LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K220813
    Device Name
    ART-PLAN
    Manufacturer
    TheraPanacea
    Date Cleared
    2022-06-17

    (88 days)

    Product Code
    QKB,LLZ,MUJ
    Regulation Number
    892.2050
    Type
    Traditional
    Panel
    Radiology (RA)
    Reference & Predicate Devices
    K210632,K071964,K182888,K193109,K173635,K202700
    Why did this record match?
    Reference Devices :

    K210632, K071964, K182888, K193109, K173635

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    ART-Plan is indicated for cancer patients for whom radiation treatment has been planned. It is intended to be used by trained medical professionals including, but not limited to, radiation oncologists, dosimetrists, and medical physicists.

    ART-Plan is a software application intended to display and visualize 3D multi-modal medical image data. The user may import, define, display, transform and store DICOM3.0 compliant datasets (including regions of interest structures). These images, contours and objects can subsequently be exported/distributed within the system, across computer networks and/or to radiation treatment planning systems. Supported modalities include CT, PET-CT, CBCT, 4D-CT and MR images.

    ART-Plan supports Al-based contouring on CT and MR images and offers semi-automatic and manual tools for segmentation.

    To help the user assess changes in image data and to obtain combined multi-modal image information, ART-Plan allows the registration of anatomical and functional images and display of fused and non-fused images to facilitate the comparison of patient image data by the user.

    With ART-Plan, users are also able to generate, visualize, evaluate and modify pseudo-CT from MRI images.

    Device Description

    The ART-Plan application is comprised of two key modules: SmartFuse and Annotate, allowing the user to display and visualize 3D multi-modal medical image data. The user may process, render, review, store, display and distribute DICOM 3.0 compliant datasets within the system and/or across computer networks. Supported modalities cover static and gated CT (computerized tomography including CBCT and 4D-CT), PET (positron emission tomography) and MR (magnetic resonance).

    Compared to ART-Plan v1.6.1 (primary predicate), the following additional features have been added to ART-Plan v1.10.0:

    • · an improved version of the existing automatic segmentation tool
    • · automatic segmentation on more anatomies and organ-at-risk
    • image registration on 4D-CT and CBCT images .
    • automatic segmentation on MR images .
    • · generate synthetic CT from MR images
    • a cloud-based deployment

    The ART-Plan technical functionalities claimed by TheraPanacea are the following:

    • . Proposing automatic solutions to the user, such as an automatic delineation, automatic multimodal image fusion, etc. towards improving standardization of processes/ performance / reducing user tedious / time consuming involvement.
    • . Offering to the user a set of tools to assist semi-automatic delineation, semi-automatic registration towards modifying/editing manually automatically generated structures and adding/removing new/undesired structures or imposing user-provided correspondences constraints on the fusion of multimodal images.
    • . Presenting to the user a set of visualization methods of the delineated structures, and registration fusion maps.
    • . Saving the delineated structures / fusion results for use in the dosimetry process.
    • . Enabling rigid and deformable registration of patients images sets to combine information contained in different or same modalities.
    • Allowing the users to generate, visualize, evaluate and modify pseudo-CT from MRI images.

    ART-Plan offers deep-learning based automatic segmentation for the following localizations:

    • head and neck (on CT images) .
    • . thorax/breast (for male/female and on CT images)
    • abdomen (on CT images and MR images) ●
    • . pelvis male(on CT images and MR images)
    • . pelvis female (on CT images)
    • brain (on CT images and MR images)

    ART-Plan offers deep-learning based synthetic CT-generation from MR images for the following localizations:

    • pelvis male .
    • brain
    AI/ML Overview

    Here's a summary of the acceptance criteria and study details for the ART-Plan device, extracting information from the provided text:

