Search Results

EConsole1 is indicated for use in general radiographic images of human anatomy. It is intended to replace radiographic film/screen systems in all general-purpose diagnostic procedures (excluding fluoroscopic, and mammographic applications).

The main features of this software are controlling and interfacing the detector, controlling the x-ray generator acquisition settings, storing acquired images, data management and image processing.

Radiological Image Processing Software, EConsolel is complete digital image processing console software specialized for the digital X-ray detector series developed by DRTECH Corporation.

EConsole1 not only processes the acquired images but also complies with DICOM standards which allow the user to transmit and receive data with the PACS system and print images through the DICOM printer.

The provided text does not contain the detailed information necessary to fully answer the request regarding specific acceptance criteria, study methodologies, and performance results for the EConsole1 device.

The document is a 510(k) summary for a medical image management and processing system (EConsole1). Its primary purpose is to demonstrate substantial equivalence to a predicate device, not to present a comprehensive study proving specific performance metrics against pre-defined acceptance criteria for, for example, diagnostic accuracy of an AI component.

Here's a breakdown of what can be extracted and what is missing, based on the provided text:

What is Present:

• Device Name: EConsole1
• Device Type: Radiological Image Processing Software (Medical Image Management and Processing System)
• Intended Use: General radiographic images of human anatomy, to replace film/screen systems in general-purpose diagnostic procedures (excluding fluoroscopic, angiographic, and mammographic applications). Its main features involve controlling and interfacing the detector, controlling X-ray generator acquisition settings, storing acquired images, data management, and image processing.
• Regulatory Classification: Class II, Product Code LLZ.
• Predicate Device: FEEL-DRCS (K110033) and a reference device EConsole1 (K152172).
• Non-Clinical Data: Mentions compliance with standards (IEC 62304, NEMA PS 3.1-3.20 DICOM, ISO 20417, IEC 62366-1, ISO 14971) and software verification/validation activities (code, module, integration, dynamic tests, risk analysis).
• Cybersecurity: States conformity to FDA guidance for managing cybersecurity.
• Conclusion: The device is substantially equivalent to the predicate, passed V&V testing, and performs as intended without new safety risks.

What is NOT Present (and therefore cannot be answered from this document):

1. A table of acceptance criteria and the reported device performance: The document states, "The test results suggest that all software specifications meet the acceptance criteria." However, it does not list what those specific acceptance criteria were (e.g., minimum accuracy, sensitivity, specificity, processing speed, image quality metrics) nor does it provide the reported numerical values for the device's performance against these criteria.
2. Sample size used for the test set and the data provenance: No information on the number of images/cases used specifically for a "test set" to evaluate performance. No details on the country of origin or whether the data was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and their qualifications: No mention of expert review or ground truth establishment for performance data, as specific clinical performance evaluation data is not provided.
4. Adjudication method for the test set: Not applicable, as detailed performance test set data is not provided.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: The document explicitly states "Clinical studies are unnecessary to validate the safety and effectiveness of the software in EConsole1". This indicates no MRMC study was conducted or deemed necessary for this 510(k) submission.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: While general "verification and validation" and "non-clinical tests" are mentioned, no specific standalone performance metrics for an AI algorithm (e.g., for disease detection) are provided. The device described appears to be an image processing and management system, not an AI for diagnostic interpretation.
7. The type of ground truth used: Not applicable, as no specific performance study against a diagnostic ground truth is described. The V&V described are for software functionality, not diagnostic accuracy.
8. The sample size for the training set: Not applicable, as no AI model requiring a training set for diagnostic classification/segmentation is described. The software's function is image management and processing.
9. How the ground truth for the training set was established: Not applicable for the same reason as above.

In summary, the provided FDA 510(k) summary is for an image management and processing system, not an AI diagnostic algorithm. Therefore, it focuses on software V&V, functional equivalence, and compliance with standards rather than clinical performance metrics, ground truth establishment, or human reader studies typically associated with AI-powered diagnostic devices.

Ask a specific question about this device

Intended for use by a qualified/trained physician or technician for the purpose of acquiring X-ray images of the desired parts of patient's anatomy (including head, cervical spine, chest, abdomen, lumbar spine, pelvis and extremities).This device is not intended for mammography.

