(299 days)
The Quicktome Software Suite is composed of a set of modules intended for display of medical images and other healthcare data. It includes functions for image review, image manipulation, basic measurements, planning, 3D visualization (MPR reconstructions and 3D volume rendering) and display of BOLD (blood oxygen level dependent) resting-state MRI scan studies.
Modules are available for image processing, atlas-assisted visualization, resting state analysis and visualization, and target export creation, where an output can be generated for use by a system capable of reading DICOM image sets.
Quicktome is indicated for use in the processing of diffusion-weighted MRI sequences into 3D maps that represent whitematter tracts based on constrained spherical deconvolution methods and for the use of said maps to select and create exports. Quicktome can generate motor, language, and vision resting state fMRI correlation maps using task-analogous seeds.
Typical users of Quicktome are medical professionals, including but not limited to surgeons, clinicians, and radiologists.
Quicktome is a software-only, cloud-deployed, image processing package which can be used to perform DICOM image viewing, image processing, and analysis.
Quicktome can receive ("import") DICOM images from picture archiving and communication systems (PACS), acquired with MRI, including Diffusion Weighted Imaging (DWI) sequences, T1, T2, BOLD, and FLAIR images. Quicktome can also receive Resting State functional MRI (rs-fMRI) blood-oxygen-level-dependent (BOLD) datasets. Once received, Quicktome removes protected health information (PHI) and links the dataset to an encryption key, which is then used to relink the data back to the patient when the data is exported to hospital PACS or other DICOM device.
The software provides a workflow for a clinician to:
- . Select an image for planning and visualization,
- Validate image quality,
- Explore the available anatomical regions, network templates, tractography bundles, and ● parcellations,
- . Select regions of interest,
- . Display resting state fMRI (BOLD) correlation maps using task-analogous seeds for Motor, Vision and Language networks, and
- . Export black and white and color DICOMs for use in systems that can view DICOM images.
The provided text describes the Quicktome Software Suite (K222359), a medical image management and processing system, and its performance evaluation for FDA 510(k) clearance.
Here's a breakdown of the acceptance criteria and study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't provide a precise, quantified table of acceptance criteria with corresponding performance metrics in a single, clear format. However, it implicitly states the key performance evaluation for the BOLD processing pipeline, which is a significant new feature of this version of the Quicktome Software Suite.
The primary acceptance criteria for the BOLD processing pipeline appears to be the comparability of resting-state fMRI correlation maps generated by Quicktome to task-based fMRI activation maps for a range of pre-specified seeds.
| Acceptance Criteria (Implied) | Reported Device Performance (as stated in the document) |
|---|---|
| Resting-state fMRI correlation maps generated by Quicktome are analytically comparable to task-based fMRI activation maps. | "Analytical evaluation demonstrated that activation in a task-based activation map is represented within the bounds of a correlation map generated with resting-state data when using a range of pre-specified seeds and thresholds, supporting substantial equivalence of the two maps." |
| Clinicians rate the Quicktome-generated resting-state networks as comparable to task-based fMRI maps for clinical intended uses. | "Clinicians rated the networks as comparable per the pre-specified acceptance criteria to task-based fMRI maps for the clinical intended uses of presurgical planning and post-surgical assessment." |
| Software units and modules function as required. | "Testing was conducted on software units and modules. System verification was performed to confirm implementation of functional requirements." |
| Cloud infrastructure is suitable. | "Cloud infrastructure verification was performed to ensure suitability of cloud components and services." |
| Algorithm computations are sound. | "Algorithm performance verification was conducted to ensure computations were sound." |
| Usability and design are validated by representative users. | "Summative usability evaluation and design validation were performed by representative users." |
| BOLD processing pipeline protocols (motion/noise correction, skull stripping, coregistration, noise correction, correlation computation) perform correctly. | "Performance evaluations were conducted for the BOLD processing pipeline. Evaluations included protocols for motion and noise correction, skull stripping, co-registration of anatomical scans and BOLD series, physiological noise correction, and correlation matrix computation." (No explicit pass/fail |
| rates or metrics are provided here beyond the statement that evaluations were conducted for the specified protocols.) |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size (number of cases/patients) used for the test set. It mentions "a range of pre-specified seeds and thresholds" for the analytical evaluation and "the networks" for the clinician evaluation, implying multiple cases, but no specific count.
The data provenance (country of origin, retrospective/prospective) for the test set is not specified in the provided text.
3. Number of Experts and Qualifications for Ground Truth
The document states "expert clinician evaluation" and "Clinicians rated the networks," but it does not specify the number of experts used or their specific qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication Method for the Test Set
The document does not specify an adjudication method (e.g., 2+1, 3+1, none) for the test set's ground truth or clinician evaluation.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The text mentions "expert clinician evaluation" where "Clinicians rated the networks as comparable...to task-based fMRI maps for the clinical intended uses of presurgical planning and post-surgical assessment." This suggests a human-in-the-loop component. However, it does not explicitly describe a traditional MRMC comparative effectiveness study designed to quantify how much human readers improve with AI vs. without AI assistance, nor does it provide an effect size for such improvement. The evaluation focuses on the comparability of the Quicktome-generated maps to established task-based fMRI maps, rather than improvement in human reader performance.
6. Standalone (Algorithm Only) Performance
Yes, a standalone performance evaluation was implicitly done. The "Analytical evaluation" compared the AI-generated resting-state correlation maps to task-based activation maps. This part of the evaluation assesses the algorithm's output directly without human intervention to rate "substantial equivalence."
7. Type of Ground Truth Used
The ground truth used for evaluating the BOLD processing pipeline was task-based fMRI activation maps. These are generally considered a well-established method for localizing brain function.
- Analytical Ground Truth: Task-based fMRI activation maps for direct comparison of spatial patterns and activation.
- Expert Consensus Ground Truth (for clinical relevance): The clinical intended uses for presurgical planning and post-surgical assessment, based on expert opinions validating the comparability of the Quicktome output to established methods.
8. Sample Size for the Training Set
The document does not specify the sample size used for the training set.
9. How Ground Truth for the Training Set Was Established
The document does not describe how the ground truth for the training set was established. It focuses on the validation of the device's performance post-development.
§ 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).