Search Results

The Histolog® Scanner is a confocal laser system intended to allow imaging of the internal microstructure of tissues including, but not limited to, the identification of cells, vessels and their organization or architecture.

The Histolog® Scanner is a digital microscopy scanner for use on excised human tissue. Its operating principle is based on confocal fluorescence microscopy and uses non-ionizing, lowpower optical radiation (Class 1 laser product as per IEC 60825-1:2014-05). The Histolog® Scanner acquires digital images with high, micrometer-range resolution and enables the visualization of tissue microstructures down to the cellular level.

The Histolog® Scanner is based on a massively parallel signal acquisition and processing technology providing fast digital imaging over large areas. Image reconstruction does not involve any image stitching or any other similar image blending algorithms. Each pixel in the image is assigned an intensity value based on the light intensity collected by the detector for this particular position in the scan pattern.

The provided text does not contain the detailed information required to fulfill all aspects of the request regarding the device's acceptance criteria and the study proving it meets them. The document focuses on the regulatory submission and comparison to a predicate device, rather than a detailed clinical performance study.

Here's a breakdown of what can and cannot be extracted from the provided text:

What can be extracted:

• Acceptance Criteria for Non-Clinical Tests: The document lists acceptance criteria for various non-clinical performance and safety tests.
• Results for Non-Clinical Tests: The document states "PASS" for all listed internal validation tests.

What cannot be extracted (critical for a clinical performance study):

• Table of Acceptance Criteria and Reported Device Performance for Imaging Quality (Clinical): While "Imaging Quality" is listed as a test, the specific acceptance criteria (e.g., sensitivity, specificity, accuracy for a specific diagnostic task) and the actual reported performance values are not provided. The text only says "Histolog® Scanner system imaging requirements verification protocols. All requirements met." This is insufficient for a clinical performance study.
• Sample size used for the test set and data provenance: No information on the number of images/patients, or whether the data was retrospective/prospective or its origin.
• Number of experts used to establish ground truth and qualifications: No mention of experts or their qualifications.
• Adjudication method for the test set: No information.
• MRMC comparative effectiveness study details: No mention of human readers or AI assistance in a comparative study.
• Standalone (algorithm only) performance: While the device images tissue, there's no mention of an algorithm being evaluated in a standalone capacity against a ground truth. The device itself is the "scanner."
• Type of ground truth used: No mention of ground truth (e.g., pathology, outcomes).
• Sample size for the training set: The document discusses validation, not training.
• How the ground truth for the training set was established: Not applicable, as training data and ground truth establishment for AI are not mentioned.

Based on the provided text, here is the information that can be extracted and a clear indication of what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

For non-clinical safety and performance tests:

Missing: Specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy) and corresponding reported performance metrics for "Imaging Quality" related to the device's diagnostic capabilities or image interpretation for identifying specific microstructures (cells, vessels, organization). The document confirms internal verification protocols were met, but doesn't detail these protocols or their outcomes for clinical relevance.

2. Sample size used for the test set and the data provenance

Missing: No information regarding the sample size of any test set (e.g., number of tissue samples, patients, or images) used for evaluating the device's clinical performance or imaging quality related to microstructure identification. Data provenance (country of origin, retrospective/prospective) is also not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Missing: The document does not describe any expert involvement in establishing ground truth for a test set.

4. Adjudication method for the test set

Missing: No information on an adjudication method.

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

Missing: No MRMC study is described. The device is a scanner intended for imaging the microstructure of tissues, not explicitly an AI-assisted diagnostic tool for human readers based on this submission.

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

Missing: While the device performs standalone imaging, the document doesn't describe a separate "algorithm only" performance evaluation that would assess, for example, automated detection or classification capabilities without human interpretation of the images. The device itself is the imaging system.

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

Missing: No information on the type of ground truth used for any clinical performance or imaging quality assessment.

8. The sample size for the training set

Missing: No information on a training set, as the document focuses on device performance validation rather than machine learning model development.

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

Missing: Not applicable, as detailed training data and its ground truth establishment are not mentioned.

Conclusion: The provided FDA submission letter and summary focus explicitly on demonstrating substantial equivalence to a predicate device primarily through non-clinical performance and safety data, and a high-level statement about meeting "imaging quality" requirements. It does not present a clinical performance study with detailed acceptance criteria, sample sizes, ground truth establishment, or human reader performance metrics that would be typical for an AI/CADe device or a device requiring such detailed clinical validation.

Ask a specific question about this device