have the following indications for use:

Indications for Use (EG-530CT):

The EG-530CT Endoscope: This device is intended for the upper digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the esophagus, stomach, and duodenum.

Indications for Use (EG-530D):

The EG-530D Endoscope: This device is intended for the upper digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the esophagus, stomach, and duodenum.

Indications for Use (EC-530DL):

The EC-530DL Endoscope: This device is intended for the lower digestive tract, soecifically for the observation, diagnosis, and endoscopic treatment of the rectum and large intestine.

Indications for Use (ES-530WE):

The ES-530WE Endoscope: This device is intended for the lower digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the rectum and sigmoid colon.

The endoscopes are comprised of three general sections: an insertion portion and an umbilicus. The operation section controls the angulation (up/down/left/ight) of the endoscope. The insertion portion contains glass fiber bundles, several channels and a charged couple device (CCD) image sensor. The glass fiber bundles allow light to travel through the endoscope and emit light from the insertion portion 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 endoscope also contains several channels to deliver air/water, provide suction, and a forceps channel. The forceps channels are 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 to the video processor and the light source.

The proposed models are used in combination with Fuilfilm's video processor, light source and peripheral devices (water tank, endoscope accessories, monitor, printer, DVD recorder, electrosurgical instruments, foot switch, and cart).

The minor modifications to the endoscopes were made for the purpose of overall product enhancement and general technological advancement.

The document describes the regulatory submission for several new endoscopes (EG-530CT, EG-530D, EC-530DL, and ES-530WE) from Fujifilm Medical Systems U.S.A., Inc. This is a 510(k) premarket notification, where the manufacturer demonstrates that the new devices are "substantially equivalent" to legally marketed predicate devices.

This submission does NOT involve a device that uses Artificial Intelligence (AI) or machine learning. Therefore, many of the requested criteria related to AI/ML device performance (like multi-reader multi-case studies, effect size of human improvement with AI, standalone performance, training set details, expert ground truth establishment for training data) are not applicable.

Instead, the acceptance criteria and proof of device performance are based on compliance with established medical device safety and performance international standards and engineering testing for physical and electrical characteristics.

Here's a breakdown of the requested information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states, "No clinical testing was conducted." The testing was primarily engineering bench testing and compliance with standards. Therefore, concepts like "test set," "sample size," and "data provenance" in the context of patient data do not apply here. The performance was demonstrated through compliance with recognized standards using the actual devices, their components, and reprocessing methods.

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

Not applicable. As noted above, no clinical testing in the form of a diagnostic performance study was conducted. The "ground truth" here is the adherence to established engineering and safety standards, assumed to be verified by qualified professionals within the testing labs and manufacturer's quality system (e.g., test engineers, biocompatibility specialists, electrical safety engineers).

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

Not applicable. There was no clinical ground truth established by multiple readers requiring adjudication.

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

Not applicable. This device is not an AI/ML device. It is a traditional medical endoscope.

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

Not applicable. This device is not an AI/ML algorithm. It is a physical medical device requiring human operation.

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

The "ground truth" for this submission is based on:

• Compliance with recognized international and national consensus standards (e.g., IEC, ISO, ANSI/AAMI for safety, EMC, usability, biocompatibility, and reprocessing).
• Engineering test results confirming the physical, electrical, and optical properties of the devices meet the specified requirements of these standards.
• Substantial equivalence to previously cleared predicate devices, suggesting that the established safety and effectiveness profiles of the predicates are maintained or improved upon by the minor modifications of the new devices.

8. The sample size for the training set

Not applicable. There is no AI/ML model involved, so there is no training set.

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

Not applicable. There is no AI/ML model involved.

Ask a specific question about this device

The Wireless/Wired FDR D-EVO II flat panel detector system is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications including pediatric and neonatal exams wherever conventional film/screen or CR systems may be used. The FDR D-EVO II is not intended for mammography, fluoroscopy, tomography, and angiography applications.

Fujifilm's FDR D-EVO II Flat Panel Detector System (DR-ID1200) is a portable digital detector system that interfaces with, and acquires and digitizes x-ray exposures from, standard radiographic systems. The FDR D-EVO II 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 or free cassette exams.

While maintaining Fujifilm's unique Irradiated Side Sampling (ISS) design delivering high image quality. FDR D-EVO II offers the new and improved 1200 series flat panel detectors with upgraded wireless feature, memory exposure mode, and extended image readout feature. Additionally, the 1200 series detectors are equipped with several changes: Rounded-edge design for easy handling, image compression algorithm for faster image transfer, improved internal circuit design for electronic noise reduction, new LED design for easy detector identification, extra protection against ingress of water, and antibacterial coating designed to maintain cleanness. Not only the 1200 series detectors' robust design enhances load-bearing characteristics, but also the powersaving designs combined with the new battery packs and charger improve battery performance. The weight of 1200 series detectors is less than that of 600 series.

