Predicate Devices

Reference Devices

Not Found

AI/ML (Artificial Intelligence / Machine Learning)

Yes
The device description explicitly states that the system offers the choice to incorporate third-party AI models that have been cleared by the FDA and that CARPL simply presents the simple AI response output.

Therapeutic

No.
The device is a PACS and radiology workflow management device used for viewing and assessing DICOM images, aiding in diagnosis, but not directly providing therapy or treatment.

Diagnostic

Yes

CARPL is a diagnostic device because its "Intended Use / Indications for Use" states that it is "used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography," and it explicitly mentions that "pre-processed DICOM images specifically intended for presentation are suitable for primary image diagnosis in mammography." It also aids in "diagnostic assessment" through post-processing elements and the visualization of third-party AI model outcomes.

SaMD (Software as a Medical Device)

Yes

The device is described as a "web-based PACS and radiology workflow management device" that handles digital images and information. While it interacts with hardware sources (imaging equipment) and displays (monitors), the core functionality described is software-based: gathering, storing, transmitting, processing (filtering, MPR/MIP), visualizing, and integrating with third-party AI models. There is no indication that the device itself includes any hardware components beyond the software running on a web platform.

IVD (In Vitro Diagnostic)

Based on the provided text, this device is not an IVD (In Vitro Diagnostic).

Here's why:

IVD Definition: In vitro diagnostics are tests performed on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections.
CARPL's Function: CARPL is described as a web-based PACS and radiology workflow management device. Its primary functions are viewing, assessing, storing, transmitting, and visualizing medical images (DICOM images) obtained from various imaging modalities. It also facilitates the integration and display of results from third-party AI models that process these images.
No Sample Analysis: The description of CARPL's intended use and device description does not involve the analysis of biological samples from the human body. It deals exclusively with medical images.

Therefore, while CARPL is a medical device used in the diagnostic process, it does not fit the definition of an In Vitro Diagnostic device.

PCCP (Predetermined Change Control Plan) Authorized

No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.

Overview

Intended Use / Indications for Use

CARPL, a web-based PACS and radiology workflow management device, used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography. It gathers digital images and information from a variety of sources that adhere to the DICOM standard. These sources encompass a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, and visualization of images and data within the system itself or over computer networks spanning different locations.

Only pre-processed DICOM images specifically intended for presentation are suitable for primary image diagnosis in mammography. Lossy compressed Mammographic images and digitized film screen images must not be reviewed for primary interpretation on the CARPL. To ensure accurate interpretation, mammographic images should only be evaluated on a monitor that adheres to the technical specifications outlined by the FDA.

This system is designed exclusively for use by proficient and certified medical experts, including physicians, radiologists, and medical technicians.

Product codes (comma separated list FDA assigned to the subject device)

LLZ

Device Description

CARPL, a web-based PACS and radiology workflow management device, used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography. It gathers digital images and information from a variety of sources that adhere to the DICOM standard. These sources encompass a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, processing, and visualization of images and data within the system itself or over computer networks spanning different locations.

Only preprocessed DICOM "for presentation" images can be interpreted for primary image diagnosis in mammography. Mammographic images with lossy compression and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using a display that is cleared, and that meets technical specifications reviewed and accepted by your regulatory authorities. Preprocessing occurs during the transfer of DICOM images from PACS to CARPL Platform involving the filtering of data based on the DICOM tags like "Modality", "Study Description", "Accession Number", etc. This process is aimed at extracting DICOM images that align with the requirements of the deployment workflow. Images that have not undergone this preprocessing are not included in the deployment workflow. CARPL accepts digital images and information from various sources that adhere to the DICOM standard. These sources include CT scanners, MR scanners, ultrasound systems, RF Units, PET Units, computed and digital radiographic devices, secondary capture devices, imaging gateways, and other imaging equipment. The system features post-processing elements like MPR/MIP that improve visualization for radiologists, aiding them in the diagnostic assessment and measurement of Computed Tomography (CT) and Magnetic Resonance (MR) images.

When assessing images for diagnostic purposes, it becomes the duty of the healthcare expert to ascertain whether the image quality is appropriate for clinical use. The system offers the choice to incorporate third-party AI models that have been cleared by the FDA. A regulatory compliance team continually oversees and verifies the clearance status of each algorithm. Each algorithm developer must prove regulatory clearances before their products can be incorporated with CARPL. FDA-cleared 3rd party algorithms listed in CARPL display the FDA clearance "K" number along with a hyperlink to the algorithm's FDA clearance URL. The solution solely aids in visualizing the outcomes of these third-party AI models without modifications. The safety and efficacy of the third-party model are governed by the regulatory approval granted to the original manufacturer of the said model.