This SR-2300/SR-2300S Portable DR Imaging System is a portable digital device developed, designed and manufactured by SIUI. The device consists of the following major components: a portable X-ray unit, a flat panel detector, and workstation. The difference between SR-2300 and SR-2300S is the operation interface of the portable X-ray Unit only, while the flat panel detector and the workstation are the same for SR-2300 and SR-2300S. The SR-2300S has the display interface with button-operation digital tube, while the SR-2300 has the display interface with touch screen operation.

The provided text describes a 510(k) premarket notification for the SR-2300/SR-2300S Portable DR Imaging System. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets specific acceptance criteria through a clinical performance study for an AI/ML-enabled medical device.

Therefore, many of the requested details about acceptance criteria, study design (sample size, ground truth, experts, adjudication, MRMC), and training set information for an AI/ML device are not present in this document. This submission is for a traditional medical device (portable X-ray system), not an AI/ML diagnostic software.

Here's a breakdown of the available information based on your request, highlighting what is not applicable (N/A) or not provided in this type of submission:

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

• Acceptance Criteria: N/A. This submission focuses on demonstrating substantial equivalence to a predicate device through technical specifications and compliance with established performance standards for X-ray systems, rather than meeting specific performance metrics for a diagnostic or AI algorithm.
• Reported Device Performance: The document provides a comparison of technical characteristics between the subject device and the predicate device (Table 1 on page 6-7). This table serves to show that the new device's specifications meet or exceed those of the predicate, or that any differences do not impact safety or efficacy. For example:
  • X-ray Generator Peak Power: Predicate: 2kW; Subject: 3.2kW (implied from "Tube voltage 40-125kV, Tube current 10-100mA")
  • Tube Voltage Adjustable Range: Predicate: 40-100kV; Subject: 40-125kV
  • mAs Range: Predicate: 0.4mAs-50mAs; Subject: 0.4mAs-200mAs
  • DQE: Predicate: 25% at 1.0 lp/mm, 5% at 3.0 lp/mm; Subject: 36% at 1.0 lp/mm, 13% at 3.0 lp/mm
  • MTF: Predicate: 35% at 2.0 lp/mm; Subject: 38% at 2.0 lp/mm

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

• Sample Size for Test Set: N/A. No clinical test set data is reported as "Clinical testing is not necessary for the SR-2300/SR-2300S Portable DR Imaging System in order to demonstrate substantial equivalence to the predicate device." (Page 10, Section 5.9).
• Data Provenance: N/A for clinical performance. The document states "Clinical images were provided; these images were not necessary to establish substantial equivalence based on the modifications to the predicate device, but they provide further evidence in addition to bench testing data to show that the complete system works as intended." (Page 10, Section 5.7). No details on the number or origin of these "clinical images" are given.

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

• N/A. No clinical test set with expert-established ground truth was required or performed for this 510(k) submission.

4. Adjudication method for the test set

• N/A. No clinical test set.

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

• N/A. This is not an AI/ML-enabled device, and no MRMC study was conducted.

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

• N/A. This is a hardware device (portable X-ray system), not a standalone algorithm.

7. The type of ground truth used

• N/A. No clinical performance study requiring ground truth was conducted. The "ground truth" for this type of device is typically established through engineering specifications, phantom testing, and comparisons to established performance standards for X-ray imaging, as well as the predicate device's characteristics.

8. The sample size for the training set

• N/A. This is a traditional medical device, not an AI/ML device that requires a training set.

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

• N/A. No training set for an AI/ML algorithm.

Summary of what the document does provide regarding device performance proof:

The document primarily relies on non-clinical testing and compliance with established standards to demonstrate substantial equivalence and ensure safety and effectiveness.

• Non-clinical Testing Summary (pages 8-10, Section 5.7):
  • The device complies with and was tested in accordance with numerous international standards for medical electrical equipment, X-ray equipment, electromagnetic compatibility, radiation protection, risk management, biological evaluation, software life cycle processes, usability, and symbols.
  • Examples of standards: IEC 60601-1, IEC 60601-1-2, IEC 60601-2-54, IEC 60601-1-3, ISO 14971, ISO 10993 (various parts), IEC 62304, IEC 60601-1-6, IEC 62366-1, ISO 15223-1, ISO 13485.
  • Proof: "The test results showed compliance with the above standards. Validation was performed for overall operation by taking and reviewing test images. Clinical images were provided; these images were not necessary to establish substantial equivalence based on the modifications to the predicate device, but they provide further evidence in addition to bench testing data to show that the complete system works as intended. The non-clinical tests demonstrate that the device is as safe, as effective, and performs as well as the predicate." (Page 10, Section 5.7).
• Comparison to Predicate Device (Table 1, pages 6-7): Shows that the subject device's technical specifications are comparable or superior to the predicate, and any differences do not raise new safety or effectiveness concerns.

