Search Results

True Definition DL is a deep learning based CT reconstruction method intended for high contrast spatial resolution enhancement for bone and lung imaging. True Definition DL may be used for patients of all ages.

Computed Tomography (CT) is an indispensable imaging modality in clinical diagnostics due to its ability to provide detailed cross-sectional images of anatomical structures. However, achieving high spatial resolution remains a persistent challenge, particularly in applications requiring the visualization of fine structural details such as in inner auditory canal imaging, vascular studies, lung imaging, and bone microarchitecture analysis. Reconstruction techniques that attempt to boost spatial resolution typically also would amplify the noise which often result in tradeoffs to be made between resolution and noise.

As part of the continuous innovation to solve the above challenges in CT imaging, GEHC developed a deep learning-based CT reconstruction algorithm specifically designed for high contrast lung and bone imaging, which is the subject of this premarket notification. This reconstruction algorithm, marketed under the name True Definition DL (TDDL), is an additional user-selectable recon option specifically designed for lung and bone imaging. It aims to enhance spatial resolution for both in-plane and cross-plane directions. This algorithm is incorporated into the reconstruction chain of the Revolution CT /Apex Family CT systems including Revolution CT/Revolution CT ES, Revolution Apex Elite, Revolution Apex Plus, Revolution Apex Select all cleared under (K213715) and Revolution Vibe (K250941).

True Definition DL offers three strengths that the user can choose depending on enhancement preferences. The benefits provided by this enhancement include improved spatial resolution measured by MTF.

Here's a breakdown of the acceptance criteria and study details for the "True Definition DL" device, as extracted from the provided FDA 510(k) clearance letter:

Acceptance Criteria and Device Performance

Study Details

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

   • Sample size: Not explicitly stated for the clinical reader study, only referred to as "sample clinical data."
   • Data provenance: Not explicitly stated (e.g., country of origin or retrospective/prospective).

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

   • Number of experts: Not explicitly stated.
   • Qualifications: "US board-certified radiologists."

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

   • Not explicitly stated. The document mentions "readers confirmed," implying a consensus or majority opinion, but the specific adjudication method is not described.

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

   • A reader study was performed ("clinical testing was carried out in the form of a reader study").
   • The document states that the study "validated that True Definition DL provides diagnostic value by improving high contrast spatial resolution... and improves confidence in the assessment of high contrast structures."
   • However, the document does not explicitly state that it was an MRMC comparative effectiveness study comparing human readers with AI vs. without AI assistance. It primarily focuses on the diagnostic value and confidence with the use of the images enhanced by True Definition DL.
   • No effect size or specific metrics quantifying improvement with AI assistance are provided.

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

   • Yes, a standalone evaluation of the algorithm's performance was indicated through "robustness of the True Definition DL algorithm" testing. This included assessment of hallucination risks, enhancement of anatomical edges, preservation of noise texture, and correlation with input/target images, suggesting an algorithm-level assessment.
   • Bench testing on phantoms also measured the performance of True Definition DL against industry-standard IQ metrics and traditional metrics without direct human interaction.

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

   • For the clinical reader study, the "ground truth" was established by expert opinion/consensus of US board-certified radiologists who evaluated the images and confirmed diagnostic value and lack of artifacts.
   • For bench testing, "well established test methods using industry-standard IQ metrics" provided quantifiable reference points for performance.

7. The sample size for the training set:

   • Not explicitly stated.

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

   • Not explicitly stated. The document only mentions that True Definition DL is a "deep learning-based CT reconstruction algorithm," implying a training phase, but provides no details on how the training data was curated or its ground truth established.

Ask a specific question about this device

TrueFit Bolus is indicated for and intended to be placed on the patient's skin as an accessory to attenuate and/or compensate external beam (photon or electron) radiation during prescribed radiation therapy for the treatment of cancer or other non-malignant tissue conditions for which radiation therapy is indicated.

The device is for a single patient's use only and can be reused throughout the entirety of the treatment course.

The device is designed by the radiation therapy professional using patient imaging data as input and must be verified and approved by the trained radiation therapy professional prior to use.

The device is restricted to sale by or on the order of a physician and is by prescription only.

TrueFit Bolus is a 3D printed patient-matched radiation therapy accessory that expands the application of external beam radiation therapy by providing a patient-specific fit.