CARPL's integrated FDA-cleared algorithm list is exclusively managed by CARPL.AI Customers do not have the ability technically or administratively to add or modify which FDA-cleared AI algorithms are integrated with CARPL. Only FDA-cleared algorithms which have passed rigorous regulatory and quality standards review by CARPL.AI Inc. to guarantee functionality, safety and security are made available in CARPL.

CARPL simply presents the simple AI response output, and the initial anonymized image remains consistently available. The duty of evaluating the AI output, validating the results, and conducting the diagnosis lies with competent medical professionals.

CARPL incorporates the following:

1. The setup includes a Gateway, situated on the client's end within the modality/PACS network, which can be implemented using the widely available conventional TCP/IP network framework in healthcare institutions. This Gateway is set up on a computer having a reliable internet connection for online transmission, or it can be linked to a Local Area Network (LAN) to transmit images within the network. The Gateway is responsible for collecting DICOM images from different DICOM-compliant sources, forwarding them to the CARPL platform. Additionally, it accepts secondary capture images from CARPL and relays them to the linked hospital PACS.
It has a dataset manager i.e., study list, which includes all the studies that are uploaded to the system.
It has a radiology workflow management system. Supervisors or project Managers can assign the studies to Radiologists. Radiologists can then view the study images, diagnose them, and share feedback on CARPL Viewer.
It is used by radiologists to view the DICOM images for diagnosis and sharing feedback. The viewer supports DICOM images from Digital X-Ray (DX), Computerized Radiography (CR), Ultrasound (US), Computed Tomography (CT), Magnetic Resonance (MR), Nuclear Medicine (NM), Digital Mammography (MG), Positron Emission Tomography (PET), Radiographic imaging (RG), Radio Fluoroscopy (RF) and X-Ray Angiography (XA).
It only incorporates algorithms that have received FDA clearance. The inclusion of KNumber is obligatory and serves as an authentication factor during the integration process. CARPL verifies the 510 (k) Number against the 510 (k) Number database before proceeding with integration.
The system forwards the input study to the third-party AI model, obtains the AI-generated results, and presents these results directly in the Viewer. This enables Radiologists to visualize and utilize the outputs from the third-party AI model to aid in diagnosing the study. The displayed outcomes adhere to the regulatory clearance specifications of the third-party provider. The original image remains accessible at all times.
It can provide status for the studies in the dataset list based on the outputs provided by the 3rd party AI models.
It displays the output of the 3rd party AI model in the Viewer for visualization by the Radiologist to assist in diagnosing the study.
It provides radiologists MPR/MIP 2D multi-planar reconstruction post-processing elements, enhancing visualization and aiding in diagnostic analysis.
1. CARPL also provides a list of annotation tools that the user can use to annotate a case and carry out measurements. The following tools are provided by CARPL:
- Length : The user can use this to measure the distance of the suspected lesion from point 'A'- 'B', which is expressed in cm. The user places the cursor over the starting point on a lesion and drags to draw a segment with visible measurement. To finish the segment, the user releases the cursor. If need be, the user can move the entire segment or the measurement value to a convenient place.
- Annotate : Users can mark a suspected lesion on the image. After the user finishes the marking, a pop-up appears on the image from which the user can select a label or write a label on the annotated area.
Angle : Angle tool can be used when a user wants to measure the angle of a ROI. The user, from a left button on the mouse, draws the first arm of the angle and releases it, and similarly draws the second arm, after which the value is displayed in degrees.
Bidirectional : It is a tool to measure ROI's length and width. The user annotates a suspected lesion, e.g., Nodule; using this tool the user can have the length and width of the marked ROI. The user drags the cursor to a position where they think ROI is present. The values are displayed in mm.
Ellipse : This tool helps users mark an ROI on an image in a defined elliptical border. The user draws an ellipse by dragging the mouse cursor on the ROI and releasing it to finish the Ellipse. Once an ellipse is completed, a pop-up appears to label the ROI. Users can also move the Ellipse to a different position by dragging it.
f. Rectangle : Similar functions to Ellipse. The only difference is the shape of the ROIwhich appears as a rectangle.
Freehand/Close polygon : This is used for giving a freehand shape to an ROI. The user clicks on the left button on the mouse to create a starting node on the ROI; the user then drags the node and finishes it where they want to end the node around the ROI. A pop-up then appears to label the ROI. Users can edit the final shape by clicking on the drawing and dragging it to the desired position.
Eraser: The user can click on the marked ROI and erase it.
Reset: This button restores the study image to its original state.
All sigmificant events within the application trigger Smart Notifications to be distributed to every registered or non-registered user. These notifications do not pertain to any potentially suspected findings that might be recognized by the FDA-cleared third-party AI models, which can be optionally integrated with CARPL.
It provides a communication feature to all the users associated with a given study.
An RDBMS is employed for data storage, while an object storage server is utilized for the purpose of storing and retrieving DICOM images and thumbnails.

