Search Results
Found 5 results
510(k) Data Aggregation
(76 days)
BioTraceIO Vision is a Computed Tomography (CT) and Magnetic Resonance (MR) image processing software package available for use with ablation procedures.
BioTraceIO Vision is controlled by the user via a user interface.
BioTraceIO Vision imports images from CT and MR scanners and facility PACS systems for display and processing during ablation procedures.
BioTraceIO Vision is used to assist physicians in planning ablation procedures, including identifying ablation targets and virtual ablation needle placement. BioTraceIO Vision is used to assist physicians in confirming ablation zones.
The software is not intended for diagnosis. The software is not intended to predict ablation volumes or predict ablation success.
BioTraceIO Vision is a stand-alone software application with tools and features designed to assist users in planning ablation procedures as well as tools for treatment confirmation. The use environment for BioTraceIO Vision is the Operating Room and the hospital healthcare environment such as interventional radiology control room.
BioTraceIO Vision has six distinct workflow steps:
- Data Import
- Anatomic Structures Segmentation (Liver, Kidney, Hepatic Vein, Portal Vein, Ablation Target)
- Instrument Placement (Needle Planning) for Microwave Ablation (MWA) or Cryoablation (Cryo) Procedures
- Ablation Zone/Ice ball Segmentation
- Registration of Pre-Procedure Images
- Treatment Confirmation (Registration of Pre- and Post-Interventional Images; Quantitative Analysis)
Of these workflow steps, four (Anatomic Segmentation, Ablation Target Segmentation, Registration of Pre-Procedure Images and Instrument Placement) make use of the planning image. These workflow steps contain features and tools designed to support the planning of ablation procedures. The other two (Ablation Zone Segmentation, and Treatment Confirmation) make use of the confirmation image volume. These workflow steps contain features and tools designed to support the evaluation of the ablation procedure's technical performance in the confirmation image volume.
Key features of the BioTraceIO Vision Software include:
- Workflow steps availability
- Manual and automated tools for anatomic structures and ablation target/zone segmentation
- Overlaying and positioning virtual instruments (ablation needles) and user-selected estimates of the ablation regions onto the medical images
- Image registration
- Compute achieved margins and missed volumes to help the user assess the coverage of the ablation target by the ablation zone
- Data saving and secondary capture generation
The software components provide functions for performing operations related to image display, manipulation, analysis, and quantification, including features designed to facilitate segmentation of the ablation target and ablation zones.
The software system runs on a dedicated computer and is intended for display and processing, of a Computed Tomography (CT) and Magnetic Resonance (MR), including contrast enhanced images.
The system can be used on patient data for any patient demographic chosen to undergo the ablation treatment.
BioTraceIO Vision uses several algorithms to perform operations to present information to the user in order for them to evaluate the planned and post ablation zones. These include:
- Segmentation
- Image Registration
- Measurement and Quantification
BioTraceIO Vision is intended to be used for ablations with the following ablation instruments:
For needle planning, the software currently supports the following needle models:
- Microwave ablation
- AngioDynamics: Solero Probe 14CM, 19CM, 29CM
- HS HOSPITAL SERVICE: Amica Probe (16G) 15CM, 20CM, 27CM; Amica Probe (14G) 15CM, 20CM, 27CM
- Medtronic Covidien: Emprint Antenna 15CM, 20CM, 30CM
- NeuWave Medical: LK Probe 15CM, 20CM; LK XT Probe 15CM, 20CM; PR Probe 15CM, 20CM; PR XT Probe 15CM, 20CM
- Varian Medical Systems: Ximitry Probe 15CM, 20CM, 27CM
- Cryo ablation
- Boston Scientific: IceForce 2.1 CX, CX L; IcePearl 2.1 CX, CX L; IceRod 1.5 CX; IceSeed 1.5 CX, CX S;Ice Sphere 1.5 CX
- IceCure Medical: ProSense 10G Spheric, Elliptic 14CM, Elliptic 18.5CM; ProSense 13G Spheric, Elliptic
- Varian Medical Systems: ISOLIS 2.1 E Probe 15CM, 20CM; ISOLIS 2.1 S Probe 15CM, 20CM; RA Slimline 1.7 15CM, 20CM; RA Slimline 1.7 Round 15CM, 7CM; RA Slimline 2.4 15CM, 23CM; RA 3.8 13CM, 28CM; V-Probe
For treatment confirmation (including segmentation and registration), the software is compatible with all ablation devices as these functions are independent from probes/power settings.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) clearance letter for BioTraceIO Vision (V1.7):
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state "acceptance criteria" with numerical thresholds against which the performance metrics are directly compared. Instead, it presents performance metrics from various algorithmic tests, implying that the achieved performance was deemed acceptable for clearance. Based on the provided performance data, here's a table that summarizes the key metrics:
| Imaging Modality | Algorithm | Metric | Reported Device Performance | Implied Acceptance Criteria (Minimum Threshold for Clearance) |
|---|---|---|---|---|
| CT | Liver Segmentation | Mean DICE | 0.98 | Implied: High DICE score (e.g., >0.90 for organ segmentation) |
| MR | Liver Segmentation | Mean DICE | 0.93 | Implied: High DICE score (e.g., >0.90 for organ segmentation) |
| CT | Kidney Segmentation | Mean DICE | 0.91 | Implied: High DICE score (e.g., >0.90 for organ segmentation) |
| CT | Liver Ablation Target Segmentation | Mean DICE | 0.82 | Implied: Good DICE score (e.g., >0.75 for target segmentation) |