The provided document
"FUJIFILM Medical Systems U.S.A., Inc." (K142003)
is a 510(k) premarket notification for the "FDR D-EVO II Flat Panel Detector System (DR-ID1200)".
This document states that no clinical study was performed to demonstrate that the device meets acceptance criteria. Instead, substantial equivalence was demonstrated by non-clinical studies. This means there is no data on human clinical performance provided in this document to populate the requested table or answer several of the questions, as they pertain to clinical studies.

However, the document does mention non-clinical performance data and states that "the image quality evaluation confirmed that the image quality of the FDR D-EVO II system using new 1200 series detectors is substantially equivalent to that of the predicate device." This suggests that image quality was a key acceptance criterion and was evaluated through non-clinical means.

Here's a breakdown of the requested information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Not applicable for clinical data: "No clinical study has been performed."
• For non-clinical tests: The document does not specify sample sizes for the various non-clinical engineering and performance tests (e.g., load-bearing, water ingress, EMC, antibacterial coating). The data provenance is internal to Fujifilm's testing and validation processes.

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 for clinical data: "No clinical study has been performed." For non-clinical tests, "ground truth" as referred to in a clinical context (expert consensus on disease presence) is not relevant. Engineering standards and specifications served as the "ground truth" for non-clinical performance.

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

• Not applicable for clinical data: "No clinical study has been performed."

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, an MRMC comparative effectiveness study was not done. The device itself is a flat panel detector (hardware), not an AI-assisted diagnostic tool. No clinical studies were performed.

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

• No standalone clinical performance study was done. The device is a digital X-ray detector; it does not operate as an "algorithm only" device in a diagnostic sense. Its standalone performance was evaluated through non-clinical means, primarily engineering tests and comparisons of technical imaging characteristics (MTF, DQE) to a predicate device.

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

• For non-clinical studies: The "ground truth" for the non-clinical tests was established by adherence to recognized industry standards (e.g., AAMI/ANSI ES60601-1, IEC series, ISO 10993, JIS Z 2801, DICOM), FDA guidance documents, and internal design specifications/requirements verified through engineering testing.
• For clinical studies: Not applicable, as no clinical studies were performed.

8. The sample size for the training set:

• Not applicable: This device is a flat panel detector; it is not described as an AI/machine learning device that would require a "training set" for an algorithm.

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

• Not applicable: As the device does not employ machine learning/AI requiring a training set, this question is not relevant.

Ask a specific question about this device

This product is intended to supply CO2 gas and feed water to clean lenses in the gastrointestinal tract when used as an accessory with Fujifilm's endoscopy system.

The Fujifilm Endoscopic CO2 Regulator GW-100 supplies CO2 gas to insufflate the gastrointestinal tract and water to wash the endoscope lens during an examination. The GW-100 is similar to Olympus' XECR-2 Endoscopic Insufflation Unit. The scientific fundamental technology and operating principle of the subject and predicate devices are similar. Both devices utilize a solenoid/decompression valve mechanism to dispense CO2. CO2 can either be supplied from a CO2 gas cylinder or from a facility's main CO2 supply.

The GW-100 can be used with any Fujnon/Fujifilm gastrointestinal endoscope, Fujinon/Fuiifilm Video Processor/Light Source system, video monitor, footswitch, cart, endoscopic accessories, electrosurgical unit and other peripheral devices used for endoscopy.

The provided document is a 510(k) summary for the Fujifilm Endoscopic CO2 Regulator GW-100. It details the device's intended use and substantial equivalence to a predicate device, but it does not contain information about acceptance criteria for device performance or a study demonstrating that the device meets those criteria, as typically found for AI/ML-based devices.

This document describes a medical device seeking clearance based on substantial equivalence, which is a different regulatory pathway than proving performance against specific clinical acceptance criteria for new AI/ML-based diagnostic or therapeutic devices. The studies mentioned are primarily related to electrical safety, electromagnetic compatibility (EMC), software validation, and biocompatibility, not clinical performance metrics like sensitivity, specificity, or reader improvement.

Therefore, most of the requested information cannot be extracted from this document.