In conclusion, this 510(k) submission is for a conventional X-ray system, and therefore, the detailed criteria for an AI/ML device performance study are not applicable or provided. The "proof" of meeting acceptance criteria for this device rests on demonstrating adherence to recognized performance standards for X-ray equipment and showing substantial equivalence to a legally marketed predicate device through technical comparisons and non-clinical bench testing.

Ask a specific question about this device

Intended for use by a qualified/trained doctor or technician on both adult and pediatric subjects for taking diagnostic radiographic exposures of the skull, spinal column, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. Not for mammography.

This is a multifunctional fixed X-ray equipment consisting of Examination Table, Bucky Stand, Tube/Bucky Stand, X-ray Source Assembly (Tube/Collimator), High Voltage Generator plus Operating Panel, Conventional Image Receivers and, in specific version, Image System with Flat panel detector and Workstation for image acquisition, processing and visualization. The equipment was developed to perform radiographic examinations of patients in reclining, standing or sitting positions. Six possible tube head configurations are available: FLOOR TO CELLING TUBE STAND, FLOOR MOUNTED TUBE STAND, ROTARY U-ARM mount with integrated film/digital cassette mount, MANUAL CEILING-MOUNTED TELESCOPIC TUBE STAND, MOTORIZED CEILING-MOUNTED TELESCOPIC TUBE STAND, ROTARY STRAIGHT ARM mount with integrated film/digital cassette mount. The Apolo provides a complete x-ray system with generator, tube head, and collimator. The generator is made by us, VMI, whereas the tube head, collimator, and digital x-ray receptor panels/software are made by other manufacturers. Tube heads are typically Toshiba and collimators are typically Ralco. The Apolo D comes with digital x-ray receptor panels (see the comparison table below) while the Apolo S comes without digital x-ray receptor panels. This system employs without modification software Econsole cleared in K152172. This software has a Moderate level of concern. The reference detectors made by DRTECH can be used with anti-scatter grids.

This document is a 510(k) premarket notification for the Apolo D / Apolo S stationary x-ray system. It does not contain information about an AI/ML-based device or a study involving acceptance criteria for such a device. The device described is a traditional x-ray system, and the clearance is based on substantial equivalence to a predicate device, not on AI-driven performance metrics.

Therefore, I cannot extract the requested information (acceptance criteria, details of a study proving device meets acceptance criteria, sample sizes, expert involvement, adjudication, MRMC, standalone performance, ground truth, training set specifics) from the provided text because these elements are related to the evaluation of AI/ML devices, which is not applicable here.

The document explicitly states regarding clinical testing:
"Clinical testing was not required to establish substantial equivalence because all digital x-ray receptor panels have had previous FDA clearance." This further confirms that no clinical performance study, particularly one measuring AI-driven diagnostic accuracy, was conducted for this submission.

Ask a specific question about this device

Intended for use by a qualified/trained physician or technician on both adult and pediatric subjects for taking diagnostic x-rays. Not for mammography.

RadmediX AcuityPDR combines components into a complete mobile x-ray system, including software, a generator/collimator combination, and digital radiography panels. Radmedix combines components from various manufacturers into a complete mobile x-ray system. The customer selects one (or more) of the following digital x-ray receptor panels: DRTech 4343A, (K192400); DRTech 4343W, (K193017); AcuityDR (K171137); AcuityDR 1417 (K162552 EVS 3643, EVS 3643G) or AcuityDR 1717 (K162555 EVS 4343, EVS 4343G). In addition, the customer selects one of three software packages: Accuvue+ (K130883), AccuVueMED, (K152172) or AccuVue (K141440). The generator can be battery operated. A single battery charge produces 200 Exposures at max KV and MAS settings. The battery charger is UL Listed and the internal lithium ion battery is overcharge and overcurrent protected. A typical acquisition computer would be a Lenovo P53S or a Dell Precision 3541.

This document describes a medical device, AcuityPDR, a mobile X-ray system, and its 510(k) submission for FDA clearance. The submission relies on demonstrating substantial equivalence to a predicate device (MinXray CMDR 2CW).

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

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

The document does not explicitly state acceptance criteria in the form of quantitative performance metrics for the AcuityPDR device itself. Instead, it focuses on demonstrating "substantial equivalence" to a predicate device. The acceptance criteria for this type of submission are typically that the device performs as safely and effectively as the predicate and has the same indications for use.