    Acceptance Criteria and Device Performance

    Criterion CategoryAcceptance CriteriaReported Device Performance
    Auto-segmentation - Dice Similarity Coefficient (DSC)DSC (mean) ≥ 0.8 (AAPM standard) OR DSC (mean) ≥ 0.54 or DSC (mean) ≥ mean(DSC inter-expert) + 5% (inter-expert variability)Multiple tests passed demonstrating acceptable contours, exceeding AAPM standards in some cases (e.g., Abdo MRI auto-segmentation), and meeting or exceeding inter-expert variability for others (e.g., Brain MR, Pelvis MRI). For Brain MRI, initially some organs did not meet 0.8 but eventually passed with further improvements and re-evaluation against inter-expert variability. All organs for all anatomies met at least one acceptance criterion.
    Auto-segmentation - Qualitative EvaluationClinicians' qualitative evaluation of auto-segmentation is considered acceptable for clinical use without modifications (A) or with minor modifications/corrections (B), with A+B % ≥ 85%.For all tested organs and anatomies, the qualitative evaluation resulted in A+B % ≥ 85%, indicating that clinicians found the contours acceptable for clinical use with minor or no modifications. For example, Pelvis Truefisp model achieved ≥ 85% A or B, and H&N Lymph nodes also met this.
    Synthetic-CT GenerationA median 2%/2mm gamma passing criteria of ≥ 95% OR A median 3%/3mm gamma passing criteria of ≥ 99.0% OR A mean dose deviation (pseudo-CT compared to standard CT) of ≤ 2% in ≥ 88% of patients.For both pelvis and brain synthetic-CT, the performance met these acceptance criteria and demonstrated non-inferiority to previously cleared devices.
    Fusion PerformanceNot explicitly stated with numerical thresholds, but evaluated qualitatively.Both rigid and deformable fusion algorithms provided clinically acceptable results for major clinical use cases in radiotherapy workflows, receiving "Passed" in all relevant studies.

    Study Details

    1. Sample Size used for the test set and the data provenance:

      • Test Set Sample Size: The exact number of patients in the test set is not explicitly given as a single number but is stated that for structures of a given anatomy and modality, two non-overlapping datasets were separated: test patients and train data. The number of test patients was "selected based on thorough literature review and statistical power."
      • Data Provenance: Real-world retrospective data, initially used for treatment of cancer patients. Pseudo-anonymized by the centers providing data before transfer. Data was sourced from both non-US and US populations.

    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

      • Number of Experts: Varies. For some tests (e.g., Abdo MRI auto-segmentation, Brain MRI autosegmentation, Pelvis MRI auto-segmentation), at least 3 different experts were involved for inter-expert variability calculations. For the qualitative evaluations, it implies multiple clinicians or medical physicists.
      • Qualifications of Experts: Clinical experts, medical physicists (for validation of usability and performance tests) with expertise level comparable to a junior US medical physicist and responsibilities in the radiotherapy clinical workflow.

    3. Adjudication method for the test set:

      • The document describes a "truthing process [that] includes a mix of data created by different delineators (clinical experts) and assessment of intervariability, ground truth contours provided by the centers and validated by a second expert of the center, and qualitative evaluation and validation of the contours." This suggests a multi-reader approach, potentially with consensus or an adjudicator for ground truth, but a specific "2+1" or "3+1" method is not detailed. The "inter-expert variability" calculation implies direct comparison between multiple experts' delineations of the same cases.

    4. 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:

      • A direct MRMC comparative effectiveness study with human readers improving with AI vs without AI assistance is not explicitly described in the provided text. The studies focus on the standalone performance of the AI algorithm against established criteria (AAPM, inter-expert variability, qualitative acceptance) and non-inferiority to other cleared devices.

    5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

      • Yes, a standalone performance evaluation of the algorithm was done. The acceptance criteria and performance data are entirely based on the algorithm's output (e.g., DSC, gamma passing criteria, dose deviation) compared to ground truth or existing standards, and qualitative assessment by experts of the algorithm's generated contours.

    6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

      • The ground truth used primarily involved:
        • Expert Consensus/Delineation: Contours created by different clinical experts and assessed for inter-variability.
        • Validated Ground Truth Contours: Contours provided by the centers and validated by a second expert from the same center.
        • Qualitative Evaluation: Clinical review and validation of contours.
        • Dosimetric Measures: For synthetic-CT; comparison to standard CT dose calculations.

    7. The sample size for the training set:

      • Training Patients: 8,736 patients.
      • Training Samples (Images/Anatomies/Structures): 299,142 samples. (One patient can have multiple images, and each image multiple delineated structures).

    8. How the ground truth for the training set was established:

      • "The contouring guidelines followed to produce the contours were confirmed with the centers which provided the data. Our truthing process includes a mix of data created by different delineators (clinical experts) and assessment of intervariability, ground truth contours provided by the centers and validated by a second expert of the center, and qualitative evaluation and validation of the contours." This indicates that the ground truth for the training set was established through a combination of expert delineation, internal validation by a second expert, adherence to established guidelines, and assessment of variability among experts.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1