| CT | Kidney Ablation Target Segmentation (1, 2, 3 strokes) | Mean DICE | 0.79 | Implied: Good DICE score (e.g., >0.75 for target segmentation) |
| MR | Liver Ablation Target Segmentation | Mean DICE | 0.76 | Implied: Good DICE score (e.g., >0.75 for target segmentation) |
| CT | Liver Ablation Zone Segmentation | Mean DICE | 0.88 | Implied: Good DICE score (e.g., >0.85 for ablation zone) |
| CT | Kidney Ablation Zone Segmentation (1, 2, 3 strokes) | Mean DICE | 0.76, 0.77, 0.78 | Implied: Good DICE score (e.g., >0.75 for ablation zone) |
| CT | Kidney Ice Ball Segmentation (1, 2, 3 strokes) | Mean DICE | 0.80, 0.81, 0.83 | Implied: Good DICE score (e.g., >0.80 for ice ball) |
| CT | Liver Vessels Segmentation (HV+PV) | Mean DICE | 0.72 | Implied: Acceptable DICE score (e.g., >0.70 for vessels) |
| CT | Liver Vessels Segmentation (HV+PV) | Mean Centerline DICE | 0.76 | Implied: Acceptable Centerline DICE score (e.g., >0.75 for vessels) |
| CT/MR | Liver Registration Pre-ablation MR – Pre-ablation CT | MCD | 5.04 mm | Implied: Acceptable registration accuracy (e.g., < 5-10 mm) |
| CT | Kidney Registration Diagnostic CT – Pre-ablation CT | MCD | 4.61 mm | Implied: Acceptable registration accuracy (e.g., < 5 mm) |
| CT | Liver Registration Pre-ablation CT – Post-ablation CT | MCD | 4.09 mm | Implied: Acceptable registration accuracy (e.g., < 5 mm) |
| CT | Kidney Registration Pre-ablation CT – Post-ablation CT | MCD | 3.06 mm | Implied: Acceptable registration accuracy (e.g., < 5 mm) |
| CT/MR | Liver Registration Pre-ablation MR – Post-ablation CT | MCD | 4.75 mm | Implied: Acceptable registration accuracy (e.g., < 5 mm) |
Note: The "Implied Acceptance Criteria" are inferred from the successful clearance and commonly accepted performance benchmarks in medical imaging. The FDA clearance document itself does not explicitly list these thresholds.
2. Sample Sizes Used for the Test Set and the Data Provenance
The document provides details of the training sets for different algorithms. However, it does not explicitly state the sample size or provenance for the test set used for the performance validation summarized in the table. The performance data section refers to "validation results" but doesn't detail the test cohort separately from the training cohort or its specific characteristics (country of origin, retrospective/prospective). This is a common characteristic of 510(k) summaries which often highlight training data but may not provide granular details on validation sets.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts
The document does not specify the number or qualifications of experts used to establish the ground truth for the test set. It mentions that ground truth for the training set was established, but not for the validation exercises specifically.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method (e.g., 2+1, 3+1) used for establishing the ground truth for the algorithms' test sets.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs without AI Assistance
The provided text does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was performed. The performance data focuses on algorithmic performance (DICE, MCD) in a standalone manner, not on human reader improvement with AI assistance. The device's intended use is to "assist physicians" and the clinical accuracy of segmentation/registration is stated as "the responsibility of the user." This suggests the focus was on the algorithm's accuracy as a tool rather than a comprehensive human-AI interaction study.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone performance study was done. The performance data presented (Mean DICE and Mean Corresponding Distance) directly reflects the accuracy of the algorithms (segmentation, registration) in isolation, without human intervention in the loop during the measurement of these specific metrics. For example, for "Ablation Target Segmentation", it presents the algorithm's DICE score, not a human reader's improvement using the tool. However, it's important to note that for "Ablation Target Segmentation" (Kidney and Liver) and "Ablation Zone Segmentation" (Kidney and Ice Ball), it differentiates between 1, 2, or 3 strokes, indicating that some level of user input still contributes to the algorithm's final output for these specific functionalities. The performance metrics themselves ("Mean DICE", "MCD") are measures of the algorithm's output compared to ground truth.
7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)
The document does not explicitly state the type of ground truth used for validation (e.g., expert consensus, pathology, surgical findings). For the training set, it can be inferred that expert annotations were used, but this is not explicitly stated for the validation.
8. The Sample Size for the Training Set
The training set sample sizes are provided for the AI algorithms:
- Liver Segmentation Algorithm for CT Processing: 1091 contrast-enhanced CT images.
- Liver Segmentation for MR Processing: 418 MR images.
- Liver Vessel Segmentation Algorithm for CT processing: 393 contrast-enhanced CT images.
- Kidney Segmentation for CT processing: 300 contrast-enhanced preoperative CT images.
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly detail the method for establishing the ground truth for the training set. It mentions the imaging procedure (e.g., "Contrast-enhanced CT images taken for diagnostic reading") which implies that clinical images with pre-existing or subsequently generated expert annotations would have been used for training. However, the exact process (e.g., number of annotators, their qualifications, adjudication) is not specified.
