(104 days)
The IBM iConnect Access application provides internet access to multi-modality softcopy medical images, reports, and other patient-related information to conduct diagnostic review, planning and reporting through the interactive display and manipulation of medical data. IBM iConnect Access provides healthcare professional tools to aid in interpreting medical images including:
- · Displaying DICOM compliant medical images and non-DICOM content using XDS
- · Reformatting images, including creation of MPRs, MIPS, MinIPs, color/monochrome 3D volume rendered images
· Manipulating displayed images via control of slice interval, obliquity, perspective, rotation, window/ level, crop, zoom, color/monochrome transformation, sculpting, straightening the display of curved structures, and creating images perpendicular to a curvilinear path. - · Creating individually captured DICOM images that can be displayed and stored in a PACS
• Measuring coronary calcium, which is intended for non-invasive identification of calcified atherosclerotic plaques in the coronary arteries using tomographic medical image data and clinically accepted calcium scoring algorithms.
· Creating and outputting digital files suitable for the fabrication of physical replicas, such as 3D printing, using DICOM files as inputs. Physical/3D printed models generated from the digital output files are not for diagnostic use.
The IBM iConnect Access application can be configured to provide either lossless or lossy compressed images for display. The medical professional user must determine the appropriate level of image data compression that is suitable for their purpose.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 MP resolution and meets other technical specifications reviewed and accepted by FDA.
Display monitors used for reading medical images for diagnostic purposes must comply with applicable regulatory approvals and with quality control requirements for their use and maintenance. Use of IBM iConnect Access application on mobile devices such as iPhones and iPads is not intended for diagnostic use.
IBM iConnect Access provides healthcare professionals with access to diagnostic quality images, reports, and various types of patient data over conventional TCP/IP networks.
With no download or application-specific installation required on the user's computer, healthcare professionals can use IBM iConnect Access with a standard internet browser to view exams and patient information including but not limited to the following content: Diagnostic Reports. Kev Images, Presentation Series, Modality Imaging, Scope/ Surgery Videos, Visible Light, and File Attachments.
IBM iConnect Access was designed with an easy and convenient workflow providing image viewing and manipulation capabilities including but not limited to zoom, pan, window/ level, scroll, CINE, link series, line/ angle/ ROI measurements, and MPR.
The software displays patient studies and other patient data but does not interpret or provide a diagnosis. Medical diagnosis is the responsibility of the user.
When configured by an Administrator, patients can view their radiological information via portals that launch IBM iConnect Access and provide the ability to view clinical results, modality imaging, key images, scope/surgery videos, and associated clinical documentation. The role for patient access is limited to zooming the image, panning the image, and scrolling through a series of images.
The IBM iConnect Access 3D advanced imaging solution supports MIP (maximum intensity project), MPR (multiplanar reconstruction), 3D volume rendering, and cardiac calcium scoring. Reading physicians, referring physicians, and other appropriate healthcare personnel and can employ advanced image processing and display from local or remote locations.
IBM iConnect Access provides advanced image segmentation and editing tools for the purpose of creating digital 3D anatomical models. These models can be exported as STL files for the purpose of fabricating physical replicas, such as 3D printing. Physical/3D printed models generated from the digital output files are not for diagnostic use.
IBM iConnect Access can be used to query and retrieve content from the IBM iConnect Enterprise Archive. IBM iConnect Enterprise Archive is a software system that supports storage and communications of medical images and data. Qualified system administrators monitor and maintain the software in their healthcare enterprise environment.
IBM iConnect Suite is an offering that combines the image storage capability of IBM iConnect Enterprise Archive with the diagnostic viewer capability of IBM iConnect Access.
This 510(k) premarket notification describes the IBM iConnect Access (v8.0), a Picture Archiving and Communication System (PACS), which is substantially equivalent to a previously cleared version (IBM iConnect Access v7.0, K182290).
The primary focus of this submission revolves around the addition of new features related to 3D model manipulation and export for 3D printing. Because it is a PACS system and the changes are primarily functional enhancements to existing capabilities (e.g., image manipulation, 3D reconstruction, and data export), the submission states that clinical studies are not required to demonstrate safety and effectiveness.
Therefore, the following information, which would typically be found in a study demonstrating clinical performance, is not available in this document:
- A table of acceptance criteria and reported device performance (for clinical endpoints)
- Sample sizes for test sets and data provenance
- Number of experts and their qualifications for establishing ground truth
- Adjudication method
- MRMC comparative effectiveness study results
- Standalone algorithm performance
- Type of ground truth used (for clinical validation)
- Sample size for the training set
- Ground truth establishment for the training set
The document does, however, provide information regarding non-clinical testing for the new features.
1. A table of acceptance criteria and the reported device performance
The document does not provide a formal table with acceptance criteria and reported device performance metrics in the way one would typically see for a diagnostic AI device. Instead, it describes compliance with voluntary standards and in-house testing for the new features.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document mentions "in-house testing of de-identified CT and MRI DICOM images" but does not specify the sample size or the data provenance (country of origin, retrospective/prospective nature).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
Not applicable, as clinical ground truth establishment by experts for specific diagnostic performance metrics was not part of this submission. The testing focused on technical functionality.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as no clinical adjudication of diagnostic findings from a test set is described.
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 conducted or reported. The device is a PACS system with added image manipulation and export features, not an AI-assisted diagnostic tool in the sense of providing specific interpretations.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device's functionality is to provide tools for healthcare professionals; it does not operate in a standalone diagnostic manner. The document does not describe standalone algorithm performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the non-clinical testing described, the "ground truth" was likely the expected technical output for the interactive segmentation and mesh generation features, rather than clinical ground truth (e.g., pathology confirmed disease presence). The document states: "in-house testing of de-identified CT and MRI DICOM images confirmed that interactive segmentation of digital 3D models and mesh generation for STL file creation was acceptable." This implies a verification against pre-defined technical specifications for the output.
8. The sample size for the training set
Not applicable. The description does not involve a training set for an AI model that performs diagnostic interpretation. The software's new features are based on algorithms for image manipulation and geometric processing, not typically requiring a distinct "training set" in the context of deep learning for image classification or detection.
9. How the ground truth for the training set was established
Not applicable, as there is no mention of a training set for an AI model.
§ 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).