Here's what can be gathered, with notes explaining the absence of other details:

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

• Acceptance Criteria: Not explicitly stated in terms of clinical performance metrics. The device's "acceptance" is based on its substantial equivalence to a predicate device and meeting safety/performance standards (electrical safety, EMC, software, biocompatibility).
• Reported Device Performance: Performance is demonstrated through compliance with safety and engineering standards. No clinical performance metrics (e.g., accuracy, sensitivity, specificity) are reported.

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

• Not applicable for this type of submission. This submission relies on substantial equivalence and non-clinical engineering tests, not a clinical test set with patient data for performance 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)

• Not applicable. No clinical ground truth was established for a test set in this submission.

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

• Not applicable. No clinical test set or adjudication was performed.

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. This is a hardware device (CO2 regulator), not an AI-assisted diagnostic or therapeutic tool. Therefore, an MRMC study is not relevant.

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

• Not applicable. This device is a hardware accessory for an endoscopy system, not a standalone algorithm.

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

• Not applicable. No clinical performance ground truth was established. The "ground truth" here is compliance with established engineering and safety standards.

8. The sample size for the training set

• Not applicable. As this is not an AI/ML device, there is no concept of a training set for an algorithm. Device validation was based on testing against design specifications and international standards.

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

• Not applicable. See point 8.

Ask a specific question about this device

ASPIRE Bellus is intended to receive digital mammography images and to display these images on monitors for radiologists' review for diagnostic and screening purposes. To assist radiologists, ASPIRE Bellus provides functions such as image review, measurement, post-processing, film printing, displaying mammography CAD results, and image manipulation.

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

FUJIFILM's Mammography Viewer SMV658 (V3.0) system receives mammography images directly from FUJIFILM's digital mammography acquisition systems using DICOM protocol and PACS via network. These images are displayed on mammography diagnostic monitors for doctors' review. The SMV658 system works as mammography workstation depending on its configuration (monitors) and license information (software key). The system provides visualization and image enhancement tools (such as image review, measurement, postprocessing, film printing, displaying mammography CAD results, and image manipulation) to assist the radiologists' review of mammography images for diagnostic and screening purposes.

Here's an analysis of the provided text regarding the acceptance criteria and study for the FUJIFILM Medical Systems U.S.A., Inc. SMV658 V3.0 (ASPIRE Bellus / Mammography Viewer SMV658) 510(k) submission.

Critical Note: The provided 510(k) summary is for a mammography viewer software (PACS), not an AI or CAD device. Therefore, the typical performance metrics (sensitivity, specificity, AUC) and study designs (MRMC, standalone) associated with AI diagnostic aids are not present because the device's function is image display and manipulation, not diagnostic interpretation. The "acceptance criteria" discussed are primarily related to software functionality and safety, not diagnostic accuracy.

Acceptance Criteria and Reported Device Performance

Study Details (Based on the provided text)

1. 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 performance testing using actual clinical images." However, it does not specify the sample size of these clinical images.
   • The provenance (country of origin, retrospective/prospective) of the clinical images used for bench performance testing is not mentioned in the provided text.

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

   • The document does not describe an expert-based ground truth establishment process for a diagnostic performance study. The "testing" mentioned is primarily focused on software functionality and its ability to display images and perform measurements as intended. For "bench performance testing using actual clinical images," it's implied that the accuracy of the software's display and measurement capabilities was assessed, but not against a "ground truth" of disease presence/absence established by experts for diagnostic purposes.

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

   • Not applicable / not mentioned. Since there is no expert-based ground truth establishment for diagnostic performance, adjudication methods for disagreements among experts are not relevant to the described testing.

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, an MRMC comparative effectiveness study was not done. The device is a mammography viewer, not an AI or CAD system intended to provide diagnostic interpretations or assist human readers in lesion detection/diagnosis. Therefore, the concept of human reader improvement with or without AI assistance is not relevant to this device's intended use and testing.

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

   • No, a standalone diagnostic performance study was not done. This device is a viewer that supports radiologists; it is not an algorithm designed to make diagnostic interpretations or detections independently. Its "performance" relates to its functionality, display accuracy, and measurement capabilities, not standalone diagnostic accuracy. The bench testing with clinical images likely validated its ability to correctly display and measure features, not to diagnose.

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

   • For the "bench performance testing using actual clinical images," the document does not explicitly state the type of "ground truth" used. However, given the device's function (viewer with measurement tools), the "ground truth" for these tests would likely involve:
     • Reference measurements: For measurement accuracy, a known, precise measurement (e.g., from a calibrated tool or pre-adjudicated measurement on the image) would serve as ground truth to compare against the device's measurement function.
     • Image integrity/display fidelity: For display-related performance, the ground truth would be the original image data and its accurate representation on the monitor.
   • It is not using pathology, expert consensus on disease, or outcomes data, as those are typical for diagnostic AI devices, which this is not.