The device performance is reported implicitly through the comparison table on page 4, showing that the AcuityPDR either matches or has comparable/equivalent functionality to the predicate in various technical parameters.

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

The document explicitly states in section 6, "Clinical testing. Not required for a determination of substantial equivalence." This indicates that no clinical test set was used for this specific submission. The submission relies on non-clinical testing (bench testing, standards compliance) and comparison to the predicate device.

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)

Since no clinical test set was required or used for this submission, there is no mention of experts being used to establish ground truth for a test set.

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

As no clinical test set was used, no adjudication method is 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

No MRMC study was performed as clinical testing was "Not required for a determination of substantial equivalence." The device is a mobile X-ray system, not an AI-powered diagnostic tool, so the concept of human readers improving with AI assistance is not applicable in this context.

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

This is not an AI algorithm; it's a mobile X-ray system. Therefore, standalone algorithm performance is not applicable. The performance is assessed through compliance with electrical and safety standards for X-ray devices and comparison of technical specifications to a predicate.

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

For this type of 510(k) submission, "ground truth" is primarily established by:

• Compliance with recognized electrical, safety, and performance standards for X-ray generating equipment (e.g., IEC 60601 series, 21 CFR 1020).
• Demonstration that the device's technical specifications and intended use are substantially equivalent to a legally marketed predicate device.
• Component certifications: "All of the components subject to the CDRH performance standard are certified to comply with the standard by their respective manufacturers."

8. The sample size for the training set

The document does not describe a training set for an AI model, as this is not an AI device. The "training" for such a device would refer to its design and manufacturing processes adhering to established engineering principles and standards.

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

Not applicable, as no AI model or training set is described. The "ground truth" for the device's design and manufacturing relies on established medical device regulations, design controls, and industry standards for X-ray imaging equipment.

Ask a specific question about this device

The purpose of Acuity is to acquire, store, communicate, display and process medical X-ray images. These radiographic systems are intended for use by a qualified/trained physician or technician on both adult and pediatric subjects for taking diagnostic x-rays. Not for mammography, angiography, interventional, or fluoroscopy use.

RadmediX Acuity combines components into a complete stationary x-ray system, including software, tube stands, tube heads, collimators, generators, tables, and digital radiography panels.

Here's a breakdown of the acceptance criteria and the study information based on the provided text:

Acceptance Criteria and Device Performance:

The document describes the Acuity SDR Standard, Acuity SDR Plus, and Acuity FDR Standard as stationary x-ray systems. The core claim for substantial equivalence is that the device performs the same functions using the same technological methods as the predicate device (Visaris Vision®) to produce diagnostic x-ray images.

Study Information:

1. Sample Size and Data Provenance:

   • Test Set Sample Size: Not explicitly stated as a numerical sample size of clinical cases for a formal clinical trial. Instead, the non-clinical testing involved acquiring DICOM images from "all major body structures" using one AcuitySDR system configuration.
   • Data Provenance: The document does not specify the country of origin for the image acquisition or whether it was retrospective or prospective. It was a "field tested" system, implying real-world or simulated real-world scenarios.

2. Number of Experts and Qualifications (for Ground Truth):

   • Number of Experts: Not specified.
   • Qualifications of Experts: Not specified, beyond the statement that images were generated for "diagnostic x-rays" and assessed as "clinically acceptable." This implies evaluation by trained personnel (e.g., radiologic technologists, radiologists), but their specific qualifications or number are not detailed.

3. Adjudication Method:

   • No formal adjudication method is described. The assessment of image quality was based on whether images were "of high quality and contrast and clinically acceptable."

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No MRMC comparative effectiveness study was performed or described. The submission focuses on demonstrating substantial equivalence through technical characteristics and non-clinical image quality assessment, not on human reader performance improvement with or without AI assistance.

5. Standalone Performance Study (Algorithm Only):

   • Yes, a standalone study (non-clinical testing) was performed. The algorithm (software) alongside the hardware components was tested to acquire and process images. The output (DICOM images) was then evaluated for inherent quality and acceptability. The assessment "all images were of high quality and contrast and clinically acceptable" refers to the output of the integrated system.

6. Type of Ground Truth Used:

   • Expert Consensus / Clinical Acceptability: The ground truth for image quality was established through subjective expert assessment of "high quality and contrast and clinically acceptable." It does not mention pathology or outcomes data.