Patient imaging data from the treatment planning system (TPS) are used as inputs to generate digital design of the radiation therapy bolus (TrueFit) by 3D Bolus Software Application (K213438), previously developed by Adaptiiv. The resulting output Stereolithography (STL) file is compatible with the third-party 3D printers. A TrueFit Bolus can be 3D-printed using MJF with polyamide or polyurethane, or SLA with methacrylate photopolymer resin, based on the user's preference.

The bolus is used in radiation therapy when a patient requires the total prescription dose to be delivered on or near the skin surface. The bolus acts as a tissue-equivalent material placed on the patient skin to account for the buildup region of the treatment beam.

N/A

Ask a specific question about this device

The TrueBeam™, TrueBeam STx and Edge™ Systems are intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation therapy is indicated for adults and pediatric patients. The TrueBeam radiotherapy system can produce CBCT images that can be used in image guided radiation therapy, and the simulation and planning for adaptive radiation therapy.

The TrueBeam, TrueBeam STx and Edge Systems may be used in the delivery of radiation for treatment that includes: brain and spine tumors (such as glioma, meningioma, craniopharyngioma, pituitary tumors, spinal cord tumors, hemangioblastoma, orbital tumors, ocular tumors, optic nerve tumors, and skull based tumors), head and neck tumors (such as unknown primary of the head and neck, oral cavity, hypopharynx, larynx, oropharynx, nasopharynx, sinonasal, salivary gland, and thyroid cancer), thoracic tumors (such as lung cancer, esophageal cancer, thymic tumors, and mesothelioma), gynecologic tumors (such as ovarian, cervical, endometrial, vulvar, and vaginal), gastrointestinal tumors (such as gastric, pancreatic, hepatobiliary, colon, rectal, and anal carcinoma), genitourinary tumors (such as prostate, bladder, testicular, and kidney), breast tumors, sarcomas, lymphoid tumors (such as Hodgkin's and non-Hodgkin's lymphoma), skin cancers (such as squamous cell, basal cell, and melanoma), benign diseases (such as schwannoma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, chordoma, glomus tumors, hemangiomas, and medically refractory essential tremor (indicated for adults only)), metastasis (including all parts of the body such as brain, bone, liver, lung, kidney, and skin), pediatric tumors (such as glioma, ependymoma, pituitary tumors, hemangioblastoma, craniopharyngioma, meningioma, metastasis, medulloblastoma, nasopharyngeal tumors, arteriovenous malformation, cavernous malformation, and skull base tumors), and low-dose radiotherapy for adults with medically refractory osteoarthritis.

VitalBeam® is intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation therapy is indicated for adults and pediatric patients.

VitalBeam may be used in the delivery of radiation for treatment that includes: brain and spine tumors (such as glioma, meningioma, craniopharyngioma, pituitary tumors, spinal cord tumors, hemangioblastoma, orbital tumors, ocular tumors, optic nerve tumors, and skull based tumors), head and neck tumors (such as unknown primary of the head and neck, oral cavity, hypopharynx, larynx, oropharynx, nasopharynx, sinonasal, salivary gland, and thyroid cancer), thoracic tumors (such as lung cancer, esophageal cancer, thymic tumors, and mesothelioma), gynecologic tumors (such as ovarian, cervical, endometrial, vulvar, and vaginal), gastrointestinal tumors (such as gastric, pancreatic, hepatobiliary, colon, rectal, and anal carcinoma), genitourinary tumors (such as prostate, bladder, testicular, and kidney), breast tumors, sarcomas, lymphoid tumors (such as Hodgkin's and non-Hodgkin's lymphoma), skin cancers (such as squamous cell, basal cell, and melanoma), benign diseases (such as schwannoma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, chordoma, glomus tumors, and hemangiomas), metastasis (including all parts of the body such as brain, bone, liver, lung, kidney, and skin), pediatric tumors (such as glioma, ependymoma, pituitary tumors, hemangioblastoma, craniopharyngioma, meningioma, metastasis, medulloblastoma, nasopharyngeal tumors, arteriovenous malformation, cavernous malformation, and skull base tumors), and low-dose radiotherapy for adults with medically refractory osteoarthritis.

The TrueBeam and VitalBeam Radiotherapy System is a medical linear accelerator that delivered therapeutic radiation to patient in accordance with the physician's prescription.

The system consists of two major components – a photon, electron and diagnostic kV X-ray radiation beam producing component that is installed in a radiation-shielded vault and a control console area located outside the treatment room.

