The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communication of suspected positive findings of pathologies in head CT images, namely Intracranial Hemorrhage (ICH).

BriefCase uses an artificial intelligence algorithm to analyze images and highlight cases with detected ICH on a standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected ICH findings. Notifications include compressed preview images that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

The results of BriefCase are intended to be used in conjunction with other patient information and based on professional judgment, to assist with triage/prioritization of medical images. Notified clinicians are responsible for viewing full images per the standard of care.

Device Description

BriefCase is a radiological computer-assisted triage and notification software device. The software system is based on an algorithm programmed component and is comprised of a standard off-the-shelf operating system, the Microsoft Windows server 2012 64bit, and additional applications, which include PostgreSQL. DICOM module and the BriefCase Image Processing Application. The device consists of the following three modules: (1) Aidoc Hospital Server (AHS); (2) Aidoc Cloud Server (ACS); and (3) Aidoc Worklist Application that is installed on the radiologist' desktop and provides the user interface in which notifications from the BriefCase software are received.

DICOM images are received, saved and filtered and de-identified before processing. Series are processed chronologically by running an algorithm on each series to detect suspected findings and then notifications on flagged series are sent to the Worklist desktop application, thereby prompting preemptive triage and prioritization.

The Worklist Application displays the pop-up notifications of new studies with suspected findings when they come in. Notifications are in the form of a small pop-up containing patient name and accession number. A list of all incoming cases with suspected findings is also displayed. In addition, a compressed, small black and white image that is marked "not for diagnostic use" is displayed as a preview function. This compressed preview is meant for informational purposes only, does not contain any marking of the findings, and is not intended for primary diagnosis beyond notification. Presenting the radiologist with notification facilitates earlier triage by allowing one to assess the available images in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care practice alone.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance Study for Aidoc Medical, Ltd.'s BriefCase (K180647)

Device: BriefCase, a radiological computer-aided triage and notification software for Intracranial Hemorrhage (ICH) detection on non-enhanced head CT scans.

1. Table of Acceptance Criteria and the Reported Device Performance

The document states a primary performance goal for sensitivity and specificity.

Metric	Acceptance Criteria (Performance Goal)	Reported Device Performance (95% CI)
Sensitivity	Exceeded 80%	93.6% (86.6%-97.6%)
Specificity	Exceeded 80%	92.3% (85.4%-96.6%)

Additionally, a secondary endpoint related to workflow prioritization was assessed. While not explicitly stated as an "acceptance criterion" with a specific threshold, the study aimed to demonstrate a significant reduction in time to notification compared to standard-of-care time to exam open.

Metric	Reported Device Performance (Mean, 95% CI)	Statistical Significance (P-value)
Standard of Care Time-to-exam-open	72.58 minutes (45.02-100.14)
BriefCase Time-to-notification	4.46 minutes (4.10-4.83)
Mean Difference (Time-to-exam-open - Time-to-notification)	68.11 minutes (40.50-95.72)	<0.0001

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

Sample Size for Test Set: 198 cases
Data Provenance: Retrospective, multicenter, multinational.
- Countries of Origin: 3 clinical sites (2 US and 1 OUS - outside US, specifically Israel is mentioned for the time-to-notification study). The document specifies "one in Israel and one in the US" for the 59 true positive cases analyzed for time-to-notification.

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

The document does not explicitly state the number of experts or their specific qualifications (e.g., years of experience) used to establish the ground truth for the test set. It only refers to cases being "identified as positive by both the BriefCase and the ground truth," suggesting an expert consensus or review process but providing no details about it.

4. Adjudication Method for the Test Set

The document does not explicitly state the full adjudication method (e.g., 2+1, 3+1). It only mentions "ground truth" without detailing how consensus was reached if multiple readers were involved.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No, a pure MRMC comparative effectiveness study that quantitatively measures how much human readers improve with AI vs. without AI assistance was not explicitly described. The study
focused on the standalone performance of the AI algorithm (sensitivity and specificity) and the potential for workflow prioritization (time-to-notification vs. time-to-exam-open). While the latter implies a benefit for radiologists by providing earlier notifications, it's not a direct human reader performance study (e.g., ROC analysis with and without AI assistance).

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

Yes. The primary performance metrics (sensitivity and specificity) of 93.6% and 92.3% respectively were obtained from the algorithm's performance in identifying ICH findings on the 198 cases, independent of human interpretation at that specific measurement. The time-to-notification metric also reflects the algorithm's speed in processing and flagging cases.

