Search Results

eyonis® LCS is indicated for use by radiologists. eyonis® LCS assists radiologists in the detection, localization and characterization of solid and part-solid probably benign, suspicious and very suspicious pulmonary parenchymal nodules with a diameter of 4-30 mm (pure ground glass, mediastinal lesions and masses - including but not limited to hilar masses - are excluded).

The eyonis® LCS - lung nodules result report provides, for each reported nodule, the following information: slice number, malignancy score, full snapshot, close-up snapshot, diameters (long/short/average) and volume.

The eyonis® LCS - lung nodules result report is indicated to aid in diagnosis as well as to aid in follow-up exam evaluations and as an adjunct to support clinical/patient management.

It cannot, however, substitute for medical experts' clinical judgment.

The target population is higher-risk patients eligible for participation in lung cancer screening programs (as per USPSTF criteria) with the exception of patients with pure ground glass cancer only and hilar/mediastinal cancer who are excluded from the intended population.

It is indicated for use with low-dose Chest CT DICOM images. The exact specifications are described in a DICOM Conformance Statement (DCS) document.

eyonis® LCS is an AI/ML technology-based end-to-end CADe/CADx Software as Medical Device (SaMD) intended to allow early detection, localization and characterization of pulmonary parenchymal nodules from LDCT DICOM images produced during Chest CT examinations.

The product consists of a Container-based Image Processing chain with no associated viewer. The software applies algorithms for detection, localization and characterization of solid and part-solid nodules. These algorithms employ proprietary AI and Machine Learning models trained with large databases containing proven examples of lung cancer lesions and benign nodules.

Processing results of eyonis® LCS are given in the form of a DICOM 'result report' which displays probably benign/suspicious/very suspicious nodules with a malignancy risk score per nodule, ranked by score and an associated malignancy rate observed in our reference population.

The result report is saved directly as a DICOM file for the purpose of being stored on a PACS system. It is transmitted back to the Median Gateway to be dispatched to a configured location, local hard drive or a DICOM Service class provider. Alternatively, Dicom Web and HL7 are supported.

eyonis trust, a license server, addresses important challenges such as authorizing or revoking customer access to eyonis® LCS 1.1, tracking software usage, and ensuring legal compliance with licensing contracts.

eyonis® LCS output is not intended to replace the clinical judgment of the interpreting physician and should only be used along with clinical interpretation.

The software can be deployed in any environment that supports Kubernetes deployment (Cloud based or on premises) as a set of orchestrated containers.

Software deployment is flexible and allows 3 installation methods, depending on the infrastructure, resources and capabilities.

Here's a breakdown of the acceptance criteria and study details for the eyonis® LCS 1.1 device, based on the provided FDA 510(k) Clearance Letter:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Standalone Study Test Set:
  • Sample Size: 1,147 patients (342 cancers, 805 non-cancer cases).
  • Data Provenance: Retrospective cohort study from 7 different datasets: 2 academic sites in Europe, 3 academic sites in the United States, and 2 private American data providers. The study population was high-risk individuals (50-80 years old with a history of smoking) and enriched for cancer prevalence, nodule size, and spiculation.
• MRMC Reader Study Test Set:
  • Sample Size: 480 total patient images.
  • Data Provenance: Retrospective study from patients across the United States and Europe.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Standalone Study: The ground truth was established by "radiologist consensus." The number of radiologists involved specific to this consensus is not explicitly stated, nor are their detailed qualifications beyond being "radiologist."
• MRMC Reader Study: The ground truth was established by a "reference standard" which the radiologists' performance was compared against. The document doesn't explicitly state the number of experts used to establish this specific reference standard, nor their qualifications. However, the readers involved in the study were 16 US Board Certified radiologists with an average of 13.31 years of experience (ranging from 2 to 32 years). These are the readers whose performance was evaluated against the ground truth.

4. Adjudication Method for the Test Set

The document does not explicitly state a specific adjudication method (e.g., 2+1, 3+1) for establishing the ground truth for either the standalone or MRMC study. It mentions "radiologist consensus" for the standalone study and "reference standard" for the MRMC study, implying a consensual agreement but without detailing the process.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

Yes, a pivotal MRMC comparative effectiveness study was done.

• Effect Size of Human Readers' Improvement with AI vs. without AI Assistance:
  • Primary Endpoint (AUC): The ∆AUC (aided – unaided) was 0.0158 [0.0032-0.0288], with a p-value of 0.0277, indicating a statistically significant improvement in diagnostic accuracy.
  • Sensitivity: The ∆Sensitivity (aided – unaided) was 1.25% (aided = 93.75%, unaided = 92.50%). While numerically superior, this was not statistically significant for superiority (p>0.05). However, it met the secondary non-inferiority objective.
  • Specificity: The ∆Specificity (aided – unaided) was 4.14% (aided = 53.59%, unaided = 49.45%), which was statistically significant (p<0.05), demonstrating improved specificity.
  • Inter-reader Agreement (Patient Score): Increased from ICC of 0.707 (unaided) to 0.830 (aided), with p<0.0001.
  • Inter-reader Agreement (Patient Management): Kappa value increased from 0.3507 (unaided) to 0.4898 (aided), with p<0.05.

