Sectra Digital Pathology Module (3.3) is a software device intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. It is an aid to the pathologist to review and interpret these digital images for the purposes of primary diagnosis. Sectra Digital Pathology Module (3.3) is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of the pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images using Sectra Digital Pathology Module (3.3). Sectra Digital Pathology Module (3.3) is intended for use with Leica’s Aperio GT 450 DX scanner and Dell U3223QE display, for viewing and management of the ScanScope Virtual Slide (SVS) and Digital Imaging and Communications in Medicine (DICOM) image formats.
Device Story
Sectra Digital Pathology Module (3.3) is a software-only digital slide viewing system; functions as an add-on module to Sectra PACS (Workstation IDS7). It retrieves and displays digital pathology images (SVS and DICOM formats) generated by the Leica Aperio GT 450 DX scanner. Pathologists use the system on a Dell U3223QE display to perform primary diagnosis, replacing conventional light microscopy. The system provides tools for panning, zooming, annotating, and measuring (distance/area). It supports remote intranet access. Images from non-indicated scanners are marked 'For Non-clinical Use Only'. By enabling digital review, the device allows pathologists to manage and interpret slides efficiently, potentially improving workflow and diagnostic accessibility. The system ensures color reproducibility and accurate measurement, with performance validated against light microscopy standards.
Clinical Evidence
Prospective clinical study (n=258 cases, 774 total reads) compared WSI review (WSIR) using DPAT (3.3) to traditional light microscopy (MSR). Primary endpoint: difference in major discrepancy rates between WSIR and MSR vs. reference diagnosis. Results: WSIR major discrepancy rate 3.00%, MSR 3.01%; difference -0.01% (95% CI: -1.71% to 1.69%), meeting the ≤4% non-inferiority criterion. Secondary endpoint: WSIR major discrepancy rate 3.00% (95% CI: 1.64% to 5.25%), meeting the <7% criterion. Bench testing confirmed measurement accuracy and turnaround times.
Technological Characteristics
Software-only digital pathology viewer. Operates as a client-side module (Pathology Image Window) within Sectra PACS. Supports SVS and DICOM image formats. Compatible with Dell U3223QE display. Connectivity via intranet/network. No hardware scanner included. Image manipulation: panning, zooming, gamma adjustment, annotation, distance/area measurement.
Indications for Use
Indicated for use by pathologists as an aid in the review and interpretation of digital images of scanned surgical pathology slides prepared from FFPE tissue for primary diagnosis. Not for use with frozen section, cytology, or non-FFPE hematopathology specimens.
Regulatory Classification
Identification
The whole slide imaging system is an automated digital slide creation, viewing, and management system intended as an aid to the pathologist to review and interpret digital images of surgical pathology slides. The system generates digital images that would otherwise be appropriate for manual visualization by conventional light microscopy.
Special Controls
A whole slide imaging system must comply with the following special controls: (1) Premarket notification submissions must include the following information: (i) The indications for use must specify the tissue specimen that is intended to be used with the whole slide imaging system and the components of the system. (ii) A detailed description of the device and bench testing results at the component level, including for the following, as appropriate: (A) Slide feeder; (B) Light source; (C) Imaging optics: (D)Mechanical scanner movement; (E) Digital imaging sensor; (F) Image processing software; (G)Image composition techniques; (H)Image file formats; (I) Image review manipulation software; (J) Computer environment; (K)Display system. (iii)Detailed bench testing and results at the system level, including for the following, as appropriate: (A)Color reproducibility; (B) Spatial resolution; (C) Focusing test; (D) Whole slide tissue coverage; (E) Stitching error: (F) Turnaround time. (iv) Detailed information demonstrating the performance characteristics of the device, including, as appropriate: (A)Precision to evaluate intra-system and inter-system precision using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included. (B) Reproducibility data to evaluate inter-site variability using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included. (C) Data from a clinical study to demonstrate that viewing, reviewing, and diagnosing digital images of surgical pathology slides prepared from tissue slides using the whole slide imaging system is non-inferior to using an optical microscope. The study should evaluate the difference in major discordance rates between manual digital (MD) and manual optical (MO) modalities when compared to the reference (e.g., main sign-out diagnosis). (D) A detailed human factors engineering process must be used to evaluate the whole slide imaging system user interface(s). (2) Labeling compliant with 21 CFR 809.10(b) must include the following: The intended use statement must include the information described in paragraph (i) (1)(i) of this section, as applicable, and a statement that reads, "It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using this device." (ii) A description of the technical studies and the summary of results, including those that relate to paragraph (1)(ii) and (1)(iii) of this section, as appropriate. (iii) A description of the performance studies and the summary of results, including those that relate to paragraph (1)(iv) of this section, as appropriate. (iv) A limiting statement that specifies that pathologists should exercise professional judgment in each clinical situation and examine the glass slides by conventional microscopy if there is doubt about the ability to accurately render an interpretation using this device alone.
