Search Results
Found 2 results
510(k) Data Aggregation
(84 days)
ME-APDS (Magentiq Eye's Automatic Polyp Detection System) is intended to be used by endoscopists as an adjunct to the common video colonoscopy procedure (screening and surveillance), aiming to assist the endoscopist in identifying lesions during colonoscopy procedure by highlighting regions with visual characteristics consistent with different types of mucosal abnormalities that appear in the colonoscopy video during the procedure. Highlighted regions can be independently assessed by the endoscopist and appropriate action taken according to standard clinical practice.
ME-APDS is trained to process video images which may contain regions consistent with polyps.
ME-APDS is limited for use with standard white-light endoscopy imaging only.
ME-APDS is intended to be used as an adjunct to endoscopy procedures and is not intended to replace histopathological sampling as means of diagnosis.
ME-APDS™/MAGENTIQ-COLO is intended to be used as an adjunct to the common video colonoscopy procedure. The system application aims to assist the endoscopist in identifying lesions, such as polyps, during the colonoscopy procedures in real time. The device is not intended to be used for diagnosis or characterization of lesions, and does not replace clinical decision making.
The system acquires the digital video output signal from the local endoscopy camera and processes the video frames. It runs deep machine learning and additional supporting algorithms in real time on the video frames in order to detect and identify regions having characteristics consistent with different types of mucosal abnormalities such as polyps. The output video with the detected lesions is presented on a separate screen, highlighting the suspicious areas on the original video. The user can also take snapshots of the videos, with and without the highlighting of the suspicious areas, record videos and view in full screen mode. The ME-APDS™ includes an additional feature that removes the presentation of the bounding box once the physician has inserted an endoscopic tool (e.g. snare or forceps) into the endoscopic field of view.
Acceptance Criteria and Study for MAGENTIQ-COLO (ME-APDS)
Based on the provided FDA 510(k) clearance letter, here's a detailed breakdown of the acceptance criteria and the study conducted for MAGENTIQ-COLO (ME-APDS):
1. Table of Acceptance Criteria and Reported Device Performance
The document states that "All testing met pre-specified acceptance criteria," implying that the reported performance metrics achieved or exceeded predefined thresholds, though the specific numerical thresholds for acceptance are not explicitly stated within this document. The table below presents the reported performance metrics based on the standalone algorithm performance testing.
| Metric | Context | Reported Performance |
|---|---|---|
| Polyp Detection | ||
| Polyp-wise Recall (PRc1) | With Histology | 99.7% |
| Polyp-wise Recall (PRc3) | With Histology | 99.7% |
| Polyp-wise Recall (PRc5) | With Histology | 99.7% |
| Polyp-wise Recall (PRc7) | With Histology | 99.7% |
| Polyp Coverage (MPC) | With Histology | 81.7% (median) |
| Polyp-wise Recall (PRc1) | Without Histology | 100.0% |
| Polyp-wise Recall (PRc3) | Without Histology | 100.0% |
| Polyp-wise Recall (PRc5) | Without Histology | 100.0% |
| Polyp-wise Recall (PRc7) | Without Histology | 100.0% |
| Polyp Coverage (MPC) | Without Histology | 81.3% (median) |
| Frame-wise Recall (FRecall) | Full Testing Dataset | 73.0% |
| Polyp Coverage (MPC) | Full Testing Dataset | 72.0% (median) |
| Polyp-wise Recall (PRc1) | Full Testing Dataset | 98.1% |
| Polyp-wise Recall (PRc3) | Full Testing Dataset | 95.8% |
| Polyp-wise Recall (PRc5) | Full Testing Dataset | 93.8% |
| Polyp-wise Recall (PRc7) | Full Testing Dataset | 91.2% |
| False Positives Per Full Video (procedure) rate | Algorithm Performance | Target achieved (specific rate not stated) |
| False Positives Per Frame (TPP) | Algorithm Performance | 0.0334 (threshold achieved) |
| Tool Detection | ||
| Tool Detection Frame-wise Recall (FRecall) | Tool Detection | 85.9% |
| Median Tool Coverage (MTC) | Tool Detection | 96.5% |
| Tool Recall (TRc1) | Tool Detection | 99.7% |
| Tool Recall (TRc3) | Tool Detection | 99.7% |
| Tool Recall (TRc5) | Tool Detection | 99.7% |
| Tool Recall (TRc7) | Tool Detection | 99.7% |
| False Positives Per Frame (TPP) | Tool Detection | 0.0118 (calculated) |
| System Performance | ||
| Marker Annotation Delay | All cases (new system, with/without tool detection) | Adequate performance (specific metric not stated, but criteria met) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 252 unique full colonoscopy videos. These videos contained 806 polyps (660 small, 111 medium, 35 large). 24 videos contained no polyps.
- Data Provenance: The document does not explicitly state the country of origin. The test set appears to be retrospective, as it is referred to as "the algorithm was tested offline on... videos."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts or their specific qualifications (e.g., number of years of experience) used to establish the ground truth for the test set. It mentions "polyps verified by histology" and "polyps that were reported in the procedure report," implying a clinical and pathological review process, but details on the experts involved are missing.