7. The Type of Ground Truth Used

The document refers to the ground truth as "identified as positive by both the BriefCase and the ground truth" for the 59 "true positive" cases, implying expert consensus (radiological interpretation) was used to establish the presence or absence of ICH. It doesn't mention pathology or outcomes data.

8. The Sample Size for the Training Set

The document does not specify the sample size used for the training set. It only mentions that the device utilizes a "deep learning algorithm trained on medical images."

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

The document does not specify how the ground truth for the training set was established. It generally states that the deep learning algorithm was "trained on medical images," but doesn't detail the process for labeling these images for training purposes.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logos of the Department of Health & Human Services and the U.S. Food & Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. Food & Drug Administration" in blue text. The word "Administration" is on the second line.

August 1st, 2018

Aidoc Medical, Ltd. % John J. Smith, M.D., J.D. Regulatory Counsel/Partner Hogan Lovells US LLP 555 Thirteenth Street, NW WASHINGTON DC 20004

Re: K180647

Trade/Device Name: BriefCase Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: II Product Code: QAS Dated: July 5, 2018 Received: July 5, 2018

Dear Dr. Smith:

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 (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. The general controls provisions of the Act include requirements for annual registration. Iisting 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.

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 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

{1}------------------------------------------------

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Jeff Rodgers

Digitally signed by Jeffrey J.
Ballyns -S
DN: c=US, o=U.S. Government,
ou=HHS, ou=FDA, ou=People,
0.9.2342.19200300.100.1.1=200
9569725, cn=Jeffrey J. Ballyns -S
Date: 2018.08.01 09:12:29
04'00'

for Robert Ochs, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration Indications for Use

510(k) Number (if known) K180647

Device Name

BriefCase

Indications for Use (Describe)

BriefCase is a radiological computer aided triage and notification software indicated for use in the analysis of non-enhanced head CT images. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communication of suspected positive findings of pathologies in head CT images, namely Intracranial Hemorrhage (ICH) .

BriefCase uses an artificial intelligence algorithm to analyze images and highlight cases with detected ICH on a standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected ICH findinas. Notifications include compressed preview images that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

The results of BriefCase are intended to be used in conjunction with other patient information and based on professional judgment to assist with triace/prioritization of medical images. Notified clinicians are responsible for viewing full images per the standard of care.

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

[X] Prescription Use (Part 21 CFR 801 Subpart D)

| Prescription Use (Part 21 CFR 801 Subpart D)

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}------------------------------------------------

510(k) Summary

Aidoc Medical, Ltd.'s BriefCase (K180647)

Submitter:

Aidoc Medical, Ltd.Yigal Alon 92Tel-Aviv, Israel
Phone:	+1 315-207-3494
Contact Person:	N. Epstein, Ph.D.
Date Prepared:	July 31, 2018
Name of Device:	BriefCase
Classification Name:	Radiological computer aided triage and notification software
Regulatory Class:	Class II
Product Code:	QAS (21 C.F.R. 892.2080)
Predicate Device:	Viz.Al's ContaCT (DEN170073)

Device Description

The Worklist Application displays the pop-up notifications of new studies with suspected findings when they come in. Notifications are in the form of a small pop-up containing patient name and accession number. A list of all incoming cases with suspected findings is also displayed. In addition, a compressed, small black and white image that is marked "not for diagnostic use" is displayed as a preview function. This compressed preview is meant for informational purposes only, does not contain any marking of the findings, and is not intended for primary diagnosis bevond notification. Presenting the radiologist with notification facilitates earlier triage by allowing one to assess the available images in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care practice alone.

{4}------------------------------------------------

Intended Use / Indications for Use

BriefCase is a radiological computer aided triage and notification software indicated for use in the analysis of non-enhanced head CT images.

Comparison of Technological Characteristics

The subject and predicate devices are radiological computer-assisted triage and notification software programs. Both devices are artificial intelligence algorithms incorporated software packages for use with CT scanners, PACS, and workstations. Both devices process images intended to aid in prioritization and triage of radiological medical images. The predicate device processes brain CT angiogram images and is indicated for the detection of large vessel occlusion, while the subject device processes head CT images and is indicated for Intracranial Hemorrhage. While the subject device's indications for use differ slightly from the predicate device, both devices are intended to provide notifications and preview head images of potential findings to radiologists and other clinicians for the purpose of treatment planning and follow up.

