(137 days)
Not Found
Yes
The device description explicitly states that Saige-Q uses an "artificial intelligence algorithm" to process and analyze the mammogram images and generate a code indicative of suspicion.
No
The device is described as a software workflow tool for prioritizing exams and providing passive notification, not for treatment or direct medical intervention.
No
The device is explicitly stated as "not intended to provide any diagnostic information beyond triage and prioritization," and it "does not provide any diagnostic information beyond triage and prioritization," serving as a "software workflow tool designed to aid radiologists in prioritizing exams."
Yes
The device description explicitly states, "As a software-only device, Saige-Q can be hosted on a compatible host server connected to the necessary clinical IT systems..." and the intended use and device description focus solely on the software's function of processing images and generating codes for prioritization. There is no mention of accompanying hardware components included with the device itself.
Based on the provided information, Saige-Q is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs are used to examine specimens derived from the human body. Saige-Q processes medical images (mammograms), which are not biological specimens.
- IVDs are used to provide information for diagnosis, monitoring, or treatment. While Saige-Q aids in prioritizing exams that may contain suspicious findings, its intended use explicitly states it "does not provide any diagnostic information beyond triage and prioritization" and is "not intended to replace the review of images or be used on a stand-alone basis for clinical decision-making."
Saige-Q falls under the category of a medical device, specifically a software workflow tool that uses AI for image analysis and prioritization. It is not designed to analyze biological samples for diagnostic purposes, which is the core function of an IVD.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The 'Control Plan Authorized (PCCP) and relevant text' section explicitly states 'Not Found'.
Intended Use / Indications for Use
Saige-Q is a software workflow tool designed to aid radiologists in prioritizing exams within the standard-of-care image worklist for compatible full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) screening mammograms. Saige-Q uses an artificial intelligence algorithm to generate a code for a given mammogram, indicative of the software's suspicion that the mammogram contains at least one suspicious finding. Saige-Q makes the assigned codes available to a PACS/EPR/RIS/workstation for worklist prioritization or triage.
Saige-Q is intended for passive notification only and does not provide any diagnostic information beyond triage and prioritization. Thus, it is not intended to replace the review of images or be used on a stand-alone basis for clinical decision-making. The decision to use Saige-Q codes and how to use those codes is ultimately up to the interpreting radiologist. The interpreting radiologist is reviewing each exam on a diagnostic viewer and evaluating each patient according to the current standard of care.
Product codes
QFM
Device Description
Saige-Q is a software workflow device that processes Digital Breast Tomosynthesis (DBT) and Full-Field Digital Mammography (FFDM) screening mammograms using artificial intelligence to act as a prioritization tool for interpreting radiologists. By automatically indicating whether a given mammogram is suspicious for malignancy. Saige-Q can help the user prioritize or triage cases in their worklist (or queue) that may benefit from prioritized review.
Saige-Q takes as input a set of x-ray mammogram DICOM files from a single screening mammography study (FFDM or DBT). The software first checks that the study is appropriate for Saige-Q analysis and then extracts, processes and analyses the DICOM images using an artificial intelligence algorithm. As a result of the analysis, the software generates a Saige-Q code indicating the software's suspicion of the presence of findings suggestive of breast cancer. For mammograms given a Saige-Q code of "Suspicious," the software also generates a compressed preview image, which is for informational purposes only and is not intended for diagnostic use.
The Saige-Q code can be viewed by radiologists on a picture archiving and communication system (PACS), Electronic Patient Record (EPR), and/or Radiology Information System (RIS) worklist and can be used to reorder the worklist. As a software-only device, Saige-Q can be hosted on a compatible host server connected to the necessary clinical IT systems such that DICOM studies can be received and the resulting outputs returned where they can be incorporated into the radiology worklist.
The Saige-Q codes can be used for triage or prioritization. For example, "Suspicious" studies could be given prioritized review. With a worklist that supports sorting, batches of mammograms could also be sorted based on the Saige-Q code.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Mentions AI: Saige-Q uses an artificial intelligence algorithm to generate a code for a given mammogram, indicative of the software's suspicion that the mammogram contains at least one suspicious finding.
Mentions AI: Saige-Q is a software workflow device that processes Digital Breast Tomosynthesis (DBT) and Full-Field Digital Mammography (FFDM) screening mammograms using artificial intelligence to act as a prioritization tool for interpreting radiologists.
Mentions AI: The software first checks that the study is appropriate for Saige-Q analysis and then extracts, processes and analyses the DICOM images using an artificial intelligence algorithm.
Mentions AI: The device provides triage or notification that is informed by artificial intelligence algorithms.
Mentions AI: The preprocessed images become the input to the AI algorithm, which generates the Saige-Q code using deep neural networks that have been trained on large numbers of mammograms where cancer status is known.
Mentions DNN: deep neural networks
Input Imaging Modality
full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) screening mammograms
x-ray mammogram DICOM files
FFDM and DBT mammogram studies acquired using Hologic mammography equipment.