*Classification.* Class II (special controls). The special controls for this device are:(1) Premarket notification submissions must include the following information:
(i) The indications for use must specify the tissue specimen that is intended to be used with the whole slide imaging system and the components of the system.
(ii) A detailed description of the device and bench testing results at the component level, including for the following, as appropriate:
(A) Slide feeder;
(B) Light source;
(C) Imaging optics;
(D) Mechanical scanner movement;
(E) Digital imaging sensor;
(F) Image processing software;
(G) Image composition techniques;
(H) Image file formats;
(I) Image review manipulation software;
(J) Computer environment; and
(K) Display system.
(iii) Detailed bench testing and results at the system level, including for the following, as appropriate:
(A) Color reproducibility;
(B) Spatial resolution;
(C) Focusing test;
(D) Whole slide tissue coverage;
(E) Stitching error; and
(F) Turnaround time.
(iv) Detailed information demonstrating the performance characteristics of the device, including, as appropriate:
(A) Precision to evaluate intra-system and inter-system precision using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included.
(B) Reproducibility data to evaluate inter-site variability using a comprehensive set of clinical specimens with defined, clinically relevant histologic features from various organ systems and diseases. Multiple whole slide imaging systems, multiple sites, and multiple readers must be included.
(C) Data from a clinical study to demonstrate that viewing, reviewing, and diagnosing digital images of surgical pathology slides prepared from tissue slides using the whole slide imaging system is non-inferior to using an optical microscope. The study should evaluate the difference in major discordance rates between manual digital (MD) and manual optical (MO) modalities when compared to the reference (
*e.g.,* main sign-out diagnosis).(D) A detailed human factor engineering process must be used to evaluate the whole slide imaging system user interface(s).
(2) Labeling compliant with 21 CFR 809.10(b) must include the following:
(i) The intended use statement must include the information described in paragraph (b)(1)(i) of this section, as applicable, and a statement that reads, “It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using this device.”
(ii) A description of the technical studies and the summary of results, including those that relate to paragraphs (b)(1)(ii) and (iii) of this section, as appropriate.
(iii) A description of the performance studies and the summary of results, including those that relate to paragraph (b)(1)(iv) of this section, as appropriate.
(iv) A limiting statement that specifies that pathologists should exercise professional judgment in each clinical situation and examine the glass slides by conventional microscopy if there is doubt about the ability to accurately render an interpretation using this device alone.
Predicate Devices
Aperio WebViewer DX component of the Aperio GT 450 DX System (K232202)
Submission Summary (Full Text)
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
## I Background Information:
A 510(k) Number
K232208
B Applicant
Sectra AB
C Proprietary and Established Names
Sectra Digital Pathology Module (3.3)
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QKQ | Class II | 21 CFR 864.3700 - Whole Slide Imaging System | PA - Pathology |
## II Submission/Device Overview:
Purpose for Submission:
New Device
A Type of Test:
Not applicable – software only device
## III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for the Use below.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
B Indication(s) for Use:
For In Vitro Diagnostic Use
Sectra Digital Pathology Module (3.3) is a software device intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. It is an aid to the pathologist to review and interpret these digital images for the purposes of primary diagnosis.
Sectra Digital Pathology Module (3.3) is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of the pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images using Sectra Digital Pathology Module (3.3).