7. The sample size for the training set:

   • Not applicable / not mentioned. This device is an image viewer with image processing and manipulation tools. It does not appear to be an AI or machine learning model that requires a "training set" in the conventional sense for diagnostic prediction. Its development likely involved standard software engineering practices and testing against specifications.

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

   • Not applicable / not mentioned. As there's no indication of a training set for an AI/ML model, the establishment of ground truth for such a set is not discussed.

Summary of Device and Context:

It's crucial to understand that the FUJIFILM Medical Systems U.S.A., Inc. SMV658 V3.0 (ASPIRE Bellus / Mammography Viewer SMV658) is a PACS (Picture Archiving and Communications System) or a specialized workstation for viewing digital mammography images. Its primary functions are receiving, displaying, enhancing, and manipulating images, as well as displaying CAD results (generated by other cleared CAD systems, not the viewer itself).

Therefore, the "acceptance criteria" and "study" described in this 510(k) are focused on:

• Software verification and validation: Ensuring the software functions as designed, is reliable, and meets its specifications.
• Safety: Hazard analysis and mitigation.
• Substantial equivalence: Demonstrating that it performs similarly to other legally marketed mammography viewers without raising new safety or effectiveness concerns.

It is not a diagnostic AI device, and thus, its regulatory submission does not include the typical performance metrics or study designs (e.g., MRMC, standalone performance, sensitivity/specificity) associated with AI-based diagnostic aids.

Ask a specific question about this device

Synapse 3D Lung and Abdomen 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, reporting, and treatment planning. Synapse 3D Lung and Abdomen Analysis accepts DICOM compliant medical images acquired from CT.

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 Lung and Abdomen Analysis is intended to;

• use non-contrast and contrast enhanced computed tomographic images of the lung, provide custom workflows and UI, and reporting functions for lung analysis including boundary detection and volume calculation for pulmonary nodules in the lung based on the location specified by the user, segmentation of bronchial tubes in the lung, approximation of air supply region by the user specified bronchial tube, identifying, displaying and processing low absorption regions in the lung.

• use non-contrasted CT images and calculate subcutaneous fat and visceral fat areas in 2D and both volumes in 3D.

• analyze a bronchus path to reach a lung nodule using the volume data collected with CT, and simulate insertion of bronchoscope into the path.

Synapse 3D Lung and Abdomen Analysis is the updated version of previously - cleared Synapse 3D Lung and Abdomen Analysis software (cleared by CDRH via K120648 on 06/14/2012).

Synapse 3D Lung and Abdomen Analysis is used in addition to Synapse 3D Base Tools (K120361) to analyze the images acquired from CT. Synapse 3D Lung and Abdomen Analysis is intended to provide trained medical professionals with tools to aid them in reading, interpreting, reporting, and treatment planning of DICOM compliant medical images. Synapse 3D Lung and Abdomen Analysis is an application that performs the CT lung analysis/airway, lung analysis scope, and abdomen 2D and 3D fat analysis.

Here's an analysis of the provided text regarding the Synapse 3D Lung and Abdomen Analysis device, focusing on acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states: "we conducted the bench performance testing using actual clinical images". However, it does not specify the sample size for the test set or the data provenance (e.g., country of origin, retrospective or prospective nature of the "clinical images").

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

The document does not specify the number of experts used or their qualifications to establish ground truth for the test set.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method for the test set.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or described in the provided text. The submission focuses on device performance studies against defined criteria rather than comparative effectiveness with human readers.

6. Standalone Performance Study

Yes, a standalone performance study was done. The document states: "Testing involved system level functionality test, segmentation accuracy test, measurement accuracy test, interfacing test, usability test, serviceability test, labeling test, as well as the test for risk mitigation method analyzed and implemented in the risk management process. In addition, we conducted the bench performance testing using actual clinical images to help demonstrate that the proposed device achieved the expected accuracy performance." This indicates that the device was tested on its own to meet set criteria.

7. Type of Ground Truth Used

The document implies that the ground truth for "segmentation accuracy" and "measurement accuracy" was based on some form of pre-established "requirements" and "expected accuracy performance" but does not explicitly state the type of ground truth used (e.g., expert consensus, pathology, outcomes data, etc.) for the clinical images. It only mentions that "Pass/Fail criteria were based on the requirements and intended use of the product."

8. Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set.

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

The document does not provide any information on how the ground truth for the training set (or if a training set was even used, though implied for such a device) was established.

Ask a specific question about this device