4. Adjudication Method for the Test Set
The document does not specify an explicit adjudication method (e.g., 2+1, 3+1). The ground truth for polyps is based on "histology findings" and "procedure report," suggesting a consensus or standard clinical reporting process but not a formal adjudication process by a panel for the study.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, an MRMC comparative effectiveness study is not mentioned in the provided document. The study described is a standalone performance test of the algorithm.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone study was performed. The document explicitly states: "The algorithm was tested offline on 252 unique full colonoscopy videos..." and "Standalone algorithm performance testing was conducted..."
7. Type of Ground Truth Used
The ground truth used for the test set was primarily based on:
- Histology findings: This is considered a high-quality ground truth for polyp characteristics.
- Procedure report: This likely refers to the endoscopist's findings documented during the colonoscopy.
- The presence and size of polyps were noted, and 375 polyps had histology findings (302 adenoma polyps).
8. Sample Size for the Training Set
The document does not specify the sample size used for the training set. It only states that the device "is trained to process video images."
9. How the Ground Truth for the Training Set Was Established
The document does not specify how the ground truth for the training set was established. It only mentions that "ME-APDS is trained to process video images which may contain regions consistent with polyps."
Ask a specific question about this device
(28 days)
ME-APDS (Magentig Eye's Automatic Polyp Detection System) is intended to be used by endoscopists as an adjunct to the common video colonoscopy procedure (screening and surveillance), aiming to assist the endoscopist in identifying lesions during colonoscopy procedure by highlighting reqions with visual characteristics consistent with different types of mucosal abnormalities that appear in the colonoscopy video during the procedure. Highlighted regions can be independently assessed by the endoscopist and appropriate action taken according to standard clinical practice.
ME-APDS is trained to process video images which may contain regions consistent with polyps.
ME-APDS is limited for use with standard white-light endoscopy imaging only.
ME-APDS is intended to be used as an adjunct to endoscopy procedures and is not intended to replace histopathological sampling as means of diagnosis.
ME-APDS™MAGENTIQ-COLO is intended to be used as an adjunct to the common video colonoscopy procedure. The system application aims to assist the endoscopist in identifying lesions, such as polyps, during the colonoscopy procedures in real time. The device is not intended to be used for diagnosis or characterization of lesions, and does not replace clinical decision making.
The system acquires the digital video output signal from the local endoscopy camera and processes the video frames. It runs deep machine learning and additional supporting algorithms in real time on the video frames in order to detect and identify regions having characteristics consistent with different types of mucosal abnormalities such as polyps. The output video with the detected lesions is presented on a separate screen, highlighting the suspicious areas on the original video. The user can also take snapshots of the videos, with and without the highlighting of the suspicious areas, record videos and view in full screen mode.
Here's an analysis of the acceptance criteria and study details for the MAGENTIQ-COLO device, based on the provided document:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria are implied by the reported performance metrics, particularly "Polyp-wise Recall" and "False Positives Per Frame (FPPF)". The study aims to demonstrate that the device performs comparably to or better than the predicate device.
| Acceptance Criteria / Metric | Reported Device Performance (Full Testing Dataset) |
|---|---|
| Polyp-wise Recall (PRecall1) | 97.9% [96.63%, 98.94%] |
| Polyp-wise Recall (PRecall3) | 95.3% [93.39%, 96.96%] |
| Polyp-wise Recall (PRecall5) | 93.2% [91.01%, 95.15%] |
| Polyp-wise Recall (PRecall7) | 90.6% [88.19%, 92.91%] |
| False Positives Per Frame (FPPF) | 0.0333 (threshold achieved) |
| Polyps with Histology: PRecall1 | 99.7% [99.12%, 100.0%] |
| Polyps with Histology: PRecall7 | 99.7% [99.11%, 100.0%] |
| Median Coverage of Polyps (with histology) | 81.7% |
| Marker Annotation Latency (Median) | 133 msec for FHD, 157 msec for 4K |
Note: The document states that "The testing results were observed to be as expected and support that the device has similar performance to the predicate device," implying that these reported values met the implicit acceptance criteria for substantial equivalence.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size (Test Set): 212 unique full colonoscopy videos, containing 702 polyps (16 videos contained no polyps).
- Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The document does not explicitly state the number of experts used to establish the ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience"). However, it references polyps "verified by histology" and "reported in the procedure report," implying clinical expert input.
4. Adjudication Method for the Test Set
The document does not describe a specific adjudication method like 2+1 or 3+1. The ground truth seems to be derived from documented polyps in the "procedure report" and "histology findings," suggesting a standard clinical reporting process rather than a specific consensus method for this study.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported in this document. The study described is a standalone performance test of the algorithm. The document mentions that the clinical validation used to support the device's polyp detection functions was conducted in a previous submission (K223473). This K223473 submission might contain an MRMC study, but it's not detailed here.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone performance study was done. The "Standalone Performance Testing" section describes how "The algorithm was tested offline" on an independent dataset to evaluate its recall, false positive performance, and false positives per full video rate without direct human interaction during the test.
7. Type of Ground Truth Used
The ground truth used for the test set was a combination of:
- Histopathology findings: For polyps with histology reports.
- Procedure reports: For polyps identified and documented during the colonoscopy procedure.
8. Sample Size for the Training Set
The document does not provide the sample size for the training set. It only states that "ME-APDS is trained to process video images which may contain regions consistent with polyps."
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only broadly states that the system "runs deep machine learning" and is "trained to process video images."
Ask a specific question about this device
Page 1 of 1