N/A

Ask a specific question about this device

The DRX9000-SL True Non-Surgical Spinal Decompression System provides a primary treatment modality for the management of pain and disability for patients suffering with incapacitating low back pain and sciatica. It is designed to apply spinal decompressive forces to compressive and degenerative injuries of the spine. It has been found to provide relief of pain and symptoms associated with herniated discs, bulging or protruding intervertebral discs, degenerative disc disease, posterior facet syndrome and sciatica.

The DRX9000-SL True Non-Surgical Spinal Decompression System provides accurately controlled tensions designed to relax and confuse paraspinal muscles and allow distractive forces to decompress intervertebral spinal disc space. The user interface provided by the treatment computer constantly updates a servo-amplifier controlling a servo-motor to immediately and safely apply forces as determined by qualified healthcare personnel. Load-cell feedback is utilized to further verify and adjust tensile forces, allowing for variations in patient posture and outside forces such that continuous and smooth tension is experienced by the patient.

An upper chest harness and a lower pelvic harness are used to help distribute the applied forces evenly. Once in place, the patient is slowly reclined to a horizontal position. Following the physician's orders, the therapist localizes the pain, makes any adjustments and directs the treatment to the proper area. The DRX9000-SL True Non-Surgical Spinal Decompression System helps to mobilize the troubled disc segment without introducing further damage to the spine.

The patient safety switch is held by the patient who at any time and for any reason may quickly pause any tensile forces. The patient safety switch is monitored and executed by two redundant systems, which will gradually reduce the tension to zero to stop the treatment and after a 5 second delay directly disable the treatment motor.

The emergency stop button is accessible to the operator who at any time and for any reason may quickly pause any tensile forces. The emergency stop button is monitored and executed by two redundant systems, which will gradually reduce the tension to zero to stop the treatment and after a 5 second delay directly disable the treatment motor.

Integral to effective spinal decompression and included in the device are continuous load-cell tensile feedback into the treatment computer, dedicated and matched servo-amplifier and servo-motor, smoothly modulated cyclic tension application (high and low tension plateaus transitioned into via non-linear tension change), two segment (upper and lower) textile patient harness, patient safety switch, and free-floating lower body mattress. The free-floating lower body mattress allows the interdiscal segments of the lumbar spine to decompress at their own rate. As tension is cycled, the lower body can extend independent of the upper body which is held in place via an upper body textile patient harness. The treatment bed and textile harness allow the patient to relax completely and require no conscious exertion on the part of the patient. Total patient relaxation encourages paraspinal muscle relaxation from both a physical and psychological standpoint and is a key to spinal decompression.

The provided FDA 510(k) clearance letter and summary for the DRX9000-SL True Non-Surgical Spinal Decompression System do not contain information related to acceptance criteria for an AI device, nor any study that proves an AI device meets such criteria.

The submission is for a medical device that applies spinal decompressive forces, and it primarily focuses on demonstrating substantial equivalence to a predicate device (DRX9000 True Non-Surgical Spinal Decompression System) through non-clinical testing of electrical safety, EMC, usability, risk management, biocompatibility, and software.

Therefore, I cannot provide the requested information, as the input document does not pertain to an AI device or a study with typical AI-related acceptance criteria.

Ask a specific question about this device

TrueLok Elevate is intended for treatment of non-union or pseudoarthrosis of long bones and correction of bony or soft tissue defects or deformities. The TrueLok Elevate is indicated for adult and pediatric (greater than 2 through 21 years of age) patients.

The subject TrueLok Elevate is an external fixation component system (including its accessories) to be used with the Orthofix TrueLok family, for which Orthofix identified as a predicate device TrueLok Hexapod System (TL-HEX) V2.0 (K170650). The subject device consists in a further series of elements for external fixation added to the Orthofix TrueLok family with the aim of supporting the Orthofix TrueLok external fixator systems family falling within the indications for use of the more extensive, cleared indications for use of the chosen predicate device, for the specific use in bone transport treatment.
The subject TrueLok Elevate is intended for treatment of non-union or pseudoarthrosis of long bones and correction of bony or soft tissue defects or deformities.
The TrueLok Elevate is indicated for adult and pediatric (greater than 2 through 21 years of age) patients.
The subject device is constituted by an external fixator and related accessories (half pins, k-wires, drill positioning guide, template and template inserts and convenience kits).
The technique for the use of the subject device consists in fixing two half pins on the first cortical of the bone segment that the surgeon decided to transport, and two half pins on both cortexes of the bone.
The positioning of the half pins is driven by a template.
During the treatment, through the knob present on the device, the bone segment is gradually pulled outward by the patient/caregiver to laterally transport the bone segment.
The subject device, as the predicate, will be implanted only by Healthcare Professionals (HCP), with full awareness of the appropriate orthopedic procedures (including application and removal), in the operating theatre only. The distraction of the limb will be activated in home by the patient/caregiver or in clinic theatre by the HCP. Treatment activation for pediatric patients in the home environment may require the assistance of a caregiver.

