(85 days)
MIM software is used by trained medical professionals as a tool to aid in evaluation and information management of digital medical images. The medical image modalities include, but are not limited to. CT. MRI, CR, DX, MG, US. SPECT, PET and XA as supported by ACR/NEMA DICOM 3.0. MIM assists in the following indications:
· Receive, transmit, store, retrieve, display, print, and process medical images and DICOM objects.
· Create, display and print reports from medical images.
· Registration, fusion display, and review of medical images for diagnosis, treatment planning.
· Evaluation of cardiac left ventricular function, including left ventricular end-diastolic volume, end-systolic volume, and ejection fraction.
· Localization and definition of objects such as tumors and normal tissues in medical images.
· Creation, transformation, and modification of contours for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow-up and management.
· Quantitative and statistical analysis of PET/SPECT brain scans by comparing to other registered PET/SPECT brain scans.
· Planning and evaluation of permanent implant brachytherapy procedures (not including radioactive microspheres).
· Calculating absorbed radiation dose as a result of administering a radionuclide.
MIM - MRT Dosimetry extends features of MIM SurePlan. It is designed for use in medical imaging and operates on both Windows and Mac computer systems. MIM - MRT Dosimetry extends the functionality of the MIM - Y90 Dosimetry (K172218) software and utilizes functionality of MIM – SPECTRA Quant (K180815). Both of these are predicates for this submission. The following functions have been added to allow calculations of absorbed dose as a result of administering a radionuclide.
- Allows for quantification of planar images
- Allows for calculation of time-integrated activity coefficients
- . Allows for voxel-based dose calculation of radionuclides
- Allows for correction of dose for tissue density .
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Average errors for planar corrections (attenuation, scatter, background) for most regions. | Less than 12% for all regions except the smallest (2.6 cm). |
| Average errors for planar corrections (attenuation, scatter, background) for the smallest region (2.6 cm). | 21% error for Lu-177 and 17% error for I-131 (attributed to partial volume effect, deemed acceptable). |
| Accuracy of area-under-the curve (AUC) calculations for different fitting options compared to manual AUC calculations, considering Poisson noise. | Differences less than 3.1%. |
| Accuracy of generation of CT-derived physical density maps compared to published results for soft tissue regions. | Less than 5% difference. |
| Accuracy of generation of CT-derived physical density maps compared to published results for bone regions. | Less than 10% difference. |
| Accuracy of generation of CT-derived physical density maps for lung density. | Fell within the range of expected density values. |
| Difference of mean dose calculation for MIM - MRT Dosimetry compared to a commercially available solution (after mass correction of standard phantoms in the commercial solution to match patient data). | Smaller or equal to 20% for I-131 and Lu-177. |
| Difference between Voxel S Value method in MIM - MRT Dosimetry and Local Deposition Model values for Lu-177 for all organs tested. | Less than 1%. |
| Overall: The software passed its performance requirements and met specifications in all cases. | Overall: All tests demonstrated acceptable agreement and the software passed its performance requirements and met specifications. |
Study Details
-
Sample sizes used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- Test Set Sample Sizes:
- Planar Corrections: Simulated phantoms. Specific number of phantoms not provided.
- AUC Calculations: Simulated data. Specific number of datasets not provided.
- CT-derived physical density maps: Clinical patient data. Specific number of patient datasets not provided.
- Dose Calculations:
- Simulated phantoms (I-131 and Lu-177). Specific number of phantoms not provided.
- Clinical patient data (I-131 and Lu-177). Specific number of patient datasets not provided.
- Voxel S Value vs. Local Deposition Model: Not explicitly stated if this was done on simulated or clinical data, but it was for "all organs tested."
- Data Provenance:
- The text mentions "simulated phantoms based on the NEMA IEC Body Phantom, simulated phantoms based on patient data, and clinical patient data." This indicates a mix of synthetic and real-world data.
- The country of origin is not specified, and it's unclear if the clinical data was retrospective or prospective.
- Test Set Sample Sizes:
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document does not provide information on the number of experts or their qualifications for establishing ground truth for the test set. The comparisons are made against "commercially available solutions," "manual AUC calculations," and "published results," rather than direct expert consensus on ground truth data.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- The document does not specify any adjudication method. The performance is assessed by comparing the device's output to other established methods or reference data.
-
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, an MRMC comparative effectiveness study was not done. The study focuses on the standalone performance of the software's dosimetry calculations against established methods, not on human reader performance with or without AI assistance.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance study was done. The entire "Performance Data" section describes the evaluation of the MIM - MRT Dosimetry software's calculations (planar corrections, AUC, density maps, dose calculations) against other solutions, manual calculations, or published results. This is an assessment of the algorithm's performance in isolation.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- The ground truth varied:
- Simulated phantoms: The "ground truth" for these would be the known, pre-programmed values or properties of the phantom.
- Manual AUC calculations: This served as a reference for the AUC accuracy.
- Published results: Used as a reference for the accuracy of CT-derived physical density maps.
- Commercially available solution: Used as a benchmark for dose calculations, with corrections made to align mass.
- Local Deposition Model values: Used as a reference for the Voxel S Value method comparison.
- There is no mention of expert consensus, pathology, or outcomes data being used directly as ground truth in these specific performance tests.
- The ground truth varied:
-
The sample size for the training set:
- The document does not provide information on the sample size used for any training set. The descriptions focus on verification and validation testing, implying the software's models were already developed.
-
How the ground truth for the training set was established:
- Since no information on a training set is provided, there is no information on how its ground truth was established.
§ 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).