7. Training Set Sample Size:

   • Not applicable. This device is an X-ray system, not an AI/ML algorithm that requires a training set in the typical sense for image interpretation or diagnosis. The "software" components mentioned (AccuVueMED, AccuVue) are image acquisition and processing software, which are generally deterministic and not "trained" on data in the way a diagnostic AI would be. They are "previously cleared software supplied with the system."

8. How Ground Truth for Training Set Was Established:

   • Not applicable, as there is no specific "training set" for an AI/ML algorithm in this submission. The software components were previously cleared by the FDA, implying their performance was established through other means at the time of their original clearance (K152172 and K141440).

Ask a specific question about this device

The EVS 4343W / EVS 4343WG / EVS 3643W / EVS 3643WG / EVS 3643WP Digital X-ray detector is indicated for digital imaging solution designed for providing general radiographic diagnosis of human anatomy. This device is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The EVS 4343W / EVS 4343WG / EVS 4343WP / EVS 3643W / EVS 3643WG / EVS 3643WP Detector is an indirect conversion device in the form of a square plate in which converts the incoming X-rays into visible light. This visible light is then collected by an optical sensor, which generates an electric charges representation of the spatial distribution of the incoming X-ray quanta. The charges are converted to a modulated electrical signal thin film transistors. The amplified signal is converted to a voltage signal and is then converted from an analog to digital signal which can be transmitted to a viewed image print out, transmitted to remote viewing or stored as an electronic data file for later viewing.

Here's a breakdown of the acceptance criteria and the study details for the DRTECH EVS detectors, based on the provided FDA 510(k) summary:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the new devices (EVS 4343WP, EVS 3643WP) were primarily to demonstrate equivalent diagnostic capability to the predicate device (EVS 3643). This was assessed through clinical image evaluation, comparing image performance scores. For other device models and parameters (DQE, MTF), the acceptance typically involved being "basically equal or [better] than the predicate device."

Here's a table summarizing the comparison for key performance metrics:

Note: For DQE and MTF, the acceptance criterion implicitly means that the values should be close to or exceed the predicate's performance, indicating comparable or improved image quality metrics. The document states "basically equal or [better] than the predicate device." In some cases (e.g., EVS 4343W/EVS 3643W DQE vs. EVS 3643), the subject device values are slightly lower than the predicate, but this is presented within the context of "basically equal or [better] than" and ultimately deemed acceptable for substantial equivalence. For the GOS models, the subject devices showed improvement in DQE and MTF.

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

• Sample Size: The document mentions "8 positions of body parts (Chest PA, Cspine AP, C-spine LAT, L-spine LAT, Shoulder AP, Shoulder LAT, Extremities)" were selected for the clinical image evaluation. It does not explicitly state the number of images per body part or the total number of images in the test set. It also doesn't specify if these were real patient cases or phantoms.
• Data Provenance: Not explicitly stated. The manufacturer is based in the Republic of Korea, so the data could originate from there, but this is not confirmed. The study is described as a "clinical image evaluation." It's not specified if it's retrospective or prospective.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication Method for the Test Set

• Adjudication Method: Described as a "single blind clinical image evaluation." This implies that the readers were blind to which device produced the image (subject vs. predicate). However, the specific method of consensus or individual scoring (e.g., 2+1, 3+1, none) among multiple readers is not detailed.

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

• MRMC Study: The document describes a "single blind clinical image evaluation" to compare image performance. This sounds like a MRMC study, as it compares the image performance of multiple devices (subject vs. predicate) using human readers.
• Effect Size of Human Reader Improvement: The document states that "it is indicated that there is no significant difference of image performance between EVS 4343WP, EVS 3643WP and EVS 3643 as difference in the score is within one standard deviation." This implies equivalence rather than an improvement with AI vs. without AI assistance, as this is a comparison of X-ray detectors themselves, not an AI software. The study's focus was on the diagnostic capability of the new hardware, not an AI's impact on human performance. Thus, no effect size of human improvement with AI is provided.

6. Standalone Performance (Algorithm Only)

• This section does not involve an algorithm with standalone performance, as the device is a digital X-ray detector (hardware). The software (Econsolel) is mentioned and being the same as the predicate's, but the evaluation focuses on the hardware's image acquisition performance.

7. Type of Ground Truth Used

• Ground Truth: For the clinical image evaluation, the "ground truth" was established by comparing the "image performance" scores between the subject device's images and the predicate device's images. This is an expert consensus or subjective evaluation of image quality and diagnostic capability, rather than an objective pathology or outcomes data.