The Orthofix TrueLok™ Elevate is an external fixation component system intended for the treatment of non-union or pseudoarthrosis of long bones and correction of bony or soft tissue defects or deformities in adult and pediatric patients (greater than 2 through 21 years of age).

Here's an analysis of the acceptance criteria and the study performed, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific pass/fail acceptance criteria values for the mechanical tests conducted. Instead, it describes comparative testing against predicate or reference devices to demonstrate similarity in performance. The assessment for each technological characteristic indicates that "no different questions have been raised" or that the subject device's indications fall within the predicate's, suggesting that the goal was to demonstrate equivalence rather than meeting pre-defined numerical thresholds for acceptance.

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

The document does not explicitly state the sample sizes used for the mechanical tests (e.g., number of external fixators or half pins tested).
The provenance of the data is not specified regarding country of origin or whether it was retrospective or prospective, as these were bench tests performed on devices rather than patient data.

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

This information is not applicable to this type of submission. The ground truth for mechanical performance is established through standardized testing protocols (e.g., ASTM standards) and comparisons to previously cleared predicate devices, not through expert consensus on medical images or patient outcomes.

4. Adjudication Method for the Test Set

This information is not applicable to this type of submission as the mechanical tests are objectively measured, not subject to subjective interpretation requiring adjudication.

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

An MRMC study was not performed. This type of study is typically relevant for AI/imaging devices where human reader performance is being evaluated with and without AI assistance. The TrueLok™ Elevate is a physical external fixation system.

6. Standalone (Algorithm Only) Performance Study

A standalone study was not performed, as the device is a physical medical device, not a software algorithm.

7. Type of Ground Truth Used

The ground truth used for demonstrating performance was based on objective mechanical measurements conducted in accordance with recognized industry standards (e.g., ASTM F1541-17) and comparisons to the established performance characteristics of legally marketed predicate devices. The "truth" is that the new device's mechanical properties fall within acceptable limits or are comparable to those of the predicate, as determined by these tests.

8. Sample Size for the Training Set

This information is not applicable. The TrueLok™ Elevate is a physical medical device, not a machine learning algorithm that requires a training set.

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

This information is not applicable for the reasons stated in point 8.

Ask a specific question about this device

TrueFit/TrueFlex Bolus is indicated for and intended to be placed on the patient's skin as an accessory to attenuate and/or compensate the external beam (photon or electron) radiation during the treatment of various types of cancer.

The device is for a single patient's use only and can be reused throughout the entirety of the treatment course.

The device is designed by the radiation therapy professional using patient imaging data as input and must be verified and approved by the trained radiation therapy professional prior to use.

The device is restricted to sale by on the order of a physician and is by prescription only.

TrueFit/TrueFlex Bolus is a 3D printed patient-matched radiation therapy accessory that expands the application of external beam radiation therapy by providing a patient-specific fit.

Patient imaging data from the treatment planning system (TPS) are used as inputs to generate digital design of the radiation therapy bolus (TrueFlex) by 3D Bolus Software Application (K213438), previously developed by Adaptiv. The resulting output Stereolithography (STL) file is compatible with the third-party 3D printers. A TrueFit Bolus is 3D printed by MJF technology using polyamide or polyurethane material. A Final TrueFlex Bolus device is manufactured by filling a mould with silicone.

The bolus is used in radiation therapy when a patient requires the total prescription dose to be delivered on or near the skin surface. The bolus acts as a tissue-equivalent material placed on the patient skin to account for the buildup region of the treatment beam.

This document, a Special 510(k) Summary for K243057, does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a study proving the device meets those criteria. The provided text is a regulatory submission focused on demonstrating substantial equivalence to a predicate device rather than a comprehensive report of a clinical performance study.