Both software devices notify a designated list of clinicians (the predicate device - a neurovascular specialist, the subject device - a radiologist) of the availability of time sensitive radiological medical images for review based on computer aided image analysis performed by the device's Al algorithm. The subject device sends notifications and compressed previews to the workstations' desktop of the radiologist. Those notifications work in the standard of care. Thev prompt the radiologist to start preemptive triage of a flagged case, upon which he may decide after observing the preview on his desktop, to turn to the local PACS to perform the evaluation. If a notification is rejected, the case still remains in the queue to be handled per the standard of care.

The predicate device also sends notifications and compressed previews, but to the mobile phone of a neuro-specialist independent of the standard of care, thus both devices work in parallel to the standard of care. Both compressed previews are for informational purposes only and not for diagnostic use, and in both cases, the notified clinicians are responsible for using the local imaging system for viewing the original images and engage the referring clinician for diagnosis and treatment decision.

The predicate and subject devices process CT images using similar techniques and a similar artificial intelligence algorithm. Specifically, the subject and predicate software utilize a deep learning algorithm trained on medical images. The deep-learning process allows for high accuracy in the detection of initial suspect locations. As a system, the BriefCase raises the same types of safety and effectiveness questions as the predicate; namely, accurate detection of

{5}------------------------------------------------

findings within the reviewed and processed study on which a physician can base a clinically useful triage/prioritization assessment considering all available clinical information.

lt is important to note that, like the predicate, the device does not remove cases from a reading queue. Again, both devices operate in parallel with the standard of care, which remains the default option for all cases.

	Aidoc Briefcase Software	Viz.AI ContaCT Software(DEN170073)
Intended Use /Indications forUse	BriefCase is a radiologicalcomputer aided triage andnotification software indicated foruse in the analysis of non-enhanced head CT images.The device is intended toassist hospital networks andtrained radiologists in workflowtriage by flagging andcommunication of suspectedpositive findings of pathologies inhead CT images, namelyIntracranial Hemorrhage (ICH).BriefCase uses an artificialintelligence algorithm to analyzeimages and highlight cases withdetected ICH on a standalonedesktop application in parallel tothe ongoing standard of careimage interpretation. The user ispresented with notifications forcases with suspected ICHfindings. Notificationsinclude compressed previewimages that aremeant for informational purposesonly and not intended fordiagnostic usebeyond notification. The devicedoes not alter the original medicalimage and is not intended to beused as a diagnostic device.The results of BriefCase areintended to be used inconjunction with otherpatient information and based onprofessional judgment, to assistwith triage/prioritization of medicalimages. Notified clinicians areresponsible for viewingfull images per the standard ofcare.	ContaCT is a notification-only,parallel workflow tool for use byhospital networks andtrained clinicians to identify andcommunicate images of specificpatients to a specialist, independentof standard of care workflow.ContaCT uses an artificialintelligence algorithm to analyzeimages for findingssuggestive of a pre-specified clinicalcondition and to notify anappropriate medical specialist ofthese findings in parallel to standardof care image interpretation.Identification of suspected findingsis not for diagnostic use beyondnotification.Specifically, the device analyzes CTangiogram images of the brainacquired in the acute setting, andsends notifications to aneurovascular specialist that asuspected large vessel occlusionhas been identified andrecommends review of thoseimages. Images can be previewedthrough a mobile application.Images that are previewed throughthe mobile application arecompressed and are forinformational purposes only and notintended for diagnostic use beyondnotification.Notified clinicians are responsiblefor viewing non-compressed imageson a diagnostic viewer andengaging in appropriate patientevaluation and relevant discussionwith a treating physician beforemaking care-related decisions orrequests. ContaCT is limited toanalysis of imaging data and should

User population	Radiologist	not be used in-lieu of full patient evaluation or relied upon to make or confirm diagnosis.Clinician (e.g. neurovascular specialist)
Anatomicalregion of interest	Head	Head
Data acquisitionprotocol	Non contrast CT scan of the head or neck	CT angiogram images of the brain
View DICOMdata	DICOM Information about the patient, study and current image	DICOM Information about the patient, study and current image
Segmentation ofregion of interest	No; device does not mark, highlight, or direct users' attention to a specific location in the original image	No; device does not mark, highlight, or direct users' attention to a specific location in the original image
Algorithm	Artificial intelligence algorithm with database of images	Artificial intelligence algorithm with database of images
Notification/Prioritization	Yes	Yes
Preview images	Presentation of a preview of the study for initial assessment not meant for diagnostic purposesThe device operates in parallel with the standard of care, which remains the default option for all cases	Presentation of notification and preview of the study for initial assessment not meant for diagnostic purposesThe device operates in parallel with the standard of care, which remains the default option for all cases
Alteration oforiginal image	No	No
Removal ofcases fromworklist queue	No	No

A table comparing the key features of the subject and predicate devices is provided below.

