(37 days)
Limbus Contour is a software-only medical device intended for use by trained radiation oncologists, dosimetrists and physicists to derive optimal contours for input to radiation treatment planning. Supported image modalities are Computed Tomography and Magnetic Resonance. The Limbus Contour Software assists in the following scenarios: Operates in conjunction with radiation treatment planning systems to load, save, and display medical images and contours for treatment evaluation and treatment planning. Creation, transformation, and modification of contours for applications including, but not limited to: transferring contours to radiotherapy treatment planning systems, aiding adaptive therapy and archiving contours for patient follow-up. Localization and definition of healthy anatomical structures. Limbus Contour is not intended for use with digital mammography.
Limbus Contour is a stand-alone software medical device. It is a single purposes cross-platform application for automatic contouring (segmentation) of CT/MRI DICOM images via pre-trained and expert curated machine learning models. The software is intended to be used by trained medical professionals to derive contours for input to radiation treatment planning. The Limbus Contour software segments normal tissues using machine learning models and further postprocessing on machine learning model prediction outputs. Limbus Contour does not display or store DICOM images and relies on existing radiotherapy treatment planning systems (TPS) and DICOM image viewers for display and modification of generated segmentations. Limbus Contour interfaces with the user's operating system file system (importing DICOM image .dcm files and exporting segmented DICOM RT-Structure Set .dcm files).
The provided text describes the 510(k) submission for Limbus Contour, a software-only medical device for automatic contouring (segmentation) of CT/MRI DICOM images for radiation treatment planning. While the document outlines the device's indications for use, comparison to a predicate device, and general statements about software verification and validation, it does not provide specific acceptance criteria or detailed results of a study proving the device meets those criteria with numerical performance data.
The document states: "Validation testing of the following functions of the Limbus Contour application demonstrated that the software meets user needs and intended uses and to support substantial equivalence: Automatic Contouring Validation Test." However, it does not provide the specifics of this "Validation Test," such as pre-defined acceptance metrics (e.g., Dice Score thresholds, contour distance metrics), the performance achieved, or the methodology of the study.
Therefore, I cannot fulfill your request for:
- A table of acceptance criteria and the reported device performance: This information is not present in the provided document.
- Sample sized used for the test set and the data provenance: Not specified.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified beyond "expert curated machine learning models" in the device description.
- Adjudication method: Not specified.
- MRMC comparative effectiveness study: The document states "Clinical testing was not required to demonstrate the safety and effectiveness of Limbus Contour. Instead, substantial equivalence is based upon benchtop performance testing." This implies no MRMC study was performed.
- Standalone (algorithm only) performance: While the device is "software-only," specific numerical performance metrics for its standalone contouring accuracy are not provided.
- Type of ground truth used: Described as "pre-trained and expert curated machine learning models," but details on the ground truth for the specific validation test are missing.
- Sample size for the training set: Not specified.
- How the ground truth for the training set was established: Described as "pre-trained and expert curated machine learning models," but no specific methodology detail is given.
Conclusion based on the provided text:
The submission document only broadly states that "Validation testing" was performed and "demonstrated that the software meets user needs and intended uses." It lacks the detailed quantitative performance data and study methodologies typically found in a comprehensive clinical or performance study report. This kind of detail is usually provided in a separate report that would be referenced or included as an appendix in a full 510(k) submission, but it is not contained within this public summary letter.
§ 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).