The utilized network protocol involves TLS-based communication with HTTPS and AES encryption.

Mentions image processing

Yes

Mentions AI, DNN, or ML

Yes

Input Imaging Modality

DX, DR, CR, CT, MR, US, RF and 2D/3D mammography, NM, PET, RG, XA

Anatomical Site

Not Found

Indicated Patient Age Range

Not Found

Intended User / Care Setting

proficient and certified medical experts, including physicians, radiologists, and medical technicians.

Description of the training set, sample size, data source, and annotation protocol

Not Found

Description of the test set, sample size, data source, and annotation protocol

Not Found

Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)

Non-clinical testing:
CARPL has been assessed and tested at the factory and has passed all predetermined testing criteria. The Validation Test Plan was designed to evaluate output functions and actions performed by CARPL.AI Inc. and followed the process documented in the Validation Test Plan. Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met.

Summary:
Based on the performance as documented in the Validation Testing, CARPL, was found to have a safe and effectiveness profile that is substantially equivalent to the predicate device.

Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)

Not Found

Predicate Device(s): If the device was cleared using the 510(k) pathway, identify the Predicate Device(s) K/DEN number used to claim substantial equivalence and list them here in a comma separated list exactly as they appear in the text. List the primary predicate first in the list.

Augmento (K222781)

Reference Device(s): Identify the Reference Device(s) K/DEN number and list them here in a comma separated list exactly as they appear in the text.

Not Found

Predetermined Change Control Plan (PCCP) - All Relevant Information for the subject device only (e.g. presence / absence, what scope was granted / cleared under the PCCP, any restrictions, etc).

Not Found

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).

Summary

0

March 27, 2024

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters 'FDA' in a blue square, followed by the words 'U.S. FOOD & DRUG ADMINISTRATION' in blue text.

CARPL.AI Inc. % Josh Baker Consultant OT Consulting Inc. 33781 Bayside Lane Dana Point, CA 92629

Re: K232891

Trade/Device Name: Carpl (carpl) Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: February 20, 2024 Received: February 20, 2024

Dear Josh Baker:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

1

2

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Samal for

Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

2

Indications for Use

510(k) Number (if known) K232891

Device Name Carpl (carpl)

Indications for Use (Describe)

CARPL, a web-based PACS and radiology workflow management device, used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography. It gathers digital images and information from a variety of sources that adhere to the DICOM standard. These sources encompass a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, and visualization of images and data within the system itself or over computer networks spanning different locations.

Only pre-processed DICOM images specifically intended for presentation are suitable for primary image diagnosis in mammography. Lossy compressed Mammographic images and digitized film screen images must not be reviewed for primary interpretation on the CARPL. To ensure accurate interpretation, mammographic images should only be evaluated on a monitor that adheres to the technical specifications outlined by the FDA.

This system is designed exclusively for use by proficient and certified medical experts, including physicians, radiologists, and medical technicians.

Type of Use (Select one or both, as applicable)
-------------------------------------------------

X Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

3

Image /page/3/Picture/1 description: The image shows the letters C, R, P, and L in white font on a green background. The letter A is represented by a yellow symbol that looks like a network of interconnected nodes. The letters are arranged horizontally and are evenly spaced.

This 510(k) Summary of safety and effectiveness information is being submitted in accordance with the requirements of 21 CFR 807.92.

