(152 days)
The IQQA-Liver is a PC-based, self-contained, non-invasive image analysis software application for reviewing serial multi-phase CT acquisitions of the liver. Combining image viewing, processing and reporting tools, the software is designed to support physicians in the visualization, evaluation and reporting of liver and physician-identified liver lesions.
The software supports a workflow based on automated image registration for viewing and analyzing multi-phase volume datasets. It also includes tools for interactive segmentation and labeling of liver segments and vascular structures. The software provides functionalities for manual or interactive segmentation of physician-identified lesions, and allows for regional volumetric analysis of such lesions in terms of size, shape, position and enhancement pattern, providing information for physician's assessment of lesion characterization.
The software is designed for use by trained physicians. Image source: DICOM.
The IQQA-Liver Software is a self-contained, non-invasive radiographic image analysis application that is designed to run on standard PC hardware. The image input is DICOM. Combining image processing, viewing and reporting tools, the software supports physicians in the visualization, evaluation and reporting of liver and physician identified liver lesions. Viewing tools include 2D axial image viewing, window level adjustment, a pre-defined optimized liver window level setting, synchronized viewing of multi-phase datascts, MPR and MIP. Analysis and evaluation tools include segmentation of structures utilizing user input of seeding points, interactive labeling of segmented areas, quantitative measurement derived from segmentation and labeling results, and the measurement of distance between physician specified structures to landmarks. Reporting tools in the software automatically assemble information (including physician identified lesion locations, measurement information, physician-input lesion characterization, lesion ROl images across multi-phases, and illustrative snapshots of the GUI taken by physicians) for physician's confirmation and for further diagnosis note input. The IQQA-Liver software supports a workflow based on automated registration for viewing and analyzing multi-phase volume datasets. The software automatically matches the spatial location of axial images across multi-phases, and provides synchronized viewing of multi-phase dataset to aid visualization. The software further includes tools for interactive segmentation and interactive labeling of liver segments and vascular structures (such as liver lobes, vessels and major branches), thus facilitating the visualization of spatial relationship between suspicious liver lesions and specified anatomical structures/landmarks. The tools also allow for interactive segmentation of physician-identified lesions using user input of seed points, and regional analysis of such lesions with respect to size, shape, position and enhancement pattern, thus providing information to help physician's assessment of lesion characterization. The software is designed for use by trained physicians only. Physicians make all final patient management decisions.
The provided text is a 510(k) summary for the EDDA Technology IQQA-Liver Software. While it describes the device's intended use, comparison to predicate devices, and general statements about testing, it does not contain detailed information about specific acceptance criteria and a study proving those criteria are met.
The document states:
- "Testing was performed according to internal company procedures. Software testing and validation were done according to written test protocols established before testing was conducted. Test results were reviewed by designated technical professionals before software proceeded to release. Test results support the conclusion that actual device performance satisfies the design intent."
This is a general statement of compliance, but it does not provide the quantitative acceptance criteria, the details of a study, or the specific performance metrics.
Therefore, I cannot populate the table or answer most of your detailed questions based on the provided text.
Here's what can be inferred or explicitly stated from the document, though it falls short of your request for specific acceptance criteria and study details:
1. A table of acceptance criteria and the reported device performance
- Cannot be provided. The document does not list specific, quantifiable acceptance criteria or reported performance results (e.g., accuracy, precision, sensitivity, specificity, or error rates for segmentation, volume analysis, etc.). It only broadly claims that "actual device performance satisfies the design intent."
2. Sample size used for the test set and the data provenance
- Cannot be determined. The document does not specify the sample size of the test set or the origin (country, retrospective/prospective) of the data used for testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Cannot be determined. The document does not mention the use of experts for establishing ground truth or their qualifications. Given the device's function involves physician-identified lesions and analysis tools, it's implied that physician input is central, but no formal ground truth establishment process is described for testing.
4. Adjudication method for the test set
- Cannot be determined. The document does not describe any adjudication methods.
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
- Cannot be determined. The document does not mention a multi-reader, multi-case (MRMC) study or any comparative effectiveness study measuring human reader improvement with or without AI assistance. The device is described as "supporting physicians" but not necessarily replacing or directly augmenting their diagnostic accuracy in a quantifiable comparison presented here.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
- Cannot be determined. The document explicitly states the device is "designed for use by trained physicians" and that "Physicians make all final patient management decisions." This framework suggests a human-in-the-loop design, but it doesn't preclude standalone testing of individual algorithms within the software, though such testing is not detailed.
7. The type of ground truth used
- Cannot be determined with certainty. The software relies on "physician-identified liver lesions" and "interactive segmentation of physician-identified lesions using user input of seed points." This suggests that "expert consensus" or "physician input" forms the basis of the data the software processes, but it does not describe how a ground truth was established for testing or validation purposes. It's likely that a clinical reference (e.g., pathology, clinical follow-up) would have been used for any robust validation, but this is not stated.
8. The sample size for the training set
- Cannot be determined. The document focuses on the device's intended use and comparison to predicates, not on its development or training process.
9. How the ground truth for the training set was established
- Cannot be determined. Similar to point 8, this information is not present in the provided 510(k) summary.
In summary, the provided 510(k) document is a regulatory summary focused on substantial equivalence to predicate devices and does not detail the technical performance studies and acceptance criteria typically found in clinical trial reports or more comprehensive technical files.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).