8. Sample Size for the Training Set

• Training Set Sample Size: Not applicable. This document describes the evaluation of an X-ray detector, which is hardware, not an AI algorithm that would typically require a training set.

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

• Ground Truth for Training Set: Not applicable, as there is no mention of an AI algorithm training set.

Ask a specific question about this device

The EXPD 4343P / EXPD 3643P Digital X-ray detector is indicated for digital imaging solution designed for providing general radiographic diagnosis of human anatomy. This device is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The EXPD 4343P / EXPD 3643P is a flat-panel type digital X-ray detector that captures projection radiographic images in digital format within seconds, eliminating the need for an entire x-ray film or an image plate as an image capture medium. EXPD 4343P differs from traditional Xray systems in that, instead of exposing a film and chemically processing it to create a hard copy image, a device called a Detector is used to capture the image in electronic form. The EXPD 4343P / EXPD 3643P Detector is an indirect conversion device in the form of a square plate in which converts the incoming X-rays into visible light is then collected by an optical sensor, which generates an electric charges representation of the spatial distribution of the incoming X-ray quanta. The charges are converted to a modulated electrical signal thin film transistors. The amplified signal is converted to a voltage signal and is then converted from an analog to digital signal which can be transmitted to a viewed image print out, transmitted to remote viewing or stored as an electronic data file for later viewing.

This document describes a 510(k) submission for the EXPD 4343P / EXPD 3643P Digital X-ray detector, which is intended to replace film or screen-based radiographic systems in general diagnostic procedures. The key aspect of the submission is to demonstrate substantial equivalence to a legally marketed predicate device (EVS 4343A / EVS 4343AG / EVS 3643A / EVS 3643AG, K192400).

The primary difference and focus of the study is the change in the TFT panel technology from amorphous silicon to IGZO. The manufacturer claims that IGZO offers improved performance characteristics such as lower resistance and leakage current, which can reduce signal delay and line noise.

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 acceptance criteria for performance are implicitly tied to demonstrating that the new device (EXPD 4343P/3643P) is equal to or better than the predicate device (EVS series) in terms of established X-ray device performance metrics: Detective Quantum Efficiency (DQE) and Modulation Transfer Function (MTF). Resolution is also a key parameter.

Analysis of Performance vs. Criteria:

• DQE: For the EXPD 4343P (50.0%), it is slightly lower than the EVS 4343A (52.9%) but significantly higher than the EVS 4343AG (27.2%). For the EXPD 3643P (52.3%), it is slightly higher than the EVS 3643A (50.5%) and significantly higher than the EVS 3643AG (26.3%). The statement "basically equal or worth than the predicate device" needs to be interpreted in the context of the range of predicate devices. The claim states that the subject device's performance is "equal or worth than the predicate device," which suggests that being comparable or slightly below the predicate in some aspects (like EXPD 4343P DQE vs EVS 4343A) is acceptable, especially when other aspects (like EXPD 3643P DQE vs EVS 3643AG or EXPD 4343P MTF vs EVS 4343A) are superior. The overall conclusion is that the new device meets the criteria of being "equal or worth than" the predicate, especially considering the performance improvements over the "AG" models of the predicate.
• MTF: For the EXPD 4343P (52.3%), it is higher than both comparing EVS 4343A (44.1%) and EVS 4343AG (49.2%). For the EXPD 3643P (46.8%), it is higher than EVS 3643A (44.5%) and slightly higher than EVS 3643AG (46.3%). In all primary MTF comparisons, the subject device shows equal or better performance.
• Resolution: Matches the predicate at 3.5 lp/mm.

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

The document explicitly states that the data comes from a "bench test report" and "non-clinical performance testing."

• Sample Size: The document does not specify a sample size for the testing of DQE, MTF, or resolution. These are typically measured on a single device following standardized procedures (e.g., IEC 62220-1). It implies testing on representative units of the EXPD 4343P and EXPD 3643P.
• Data Provenance: The testing is "non-clinical," meaning it does not involve human subjects or retrospective/prospective medical data. It is laboratory performance testing. The manufacturer is DRTECH Corporation, based in the Republic of Korea.

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

• This submission is for a digital X-ray detector, not an AI/CAD device. Therefore, there is no concept of "ground truth" established by human experts in the traditional sense for image interpretation. The ground truth for performance metrics like DQE, MTF, and resolution is established through standardized physical measurements and calculations as per recognized consensus standards (e.g., IEC 62220-1).