I. SUBMITTER

Dr. Vidur Mahajan Chief Strategy Officer CARPL.AI Inc. 355 Bryant St., Suite 403, San Francisco, CA - 94107 Tel: +1 215-600-0035 Email: legal@carpl.ai

Date Prepared: March 25, 2024

II. DEVICE

Name of Device: Carpl (carpl) Submission number: K232891 Common or Usual Name: Medical Image Management and Processing System Classification Name: system, image processing, radiological (21 CFR 892.2050) Regulatory Class: II Product Code: LLZ

III. PREDICATE DEVICE

Predicate Device: Augmento (K222781) by DeepTek Medical Imaging Private Limited, Class II, CFR 892.2050, classification with product code LLZ.

IV. DEVICE DESCRIPTION

CARPL, a web-based PACS and radiology workflow management device, used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography. It gathers digital images and information from a variety of sources that adhere to the DICOM standard. These sources encompass a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, processing, and visualization of images and data within the system itself or over computer networks spanning different locations.

Only preprocessed DICOM "for presentation" images can be interpreted for primary image diagnosis in mammography. Mammographic images with lossy compression and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using a display that is cleared, and that meets technical specifications reviewed and accepted by your regulatory authorities. Preprocessing occurs during the transfer of DICOM images from PACS to CARPL Platform involving the filtering of data based on the DICOM tags like "Modality", "Study Description", "Accession Number", etc. This process is aimed at extracting DICOM images that align with the requirements of the deployment workflow. Images that have not undergone this preprocessing are not included in the deployment workflow. CARPL accepts digital images and information from various sources that adhere to the DICOM

4

Image /page/4/Picture/1 description: The image shows a logo with the letters "C", "R", "P", and "L" in white font on a green background. There is a graphic between the "C" and the "R" that is a light yellow color. The graphic appears to be a network of lines and dots. The logo is simple and modern.

standard. These sources include CT scanners, MR scanners, ultrasound systems, RF Units, PET Units, computed and digital radiographic devices, secondary capture devices, imaging gateways, and other imaging equipment. The system features post-processing elements like MPR/MIP that improve visualization for radiologists, aiding them in the diagnostic assessment and measurement of Computed Tomography (CT) and Magnetic Resonance (MR) images.

When assessing images for diagnostic purposes, it becomes the duty of the healthcare expert to ascertain whether the image quality is appropriate for clinical use. The system offers the choice to incorporate third-party AI models that have been cleared by the FDA. A regulatory compliance team continually oversees and verifies the clearance status of each algorithm. Each algorithm developer must prove regulatory clearances before their products can be incorporated with CARPL. FDA-cleared 3rd party algorithms listed in CARPL display the FDA clearance "K" number along with a hyperlink to the algorithm's FDA clearance URL. The solution solely aids in visualizing the outcomes of these third-party AI models without modifications. The safety and efficacy of the third-party model are governed by the regulatory approval granted to the original manufacturer of the said model.

CARPL's integrated FDA-cleared algorithm list is exclusively managed by CARPL.AI Customers do not have the ability technically or administratively to add or modify which FDA-cleared AI algorithms are integrated with CARPL. Only FDA-cleared algorithms which have passed rigorous regulatory and quality standards review by CARPL.AI Inc. to guarantee functionality, safety and security are made available in CARPL.

CARPL simply presents the simple AI response output, and the initial anonymized image remains consistently available. The duty of evaluating the AI output, validating the results, and conducting the diagnosis lies with competent medical professionals.