Sectra Digital Pathology Module (3.3) is intended for use with Leica’s Aperio GT 450 DX scanner and Dell U3223QE display, for viewing and management of the ScanScope Virtual Slide (SVS) and Digital Imaging and Communications in Medicine (DICOM) image formats.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
IV Device/System Characteristics:
A Device Description:
The Sectra Digital Pathology Module (3.3) [henceforth referred to DPAT (3.3)] is a digital slide viewing system for viewing and managing digital pathology images of glass slides obtained from the Aperio GT 450 DX scanner and viewed on the Dell U3223QE display. The DPAT (3.3) can only be used in combination with the external image server provided by Sectra picture archiving and communications system (PACS). The end user must log in to Sectra Workstation to access the subject device. Sectra Workstation is available in two models: IDS7 and UniView. UniView is an equivalent, web-based version of IDS7. The architecture of DPAT (3.3) consists of the following elements:
- Pathology Image Window (PIW) where the scanned slides are viewed and manipulated by end users. The PIW is a web application embedded into Sectra Workstation to offer a seamless user experience.
- Sectra Pathology Server (SPS) is the main server component of the web-based Pathology Image Window. The SPS supports displaying and manipulating the scanned slides.
- Database Engine stores metadata such as annotations required by the SPS.
- Sectra Pathology Import Server (SPIS) is used for importing digital pathology images (from scanned slides) from the Aperio GT 450 DX scanner as an alternative to the scanner sending images to Sectra PACS using the standard DICOM Storage.
K232208 - Page 2 of 14
{2}
The system capabilities include:
- retrieving and displaying digital slides
- including support for remote intranet access over computer networks
- providing tools for annotating digital slides and entering and editing metadata associated with digital slides
- displaying the scanned slide images for primary diagnosis by pathologists
The DPAT (3.3) is operated as follows:
1. The DPAT (3.3) receives quality-controlled images from the Aperio GT 450 DX scanner and extracts a copy of the images' metadata. The unaltered images are then sent to the external image storage (Sectra Core). A copy of the image metadata (e.g., the pixel size) is stored locally in the subject device to increase the operational performance (e.g., response times) of the subject device.
2. The reading pathologist selects a case (patient) from a worklist external to the subject device such as the laboratory information system (LIS) whereby the SPS fetches the associated images from the Sectra Core.
3. The reading pathologist uses DPAT (3.3) to view the images and is able to perform the following actions, as needed:
- Zoom and pan the image
- Measure distances and areas in the image
- Annotate images
- View multiple images side by side in a synchronized fashion
After viewing all images belonging to a particular case (patient), the pathologist will make a diagnosis. The diagnosis is documented in another system such as the LIS.
DPAT (3.3) operates with the following components listed below in Table 1.
Table 1: Interoperable Components Intended for Use with Sectra Digital Pathology Module (3.3)
| Scanner Hardware | Scanner Output file format | Interoperable Viewing Software | Interoperable Display |
| --- | --- | --- | --- |
| Aperio GT 450 DX scanner | SVS | Sectra Digital Pathology Module (3.3) | Dell U3223QE |
| Aperio GT 450 DX scanner | DICOM | Sectra Digital Pathology Module (3.3) | Dell U3223QE |
Minimum System Requirements - Computer Environment
The system requirements are given in Tables 2 through 4 below.