Ask a specific question about this device
(88 days)
BioTraceIO Precision is intended to provide physicians with adjunctive information in their clinical assessment of ablation zone created by liver tissue ablation, as part of their overall post-procedure clinical assessment. BioTracelO Precision generates and depicts a map (BioTrace Map or BTM) post-procedure, that correlates with image findings seen with Contrast-enhanced Computed Tomography (CECT) obtained at 24hours post treatment. The information is provided in the 2D ultrasound plane. This is the only plane and location displayed. No imaging of other portions of the ablation zone is available.
During the ablation procedure BioTraceIO Precision overlays the reference ablation zone (RAZ) provided by the ablation device manufacturer on the ultrasound image.
BioTracelO Precision is indicated for use in patients undergoing radiofrequency (RF) or microwave (MW) liver ablation procedures.
BioTraceIO Precision is not intended for standalone prediction or for diagnostic purposes. BioTraceIO Precision does not support the use of multiple needles, either simultaneously or consecutively.
Manual ablation target contours and margins as defined by the user are not intended for diagnosis, to predict ablation volumes or predict ablation success.
The physician should not rely on BioTraceIO Precisions about patient management post treatment nor should BioTraceIO Precision serve as a substitute for any other assessment method, e.g., CT scans.
BioTracelO Precision is a stand-alone software application with tools and features designed to assist users in their clinical assessment of ablation zone created by liver tissue ablation, as part of their overall post-procedure clinical assessment.
BioTracelO Precision is a software application that uses a proprietary computational algorithm to analyze ultrasound images captured during liver ablation treatment (microwave ablation [MWA] or radiofrequency ablation [RFA]), as depicted in standard abdominal ultrasound imaging.
The streamed ultrasound images are captured and analyzed by the BioTracelO algorithm. providing a visual display of the expected ablation zone, namely the Reference Ablation Zone (RAZ), calculated based on technical parameters provided by the ablation manufacturer datasheet. The RAZ is displayed during the procedure (Online Mode). BioTracelO Precision also provides a visual display of the estimated ablation zone correlative to the 24-hour CECT, namely the BioTrace Map (BTM), after the completion of the procedure (Offline Mode).
Acceptance Criteria and Study for BioTraceIO Precision (2.0)
The BioTraceIO Precision (2.0) device is a software application designed to assist physicians in assessing the ablation zone created by liver tissue ablation procedures. The key functionality is to generate a "BioTrace Map" (BTM) that correlates with the ablation zone visualized on Contrast-enhanced Computed Tomography (CECT) obtained 24 hours post-treatment.
Here's a breakdown of the acceptance criteria and the study that proves the device meets these criteria:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Metric) | Target Performance | Reported Device Performance (BioTraceIO Precision 2.0) |
|---|---|---|
| Mean DICE coefficient vs. 24-hour CECT (BTM) | Equivalent to predicate device | 84.7 [95% CI: 83.07, 86.49] vs. 85.5 [95% CI: 83.63, 87.43] for predicate (p=0.2408; Wilcoxon p=0.11) |
| Mean DICE coefficient vs. 24-hour CECT (Optimized BTM vs. T=0 CECT) | Significantly higher than T=0 CECT | 7.9 [95% CI: 4.2, 11.7) higher (p < 0.0001; Wilcoxon p < 0.0001) |
| BTM algorithm processing time | Optimized to reduce delay (display within 15 mins) | Achieves display within 15 minutes post-procedure |
| RAZ algorithm implementation | Same as BTM processing for optimization/maintenance | Adapted to have the same implementation as BTM |
| User Interface (UI) modifications | Improved user experience | Implemented (e.g., button layout improvements, selection of reference US frame for needle marking) |
| Cybersecurity | Improved security | Implemented (e.g., encryption of PHI, installation responsibilities) |
| Technical modifications | Implemented | Name change, file configuration change, architecture change |
Note: The primary acceptance criterion for the algorithmic performance was demonstrating equivalent performance of the optimized BTM algorithm to the predicate BTM algorithm when correlated with 24-hour CECT. The improved performance against T=0 CECT was a favorable additional finding.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document does not explicitly state the exact number of cases or patients in the test set. However, it implicitly indicates that the test set included sufficient data to conduct statistical analyses (paired t-test, Wilcoxon Signed-Rank test) and generate 95% Confidence Intervals (CIs) for DICE coefficients, comparing the new algorithm with the predicate and T=0 CECT. This suggests a reasonably sized dataset.
- Data Provenance: Not explicitly stated in the provided text (e.g., country of origin). The document states the data was used for "algorithmic testing," implying it was collected from actual patient procedures. The data collected was retrospectively analyzed for this validation.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: Not explicitly stated in the provided text.