| Device Name | FDA K-
Number | Company Name |
|------------------------------------------------|---------------------------------------------------|--------------------------------------------|
| Lunit INSIGHT CXR
Triage | K211733 | Lunit Inc |
| Lunit INSIGHT MMG | K211678 | Lunit Inc |
| Lunit INSIGHT DBT | K231470 | Lunit Inc |
| cmTriage | K183285 | CureMetrix, Inc |
| cmAngio | K232367 | CureMetrix, Inc |
| CINA | K200855, K210237, K22 | AVICENNA.AI |
| qXR-BT | K212690 | Qure.ai Technologies |
| qER-Quant | K211222 | Qure.ai Technologies |
| Qxr-Ptx-Pe | K230899 | Qure.ai Technologies |
| Qxr-Ctr | K231149 | Qure.ai Technologies |
| Qxr-Ln | K231805 | Qure.ai Technologies |
| BoneView | K212365 | Gleamer |
| Rayvolve | K220164 | AZmed SAS |
| CogNet | K220080 | MedCognetics, Inc. |
| QmTRIAGE | | |
| CoLumbo | K220497 | Smart Soft Healthcare
AD |
| KOALA | K192109 | IB Lab GmbH |
| Rbknee | K203696 | Radiobotics ApS |
| Aview Lung
Nodule Cad | K221592 | Coreline Soft Co.,Ltd. |
| A View Lcs | K201710 | Coreline Soft Co.,Ltd. |
| Aview | K214036 | Coreline Soft Co.,Ltd. |
| Koios DS | K212616 | Koios Medical, Inc. |
| DrAid for Radiology v1 | K221241 | VinBrain Joint Stock
Company |
| InferRead CT Stroke.AI | K211179 | Infervision Medical
Technology Co., Ltd |
| InferRead Lung Ct.Ai | K192880 | Infervision Medical
Technology Co., Ltd |
| Icobrain | K192130, K161148,
K180326, K181939,
K192962 | Icometrix NV |
| HALO (LVO Triaging
detection) | K200873 | NiCo-Lab B.V. |
| MammoScreen® 2.0 | K211541 | Therapixel |
| LiverSmart | K213776 | Resonance Health Analysis Servi |
| Cercare Medical
Neurosuite | K202793 | Cercare Medical ApS |
| Us2.v1 | K210791 | Us2.Ai |
| Annalise Enterprise Cxr
Triage Trauma | K222268,
K222179 | Annalise-AI Pty Ltd |
| Annalise Enterprise Cxr
Triage Pneumothorax | K213941 | Annalise-AI Pty Ltd |
| Clearread +Confirm | K123526 | RIVERAIN
TECHNOLOGIES |
| Clearread Ct | K221612,
K161201 | RIVERAIN
TECHNOLOGIES |
| WRDensity | K202013 | Whiterabbit.Ai Inc. |
| Claripulmo | K203783 | ClariPi Inc. |
| Transpara Density 1.0.0 | K232096 | Screenpoint |
| Veolity | K201501 | MeVis |
| VUNO Med-DeepBrain | K231398 | VUNO Inc. |

CARPL current list of integrated FDA cleared AI Models:

5

Image /page/5/Picture/1 description: The image is a logo with the letters "CARPL" in white on a dark green background. The "A" in the logo is stylized with a tan-colored design that resembles a network or interconnected nodes. The logo is simple and modern, with a focus on the text and the unique design of the letter "A".

6

Image /page/6/Picture/1 description: The image shows a logo with the letters "C", "R", "P", and "L" in white font on a green background. There is a symbol between the "C" and "R" that looks like a network of interconnected nodes. The logo is simple and clean, with a focus on the letters and the network symbol. The green background provides a contrast to the white letters, making them stand out.

CARPL incorporates the following:

1. The setup includes a Gateway, situated on the client's end within the modality/PACS network, which can be implemented using the widely available conventional TCP/IP network framework in healthcare institutions. This Gateway is set up on a computer having a reliable internet connection for online transmission, or it can be linked to a Local Area Network (LAN) to transmit images within the network. The Gateway is responsible for collecting DICOM images from different DICOM-compliant sources, forwarding them to the CARPL platform. Additionally, it accepts secondary capture images from CARPL and relays them to the linked hospital PACS.
It has a dataset manager i.e., study list, which includes all the studies that are uploaded to the 2. system.
It has a radiology workflow management system. Supervisors or project Managers can assign 3. the studies to Radiologists. Radiologists can then view the study images, diagnose them, and share feedback on CARPL Viewer.
It is used by radiologists to view the DICOM images for diagnosis and sharing feedback. The 4. viewer supports DICOM images from Digital X-Ray (DX), Computerized Radiography (CR), Ultrasound (US), Computed Tomography (CT), Magnetic Resonance (MR), Nuclear Medicine (NM), Digital Mammography (MG), Positron Emission Tomography (PET), Radiographic imaging (RG), Radio Fluoroscopy (RF) and X-Ray Angiography (XA).
న్ It only incorporates algorithms that have received FDA clearance. The inclusion of KNumber is obligatory and serves as an authentication factor during the integration process. CARPL verifies the 510 (k) Number against the 510 (k) Number database before proceeding with integration.
The system forwards the input study to the third-party AI model, obtains the AI-generated 6. results, and presents these results directly in the Viewer. This enables Radiologists to visualize and utilize the outputs from the third-party AI model to aid in diagnosing the study. The displayed outcomes adhere to the regulatory clearance specifications of the third-party provider. The original image remains accessible at all times.
1. It can provide status for the studies in the dataset list based on the outputs provided by the 3rd party AI models.
It displays the output of the 3rd party AI model in the Viewer for visualization by the 8. Radiologist to assist in diagnosing the study.
1. It provides radiologists MPR/MIP 2D multi-planar reconstruction post-processing elements, enhancing visualization and aiding in diagnostic analysis.
1. CARPL also provides a list of annotation tools that the user can use to annotate a case and carry out measurements. The following tools are provided by CARPL:
- Length : The user can use this to measure the distance of the suspected lesion from a. point 'A'- 'B', which is expressed in cm. The user places the cursor over the starting point on a lesion and drags to draw a segment with visible measurement. To finish the segment, the user releases the cursor. If need be, the user can move the entire segment or the measurement value to a convenient place.
- Annotate : Users can mark a suspected lesion on the image. After the user finishes the b. marking, a pop-up appears on the image from which the user can select a label or write a label on the annotated area.