K232208 - Page 3 of 14
{3}
Table 2: Requirements for PIW
| Sectra Workstation (Host for subject device) | IDS7 | UniView |
| --- | --- | --- |
| Operating system | MS Windows 11 or 10 (x64) | |
| CPU | 4-core CPU, 3.6 GHz | |
| RAM | 8 GB | |
| Graphics board | NVIDIA T600 or Quadro P1000 with 4GB | |
| Network | 1 Gbit/s LAN connection | |
| 3D mouse | 3Dconnexion SpaceMouse Pro | N/A |
| Browser | N/A | Google Chrome or MS Edge |
| Hardware acceleration | N/A | Enabled |
| WebGL support | N/A | Required |
Table 3: Server (SPDB and SPS) Requirements
| Operating system & Database Engine (SPDB) | • Windows Server 2019 Std Ed, with SQL Server 2019 Std Ed
• Windows Server 2016 Std Ed, with SQL Server 2016 SP3 Std Ed (upgrades only)
• Windows Server 2012 R2 Std Ed, with SQL Server 2012 SP4 Std Ed (upgrades only)
• .NET 6 |
| --- | --- |
| Operating System & Sectra Pathology Import Service (SPIS) | • Windows Server 2019
• Windows Server 2016 (upgrades only)
• Windows Server 2012 R2 (upgrades only)
• Windows 11
• Windows 10
• .NET 6 |
Table 4: Recommended Configurations, Server
| Sectra Pathology Server (SPDB and SPS) | |
| --- | --- |
| CPU RAM | 8 cores CPU, e.g., 1x Intel Xeon 4110 CPU 32 GB |
| Disk Network | RAM
2x 146 GB system disk (mirrored)
Gigabit LAN connection |
| Sectra Pathology Import Service - SPIS | |
K232208 - Page 4 of 14
{4}
K232208 - Page 5 of 14
| Sectra Pathology Server (SPDB and SPS) | |
| --- | --- |
| CPU RAM | 4 vCPU |
| Disk Network | 8 GB vRAM |
| | 146 GB system disk |
| | Gigabit LAN connection |
## B Instrument Description Information:
1. **Instrument Name:**
Sectra Digital Pathology Module (3.3)
2. **Specimen Identification:**
The Sectra Digital Pathology Module (3.3) uses digital pathology images obtained from the Aperio GT 450 DX scanner of Hematoxylin and Eosin (H&E) stained glass slides. The reading pathologist selects a case (patient) from a worklist external to the subject device whereby the subject device fetches the associated images from the external image storage. The scanned images are identified based on the previously assigned specimen identifier such as the laboratory specimen accession number.
3. **Specimen Sampling and Handling:**
Specimen sampling and handling are performed upstream and independent of the use of the subject device. Specimen sampling includes biopsy or resection specimens which are processed using histology techniques. The FFPE tissue section is hematoxylin & eosin (H&E) stained. Digital images are then obtained from these glass slides using the Aperio GT 450 DX scanner.
4. **Calibration:**
Not Applicable
5. **Quality Control:**
The subject device receives quality-controlled images from the scanner. The subject device specific quality control measures are as follows:
- Connect scanner - This test should be performed before connecting the scanner to the subject device in order to verify the on-site integration between the Aperio GT 450 DX scanner and the Sectra Workstation.
- View pathology images - Every pathologist should perform this test on review workstation before reading pathology images using the subject device to ensure that all scanned slide images have been imported and for every case, view the thumbnails in the pathology image window to verify that each slide that should be in the case is present (manually verifying tissue block and staining information from LIS).
Additional details of the quality control procedures are provided in the device User's Guide and the Installation Guide.
{5}
V Substantial Equivalence Information:
A Predicate Device Name(s): Aperio GT 450 DX
B Predicate 510(k) Number(s): K232202
C Comparison with Predicate(s):
| Device & Predicate Device(s): | Sectra Digital Pathology Module (3.3) K232208 | Aperio GT 450 DX K232202 | | | |
| --- | --- | --- | --- | --- | --- |
| General Device Characteristic: Similarities | | | | | |
| Intended Use/Indications for Use | Sectra Digital Pathology Module (3.3) is a software device intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. It is an aid to the pathologist to review and interpret these digital images for the purposes of primary diagnosis.
Sectra Digital Pathology Module (3.3) is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of the pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images | The Aperio GT 450 DX is an automated digital slide creation and viewing system. The Aperio GT 450 DX is intended for in vitro diagnostic use as an aid to the pathologist to review and interpret digital images of surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. The Aperio GT 450 DX is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy.
Aperio GT 450 DX is comprised of the Aperio GT450 DX scanner, which generates images in the Digital Imaging and Communications in Medicine (DICOM) and in the ScanScope Virtual Slide (SVS) file formats, the Aperio WebViewer DX viewer, and the displays. The Aperio GT 450 DX is intended to be used with the interoperable components specified in Table 1.
Table 1: Interoperable components of Aperio GT 450 DX | | | |
| | | Scanner Hardware | Scanner Output file format | Interoperable Viewing Software | Interoperable Displays |
| | | Aperio GT 450 DX scanner | SVS | Aperio WebViewer DX | Barco MDPC-8127
Dell UP3017
Dell U3023E
Dell U3223QE |
K232208 - Page 6 of 14
{6}
K232208 - Page 7 of 14
| | | | | | |
| --- | --- | --- | --- | --- | --- |
| using Sectra Digital Pathology Module (3.3).