Anatomical Site
Breast
Indicated Patient Age Range
Not Found
Intended User / Care Setting
Interpreting radiologists / PACS/EPR/RIS/workstation
Description of the training set, sample size, data source, and annotation protocol
The preprocessed images become the input to the AI algorithm, which generates the Saige-Q code using deep neural networks that have been trained on large numbers of mammograms where cancer status is known.
Sample size, data source, and annotation protocol for training set: Not Found - description of training set is general.
Description of the test set, sample size, data source, and annotation protocol
Data for the FFDM study was collected from eight clinical sites across two states in the United States with 501 malignant exams and 832 normal exams.
Data for the DBT study was collected from six clinical sites across two states in the United States, with 517 malignant exams and 1011 normal exams.
The test dataset excludes screening BI-RADS 0 cases that were determined to be benign after diagnostic workup.
DeepHealth had never collected data from the clinical sites previous to this study either for training or testing.
Malignant exams were confirmed using pathology reports from biopsied lesions and normal cases were confirmed with a negative clinical interpretation (BIRADS 1 or 2) followed by another negative clinical interpretation at least two years later.
Each case was reviewed by two independent expert radiologists (and an adjudicator if discordance was observed) to establish the reference standard for each case.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
DeepHealth conducted two retrospective, blinded, multi-center studies to evaluate the standalone performance of Saige-Q, one study using FFDM and a separate study using DBT mammograms.
Primary objective: to assess the sensitivity and specificity of Saige-Q relative to radiologist performance, as estimated by BCSC.
Secondary objective: to assess the processing time performance when executing Saige-Q software on FFDM and separately on DBT mammograms to ensure processing times are within clinically acceptable ranges.
FFDM Study:
Sample Size: 501 malignant exams and 832 normal exams.
Overall AUC: 0.966 (95% C1: [0.957, 0.975]).
Specificity at 86.9% sensitivity: 92.2% (95% Cl: [90.2%, 93.8%]).
Sensitivity at 88.9% specificity: 91.2% (95%: [88.4%, 93.4%]).
AUC on soft tissue densities: 0.964 (95% Cl: [0.954, 0.974]).
AUC on calcifications: 0.973 (95% Cl: [0.958, 0.988]).
AUC on dense breasts: 0.959 (95% Cl: [0.945, 0.973]).
AUC on non-dense breasts: 0.972 (95% Cl: [0.961, 0.984]).
Median processing time: 15.5 seconds.
DBT Study:
Sample Size: 517 malignant exams and 1011 normal exams.
Overall AUC: 0.985 (95% Cl: [0.979, 0.990]).
Specificity at 86.9% sensitivity: 98.3% (95% Cl: [97.3%, 99.0%]).
Sensitivity at 89.9% specificity: 95.7% (95% CI: [93.6%, 97.2%]).
AUC on soft tissue densities: 0.983 (95% Cl: [0.977, 0.990]).
AUC on calcifications: 0.989 (95% Cl: [0.983, 0.996]).
AUC on dense breasts: 0.980 (95% Cl: [0.971, 0.988]).
AUC on non-dense breasts: 0.988 (95% Cl: [0.981, 0.996]).
Median processing time: 196.8 seconds.
Key Results:
Performance meets or exceeds the predicate device and exceeds the requirement specified for the QFM product code for effective triage with an AUC >0.95.
The primary endpoint for FFDM and DBT studies was successfully met with Saige-Q demonstrating sensitivity and specificity above the 80% CI reported in BCSC data.
Sub-analysis showed similar performance across subcategories (lesion type, breast density, age, lesion size).
Processing times are within clinical expectations for screening mammograms.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Sensitivity, Specificity, AUC
Predicate Device(s)
CureMetrix, Inc., cmTriage, K183285
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 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.
0
April 16, 2021
Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
DeepHealth, Inc. A. Gregory Sorensen, M.D. President and CEO 1000 Massachusetts Ave CAMBRIDGE MA 02138
Re: K203517
Trade/Device Name: Saige-O Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological Computer aided triage and notification software Regulatory Class: Class II Product Code: QFM Dated: March 19, 2021 Received: March 19, 2021
Dear Dr. Sorensen:
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. 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 located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmp/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.
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 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see
1
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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
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 https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-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,
For
Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K203517
Device Name Saige-Q
Indications for Use (Describe)
Saige-Q is a software workflow tool designed to aid radiologists in prioritizing exams within the standard-of-care image worklist for compatible full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) screening mammograms. Saige-Q uses an artificial intelligence algorithm to generate a code for a given mammogram, indicative of the software's suspicion that the mammogram contains at least one suspicious finding. Saige-Q makes the assigned codes available to a PACS/EPR/RIS/workstation for worklist prioritization or triage.