However, I can extract and present the information that is available within the document:

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

The document mentions "acceptable spatial fidelity" and "acceptable physical and radiological properties" as performance outcomes, but it does not specify quantitative acceptance criteria for these. It states that tests "verified that the chosen methods performed as intended" and "did not affect the overall safety and effectiveness of the device."

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

• Sample size: The document states "worst-case geometrical test samples and real-patient final devices" were used for Verification and Validation activities. It does not provide a specific number for the sample size.
• Data provenance: Not specified.

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

This information is not provided in the document. The general indication statement mentions that "the device is designed by the radiation therapy professional using patient imaging data as input and must be verified and approved by the trained radiation therapy professional prior to use." This refers to the clinical use process, not the establishment of ground truth for device testing.

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

This information is not provided in the document.

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

This document describes a medical device (TrueFit Bolus, TrueFlex Bolus) which is a 3D-printed accessory for radiation therapy, applied to the patient's skin. It is not an AI-powered diagnostic or decision support software. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not applicable to this device type.

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

The device itself is a physical bolus. Its design process involves software (3D Bolus Software Application - K213438), which generates a digital design, and then a physical product is manufactured. The software component, by its nature, is "standalone" in generating the STL file, but the overall product (the bolus) is applied by a human and is a physical accessory designed to interact with external beam radiation. The document focuses on the physical and radiological properties of the manufactured bolus rather than the performance of an algorithm in isolation for diagnostic or interpretive tasks.

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

The document focuses on "acceptable spatial fidelity" and "acceptable physical and radiological properties." Ground truth for these aspects would typically involve:

• Precise measurements of the 3D printed objects against the digital design for spatial fidelity.
• Laboratory measurements of material density, Hounsfield units (for radiological properties), and physical characteristics (e.g., flexibility, rigidity) for physical/radiological properties.
  The document does not detail the specific ground truth methods or references.

8. The sample size for the training set

This information is not applicable and is not provided. This is a medical device clearance document for a manufactured product, not an AI/machine learning model where a training set size would be relevant. The "design" of the bolus is based on patient imaging data as input to software, but the software itself (K213438) has been previously developed, and details of its training (if applicable, as it's not explicitly stated to be an AI/ML product) are not covered here.

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

Not applicable, as it's not an AI/ML model for which a training set and its ground truth would be described in this context.

Ask a specific question about this device

True Enhance DL is a deep learning-based image processing method trained to estimate monochromatic, 50 keV GSI images. The algorithm is intended to improve the contrast of 120 kVp, single energy images of the body.

This device is intended to provide non-quantitative, adjunct information and should not be interpreted without the original 120 kVp image.

True Enhance DL may be used for patients of all ages.

True Enhance DL is a deep learning-based image processing method for contrast enhanced images of the body obtained using the Revolution Ascend Family (K213938), which consists of multiple commercial configurations: Revolution Ascend Elite, Revolution Ascend Plus, and Revolution Ascend Select. True Enhance DL is intended to post-process single energy, 120 kVp images to output nonquantitative, adjunctive information with better contrast than single energy input data.

True Enhance DL brings four deep leaning models that the user can choose depending on different contrast enhancement phases. These four models are CT Angiography, Arterial, Portal/Venous, and Delayed True Enhance DL.

True Enhance DL is not intended to replace hardware based Monochromatic Imaging by Gemstone Spectral Imaging (GSI) technology or replicate GSI dual energy acquisitions. The device was trained to estimate monochromatic, 50 keV GSI images, and only enhances images from 120 kVp acquisitions on non-GSI Revolution Ascend systems.

Here's a breakdown 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:

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

• Sample Size: Not explicitly stated as a number of cases. The text mentions "sample clinical data" and "Additional representative clinical cases and anthropomorphic phantom cases."
• Data Provenance: Retrospective. The study used "retrospectively collected representative clinical cases." The country of origin is not specified.

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

• Number of Experts: Four.
• Qualifications of Experts: "Four board certified radiologists." Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set:

• The text does not explicitly state a formal adjudication method (e.g., 2+1, 3+1). It indicates that the four radiologists each provided a comparative assessment of image quality related to diagnostic use. This suggests individual reader assessment rather than a consensus-building adjudication process for ground truth. However, they were asked to "rate the contrast enhancement in the True Enhance DL series vs the native image series," which implies a comparative evaluation.