Sectra Digital Pathology Module (3.3) is intended for use with Leica’s Aperio GT450 DX scanner and Dell U3223QE display, for viewing and management of the ScanScope Virtual Slide (SVS) and Digital Imaging and Communications in Medicine (DICOM) image formats. | | Aperio GT 450 DX scanner | SVS | Sectra Digital Pathology Module (3.3) | Dell U3223QE |
| | | Aperio GT 450 DX scanner | DICOM | Sectra Digital Pathology Module (3.3) | Dell U3223QE |
| The Aperio GT 450 DX is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using the Aperio GT 450 DX. | | | | | |
| Type of Software Application | Internet Browser based | Internet Browser based | | | |
| Image manipulation functions | Panning, zooming, gamma function, annotations, and distance measurements. | Same | | | |
| End User’s Interface | DPAT (3.3) - Pathology Image Window (the client component of Sectra DPAT (3.3) | DPAT (3.3) and WebViewer DX | | | |
| Image Manipulation Functions | Panning, zooming, image adjustments, annotations, and distance/area measurements | Same | | | |
| General Device Characteristic: Differences | | | | | |
| Device Components | DPAT (3.3) | Scanner, Webviewer DX, Display | | | |
| Image file format | SVS and DICOM | SVS | | | |
| Principle of Operation | After WSI images are successfully acquired by using Aperio GT 450 DX scanner, WSI images are imported by SPIS as groups of cases. The laboratory technician | After WSI images are successfully acquired by using Aperio GT 450 DX scanner, it is data is sent to end-user-provided image storage attached to the local network. During the review, the pathologist opens WSI images acquired with the WSI scanner from the image storage, performs further QC, and reads WSI images of the slides to make a diagnosis. | | | |
{7}
K232208 - Page 8 of 14
| | performs a quality control by using PIW to verify that all images have been imported. During review, the pathologist selects a patient case and opens WSI images from the Sectra Core to read the WSI images and make a Diagnosis. | |
| --- | --- | --- |
VI Standards/Guidance Documents Referenced:
1. Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices: Guidance for Industry and Food and Drug Administration Staff, April 20, 2016.
2. Applying Human Factors and Usability Engineering to Medical Devices: Guidance for Industry and Food and Drug Administration Staff February 3, 2016.
3. EN ISO 13485:2016 Medical devices — Quality management systems — Requirements for regulatory purposes.
4. EN ISO 14971:2019-12 – Medical devices - Application of risk management to medical devices (same as ISO 14971:2007, Corrected version 2007-10-01), Recognition Number: 5-40.
5. EN 62304:2006- AMD1:2015 – Medical device software - software life-cycle processes, Recognition Number: 13-32. EN ISO 62366-1:2015 - AMD1:2015 – Application of usability engineering to medical devices, Recognition Number: 5-114.
6. ISO/IEC 27001:2013 – Information technology — Security techniques - Information security management systems — Requirements.
7. ISO/IEC 27017: 2015 — Security techniques — Code of practice for information security controls based on ISO/IEC 27002 for cloud services.
8. ISO/IEC 27018: 2019 — Security techniques — Code of practice for protection of personally identifiable information (PII) in public clouds acting as PII processors.
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
a. Precision/Reproducibility:
Not applicable
b. Linearity:
Not applicable
{8}
c. Analytical Specificity/Interference:
Not applicable
d. Accuracy (Instrument):
Not applicable
e. Carry-Over:
Not applicable
B Other Supportive Instrument Performance Characteristics Data:
a. A clinical study was conducted to demonstrate that viewing, reviewing and diagnosing WSIs of H&E stained FFPE tissue slides using the DPAT (3.3) on Sectra Workstation UniView (DPAT (3.3)-UniView) is non-inferior to glass slide reads using optical (light) microscopy. The imaging pipeline/configuration in the clinical study used was as follows: Aperio GT 450 DX scanner images/SVS image format/ DPAT (3.3)-UniView/Chrome web browser/DellU3223QE display.
b. Technical bench testing to demonstrate that DPAT (3.3) generates identical images in the configurations that were not validated in the clinical study. The Aperio GT 450 DX/SVS/DPAT (3.3)-UniView/Chrome configuration which was the imaging pipeline validated in the clinical study, was used as the reference configuration in the pixelwise comparison study to validate the other 4 configurations as described in section b below.
a. Clinical Validation Study
A clinical study was conducted to demonstrate that using DPAT (3.3)-UniView for use in primary diagnosis of FFPE tissue sections when used with the Aperio GT 450 DX scanner, which generated WSIs in the SVS image file format is non-inferior to glass slide reads using optical light microscopy (MSR).