- Qualifications of Experts: Not explicitly stated. The ground truth ("ablation zone visualized on the 24-hour post ablation CECT (T=24 CECT)") is itself an objective imaging finding. While interpretation of CECT images is done by radiologists, the document doesn't detail the role or number of human experts for ground truth establishment outside of "ablation zone visualized on the 24-hour post ablation CECT." It focuses more on the correlation between the device's output and this objective imaging finding.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly mentioned for the establishment of the 24-hour CECT ground truth. The ground truth is described as the "ablation zone visualized on the 24-hour post ablation CECT." It implies that this CECT visualization is the accepted reference standard.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
- MRMC Study: No, the provided text does not describe an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The study focuses purely on the equivalence of the device's algorithmic performance (BioTraceIO Precision 2.0 BTM) against a predefined ground truth (24-hour CECT) when compared to a predicate device. The device provides "adjunctive information" and is "not intended for standalone prediction or for diagnostic purposes," which aligns with the absence of an MRMC study assessing human reader improvement.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
- Standalone Performance: Yes, the algorithmic testing described is a standalone performance evaluation of the BioTraceIO Precision (2.0) BTM algorithm. The DICE coefficient was calculated by comparing the algorithm's output directly to the 24-hour CECT images, without a human in the loop for the performance measurement itself.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth used was imaging data, specifically the "ablation zone visualized on the 24-hour post ablation CECT (T=24 CECT)." This is considered a clinical reference standard for assessing the success and extent of liver ablation.
8. The Sample Size for the Training Set
- Training Set Sample Size: The document does not provide the sample size for the training set. The focus of this 510(k) summary is on the validation of the updated device (BioTraceIO Precision 2.0) against its predicate, rather than the initial development and training specifics.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not explicitly stated in the provided text. For a device like BioTraceIO Precision, it is highly likely that similar to the testing phase, the training set ground truth would have also been established using 24-hour CECT imaging to precisely delineate the ablation zones, potentially with expert radiologist annotations or consensus. However, the document does not elaborate on this.
Ask a specific question about this device
(25 days)
VisAble.IO is a Computed Tomography (CT) and Magnetic Resonance (MR) image processing software package available for use with liver ablation procedures.
VisAble.IO is controlled by the user via a user interface.
VisAble.IO imports images from CT and MR scanners and facility PACS systems for display and processing during liver ablation procedures.
VisAble.IO is used to assist physicians in planning ablation procedures, including identifying ablation targets and virtual ablation needle placement. VisAble.IO is used to assist physicians in confirming ablation zones.
The software is not intended for diagnosis. The software is not intended to predict ablation volumes or predict ablation success.
VisAble.IO is a stand-alone software application with tools and features designed to assist users in planning ablation procedures as well as tools for treatment confirmation. The use environment for VisAble.IO is the Operating Room and the hospital healthcare environment such as interventional radiology control room.
VisAble.IO has five distinct workflow steps:
- Data Import
- . Anatomic Structures Segmentation (Liver, Hepatic Vein, Portal Vein, Ablation Target)
- . Instrument Placement (Needle Planning)
- Ablation Zone Segmentation
- . Treatment Confirmation (Registration of Pre- and Post-Interventional Images; Quantitative Analysis)
Of these workflow steps, two (Anatomic Segmentation, and Instrument Placement) make use of the planning image. These workflow steps contain features and tools designed to support the planning of ablation procedures. The other two (Ablation Zone Segmentation, and Treatment Confirmation) make use of the confirmation image volume. These workflow steps contain features and tools designed to support the evaluation of the ablation procedure's technical performance in the confirmation image volume.
Key features of the VisAble.IO Software include:
- . Workflow steps availability
- Manual and automated tools for anatomic structures and ablation zone segmentation
- Overlaying and positioning virtual instruments (ablation needles) and user-selected estimates of the ablation regions onto the medical images
- . Image fusion and registration
- . Compute achieved margins and missed volumes to help the user assess the coverage of the ablation target by the ablation zone
- . Data saving and secondary capture generation
The software components provide functions for performing operations related to image display, manipulation, analysis, and quantification, including features designed to facilitate segmentation of the ablation target and ablation zones.
The software system runs on a dedicated computer and is intended for display and processing, of a Computed Tomography (CT) and Magnetic Resonance (MR), including contrast enhanced images.
The system can be used on patient data for any patient demographic chosen to undergo the ablation treatment.
VisAble.IO uses several algorithms to perform operations to present information to the user in order for them to evaluate the planned and post ablation zones. These include:
- . Segmentation
- . Image Registration
- . Measurement and Quantification
VisAble.IO is intended to be used for ablations with the following ablation instruments:
For needle planning, the software currently supports the following needle models:
- Medtronic: Emprint Antenna 15CM, 20CM, 30CM -
- -NeuWave Medical: PR Probe 15CM, 20CM; PR XT Probe 15CM, 20CM; LK Probe 15CM, 20CM; LK XT Probe 15CM, 20CM
- -H.S. Hospital Service: AMICA Probe 15 CM, 20 CM, 27 CM.
For treatment confirmation (including segmentation and registration), the software is compatible with all ablation devices as these functions are independent from probes/power settings.