{6}------------------------------------------------

Performance Data

Aidoc conducted a retrospective, blinded, multicenter, multinational study with the BriefCase software with the primary endpoint to evaluate the software's performance in identifying noncontrast CT head images containing intracranial hemorrhage (ICH) findings in 198 cases from 3 clinical sites (2 US and 1 OUS). There were approximately an equal number of positive and negative cases (images with ICH versus without ICH) included in the analysis.

Sensitivity and specificity exceeded the 80% performance qoal. Specifically, sensitivity was observed to be 93.6% (95% Cl: 86.6%-97.6%) and specificity was observed to be 92.3% (95% Cl: 85.4%-96.6%).

In addition, a secondary endpoint measure was Briefcase's potential clinical benefit of worklist prioritization for true positive ICH cases. For that purpose, in two medical centers, one in Israel and one in the US, Aidoc compared the key standard-of-care metric of time-to-exam-open to the software's time-to-notification metric.

The BriefCase time-to-notification includes the time to get the DICOM exam, de-identify it, upload it to the cloud, analyze and send a notification back to the worklist application. The standard of care time-to-open-exam consisted of the time from the initial scan of the patient to when the radiologist first opened the exam for review.

{7}------------------------------------------------

BriefCase time-to-notification has been documented for all 198 cases. Fifty-nine (59) cases have been identified as true positive (i.e., identified as positive by both the BriefCase and the ground truth) and the time-to-exam-open has been also collected for these cases.

As shown in the table below, analysis demonstrated that standard of care time-to-exam-open (72.6 minutes: 95% Cl 45.0-100.2) is significantly longer than the parallel time-to-notification of the BriefCase software (4.5 minutes: 95% Cl 4.1-4.8). The mean difference of 68.1 minutes (95% Cl 40.5-95.7) for these two metrics is statistically significant and assuming the radiologist receives a notification on a true positive ICH case and acts on it immediately, it can on average save 68.1 (95% Cl 40.5-95.7) minutes compared to the time-to-exam-open in a FIFO reading queue. The value of 68.1 is based on the study of 59 cases, taken from 2 medical centers (1 US, 1 OUS), and may vary in practice.

Parameter	Mean estimate	LowerConfidenceLimit	UpperConfidenceLimit	Median	P-value
Time-to-open-exam inthe standard of care	72.58	45.02	100.14	41.00
Time-to-notification ofBriefCase	4.46	4.10	4.83	3.95
Difference	68.11	40.50	95.72	37.42	<0.0001

In summary, performance validation data, combined with real-world evidence, establish the achievement of effective triage by the BriefCase image analysis algorithm as well as effective notification functionality of the BriefCase application, as compared to the standard of care for improved time-to-exam-open of a notified case.

Conclusions

The subject BriefCase and the ContaCT predicate devices are both intended to aid in prioritization and triage of radiological head medical images for the indications of Intracranial Hemorrhage and large vessel occlusion, respectively. The labeling of both devices clearly states that the devices are not for diagnostic use. Both devices are software packages with similar technological characteristics and principles of operation, incorporating deep learning Al algorithms that process images, and software to send notifications and compressed preview images to pre-designated clinicians that are instructed to further evaluate the original images in the local PACS and engage the referring clinician for diagnosis.

Both devices operate in parallel to the standard of care workflow in the sense that they do not change the original image, do not provide any marking on the output preview, and do not remove images from the standard of care FIFO queue, thus not disturbing standard interpretation of the images by trained clinicians. The minor differences between the subject device and the predicate raise no new issues of safety or effectiveness. In addition, performance testing demonstrates that the BriefCase performs as intended.

The BriefCase device is thus substantially equivalent to the ContaCT predicate.

Regulation Number and Section

§ 892.2080 Radiological computer aided triage and notification software.

(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.