4. Adjudication Method for the Test Set

• Not applicable, as this is objective engineering performance measurement, not subjective clinical interpretation of images requiring adjudication.

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

• No MRMC study was done or reported. This device is a hardware component (digital X-ray detector) and not an AI-powered diagnostic tool intended for human reader assistance. The study focuses purely on the physical performance characteristics of the detector itself.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

• This is not an algorithm, but a hardware device. The reported performance metrics (DQE, MTF, Resolution) are the "standalone" or intrinsic performance of the detector itself, independent of interpretation by a human or an AI. So, in concept, the reported performance is standalone.

7. Type of Ground Truth Used

• The "ground truth" for the device's performance is based on objective physical measurements conducted according to international standards (specifically, IEC 62220-1 for DQE) and general engineering principles for X-ray detector characterization. It is not based on expert consensus, pathology, or outcomes data, as those would be relevant for diagnostic accuracy studies of interpreted images.

8. Sample Size for the Training Set

• Not applicable. This is a hardware device. There is no "training set" in the machine learning sense for the device itself.

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

• Not applicable. (See #8)

Summary of the Study:

The study proving the device meets the acceptance criteria is a non-clinical bench test comparing the objective physical performance parameters (DQE, MTF, Resolution) of the new EXPD 4343P/3643P digital X-ray detectors against their predicate devices (EVS 4343A/AG / EVS 3643A/AG). The ground truth for these parameters is established through standardized measurement methodologies defined by international consensus standards, such as IEC 62220-1 for DQE. The study found that the new devices' performance was "equal or worth than" the predicate devices, thereby demonstrating substantial equivalence, particularly highlighting improvements in MTF over the predicate. No human readers, clinical data, or AI algorithms were involved in this specific performance assessment.

Ask a specific question about this device

The EVS 4343A / EVS 4343AG / EVS 3643AG Digital X-ray detector is indicated for digital imaging solution designed for providing general radiographic diagnosis of human anatomy. This device is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.

The EVS 4343A / EVS 4343AG / EVS 3643A / EVS 3643AG is a flat-panel type digital X-ray detector that captures projection radiographic images in digital format within seconds, eliminating the need for an entire x-rav film or an image plate as an image capture medium. EVS 4343A / EVS 4343AG / EVS 3643A / EVS 3643AG differs from traditional X-ray systems in that, instead of exposing a film and chemically processing it to create a hard copy image, a device called a Detector is used to capture the image in electronic form.

The EVS 4343A / EVS 4343AG / EVS 3643A / EVS 3643AG Detector is an indirect conversion device in the form of a square plate in which converts the incoming X-rays into visible light. This visible light is then collected by an optical sensor, which generates an electric charges representation of the spatial distribution of the incoming X-ray quanta.

The charges are converted to a modulated electrical signal through thin film transistors. The amplified signal is converted to a voltage signal and is then converted from an analog to digital signal which can be transmitted to a viewed image print out, transmitted to remote viewing or stored as an electronic data file for later viewing.

The provided FDA 510(k) summary (K192400) for the DRTECH EVS 4343A, EVS 4343AG, EVS 3643A, and EVS 3643AG digital X-ray detectors focuses on demonstrating substantial equivalence to a predicate device (K162555). Therefore, the "acceptance criteria" discussed are primarily related to showing that the new devices perform as well as or better than the predicate, particularly in key physical performance metrics.

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

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the predicate device's performance and the expectation that the new devices should meet or exceed these values for key metrics like DQE and MTF.

The document states: "it is proved that the DQE and MTF of predicated device and subject device are basically equal or worth than the predicate device." and "As a result, subject devices performance is equal or worth than the predicate device." However, the presented data shows that the subject devices exceed the DQE and MTF values of the predicate device, indicating superior performance in these measured aspects.

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

The provided summary does not specify a sample size for a clinical test set involving patients or images. The "non-clinical data" discussed pertains to bench testing of the detector's physical performance (DQE, MTF, Resolution). Therefore, the concepts of "test set" in the context of clinical images, "country of origin," and "retrospective/prospective" are not applicable to the non-clinical performance evaluation described.

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

This information is not applicable as the evaluation was a non-clinical, bench-top performance assessment of the device's physical imaging characteristics (DQE, MTF, resolution), not a clinical study requiring expert interpretation of medical images.