Here's a summary of the acceptance criteria and study details for the Techsomed VisAble.IO device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Algorithm | Performance Goal (Acceptance Criteria) | Reported Performance |
|---|---|---|
| CT Processing | ||
| Liver Segmentation | Mean DICE = 0.92 | Mean DICE = 0.98 |
| Ablation Target Segmentation | Mean DICE = 0.70 | Mean DICE = 0.82 |
| Ablation Zone Segmentation | Mean DICE = 0.70 | Mean DICE = 0.88 |
| Liver Vessels Segmentation | Mean DICE = 0.70 | Mean DICE = 0.72 |
| MR Processing | ||
| Liver Segmentation | Mean DICE = 0.92 | Mean DICE = 0.93 |
| Ablation Target Segmentation | Mean DICE = 0.70 | Mean DICE = 0.76 |
| Image Registration | ||
| Pre-ablation CT to Post Ablation CT Image Registration | MCD* = 6.06 mm | MCD* = 4.09 mm |
| Pre-ablation MR to Post-ablation CT Image Registration | MCD* = 6.06 mm | MCD* = 4.72 mm |
| Pre-ablation MR to Pre-ablation CT Image Registration | MCD* = 7.90 mm | MCD* = 5.10 mm |
*MCD = Mean Corresponding Distance
Note on Segmentation and Registration Accuracy: The document explicitly states:
- "The use of the segmentation tools to achieve a satisfactory delineation of ablation target or ablation zone is a user operation and the clinical accuracy of segmentation is the responsibility of the user and not a VisAble.IO function."
- "Final accuracy of registration is dependent on user assessment and manual modification of the registration prior to acceptance, and not a VisAble.IO function."
This suggests that while the algorithms perform well against the statistical metrics, the final clinical accuracy is attributed to the user.
2. Sample Sizes Used for the Test Set and Data Provenance
| Algorithm | N (Sample Size) | Data Provenance (Countries/Regions) | Retrospective/Prospective |
|---|---|---|---|
| CT Processing | |||
| Liver Segmentation | 50 | US: 32, OUS: 18 | Not specified (implied retrospective from clinical sites) |
| Ablation Target Segmentation | 59 | US: 30, OUS: 29 | Not specified (implied retrospective from clinical sites) |
| Ablation Zone Segmentation | 59 | US: 30, OUS: 29 | Not specified (implied retrospective from clinical sites) |
| Liver Vessels Segmentation | 100 | US: 72, OUS: 28 | Not specified (implied retrospective from clinical sites) |
| MR Processing | |||
| Liver Segmentation | 25 | US: 25 | Not specified (implied retrospective from clinical sites) |
| Ablation Target Segmentation | 50 | US: 46, OUS: 4 | Not specified (implied retrospective from clinical sites) |
| Image Registration | |||
| Pre-ablation CT to Post Ablation CT Image Registration | 46 | US: 13, OUS: 33 | Not specified (implied retrospective from clinical sites) |
| Pre-ablation MR to Post-ablation CT Image Registration | 25 | US: 25 | Not specified (implied retrospective from clinical sites) |
| Pre-ablation MR to Pre-ablation CT Image Registration | 18 | US: 14, OUS: 4 | Not specified (implied retrospective from clinical sites) |
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 for the test set" or their specific "qualifications." It generally refers to "performance data demonstrate that the VisAble.IO (V 1.4) is as safe and effective as the cleared VisAble.IO (K223693)," but does not detail the specific ground truth generation process for the reported performance metrics.
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.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
No MRMC comparative effectiveness study is mentioned in the provided text, nor is there any discussion of human reader improvement with or without AI assistance.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, the performance data presented in the table (DICE scores, MCD) are for the algorithms themselves, indicating a standalone performance evaluation. The document highlights that "VisAble.IO uses several algorithms to perform operations to present information to the user in order for them to evaluate the planned and post ablation zones," and then presents the algorithmic validation results. However, it also clarifies that the final clinical accuracy of segmentations and registrations is dependent on user actions.
7. The Type of Ground Truth Used
The ground truth for the algorithmic performance (e.g., DICE scores for segmentation, MCD for registration) is implicitly expert-derived segmentation and registration. While the document doesn't explicitly detail the process, DICE scores and Mean Corresponding Distances are calculated by comparing algorithmic outputs to a pre-established "true" segmentation or correspondence, which in medical imaging is typically generated by human experts (e.g., radiologists, experienced technicians).
8. The Sample Size for the Training Set
- CT Processing - Liver Segmentation Algorithm: N = 1091 contrast-enhanced CT images
- CT Processing - Liver Vessel Segmentation Algorithm: N = 393 contrast-enhanced CT images
- MR Processing - Liver Segmentation AI algorithm: N = 418 MR images
9. How the Ground Truth for the Training Set Was Established
The document provides details on the characteristics of the training datasets but does not explicitly state how the ground truth for these training sets was established. It describes the data as "contrast-enhanced CT images taken for diagnostic reading" or "MR images taken for diagnostic reading," suggesting that these were real-world clinical images, but the manual annotation or expert review process for creating the ground truth for training is not described.
Ask a specific question about this device
(267 days)
BioTraceIO Lite is intended to provide physicians with adjunctive information in their clinical assessment of ablation zone created by liver tissue ablation, as part of their overall post-procedure clinical assessment.
BioTraceIO Lite generates and depicts a map (BioTrace Map or BTM) post-procedure, that correlates with image findings seen with Contrast-enhanced Computed Tomography (CECT) obtained at 24 hours post treatment. The information is provided in the 2D ultrasound plane. This is the only plane and location displayed. No imaging of other portions of the ablation zone is available.
During the ablation procedure BioTraceIO Lite overlays the reference ablation zone (RAZ) provided by the ablation device manufacturer on the ultrasound image. BioTraceIO Lite is indicated for use in patients undergoing radiofrequency (RF) or microwave (MW) liver ablation procedures. BioTraceIO Lite is not intended for standalone prediction or for diagnostic purposes. BioTraceIO Lite does not support the use of multiple needles, either simultaneously or consecutively. The physician should not rely on BioTraceIO Lite BTM alone in decisions about patient management post treatment nor should BioTraceIO Lite serve as a substitute for any other assessment method, e.g., CT scans.