7

Image /page/7/Picture/1 description: The image shows the logo for CRPL. The logo is set on a green background. The letters "C", "R", "P", and "L" are in white, and there is a tan-colored design between the "C" and the "R".

Angle : Angle tool can be used when a user wants to measure the angle of a ROI. The C. user, from a left button on the mouse, draws the first arm of the angle and releases it, and similarly draws the second arm, after which the value is displayed in degrees.
Bidirectional : It is a tool to measure ROI's length and width. The user annotates a d. suspected lesion, e.g., Nodule; using this tool the user can have the length and width of the marked ROI. The user drags the cursor to a position where they think ROI is present. The values are displayed in mm.
Ellipse : This tool helps users mark an ROI on an image in a defined elliptical border. e. The user draws an ellipse by dragging the mouse cursor on the ROI and releasing it to finish the Ellipse. Once an ellipse is completed, a pop-up appears to label the ROI. Users can also move the Ellipse to a different position by dragging it.
f. Rectangle : Similar functions to Ellipse. The only difference is the shape of the ROIwhich appears as a rectangle.
Freehand/Close polygon : This is used for giving a freehand shape to an ROI. The user g. clicks on the left button on the mouse to create a starting node on the ROI; the user then drags the node and finishes it where they want to end the node around the ROI. A pop-up then appears to label the ROI. Users can edit the final shape by clicking on the drawing and dragging it to the desired position.
Eraser: The user can click on the marked ROI and erase it. h.
Reset: This button restores the study image to its original state. i.
1. All sigmificant events within the application trigger Smart Notifications to be distributed to every registered or non-registered user. These notifications do not pertain to any potentially suspected findings that might be recognized by the FDA-cleared third-party AI models, which can be optionally integrated with CARPL.
1. It provides a communication feature to all the users associated with a given study.
1. An RDBMS is employed for data storage, while an object storage server is utilized for the purpose of storing and retrieving DICOM images and thumbnails.

The utilized network protocol involves TLS-based communication with HTTPS and AES encryption.

V. INDICATIONS FOR USE

CARPL, a web-based PACS and radiology workflow management device, used for viewing and assessing DICOM images Ex: DX, DR, CR, CT, MR, US, RF and 2D/3D mammography. It gathers digital images and information from a variety of sources that adhere to the DICOM standard. These sources encompass a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, processing, and visualization of images and data within the system itself or over computer networks spanning different locations.

Only pre-processed DICOM images specifically intended for presentation are suitable for primary image diagnosis in mammography. Lossy compressed Mammographic images and digitized film screen images must not be reviewed for primary image interpretation on the CARPL. To ensure accurate interpretation, mammographic images should only be evaluated on a monitor that adheres to the technical specifications outlined by the FDA.

This system is designed exclusively for use by proficient and certified medical experts, including physicians, radiologists, and medical technicians.

8

Image /page/8/Picture/0 description: The image shows the letters "C A R P L" in white font on a green background. The "A" is stylized with a network of lines and dots in a tan color. The letters are bold and sans-serif. The image is simple and clean, with a focus on the text.