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

• A MRMC-like study was done, as "four board certified radiologists" read the images.
• Effect Size: The text states, "the readers were asked to rate the contrast enhancement in the True Enhance DL series vs the native image series" and "validated that True Enhance DL software provides additional benefit by improving contrast." However, a quantitative effect size of human readers' improvement with AI vs. without AI assistance is not provided in this summary. The focus was on the software's ability to improve contrast rather than a comparative effectiveness of human performance with and without the tool.

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

• Yes, a standalone evaluation was conducted to assess image characteristics. The text mentions "Additional representative clinical cases and anthropomorphic phantom cases from a GSI system generating both single energy 120 kVp and 50 keV monochromatic images were evaluated for CT number in various anatomical regions to study image characteristics for different materials of the device output compared to 50 keV and 120 kVp reference images." This assesses the algorithm's output properties directly against a reference, which constitutes a standalone performance aspect.

7. The Type of Ground Truth Used:

• Expert Consensus / Reader Assessment: For the image quality and contrast improvement aspects, the subjective assessment of "four board certified radiologists" served as the ground truth.
• Reference Images / Clinical Data: For the standalone evaluation, "50 keV and 120 kVp reference images" (likely derived from GSI systems with known energy characteristics) were used to study the algorithm's output. Clinical cases with "disease/pathology" were used, implying the presence of known conditions, although how these conditions served as "ground truth" for the AI's performance beyond simply being present in the data is not fully detailed.

8. The Sample Size for the Training Set:

• The sample size for the training set is not provided in this document. The text only states, "The device was trained to estimate monochromatic, 50 keV GSI images."

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

• The document implies that the training was based on "to estimate monochromatic, 50 keV GSI images." This suggests that 50 keV monochromatic GSI images (likely acquired from dual-energy CT scans, which serve as a form of ground truth for spectral decomposition) were used as the target output for the deep learning model during training. The process of generating these reference 50 keV GSI images themselves would involve the CT system's physics and reconstruction algorithms.

Ask a specific question about this device

TrueBeam-TrueBeam STx-Edge: The TrueBeam ™ radiotherapy delivery system is intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation treatment is indicated.

VitalBeam: The VitalBeam system is intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation treatment is indicated.

The TrueBeam and VitalBeam Radiotherapy System is a medical linear accelerator that delivered therapeutic radiation to patient in accordance with the physician's prescription.

The system consists of two major components – a photon, electron and diagnostic kV X-ray radiation beam producing component that is installed in a radiation-shielded vault and a control console area located outside the treatment room.

The provided text does not contain information about an AI/ML device or its acceptance criteria. Instead, it is an FDA 510(k) clearance letter for the Varian Medical Systems TrueBeam, TrueBeam STx, EDGE, and VitalBeam (4.1) radiation therapy systems.

The document discusses:

• Device Name & Regulation: TrueBeam, TrueBeam STx, EDGE, and VitalBeam (4.1), regulated as a Medical Charged-Particle Radiation Therapy System (21 CFR 892.5050, Class II, Product Code: IYE).
• Intended Use & Indications for Use: The devices are intended for stereotactic radiosurgery and precision radiotherapy for various lesions, tumors, and conditions throughout the body in adult and pediatric patients. A key update in version 4.1 is the incorporation of changes to the CBCT image reconstruction algorithm to allow for the use of CBCT images in the simulation and planning for adaptive radiation therapy. However, it explicitly states that TrueBeam v4.1 cannot deliver adaptive dosimetry on a real-time, per-fraction basis, but supports off-line adaptive treatment planning or delivery.
• Predicate Device: TrueBeam / TrueBeam STx / Edge / VitalBeam (K231317), which is version 4.0.
• Technological Characteristics: The subject device (v4.1) and predicate device (v4.0) share the same medical linear accelerator, couch, integrated treatment and imaging consoles, multi-leaf collimators, and supported treatment techniques. The significant difference is the software change to the CBCT image reconstruction algorithm for adaptive radiation therapy planning.
• Performance Data: Verification and validation of the modified software and hardware were conducted to assess image quality and dose calculation accuracy against planning CT images for suitability in adaptive planning. Software was considered a "major" level of concern. Human factors validation study was conducted per IEC 62366. The system complies with various IEC and ISO standards related to safety, EMC, quality management, risk management, and biocompatibility.
• Clinical Testing: No animal or clinical tests were submitted to establish substantial equivalence.

Since the device described is a medical linear accelerator for radiation therapy and not an AI/ML device, the specific questions regarding AI/ML acceptance criteria, test set details (sample size, provenance, expert adjudication, MRMC studies, standalone performance), ground truth, and training set details are not applicable to the provided text. The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance testing and compliance with regulatory standards for a radiation therapy system.