BioTraceIO Lite is a software application that uses a computational algorithm to analyze ultrasound images captured during liver ablation treatment (microwave ablation [MWA] or radiofrequency ablation [RFA]), as depicted in standard abdominal ultrasound imaging. The streamed ultrasound images are captured and analyzed by the BioTraceIO algorithm, providing a visual display of the expected ablation zone (calculated based on technical parameters provided by the ablation manufacturer datasheet), namely the Reference Ablation Zone (RAZ), during the procedure (Online Mode - Figure 1).
Thirty (30) minutes after the completion of the procedure, BioTraceIO Lite provides a visual display of the estimated ablation zone correlative to the 24-hour CECT, namely the BioTrace Map (BTM) (Offline Mode - Figure 2).
Once in Offline Mode, it is not possible to return to Online Mode. The BTM is displayed only in Offline Mode, 30 minutes after the ablation procedure has been completed, and cannot be visualized in Online Mode, during the procedure.
Information from the ultrasound system streams in only one direction, to the BioTracelO Lite software. BioTraceIO Lite utilized in either Online or Offline mode does not control or change the functions or parameters of the ultrasound system, or the ablation device used during the liver ablation procedure.
The BioTraceIO Lite application is installed on a dedicated, off-the-shelf, computer workstation with pre-defined minimal requirements and is controlled by the user via an independent user interface, which is separate from both the ablation system and the ultrasound system. The workstation is connected by video output to a compatible ultrasound system to be used during the liver tumor ablation procedure.
Here’s a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
Acceptance Criteria
The acceptance criteria for the BioTraceIO Lite device are primarily based on demonstrating a statistically significant improvement in the correlation of the BioTrace Map (BTM) with the 24-hour post-procedure CECT (T=24 CECT) compared to the immediate post-procedure CECT (T=0 CECT). This is measured using the Dice similarity coefficient.
Specific Criteria for Effectiveness:
- Primary Effectiveness Objective: To demonstrate that the BTM available post-procedure is correlative to the area of the ablation zone as visualized on the 24-hours post-procedure (T=24) CECT scan. This is statistically assessed by comparing the Dice similarity coefficient of "BTM vs T=24 CECT" against "T=0 CECT vs T=24 CECT." The expectation is that the BTM's correlation will be significantly higher.
Specific Criteria for Safety:
- Primary Safety Objective: To demonstrate that the BioTraceIO Lite device is safe, based on an assessment of device-related Adverse Events (AEs) and serious adverse events (SAEs). The expectation is a low incidence of device-related AEs, with none being serious.
Reported Device Performance
| Acceptance Criterion (Effectiveness) | Reported Device Performance and Statistical Significance |
|---|---|
| Primary Effectiveness Objective: BTM correlation to T=24 CECT (Dice coefficient) is significantly higher than T=0 CECT correlation to T=24 CECT (Dice coefficient). | Mean Dice Coefficient (BTM vs T=24 CECT): 85.5 (SD 6.8) |
| Mean Dice Coefficient (T=0 CECT vs T=24 CECT): 76.8 (SD 12.7) | Statistical Significance: The mean Dice coefficient for BTM compared to T=24 CECT (85.5) was significantly higher than the mean Dice coefficient for T=0 CECT versus T=24 CECT (76.8). Both Paired T-Test P-Value and Wilcoxon P-Value were <.0001, indicating a statistically significant difference. |
| Secondary Effectiveness Objective (Sensitivity): BTM sensitivity compared to T=24 CECT is higher than T=0 CECT sensitivity compared to T=24 CECT. | Mean Sensitivity (BTM vs T=24 CECT): 81.6% (SD 11.0) |
| Mean Sensitivity (T=0 CECT vs T=24 CECT): 63.7% (SD 13.2) | Result: BTM sensitivity was higher by 18% compared to T=0 CECT. |
| Secondary Effectiveness Objective (PPV/Precision): BTM Positive Predictive Value (PPV) compared to T=24 CECT in relation to T=0 CECT PPV compared to T=24 CECT. | Mean PPV (BTM vs T=24 CECT): 91.2% (SD 5.3) |
| Mean PPV (T=0 CECT vs T=24 CECT): 99.6% (SD 0.8) | Result: BTM had an 8.4% loss in PPV compared to T=0 CECT. The sponsor indicates this trade-off is acceptable given the increased sensitivity. |
| Exploratory Objective (Directional Expansion): BTM provides additional information beyond T=0 CECT regarding true expansion. | Result: For 46 out of 51 ablations (90.2%), the BTM provided additional information compared to T=0 CECT. This information either partially matched, completely matched, or over-expanded compared to the "True Expansion" (maximal distance between T=0 CECT and T=24 CECT contours). This supports the clinical utility of the BTM in estimating ablation zone expansion. |
| Primary Safety Objective: Low incidence of device-related Adverse Events (AEs) and Serious Adverse Events (SAEs). | Result: Out of 59 patients in the Safety analysis set, 4 patients (5.1%) experienced a treatment-emergent adverse event (AE). One patient experienced a serious AE (intraparenchymal hematoma). None of these events were considered related to the BioTraceIO Lite. No serious or major adverse events related to the use of BioTraceIO Lite were reported in this study. This indicates the device met its safety objective, showing no device-related adverse events. |
Study Details
2. Sample Size and Data Provenance
- Test Set Sample Size:
- Effectiveness Analysis Set: 50 patients with 51 ablations. (One patient had two ablations; the remaining 49 patients had a single ablation).
