(45 days)
IntelliSpace Radiology Software (client) is a software package intended to be used by trained professionals, including but not limited to Radiologists, physicians, administrators and medical technicians.
The software is used with general purpose computing hardware for the presentation, processing, measurement and distribution of images and associated data throughout a clinical environment.
IntelliSpace Radiology contains an Advanced Mammography module for functionality specific to Mammography. Lossy compressed mammographic images and digitized film/screen images must not be reviewed for primary image interpretations.
Mammography images may only be interpreted using display monitors approved for digital mammography.
The subject device IntelliSpace Radiology product described in this section is a modification of the previously cleared IntelliSpace PACS 4.x software device (K111804). Changes made or being implemented are described in Section 12 'Substantial Equivalence Discussion'.
IntelliSpace Radiology is a software package intended to be used by trained professionals, including but not limited to physicians, administrators and medical technicians.
The software is used with general purpose computing hardware for the presentation, processing. measurement and distribution of images and associated data throughout a clinical environment.
IntelliSpace Radiology software supports receiving, sending, printing, and displaying studies received from the following modality types via DICOM: CT, MR, NM, US, XA, PET, CR, DX, DR, RF, RT, MG, SC, VL, and OP as well as hospital/radiology information systems.
IntelliSpace Radiology contains an Advanced Mammography module for functionality specific to Mammography. Lossy compressed mammographic images and digitized film/screen images must not be reviewed for primary image interpretations.
This document, K182926, is a 510(k) summary for the Philips IntelliSpace Radiology, cleared on December 6, 2018. It is a Picture Archiving and Communications System (PACS) software.
Here's an analysis of the provided information regarding acceptance criteria and the study:
Key Takeaways from the Document:
- No Clinical Studies Performed or Required: The document explicitly states: "The subject of this premarket submission, IntelliSpace Radiology did not require clinical studies to support equivalence." and "The non-clinical performance tests provided in this 510(k) premarket notification demonstrated that the subject device IntelliSpace Radiology is as safe and effective as its predicate device IntelliSpace PACS 4.x (K111804) without raising any new safety and/or effectiveness concerns." This means the evaluation was based entirely on non-clinical performance and a comparison to a predicate device.
- Focus on Verification and Validation (V&V): The primary evidence for meeting acceptance criteria comes from V&V testing. The document states: "Verification and Validation (V&V) activities were performed for proposed IntelliSpace Radiology system and demonstrated that the predetermined acceptance criteria were successfully met."
- Acceptance Criteria: The acceptance criteria are implicitly defined by compliance with several international and FDA-recognized consensus standards and an FDA guidance document, alongside Philips' own internal verification and validation processes and risk management. The general statement is that the device "meets the acceptance criteria and is adequate for its intended use."
Given the above, direct answers to some of your specific questions are not available because the device's clearance was based on non-clinical performance testing and substantial equivalence to a predicate device, not a clinical performance study with human readers or AI algorithms in the way you've framed some of the questions.
Here's the information extracted from the document in response to your prompts, along with explanations where direct answers are not applicable due to the nature of a 510(k) summary for a PACS system:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Implied by Standards/Guidance) | Reported Device Performance |
|---|---|
| Compliance with ISO 14971 (Risk Management) | All risks sufficiently mitigated, no new risks introduced, overall residual risks acceptable. |
| Compliance with IEC 62304 (Medical Device Software Lifecycle) | Software verification and validation tests conducted. |
| Compliance with IEC 62366-1 (Usability Engineering) | Software verification and validation tests conducted. |
| Compliance with NEMA-PS 3.1-PS 3.20 (DICOM Standards) | Supports DICOM studies receiving, sending, printing, and displaying from various modality types. |
| Compliance with FDA Guidance for Content of Premarket Submissions for Software Contained in Medical Devices | Software for this device considered "moderate" level of concern. Verification and validation performed as recommended by this guidance. |
| Meeting Requirement Specifications / Intended Use | "IntelliSpace Radiology was tested in accordance with Philips verification and validation processes. Verification and Validation tests have been performed to address intended use, technological characteristics claims, requirement specifications and the risk management results." The test results "demonstrate that IntelliSpace Radiology... meets the acceptance criteria and is adequate for its intended use." |
| Functional Equivalence to Predicate Device (IntelliSpace PACS 4.x - K111804) for listed features (Table 5-1 pages 6-7) | The device "is substantially equivalent to the currently marketed predicate device IntelliSpace PACS 4.x (K111804) in terms of indications for use, design features, fundamental scientific technology, and safety and/or effectiveness." Specific feature comparisons are in Table 5-1. |
| Safety and Effectiveness Equivalence to Predicate Device | "IntelliSpace Radiology is substantially equivalent... in terms of safety and effectiveness." |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the 510(k) summary. Given that this was a non-clinical V&V study for a PACS system, there isn't typically a "test set" in the sense of clinical images from patients with specific conditions. The testing would involve simulated data, synthetic data, and real (but de-identified) clinical images to verify functionalities, data integrity, display accuracy, and adherence to standards like DICOM. The provenance (country, retrospective/prospective) is not relevant for this type of non-clinical software validation.
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 applicable/provided. Since this was a non-clinical software verification and validation, there was no "ground truth" derived from expert clinical reads in the context of diagnostic accuracy. The ground truth would be conformance to specifications, software requirements, and industry standards.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not applicable/provided. No clinical adjudication method was used given the non-clinical nature of the study.
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 done. The document explicitly states: "The subject of this premarket submission, IntelliSpace Radiology did not require clinical studies to support equivalence." This device is a PACS system, not an AI-assisted diagnostic tool designed to directly improve reader performance in the diagnostic task itself. Its role is to present, process, measure, and distribute images.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not applicable/provided in the context of an "algorithm only" performance study. The device is a PACS system, which is a foundational software infrastructure for image management, not a standalone diagnostic algorithm providing a finding. Its "performance" is about its ability to correctly handle and display images and data, which was evaluated through non-clinical V&V.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The "ground truth" for this device's validation was conformance to its own technical specifications, software requirements, and adherence to recognized industry standards (e.g., DICOM). It was not based on clinical ground truth (like pathology or expert consensus on disease presence) because it's a PACS system that manages imaging data, not an AI algorithm making diagnostic inferences.
8. The sample size for the training set
This information is not applicable/provided. The IntelliSpace Radiology is a PACS system, a software package for image management, not an AI/Machine Learning model that requires a "training set" of data to learn from.
9. How the ground truth for the training set was established
This information is not applicable/provided for the same reason as point 8.
§ 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).