6. If a Standalone (i.e. Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a standalone performance test was executed on eyonis® LCS. The results are reported in the "Non-clinical Performance Testing" section and are detailed in the table above (patient-level AUROC, sensitivity, specificity, and AULROC).

7. The Type of Ground Truth Used

• Standalone Study: The reference standard was proven via histopathology or ≥12 months stability.
• MRMC Reader Study: The document refers to a "reference standard" against which reader performance was compared, but does not explicitly detail the nature of this reference standard (e.g., specific pathology, expert consensus) within the provided text for the reader study data. However, given the context of lung nodule characterization, it is highly likely to be based on histopathology for confirmed cancers and stability for benign nodules, consistent with the standalone study.

8. The Sample Size for the Training Set

The document states that the AI and Machine Learning models were "trained with large databases containing proven examples of lung cancer lesions and benign nodules." However, the exact sample size for the training set is not provided in the given text.

9. How the Ground Truth for the Training Set Was Established

The document states that the models were trained with "large databases containing proven examples of lung cancer lesions and benign nodules." This implies that the ground truth for the training set was established through definitive diagnostic methods, likely similar to the test set (e.g., histopathology for malignancies and long-term stability or biopsy for benign cases). However, the specific methodology for establishing ground truth for the training set is not explicitly detailed in the provided text.

Ask a specific question about this device

LMS-Liver is an image analysis software application for evaluating CT images covering the liver area. It is designed to assist radiologists in the evaluation and documentation of lesions. It also provides tools for assessment of lesion evolution over time. LMS-Liver offers measurement tools and 3D registration techniques for characterization and follow-up of the lesions. It also offers reporting capabilities making it possible to generate standardized reports.

LMS-Liver is intended to be used by radiologists and other clinicians qualified to interpret CT images.

LMS-Liver device is designed to be used with CT images covering the liver area in adult patients.

LMS-Liver is an image analysis software application for evaluating CT images covering the liver area. It is designed to assist radiologists in the evaluation and documentation of lesions. It also provides tools for assessment of lesion evolution over time. LMS-Liver offers measurement tools and 3D registration techniques for characterization and follow-up of the lesions. It also offers reporting capabilities making it possible to generate standardized reports. LMS-Liver can segment hepatic lesions identified by the user with a double click (seed point). Once a lesion is segmented, the software computes its characteristics such as size, volume and intensity.

LMS-Liver can match and compare lesions present in two different datasets of the same patient acquired at different dates and compute their difference of size and volume.

The provided 510(k) summary for LMS-Liver does not contain detailed information about specific acceptance criteria or an explicit study proving the device meets them in the way typically expected for a performance study. Instead, the submission focuses on demonstrating substantial equivalence to predicate devices based on functional characteristics and intended use.

Here's an analysis of the provided information relative to your requested categories:

1. Table of Acceptance Criteria and Reported Device Performance

No specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) or corresponding reported performance metrics (e.g., 90% sensitivity achieved) are provided in the document. The submission relies on a qualitative comparison to predicate devices, stating that LMS-Liver is "equivalent in function to existing legally marketed devices."

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

The document does not describe a formal performance study with a test set of images. There is no mention of a specific sample size, data provenance, or whether the data was retrospective or prospective.

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)

Since no formal test set or performance evaluation is described, there is no information about experts used to establish ground truth.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

Without a described test set or performance study, no adjudication method is mentioned.

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 describe an MRMC comparative effectiveness study. The focus is on the device's standalone functionality and its equivalence to other software, not on how it improves human reader performance.

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

While the device's functionality is described for assisting radiologists, the submission primarily focuses on the device's capabilities in isolation ("LMS-Liver can segment hepatic lesions... computes its characteristics... match and compare lesions..."). This implies a standalone evaluation of its features and functions, but without specific performance metrics. The comparison chart with predicate devices (Siemens Syngo TrueD software and Cedara I-Response/PET/CT) focuses on feature parity.

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

As no explicit performance study or test set is described, there is no mention of the type of ground truth used.

8. The sample size for the training set

The document does not provide any information about a training set or its sample size. This is common for submissions focused on feature equivalence rather than AI/ML model performance, especially in 2007.

9. How the ground truth for the training set was established

Since no training set is mentioned, there is no information on how its ground truth would have been established.