- Safety Analysis Set: 59 patients.
- Data Provenance:
- Country of Origin: United States (multi-center prospective single-arm pivotal clinical study conducted at six clinical sites in the United States).
- Retrospective or Prospective: Prospective.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: More than one, as stated "performed independently by certified interventional radiology experts, blinded to each other." The exact number is not explicitly stated, but the plurality suggests at least two.
- Qualifications of Experts: Certified interventional radiology experts. They were trained on CECT segmentation and registration processes specific to this study. The document does not specify their years of experience.
4. Adjudication Method for the Test Set
- Adjudication Method: The analysis of imaging data (T=0 and T=24 CECT) was performed independently by certified interventional radiology experts, blinded to each other. This suggests an independent reading paradigm where each expert provided their segmentation/assessment without knowledge of others' results. There is no mention of a formal adjudication process (e.g., 2+1, 3+1 where a third or fourth expert resolves discrepancies). The ground truth appears to be based on these independent analyses, which were then used to calculate metrics like Dice coefficient.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No, not in the traditional sense of comparing human readers' diagnostic performance with and without AI assistance on a per-reader basis.
- This study focused on the device's performance (BioTraceIO Lite's BTM) in correlating with the T=24 CECT as an adjunctive information source, and comparing the BTM's correlation to T=24 CECT against the T=0 CECT's correlation to T=24 CECT. It was not a reader study to assess improvement in human diagnostic performance.
- The experts were involved in establishing the ground truth (segmenting T=0 and T=24 CECTs), not as readers whose performance was being evaluated.
- Effect size of human reader improvement: Not applicable, as this was not an MRMC study designed to measure human reader improvement with AI assistance.
6. Standalone Performance
- Was standalone (algorithm only without human-in-the-loop) performance done? Yes, the primary effectiveness objective evaluated the BioTrace Map (BTM), which is generated by the BioTraceIO Lite algorithm, against the T=24 CECT. This can be considered a standalone performance assessment of the algorithm's output (BTM) in predicting the ablation zone.
- The device is intended to provide adjunctive information and is not intended for standalone prediction or for diagnostic purposes, reinforcing that while its performance is evaluated alone, its clinical use is always with a physician.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus with pathology/outcomes data is most analogous, but specifically, the ground truth for the ablation zone was established by certified interventional radiology experts segmenting the 24-hour post-procedure Contrast-enhanced Computed Tomography (CECT) scans (T=24 CECT). This is considered the reference method for the ablation zone.
8. Sample Size for Training Set
- Training Set Sample Size: Not explicitly stated in the provided text. The document describes a pivotal clinical study used for testing the device's performance, but does not specify details about the training data used to develop or train the BioTraceIO Lite algorithm.
9. How Ground Truth for Training Set Was Established
- Ground Truth for Training Set: Not explicitly stated in the provided text. The document focuses on the test set's ground truth and the pivotal study results. Standard practice would suggest that training data also requires some form of expert segmentation or clinically confirmed labels, but details are not provided here.
Ask a specific question about this device
(266 days)
VisAble.IO is a Computed Tomography (CT) image processing software package available for use with liver ablation procedures.
VisAble.IO is controlled by the user via a user interface.
VisAble.IO imports images from CT scanners and facility PACS systems for display and processing during liver ablation procedures.
VisAble.IO is used to assist physicians in planning liver ablation procedures, including identifying ablation targets and virtual ablation needle placement. VisAble.IO is used to assist physicians in confirming ablation zones.
The software is not intended for diagnosis. The software is not intended to predict ablation volumes or predict ablation success.
VisAble.IO is a stand-alone software application with tools and features designed to assist users in planning ablation procedures as well as tools for treatment confirmation. The use environment for VisAble.IO is the Operating Room and the hospital healthcare environment such as interventional radiology control room.
VisAble.IO has five distinct workflow steps:
- Data Import
- Anatomic Structures Segmentation (Liver, Hepatic Vein, Portal Vein, Ablation Target)
- Instrument Placement (Needle Planning)
- Ablation Zone Segmentation
- Treatment Confirmation (Registration of Pre- and Post-Interventional Images; Quantitative Analysis)
Of these workflow steps, two (Anatomic Segmentation and Instrument Placement) make use of the planning image. These workflow steps contain features and tools designed to support the planning of ablation procedures. The other two (Ablation Zone Seqmentation, and Treatment Confirmation) make use of the confirmation image volume. These workflow steps contain features and tools designed to support the evaluation of the ablation procedure's technical performance in the confirmation image volume.
Key features of the VisAble.IO Software include:
- Workflow steps availability
- Manual and automated tools for anatomic structures and ablation zone segmentation
- Overlaying and positioning virtual instruments (ablation needles) and user-selected estimates of the ablation regions onto the medical images
- Image fusion and registration
- Compute achieved margins and missed volumes to help the user assess the coverage of the ablation target by the ablation zone
- Data saving and secondary capture generation
The software components provide functions for performing operations related to image display, manipulation, analysis, and quantification, including features designed to facilitate segmentation of the ablation target and ablation zones.