Ask a specific question about this device

The TRUENESS™ AIR Blood Glucose Monitoring System is intended for use in the quantitative measurement of glucose in capillary whole blood from the finger. It is intended for use by people with diabetes mellitus at home as an aid in monitoring the effectiveness of their diabetes control program. The TRUENESS™ AIR Blood Glucose Monitoring System is intended to be used by a single person and should not be shared. It is for in vitro diagnostic use only. The TRUENESS™ AIR Blood Glucose Monitoring System is not intended for the diagnosis of, or screening for diabetes. It is not intended for use on neonates.

The TRUENESS™ AIR Blood Glucose Monitoring System is comprised of the TRUENESS™ AIR blood glucose meter and the TRUENESS™ blood glucose test strip.

The TRUENESS™ Blood Glucose Monitoring System is intended for use in the quantitative measurement of glucose in capillary whole blood from the finger. It is intended for use by people with diabetes mellitus at home as an aid in monitoring the effectiveness of their diabetes control program. The TRUENESS™ Blood Glucose Monitoring System is intended to be used by a single person and should not be shared. It is for in vitro diagnostic use only. The TRUENESS™ Blood Glucose Monitoring System is not intended for the diagnosis of, or screening for diabetes. It is not intended for use on neonates.

The TRUENESS™ Blood Glucose Monitoring System is comprised of the TRUENESS™ blood glucose meter and the TRUENESS™ blood glucose test strip.

The TRUENESS Blood Glucose Monitoring System and TRUENESS AIR Blood Glucose Monitoring System mainly consist of two parts as below:
(1) TRUENESS Blood Glucose Meter or TRUENESS AIR Blood Glucose Meter (With Bluetooth function)
(2) TRUENESS Blood Glucose Test Strip

A glucose test is based on measurement of electrical current caused by the reaction of glucose with flavin adenine dinucleotide (FAD) glucose dehydrogenase on the electrode of the test strip. The blood or control solution sample is drawn into the tip of the TRUENESS Blood Glucose Test Strip through capillary action. Glucose in the sample reacts with the FAD glucose dehydrogenase and generate electrons. The magnitude of the resultant current is proportional to the concentration of glucose in the blood and is converted to a glucose concentration. The glucose concentration is displayed on the meter display for the user.

The provided text primarily focuses on the FDA's 510(k) clearance for the TRUENESS™ AIR Blood Glucose Monitoring System and the TRUENESS™ Blood Glucose Monitoring System. It outlines the regulatory process, device descriptions, and a high-level summary of testing. However, it does not contain the detailed acceptance criteria or the specific study results in the format requested.

The document indicates that "Design verification and validation testing consisted of performance tests (precision, linearity, interference, flex studies), electrical/mechanical safety tests, as well as disinfection, cleaning, and robustness studies." It also mentions "A user evaluation confirmed the system accuracy, operation according to design, and ease of use to support the intended use as described in the proposed labeling."

Therefore, I cannot populate the table or answer all your questions with the information given. I can, however, extract the general statement about accuracy.

Here's a breakdown of what can and cannot be answered based on the provided text:

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

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

• Sample Size: Not specified for any of the tests.
• Data Provenance: Not specified.

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 specified. The document mentions a "user evaluation" confirmed system accuracy, but does not detail the nature or qualifications of these users as "experts" for establishing ground truth in a clinical sense.

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

• Not specified.

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/mentioned. This device is a blood glucose monitoring system, not an AI-assisted diagnostic tool that involves human readers.

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

• The device performs quantitative measurement of glucose. The "system accuracy" would refer to its standalone performance, confirmed by user evaluation. The specifics of this standalone performance are not detailed in terms of metrics.

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

• Not specified. For blood glucose monitoring systems, ground truth is typically established by comparing the device's readings against a laboratory reference method (e.g., YSI analyzer), but this is not explicitly stated in the document provided.

8. The sample size for the training set

• Not applicable/mentioned. Blood glucose monitoring systems typically don't have a "training set" in the machine learning sense. Their performance is validated through defined chemical and user studies against reference methods.

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

• Not applicable/mentioned for the same reason as above.