The study included 258 randomly selected cases that represented a diverse mixture of pathologic diagnoses and tissue/organ types. Case slides were scanned on the Aperio GT 450 DX scanner, producing WSIs in the SVS format at 40x magnification. Three (3) reading pathologists (the same pathologists who determined MSR diagnosis) at a single site reviewed all study cases using DPAT (3.3) -UniView on the Microsoft Chrome web browser and a Dell U3223QE monitor per user guide, to determine the WSIR diagnosis. The reading pathologists were masked to the reference diagnoses, their own diagnoses from the previous studies and to other reading pathologist's study diagnoses. Across the 258 selected cases, all 870 WSIs were successfully reviewed. The range of WSIs reviewed per case was 1 to 34.
The WSIR data from the current study and the existing MSR data (diagnoses, concordance scores and consensus scores) from a previous clinical study (K190332) which had the same study cases and readers as the current study were used to estimate study endpoints.
K232208 - Page 9 of 14
{9}
A minimum of two adjudicators independently assessed concordance (concordant, minor discordance, major discordance) of the WSIR diagnosis against the reference diagnosis using predefined rules. If consensus was not reached between the first 2 adjudicators, a third adjudicator reviewed the study diagnosis against the reference diagnosis. If consensus between 2 of 3 adjudicators was still not reached, then the 3 adjudicators would convene as a panel to come to a consensus for the major discordance status. WSIR diagnosis consensus scores were used to estimate WSIR diagnosis major discordance rate. For MSR diagnoses, the consensus scores generated during the previous clinical study (K190332) were used for this study to estimate MSR diagnosis major discordance rate.
A major discordance was defined as a difference in diagnosis that resulted in a clinically important difference in patient management, whereas a minor discordance would not be associated with a clinically important difference in patient management. The adjudicators' concordance scores for the same case were compared to determine a consensus score for major discordance status [no major discordance (concordant or minor discordance) or major discordance]. The diagnosis consensus scores were used to estimate WSIR diagnosis major discordance rate.
**Study Acceptance Criteria:** The primary endpoint of the study was the difference in overall major discordance rates between the 2 modalities [Whole slide image review (WSIR) using DPAT (3.3)-UniView and MSR] when compared to the reference diagnosis (original sign-out pathologic diagnosis) which was defined as the ground truth (GT) diagnosis. The secondary endpoint of the study was the major discordance rate of WSIR diagnosis relative to the reference diagnosis. The acceptance criteria associated with each study endpoint were as follows:
**Primary Endpoint:** The upper bound of the 2-sided 95% CI of the difference between the overall major discordance rates of WSIR diagnosis and MSR diagnosis when compared to the reference diagnosis shall be ≤4%.
**Secondary Endpoints:** The upper bound of the 2-sided 95% CI of the major discordance rate between WSIR diagnosis and the reference diagnosis shall be ≤7%.
**Adjudication Review:** For WSIR, there were 767 study diagnoses reviewed by 2 (primary) adjudicators. No diagnoses were deferred by the adjudicators; therefore, 767 WSIR diagnoses had concordance scores. Of these, consensus on major discordance status was obtained for 736 (96.0%, 736/767) study diagnoses by 2 adjudicators only; 31 (4.0%, 31/767) study diagnoses were transferred to a third adjudicator for review, after which consensus was obtained. No study diagnoses required panel review. Adjudication of MSR diagnoses and generation of consensus scores was conducted during the previous clinical study. All 764 MSR diagnoses were successfully adjudicated and had consensus scores.
**Study Results:** All 774 case reads (258 cases × 3 reading pathologists) were successfully performed by WSIR. Seven WSIR diagnoses were deferred (cases that could not be diagnosed by the reading pathologists), resulting in 767 WSIR diagnoses sent for adjudication.