The software system runs on a dedicated computer and is intended for display and processing, of a Computed Tomography (CT), including contrast enhanced images.
The system can be used on patient data for any patient demographic chosen to undergo the ablation treatment.
VisAble.IO uses several algorithms to perform operations to the user in order for them to evaluate the planned and post ablation zones. These include:
- Seamentation
- Image Registration
- Measurement and Quantification
VisAble.IO is intended to be used for ablations with the following ablation instruments:
For needle planning, the software currently supports the following needle models:
- Medtronic: Emprint Antenna 15CM, 20CM, 30CM
- NeuWave Medical: PR Probe 15CM, 20CM: PR XT Probe 15CM, 20CM: LK ー Probe 15CM, 20CM; LK XT Probe 15CM, 20CM
For treatment confirmation (including seqmentation and registration), the software is compatible with all ablation devices as these functions are independent from probes/power settings.
The provided text describes the VisAble.IO device and its performance testing for FDA 510(k) clearance. Here's a breakdown of the requested information based on the document:
1. A table of acceptance criteria and the reported device performance
The document uses "Primary Performance Goal" as the acceptance criterion and "Primary Endpoint" as the reported device performance.
| Algorithm | Primary Performance Goal (Acceptance Criteria) | Primary Endpoint (Reported Performance) |
|---|---|---|
| Liver Segmentation | Mean DICE = 0.92 | Mean DICE = 0.98 |
| Ablation Target Segmentation | Mean DICE = 0.70 | Mean DICE = 0.80 |
| Ablation Zone Segmentation | Mean DICE = 0.70 | Mean DICE = 0.86 |
| Liver Vessels Segmentation | Mean DICE = 0.70 | Mean DICE = 0.72 |
| PrePost Ablation Image Registration | MCD* = 6.06 mm | MCD* = 4.11 mm |
| *MCD=Mean Corresponding Distance |
Note: The document states that segmentation tools provide manual and semi-automated segmentation, and post-processing. The clinical accuracy of segmentation is referred to as "a user operation and the clinical accuracy of segmentation is the responsibility of the user and not a VisAble.IO function." Similarly, for registration, it states "Final accuracy of registration is dependent on user assessment and manual modification of the registration prior to acceptance, and not a VisAble.IO function." This suggests that the reported performance metrics (DICE scores and MCD) likely reflect the algorithm's capability to provide good initial segmentations and registrations for user refinement.
2. Sample sizes used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The sample sizes for the test sets are provided in the table. The provenance for the training/validation datasets are described generally as:
- Liver Segmentation Algorithm Test Set Size: N=50
- Provenance for training/validation (not explicitly test set data): 1091 contrast-enhanced CT images from arterial or venous phases.
- Location of clinical sites: Germany, France, Turkey, Japan, Israel, Netherlands, Canada, USA, UK (38 clinical sites)
- Ablation Target Segmentation Test Set Size: N=59
- Ablation Zone Segmentation Test Set Size: N=59
- Liver Vessels Segmentation Test Set Size: N=100
- Provenance for training/validation (not explicitly test set data): N=393 contrast-enhanced CT images from the portal-venous or late venous phases.
- Location of clinical sites: Central Europe, North America, East Asia (36 clinical sites)
- PrePost Ablation Image Registration Test Set Size: N=46
The document doesn't explicitly state whether the test set data was retrospective or prospective. Given that it's performance data for a 510(k) submission, it is typically retrospective data collected for validation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not specify the number of experts used to establish the ground truth for the test set or their qualifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not specify the adjudication method used for the test set, nor does it explicitly mention a process of expert adjudication for the ground truth.
5. 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
The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study or any effect size related to human reader improvement with AI assistance. The study focuses on the standalone algorithmic performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the performance data presented (DICE scores and MCD) are for the standalone algorithmic performance. The text explicitly states that the "clinical accuracy of segmentation is the responsibility of the user and not a VisAble.IO function" and "final accuracy of registration is dependent on user assessment and manual modification... and not a VisAble.IO function," suggesting the provided metrics are for the initial algorithmic output prior to user intervention.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not explicitly state the type of ground truth used (e.g., expert consensus, pathology, etc.) for the segmentation and registration algorithms. It implies that the "Primary Performance Goal" was set for these algorithms, suggesting a pre-defined or expert-derived ground truth was used for comparison, but the methodology for establishing it is not detailed.
8. The sample size for the training set
The document provides the sample sizes for the training and model validation datasets as:
- Liver Segmentation Algorithm: 1091 contrast-enhanced CT images.
- Liver Vessel Segmentation Algorithm: N=393 contrast-enhanced CT images.
- The sample sizes for training of Ablation Target Segmentation, Ablation Zone Segmentation, and PrePost Ablation Image Registration algorithms are not explicitly stated in the provided text.
9. How the ground truth for the training set was established
The document does not explicitly describe how the ground truth for the training set was established. It only mentions the characteristics of the images used for training (e.g., contrast-enhanced CT, arterial/venous phases, age/sex distribution, location of clinical sites, imaging procedure).
Ask a specific question about this device
Page 1 of 1