Ask a specific question about this device

TrueBeam-TrueBeam STx-Edge: The TrueBeam™, TrueBeam STx and Edge™ Systems are intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere radiation therapy is indicated for adults and pediatric patients. The TrueBeam, TrueBeam STx, and Edge Systems may be used in the delivery of radiation for treatment that includes: brain and spine tumors (such as glioma, meningioma, pitutary tumors, spinal cord tumors, hemangioblastoma, orbital tumors, ocular tumors, and skull based tumors), head and neck tumors (such as unknown primary of the head and neck, oral cavity, hypopharynx, nasopharynx, sinonasal, salivary gland, and thyroid cancer), thoracic tumors (such as lung cancer, thymic tumors, and mesothelioma), gynecologic tumors (such as ovarian, cervical, endometrial, vulvar, and vaginal), gastrointestinal tumors (such as gastric, pancreatic, hepatobiliary, colon, rectal, and anal carcinoma), genitourinary tumors (such as prostate, bladder, testicular, and kidney), breast tumors, sarcomas, lymphoid tumors (such as Hodgkin's and non-Hodgkin's lymphoma), skin cancers (such as squamous cell, and melanoma), benign diseases (such as schwannoma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, chordoma, gand hemangiomas), metastasis (including all parts of the body such as brain, bone, liver, lung, kidney, and skin) and pediatric tumors (such as glioma, ependymoma, pituitary tumors, hemangioblastoma, meningioma, metastasis, meduloblastoma, nasopharyngeal tumors, arteriovenous malformation, and skull base tumors), and medically refractory essential tremor (indicated for adults only).

VitalBeam: VitalBeam® is intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation therapy is indicated for adults and pediative patients. VitalBeam may be used in the delivery of radiation for treatment that includes: brain and spine tumors (such as glioma, meningioma, craniopharyngiona, pituitary tumors, spinal cord tumors, hemangioblastoma, orbital tumors, optic nerve tumors, and skull based tumors), head and neck tumors (such as unknown primary of the head and neck, oral cavity, hypopharynx, larynx, oropharynx, sinonasal, salivary gland, and thyroid cancer), thoracic tumors (such as lung cancer, esophageal cancer, thymic tumors, and mesothelioma), gynecologic tumors (such as ovarian, cervical, endometrial, vulvar, and vaginal), gastrointestinal tumors (such as gastric, pancreatic, hepatobiliary, colon, rectal, and anal carcinoma), genitourinary tumors (such as prostate, bladder, testicular, and kidney), breast tumors, sarcomas, lymphoid tumors (such as Hodgkin's and non-Hodgkin's lymphoma), skin cancers (such as squamous cell, and melanoma), benign diseases (such as schwannoma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, chordoma, glomus tumors, and hemangiomas), metastasis (including all parts of the body such as brain, bone, liver, lung, kidney, and skin) and pediatric tumors (such as glioma, pituitary tumors, hemangioblastoma, craniopharyngioma, meningioma, metastasis, medulloblastoma, nasopharyngeal tumors, arteriovenous malformation, cavernous malformation, and skull base tumors).

The TrueBeam and VitalBeam Radiotherapy System is a medical linear accelerator that delivered therapeutic radiation to patient in accordance with the physician's prescription.

The system consists of two major components – a photon, electron and diagnostic kV X-ray radiation beam producing component that is installed in a radiation-shielded vault and a control console area located outside the treatment room.

The provided text does not contain information about acceptance criteria or a study that proves a device meets such criteria for an AI/ML component. The document is a 510(k) summary for Varian Medical Systems' TrueBeam, TrueBeam STx, Edge, and VitalBeam radiotherapy systems (K231317).

It focuses on demonstrating substantial equivalence to a predicate device (K213977) by outlining the device's intended use, indications for use, technological characteristics, and compliance with various safety and performance standards. It explicitly states: "No animal or clinical tests are being submitted to establish substantial equivalence with the predicate device."

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance.
2. Sample sizes or data provenance for a test set.
3. Number and qualifications of experts for ground truth establishment.
4. Adjudication method for a test set.
5. MRMC comparative effectiveness study details.
6. Standalone performance data.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

The document discusses hardware and software verification and validation, human factors validation, and electrical safety/EMC testing, all against established standards, but not a specific study evaluating an AI/ML component against performance acceptance criteria. The "Templated-based fiducial detection algorithm for Auto Beam Hold" is mentioned as a new feature, suggesting an algorithmic component, but no specific performance study for this algorithm is detailed in the provided summary.

Ask a specific question about this device