K232208 - Page 10 of 14
{10}
All 774 case reads were performed by MSR during the previous clinical study. Ten (10) MSR diagnoses were deferred by the reading pathologists, resulting in 764 MSR diagnoses sent for adjudication. Study results are shown in the table below.
Table 5. Clinical Study Results Based on Major Discordance Rates
| Modality | (n/N) | Discordance Rate (%) | 95% CI (%) |
| --- | --- | --- | --- |
| WSIRD vs GT | 23/767 | 3.00 | (1.64, 5.25) |
| MSRD vs GT | 23/764 | 3.01 | (1.65, 5.27) |
| Difference | | -0.1 | (-1.71, 1.69) |
The estimated difference in major discordance rates between the 2 modalities when compared to the reference diagnosis was $-0.01\%$ (95% CI: $-1.71\%$ to $1.69\%$ ). The upper bound of the $95\%$ CI of the estimated difference in major discordance rates was $1.69\%$ which met the predefined acceptance criteria of $\leq 4\%$ for the primary endpoint. The overall major discordance rate between the WSIR diagnosis and the reference diagnosis did not exceed $7\%$ ; the upper bound of the $95\%$ CI for the overall estimated major discordance rate for WSIR diagnosis was $5.25\%$ , which met the predefined acceptance criteria of $\leq 7\%$ as shown in the table below.
Table 6. Concordance Rate between WSIR Diagnoses and MSR Diagnoses
| Number of Concordances | Number of Pairs | Concordance Rate (%) | 95% Confidence Interval |
| --- | --- | --- | --- |
| 729 | 762 | 95.7 | [94.2%, 97.1%] |
Note: 95% CI was produced using the percentile bootstrapping approach on 5000 bootstrap samples
The major discordance rates for WSIR and MSR diagnoses (relative to the reference diagnosis), and the difference between the two modalities, by each organ type is shown in the table below.
Table 7. Major Discordance Rates for WSIR and MSR Diagnoses by Organ Type
| Organ Type | Major Discordance Rate | | Difference in Major Discordance Rates (WSIRD - MSRD) |
| --- | --- | --- | --- |
| | WSIRD | MSRD | |
| Anus/Perianal | 0.00% | 0.00% | 0.00% |
| Appendix | 0.00% | 0.00% | 0.00% |
| Bladder | 13.73% | 7.84% | 5.88% |
| Brain/Neuro | 0.00% | 9.38% | -9.38% |
| Breast | 9.26% | 0.00% | 9.26% |
| Colorectal | 3.85% | 2.56% | 1.28% |
| Endocrine | 0.00% | 0.00% | 0.00% |
| GE Junction | 1.96% | 3.92% | -1.96% |
| Gallbladder | 0.00% | 0.00% | 0.00% |
K232208 - Page 11 of 14
{11}
| Organ Type | Major Discordance Rate | | Difference in Major Discordance Rates (WSIRD – MSRD) |
| --- | --- | --- | --- |
| | WSIRD | MSRD | |
| Gynecological | 1.28% | 6.41% | -5.13% |
| Hernial/Peritoneal | 0.00% | 0.00% | 0.00% |
| Kidney, Neoplastic | 0.00% | 3.70% | -3.70% |
| Liver/Bile Duct | 0.00% | 0.00% | 0.00% |
| Lung | 4.76% | 0.00% | 4.76% |
| Lymph Node | 0.00% | 0.00% | 0.00% |
| Prostate | 2.61% | 3.29% | -0.68% |
| Salivary gland | 0.00% | 3.85% | -3.85% |
| Skin | 3.57% | 0.00% | 3.57% |
| Soft Tissue Tumor | 0.00% | 0.00% | 0.00% |
| Stomach | 0.00% | 0.00% | 0.00% |
# b. Bench Testing - Pixelwise comparison study
DPAT (3.3) supports multiple file formats, multiple viewers and multiple browsers, constituting various configurations to be tested. The SVS/UniView/Chrome configuration imaging pipeline was validated in the above clinical study. Therefore, it was used as the reference configuration in the pixelwise comparison study to validate 4 additional configurations specified in the table below.
