(224 days)
Horos Mobile is a software device intended for viewing images acquired from computed tomography (CT), computed radiography (CR), magnetic resonance (MR), ultrasound (US) and other DICOM compliant medical imaging systems when installed on suitable commercial standard hardware. Images and data can be stored, communicated, processed, and displayed within the system.
It is intended for use as a diagnostic and review tool by trained healthcare professionals.
This device is not intended to replace full workstations and should be used only when there is no access to a workstation.
This device is not to be used for mammography.
It is the User's responsibility to operate the device in accordance with the software and hardware requirements listed in the instructions for use, in particular ensuring that display quality, ambient light conditions, and image compression ratios are consistent with the clinical application.
The Horos Mobile is an interactive medical image display software device for diagnostic image viewing of radiological images for the following modalities: X-ray, CT, MRI, Ultrasound, and XA for iOS and iPadOS platforms. The technological characteristics and the indications of use are identical to those of the Horos MD™ (K232589). The subject device provides both 2D and 3D image visualization tools for CT and MRI scans from various makes and models of image acquisition hardware. It does not produce any original medical images and does not contain controls for the direct operation of a diagnostic imaging system.
Horos Mobile conforms to the DICOM standard to allow the sharing of medical images with other digital imaging systems such as PACS (Picture Archiving and Communication System).
The Horos Mobile software device runs on the iOS and iPadOS platforms, leveraging of their optimized 3D graphic capabilities, which are provided by the METAL framework developed and maintained by Apple Inc.
The user interface of the software follows Apple's Human Interface Guidelines (HIG) to create a user interface that is intuitive and easy to use for users who are familiar with other Apple products. Typical users of this device are radiologists and clinicians who are familiar with 2D scan images.
Horos Mobile operates on "off-the-shelf" portable hardware devices and is therefore subject to factors not typical for reading room workstations (e.g. screen size, environmental variability, network dependencies, etc.). It is therefore required that the user follows the operating instructions properly and utilizes the risk mitigation features in order to make decisions safely and effectively.
The provided FDA 510(k) clearance letter and summary for Horos Mobile primarily focus on demonstrating substantial equivalence to a predicate device (Horos MD™) and a reference device (Mobile MIM) through comparison of technological characteristics and non-clinical performance data. It does not contain information about a clinical study involving human readers or expert consensus for ground truth beyond basic bench testing.
Therefore, many of the requested details about acceptance criteria, human reader studies, and ground truth establishment methods for a clinical test set are not available in the provided document. The document explicitly states: "No clinical testing was required to demonstrate safety or effectiveness for the subject device as the device's non-clinical (bench) testing was sufficient to support the intended use of the device."
However, I can extract information related to the bench testing, which serves as the "study" demonstrating the device meets its performance criteria for specific functionalities.
Here's a breakdown of the available information:
1. A table of acceptance criteria and the reported device performance
The document provides acceptance criteria and performance for "Bench Performance Testing" and "Display Performance Bench Testing."
Table: Acceptance Criteria and Reported Device Performance (Bench Testing)
| Function Tested | Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|---|
| Measurement Accuracy | ||
| Distance (1-10mm) | 100% accuracy | 100% |
| Distance (>10mm) | 100% accuracy | 100% |
| Area (1-10mm) | 100% accuracy | 100% |
| Area (>10mm) | 100% accuracy | 100% |
| Angle (1-190mm) | 100% accuracy | 100% |
| Point (1-190mm) | 100% accuracy | 100% |
| Display Performance | ||
| Luminance Response Evaluation (DICOM GSDF) | Conformance to IEC 62563-1 | Demonstrated conformance |
| Luminance Uniformity Evaluation | Conformance to IEC 62563-1 | Demonstrated conformance |
| Qualitative Image Quality Evaluation: Greyscale | Conformance to IEC 62563-1 | Demonstrated conformance |
| Qualitative Image Quality Evaluation: Greyscale (contrast) resolution | Conformance to IEC 62563-1 | Demonstrated conformance |
| Qualitative Image Quality Evaluation: Contrast | Conformance to IEC 62563-1 | Demonstrated conformance |
| Qualitative Image Quality Evaluation: Pixel resolution | Conformance to IEC 62563-1 | Demonstrated conformance |
| Qualitative Image Quality Evaluation: Angular viewing | Conformance to IEC 62563-1 | Demonstrated conformance |
2. Sample sized used for the test set and the data provenance
- Sample Size (Measurement Accuracy): "DROs (n=75 test cases)" were used for measurement accuracy testing.
- Data Provenance: The data for these bench tests would have been generated internally by iCat Solutions Ltd. The document does not specify country of origin for the DROs but implies they were created for the purpose of this testing. The data is retrospective in the sense that it's based on pre-defined Digital Reference Objects rather than newly acquired patient data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of Experts: Not applicable. The ground truth for the measurement accuracy tests was established by comparison against "known values" of Digital Reference Objects (DROs), implying a computed or mathematically precise ground truth, not human expert consensus. For display performance, the ground truth was conformance to an international standard (IEC 62563-1).
- Qualifications of Experts: Not applicable, as no human experts were used for ground truth establishment in the described bench tests.
4. Adjudication method for the test set
- Adjudication Method: Not applicable. Ground truth for the bench tests was objective (known values of DROs or compliance with a standard), not requiring human adjudication.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- MRMC Study: No, an MRMC comparative effectiveness study was not conducted. The document explicitly states: "No clinical testing was required to demonstrate safety or effectiveness for the subject device as the device's non-clinical (bench) testing was sufficient to support the intended use of the device."
- Effect Size: Not applicable, as no MRMC study was performed. The device is a medical image management and processing system, not an AI diagnostic aid that would typically involve a human-AI comparison for improved reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- The performance data provided is for the "algorithm only" (the software) running on specific hardware. The "bench performance testing" assesses the software's ability to perform measurements accurately and the "display performance bench testing" assesses the software's display capabilities on the designated hardware. So, yes, standalone performance testing was done for these specific functionalities, without human interpretation as part of the performance metric.
7. The type of ground truth used
- For Measurement Accuracy: "Known values" of Digital Reference Objects (DROs). This can be considered a synthetic/computed ground truth.
- For Display Performance: Conformance to an international standard, IEC 62563-1. This is a standards-based ground truth.
8. The sample size for the training set
- Sample Size for Training Set: Not applicable. This document does not describe the development of an AI/ML algorithm that requires a training set. The device is a medical image viewer and processing system, not an AI diagnostic tool in the sense that it "learns" from data. The software's capabilities are based on programmed functionalities.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable, as there is no mention of a training set for an AI/ML algorithm.
In summary, the provided document focuses on demonstrating substantial equivalence through a comparison of product specifications and non-clinical, objective bench testing, rather than a clinical study with human readers or AI performance evaluation against expert ground truth.
§ 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).