VI. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICES

The subject and predicate devices are both medical image management and processing systems, which are indicated for medical image management, review, and data distribution. The subject device and the predicate device are substantially equivalent in the areas of general function, application, and intended use. Any differences between the subject and predicate devices have no negative impact on the device safety or efficacy and does not raise any new potential or increased safety risks and is equivalent in performance to existing legally marketed devices.

| | Features
compared | Subject Device
(CARPL)
K232891 | Predicate Device
(Augmento)
K222781 | Significant
Differences? |
|----|------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------|
| | General
Information | | | |
| 1. | Manufacturer | CARPL.AI Inc | DEEPTEK MEDICAL
IMAGING PRIVATE
LIMITED | - |
| 2. | Common Name | Medical image
management and
processing system | Medical image
management and
processing system | NO |
| 3. | Classification
Name | System, Image
Processing,
Radiological | System, Image
Processing,
Radiological | NO |
| 4. | Classification | Class II | Class II | NO |
| 5. | Regulation
number | 21 CFR 892.2050 | 21 CFR 892.2050 | NO |
| 6. | Product Code | LLZ | LLZ | NO |
| 7. | Indications For
Use | CARPL, a web-based
PACS and radiology
workflow management
device, used for viewing
and assessing DICOM
images Ex: DX, DR, CR,
CT, MR, US, RF and
2D/3D mammography. It
gathers digital images and
information from a variety
of sources that adhere to
the DICOM standard. | Augmento is a web-
based PACS and
radiology workflow
management solution.
It receives digital
images and data from
various DICOM
compliant sources (i.e.
CT scanners, MR
scanners, ultrasound
systems, RF Units,
PET Units, computed
& digital radiographic | NO |

9

Image /page/9/Picture/1 description: The image shows the letters "C A R P L" in white font on a dark green background. The "A" is stylized with a tan-colored design that resembles a network of interconnected nodes. The letters are bold and evenly spaced, creating a clear and legible wordmark.

a range of devices, including digital and computed radiographic equipment, CT and MR scanners, ultrasound and RF machines, PET units, secondary capture tools, imaging gateways. CARPL enables the storage, transmission, processing, and visualization of images and data within the system itself or over computer networks spanning different locations. Only pre-processed diagnostic DICOM "for presentation" images can be interpreted for primary image diagnosis in mammography. Lossy compressed Mammographic images and digitized film screen images must not be reviewed for primary image interpretation on the CARPL. To ensure

accurate interpretation.

mammographic images

to the technical

the FDA.

should only be evaluated on a monitor that adheres

specifications outlined by

This system is designed

medical experts, including physicians, radiologists, and medical technicians.

exclusively for use by proficient and certified devices, secondary capture devices, imaging gateways and other imaqinq sources). Images and data can be stored, communicated, processed and displayed within the system and/or across computer networks at distributed locations. Only preprocessed DICOM "for presentation" images can be interpreted for primary image diagnosis in mammoqraphy. Lossy compressed images and digitized film screens of mammographic images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using a monitor that meets technical specifications identified by the FDA. This system is meant to be used by trained and qualified medical professionals, e.g physicians, radiologists, nurses, and medical technicians.

10

Image /page/10/Picture/1 description: The image shows the letters "C", "R", "P", and "L" in white font on a green background. There is a tan-colored design between the "C" and the "R" that looks like a network of lines and dots. The letters are all capitalized and appear to be part of a logo or brand name. The overall design is simple and modern.