Table 8: DPAT (3.3) Configurations Tested in the Pixelwise Comparison Testing
| Configuration | Image File format | Viewer/Browser |
| --- | --- | --- |
| DICOM/IDS7 | DICOM | IDS7 |
| DICOM/UniView/Chrome | DICOM | UniView/Chrome |
| SVS/IDS7 | SVS | IDS7 |
| SVS/UniView/Edge | SVS | UniView/Edge |
A total of 30 FFPE tissue slides from various human anatomic sites such as breast, prostate, gastrointestinal tract, lung, ovary, lymph node, bone, etc. were used in the study. This sample set was different from the sample set used in the clinical study.
The 30 glass slides were scanned with a Leica Aperio GT 450 DX scanner to generate WSI files in the SVS and DICOM file formats. For each of the 30 slides, 3 regions of interests (ROIs) were manually selected by qualified personnel to represent various features in the tissue samples. Blank or blurry areas were excluded from the ROI selection. The ROIs were captured at $10\mathrm{x}$ and $40\mathrm{x}$ magnification levels.
A total of 4 configurations specified in table 8 above were tested in the study. Each of these configurations represented an imaging pipeline and consisted of the specific file format (SVS or DICOM), viewer (IDS7 or UniView), and browser (Chrome or Edge).
The pixelwise comparison study was conducted in the intended computer environment following the labeling of the subject and predicate devices, including the Dell U3223QE display, which has
K232208 - Page 12 of 14
{12}
3840x2160 pixels. For each configuration, 180 image-pairs (30 slides * 3 ROIs * 2 magnification levels) were tested. For each comparison, screenshots were captured from the subject and predicate devices to form an image-pair. Each image-pair was cropped and registered to be pixelwise comparable. The cropped image included most of the pixels in the image except for those in the viewer-specific user interface areas. The testing data, including the screenshots and cropping/registration information of the 5 configurations were provided in the FDA specific format.
For each image-pair, the pixelwise differences between two images were calculated using the CIEDE2000 color difference metric. Two images were considered to be identical if the 95th percentile of the pixelwise color differences is less than 3 CIEDE2000 ( $< 3\Delta \mathrm{E}_{00}$ ). A configuration can be validated if all image-pairs are identical to the reference configuration.
Based on analysis of the testing data, the 4 configurations specified in table 9 below were identical, i.e., $< 3\Delta \mathrm{E}_{00}$ to reference configuration SVS/UniView/Chrome.
Table 9: Pixelwise Testing Results
| Configuration | Image File format | Viewer/Browser | Comparison to Reference Pipeline |
| --- | --- | --- | --- |
| DICOM/IDS7 | DICOM | IDS7 | ΔE =0 |
| DICOM/UniView/Chrome | DICOM | UniView/Chrome | ΔE =0 |
| SVS/IDS7 | SVS | IDS7 | ΔE =0 |
| SVS/UniView/Edge | SVS | UniView/Edge | ΔE =0 |
# c. Turnaround Time
The purpose of this test was to demonstrate that the turnaround time for rendering of images is acceptable. Turnaround times for loading a new image, image panning and zooming for both UniView and IDS7 were tested as well as opening images from SVS files and DICOM files. Test results for different scenarios met the test acceptance criteria and showed acceptable turnaround time for image loading.
# d. Measurements (area and distance)
The purpose of this test was to demonstrate that DPAT (3.3) accurately shows measurement annotations on scanned WSIs from the Aperio GT 450 DX scanner. Measurements in Uniview and IDS7 on each of the 2 image file formats SVS and DICOM were evaluated. For each combination (UniView/SVS, UniView/DICOM, IDS7/SVS and IDS7/DICOM), 6 measurements of 3 different lengths in 2 different orientations (3 horizontal and 3 vertical) were performed using the built-in measurement tool using the comparator and the DPAT (3.3). The results showed that the measurement values agreed between the comparator and DPAT (3.3). DPAT (3.3) has been found to perform accurate measurements with respect to its intended use.
# e. Human Factors (Usability) Testing
Human factors study designed around critical user tasks and use scenarios performed by representative users were conducted for previously cleared DPAT (2.2) in K193054. No new human factor study was performed for DPAT (3.3).
K232208 - Page 13 of 14
{13}
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K232208 - Page 14 of 14
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.