Summary of the Study (as presented in the 510(k)):

The provided 510(k) summary does not describe a conventional clinical or performance study with acceptance criteria and measured device performance in the modern sense of AI/ML device evaluations. Instead, the "study" proving the device meets acceptance criteria** is implicitly the comparison to predicate devices and a hazard analysis.**

• Acceptance Criteria (Implicit): That the device performs functions similar to the legally marketed predicate devices (Siemens Syngo TrueD software and Cedara I-Response; Cedara PET/CT) and does not introduce new safety risks.
• Study: The submission relies on a substantial equivalence comparison chart (section titled "Substantial Equivalence Comparison Chart") that lists functional similarities between LMS-Liver and the predicate devices. It also states that a "comprehensive hazard analysis" was conducted, concluding that "residual risks are acceptable." This hazard analysis serves as the safety "study."

In conclusion, the document demonstrates substantial equivalence by outlining the device's features and comparing them to those of established predicate devices, and by performing a safety assessment, rather than by presenting a detailed performance study with quantitative acceptance criteria and measured results on a specific dataset. This approach was more common in 510(k) submissions of that era for image analysis software.

Ask a specific question about this device

LMS-Lung/TRACK is intended to provide the radiologists and other clinicians qualified to interpret CT images the ability to

• visualize chest CT datasets acquired in low or normal dose;
• mark and automatically/manually measure characteristics (such as diameter, volume) of lung nodules selected by the user;
• compare chest CT scans of the same patient over time for quantification of pulmonary lesion evolution (volume growth and doubling time estimation)
• generate automatic reports.

LMS-Lung/Track device is designed to be used in diagnostic thoracic CT examinations in adult patients.

LMS-Lung/Track is not intended to be used for patients with prior thoracotomy.

LMS-Lung/TRACK provides visualization and analysis tools for chest CT images acquired in low or normal dose.

LMS-Lung/TRACK segments pulmonary lesions identified by the user with a double click (seed point). Once a lesion is segmented, the software computes its characteristics such as size, volume and intensity. Alternatively, the user can do its own 2D measurements on the lesion.

LMS-Lung/TRACK matches and compares lesions identified by the physician present in two different datasets of the same patient acquired at different dates. It computes the differences of volume and diameters and volume growth.

LMS-Lung/Track provides tool to generate report with snapshots, and results.

The provided 510(k) summary for HD70868 (LMS-Lung/TRACK) does not contain a specific section outlining acceptance criteria or a detailed study proving the device meets those criteria. The document focuses on demonstrating substantial equivalence to predicate devices based on functional comparison and safety analysis.

Therefore, many of the requested details, such as specific acceptance criteria, reported device performance metrics against those criteria, sample sizes for test sets, data provenance, expert qualifications, adjudication methods, MRMC study results, standalone performance, and ground truth information for both test and training sets, are not explicitly provided within this document.

The document mainly highlights the device's intended use and features, and compares them with predicate devices, concluding that it is substantially equivalent and does not raise new safety risks.

Based on the provided text, here's what can be inferred or directly stated:

1. Table of Acceptance Criteria and Reported Device Performance

Not provided in the document. The document focuses on feature comparison and substantial equivalence to predicate devices rather than specific quantitative performance metrics against defined acceptance criteria.

2. Sample Size Used for the Test Set and Data Provenance

Not provided in the document.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

Not provided in the document.

4. Adjudication Method for the Test Set

Not provided in the document.

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

Not reported or implied in the document. The document does not describe any MRMC studies or human reader improvement with AI assistance.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not directly stated as a formal study result. However, the device description strongly implies standalone algorithmic functions for "segmenting pulmonary lesions," "comput[ing] its characteristics such as size, volume and intensity," and "match[ing] and compar[ing] lesions identified by the physician present in two different datasets." The performance of these automatic functions in isolation is not quantitatively detailed with acceptance criteria in this document.

7. The Type of Ground Truth Used

Not provided in the document.

8. The Sample Size for the Training Set

Not provided in the document.

9. How the Ground Truth for the Training Set was Established

Not provided in the document.

Summary of what is present:

• Device Name: LMS-Lung/TRACK
• Intended Use: Visualization, marking, automatic/manual measurement of lung nodule characteristics (diameter, volume), comparison of CT scans over time for lesion evolution, and report generation in adult patients for diagnostic thoracic CT examinations. Not for patients with prior thoracotomy.
• Comparison to Predicate Devices: The document primarily establishes substantial equivalence by comparing the functionalities of LMS-Lung/TRACK with three predicate devices (CA-1500, Lung nodule assessment and comparison option, Primelung). Key comparable features include input CT scans, interactive 2D and 3D visualization, segmentation of lung lesions, extraction and computation of lesion characteristics (2D and 3D), manual measurement, lesion matching over time, lesion comparison over time, and report generation.
• Safety: A hazard analysis was conducted, concluding that residual risks were acceptable when weighed against the intended benefits.

The provided 510(k) summary is a high-level overview establishing substantial equivalence for market clearance and does not delve into the detailed performance validation studies that would contain the specific information requested.

Ask a specific question about this device