| | Features
compared | Subject Device
(CARPL)
K232891 | Predicate Device
(Augmento)
K222781 | Significant Differences? |
|-----|--------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | Specifications | | | |
| 8. | Modalities | Various Image
sources | Various image sources | NO |
| 9. | Web
browser
software | Google
Chrome,
Mozilla, and
Edge | Google Chrome,
Mozilla, and Edge | NO |
| 10. | Resolution | 32 bit Color
Display &
1920x1080 | 32 bit Color
Display &
1920x1080 | NO |
| 11. | Image Storage | YES | YES | NO |
| 12. | Software
environment | OS: Windows 10
or higher | OS: Windows 10 | NO - No significant difference
in the operating environment
used. The subject device and
the predicate device are
substantially equivalent in the
areas of technical
characteristics, general
function, application, and
intended use.
Therefore, it is our
determination that there is "No
impact on safety or efficacy"
and there are no new
potential safety risks. |
| | Features
compared | Subject Device
(CARPL)
K232891 | Predicate Device
(Augmento)
K222781 | Significant
Differences? |
| | Functions | | | |
| 13. | Main Functions | Log In Worklist - Search Filter Worklist - Open image Work list – study List Worklist - Report Worklist - Series Viewer - View exam Viewer – Control View window Viewer – view mode (real resolution) Viewer – View mode (Highlight) Viewer - Stacking Viewer – Changing the layout Viewer - Comparative study Viewer – Preset filter Viewer - Zoom Viewer - Panning Viewer - Invert Image Viewer – Viewing mode (Normal/ Image/ Stack/ Custom/ Annotation) Viewer - Comparative study Viewer – Rotation MIP/MPR | Log In Worklist - Search Filter Worklist - Open image Work list - study List Worklist - Report Worklist - Series Viewer – View exam Viewer - Control View window Viewer – view mode (real resolution) Viewer – View mode (Highlight) Viewer - Stacking Viewer – Changing the layout Viewer - Comparative study Viewer – Preset filter Viewer - Zoom Viewer – Panning Viewer - Invert Image Viewer – Viewing mode (Normal/ Image/ Stack/ Custom/ Annotation) Viewer - Comparative study | NO |
| | | Reconstruction
• Viewer – Reference line
• Viewer – Sharpening
• Viewer - Measure
• Viewer – Inverting
image color
• Viewer - Cine
• Viewer- Overlaying. | • Viewer – Rotation
• MIP/MPR
Reconstruction
• Viewer – Reference
line
• Viewer - Sharpening
• Viewer - Measure
• Viewer – Inverting
image color
• Viewer - Cine
• Viewer- Overlaying. | |
| 14. | 3D Cursor | YES | YES | NO |
| 15. | Optional
Integration of
FDA - cleared 3rd
party Al models | YES | YES | NO |
| 16. | Operation feature | • Web environment-based
PACS.
• Viewing and handling
DICOM medical images.
• Review and report study
located on a server
• View multiple Al model
output | • Web environment based
PACS
• Viewing and handling
DICOM medical images.
• Review and report study
located on a server | NO - There
are no
significant
differences in
the operation
features. The
subject device
and the
predicate
device are
substantially
equivalent in
the areas of
general
function,
application,
and intended
use and the
ability to view
multiple Al
model output
does not raise
any new
potential
safety risks. |

11

12

13

The technological principle for both the subject and predicate devices is the same in terms of prescription use, support of various modalities, resolution, image storage, use of the DICOM Standard, 3D Cursor, and Operation features. Most of the features, specifications, and functions of both the subject and predicate devices, like indications for use, software web browser, software intended environment, study viewer, and study worklist are similar.

CARPL provides the feature of optional integration with external FDA-cleared 3rd party AI models like the predicate device Augmento does. The integration with the FDAcleared 3rd party AI models is optional based on the user's discretion, and always in accordance with the 3rd party manufacturer's regulatory clearance. The regulatory status of integrated FDA approved algorithms is clear in the CARPL user interface as it displays the approved algorithm's 510(k) number along with a link to the FDA website page containing the algorithm's substantial equivalence ruling. Technological safeguards prevent algorithms without FDA clearance from being employed. Hence, the difference does not affect the product effectiveness and safety.

VII. PERFORMANCE DATA

Non-clinical testing:

CARPL has been assessed and tested at the factory and has passed all predetermined testing criteria. The Validation Test Plan was designed to evaluate output functions and actions performed by CARPL.AI Inc. and followed the process documented in the Validation Test Plan. Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met.

Summary:

Based on the performance as documented in the Validation Testing, CARPL, was found to have a safe and effectiveness profile that is substantially equivalent to the predicate device.

14

The following Standards were used to develop CARPL, and the device has met all the requirements listed in the Standards except for inapplicable requirements:

| Standard
Developing
Organization | Standard
Designation
Number and
Date | FDA
Recognition
Number | Title of
Standard |
|----------------------------------------|---------------------------------------------------------|------------------------------|-----------------------------------------------------------------------------------------------------------------------|
| NEMA | PS 3.1 - 3.20 2022d | 12-349 | Digital Imaging
and
Communications
in Medicine
(DICOM) Set |
| IEC | 62304 Edition 1.1
2015-06
CONSOLIDATED
VERSION | 13-79 | Medical device
software -
Software life cycle
process |
| IEC | 60812 Edition 3.0
2018-08 | 5-120 | Analysis
techniques for
system reliability -
Procedure for
failure mode and
effects analysis
(FMEA) |

VIII. CONCLUSION

The information presented in the 510(k) for CARPL contains adequate information, data, and nonclinical test results to demonstrate substantial equivalence to the predicate device. CARPL was shown to be substantially equivalent to the predicate device in the areas of technical characteristics, general function, application, and intended use and does not raise any new potential safety risks and is equivalent in performance to existing legally marketed devices.