4. Adjudication Method for the Test Set

This information is not applicable for the same reasons as point 3.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted or described in this 510(k) summary. The submission focuses on demonstrating substantial equivalence based on technical specifications and non-clinical performance, not on a comparison of human reader performance with or without AI assistance.

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

This is not applicable. The device is an X-ray detector, a hardware component that captures images. It does not contain an AI algorithm for image analysis in isolation (standalone) or for human-in-the-loop performance. Its "performance" refers to how well it acquires images, not how well it interprets them.

7. The Type of Ground Truth Used

The ground truth for the non-clinical performance evaluation (DQE, MTF, Resolution) would be based on physical phantom measurements and established international standards (e.g., IEC 62220-1) for characterizing X-ray detector performance. It is not expert consensus, pathology, or outcomes data, as those relate to clinical diagnostic accuracy.

8. The Sample Size for the Training Set

This 510(k) summary does not describe a training set. The device is a digital X-ray detector, which is a hardware component. There is no mention of machine learning or AI algorithms requiring a training set for this particular submission. The "study" here is a technical performance assessment of the detector itself.

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

This information is not applicable as no training set for an AI algorithm is described.

Ask a specific question about this device

ProRad Series Stationary Radiographic System is intended for use by a qualified, trained doctor or technician on both adult and paediatric subjects for taking diagnostic radiographic exposures of the skull, spinal column, chest, abdomen, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. Not for mammography.

The ProRad series Stationary Radiographic System is a diagnostic x-ray system intended for general purpose radiographic imaging of the human body. There are two types of configurations (2FC and 3NC) for ProRad; the difference is in the mounting of the X-ray tube. For X-ray tube mounting the configuration is either the floor mounted (2FC) or ceiling suspension (3NC) assembly.

The devices are a new combination of a previously cleared solid state digital x-ray acquisition panel and software with the diagnostic x-ray components (including Xray tube, high frequency X-ray generator, a tilting vertical bucky, X-ray table and collimator) required to make a complete system. The purchaser may select any of the digital panels and software based on the user's requirements. The other components are also available in different configurations to meet specific customer needs. The X-ray panel and imaging software have been previously cleared by the FDA, and most of the other components are used in previously cleared 510(k) devices.

Here's an analysis of the acceptance criteria and study information for the ProRad 2FC and ProRad 3NC Digital Stationary Radiographic Systems, based on the provided text:

Acceptance Criteria and Device Performance Table:

The document primarily focuses on demonstrating substantial equivalence to predicate devices rather than setting and reporting specific performance metrics with acceptance criteria in a comparative table for novel device features. The "Comparable Properties" table (pages 6-8) is used to show alignment with predicate devices.

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

• Sample Size: Not explicitly stated as a separate "test set" for a dedicated algorithm performance study. Instead, compliance is demonstrated through testing of the integrated system and reliance on previous FDA clearances for individual components.
• Data Provenance: Not applicable in the context of an algorithm performance test set. The clinical images reviewed by a radiologist were "acquired by the device," but the origin (e.g., country, prospective/retrospective status) is not specified.

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

• Number of Experts: One radiologist.
• Qualifications of Experts: Only "a radiologist" is mentioned. Specific qualifications (e.g., years of experience, board certification) are not detailed.

3. Adjudication method for the test set:

• Adjudication method: Not applicable. The radiologist's review was a single assessment, not a consensus or adjudication process among multiple readers.

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:

• MRMC Study: No. The document explicitly states: "Since the digital x-ray panels and software have previously received FDA clearance, a clinical study was not required as per the FDA guidance document." The clinical image review was supplementary.
• Effect size of human reader improvement with AI: Not applicable, as no MRMC study or AI assistance evaluation was conducted. The device is an imaging system, not an AI diagnostic tool.

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

• Standalone Performance Study: No. This device is a diagnostic X-ray system, which intrinsically requires a human (a qualified doctor or technician) in the loop for operation and interpretation. The performance of individual cleared components (digital panels, software) was relied upon.

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

• Type of Ground Truth: For the supplementary review, the "ground truth" was the radiologist's assessment that the images were "acceptable and allowed the radiologist to make an accurate diagnosis." This is a form of expert opinion on image quality and diagnostic utility, rather than an objective "truth" like pathology or outcomes.

7. The sample size for the training set:

• Sample Size for Training Set: Not applicable. This document does not describe a machine learning algorithm that requires a training set. The device is a conventional X-ray system composed of cleared components.

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

• Ground Truth for Training Set: Not applicable, as there is no machine learning algorithm described.

Ask a specific question about this device