Saige-Q is intended for passive notification only and does not provide any diagnostic information beyond triage and prioritization. Thus, it is not intended to replace the review of images or be used on a stand-alone basis for clinical decision-making. The decision to use Saige-Q codes and how to use those codes is ultimately up to the interpreting radiologist. The interpreting radiologist is reviewing each exam on a diagnostic viewer and evaluating each patient according to the current standard of care.
| Type of Use (Select one or both, as applicable) |
|---|
| ☒ 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
510(k) SUMMARY
DeepHealth's Saige-Q
501(k) Submission Number K203517
Submitter:
DeepHealth, Inc. 1000 Massachusetts Avenue Cambridge, MA 02138 Phone: 617-970-3817 Email: sorensen@deep.health
Contact Person: A. Gregory Sorensen Date Prepared: November 30, 2020
Name of Device: Saige-Q™ Common or Usual Name: Medical Imaging Software Classification Name: Radiological Computer-Assisted Triage and Notification Software Regulatory Class: Class II (21 CFR 892.2080) Product Code: QFM
Predicate Devices CureMetrix, Inc., cmTriage, K183285
Device Description
Saige-Q is a software workflow device that processes Digital Breast Tomosynthesis (DBT) and Full-Field Digital Mammography (FFDM) screening mammograms using artificial intelligence to act as a prioritization tool for interpreting radiologists. By automatically indicating whether a given mammogram is suspicious for malignancy. Saige-Q can help the user prioritize or triage cases in their worklist (or queue) that may benefit from prioritized review.
Saige-Q takes as input a set of x-ray mammogram DICOM files from a single screening mammography study (FFDM or DBT). The software first checks that the study is appropriate for Saige-Q analysis and then extracts, processes and analyses the DICOM images using an artificial intelligence alqorithm. As a result of the analysis, the software generates a Saige-Q code indicating the software's suspicion of the presence of findings suggestive of breast cancer. For mammograms given a Saige-Q code of "Suspicious," the software also generates a compressed preview image, which is for informational purposes only and is not intended for diagnostic use.
The Saige-Q code can be viewed by radiologists on a picture archiving and communication system (PACS), Electronic Patient Record (EPR), and/or Radiology Information System (RIS) worklist and can be used to reorder the worklist. As a software-only device, Saige-Q can be hosted on a compatible host server connected to the necessary clinical IT systems such that DICOM studies can be received and the resulting outputs returned where they can be incorporated into the radiology worklist.
The Saige-Q codes can be used for triage or prioritization. For example, "Suspicious" studies could be given prioritized review. With a worklist that supports sorting, batches of mammograms could also be sorted based on the Saige-Q code.
4
Intended Use / Indications for Use
Saige-Q is a software workflow tool designed to aid radiologists in prioritizing exams within the standard-of-care image worklist for compatible full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) screening mammograms. Saige-Q uses an artificial intelligence algorithm to generate a code for a qiven mammogram, indicative of the software's suspicion that the mammogram contains at least one suspicious finding. Saige-Q makes the assigned codes available to a PACS/EPR/RIS/workstation for worklist prioritization or triage.
Saige-Q is intended for passive notification only and does not provide any diagnostic information beyond triage and prioritization. Thus, it is not intended to replace the review of images or be used on a stand-alone basis for clinical decision-making. The decision to use Saige-Q codes and how to use those codes is ultimately up to the interpreting radiologist. The interpreting radiologist is responsible for reviewing each exam on a diagnostic viewer and evaluating each patient according to the current standard of care.
Summary of Technological Characteristics
Saige-Q is a software only device that consists of several core components that perform the following functions: 1) receive mammogram study data as DICOM files, 2) preprocess the DICOM files and check that the study is appropriate for analysis, 3) analyze the study images using an artificial intelligence algorithm, 4) generate outputs based on the analysis and 5) send the outputs to the appropriate clinical IT system for viewing on a radiology worklist.
The receiving and sending components are configured at the time of installation in conjunction with clinical IT staff. The software should be installed on a compatible host machine that is connected to the appropriate clinical IT systems (e.g., RIS, PACS and/or EPR) that enable the device to receive DICOM studies and return Saige-Q outputs.
The preprocessing component of the device performs two functions. The first function is to check that the study is appropriate for analysis. For example, if the study is not a mammogram, Saige-Q will not proceed with analysis. Saige-Q is compatible with FFDM and DBT mammogram studies acquired using Hologic mammography equipment. The second function is to preprocess the images to be analyzed. The preprocessed images become the input to the AI algorithm, which generates the Saige-Q code using deep neural networks that have been trained on large numbers of mammograms where cancer status is known.
The technical components described above are also found in the predicate device, though the exact implementation may vary. One difference relative to the predicate device is Saige-Q's ability to process DBT mammograms, which requires an additional Al model. A comprehensive comparison with the predicate device is provided in the following table:
| Subject device | Predicate device | Summary | Software | ||||
|---|---|---|---|---|---|---|---|
| Saige-Q | |||||||
| DeepHealth Inc. | cmTriage | ||||||
| CureMetrix. | |||||||
| K183285 | Product code | QFM | QFM | Same | |||
| Regulation | |||||||
| number | 21 CFR 892.2080 - | ||||||
| Radiological Computer- | |||||||
| Assisted Prioritization | 21 CFR 892.2080 - | ||||||
| Radiological Computer- | |||||||
| Assisted Prioritization Software | Same | Class | II | II | Same | ||
| Intended use | Saige-Q is a software | ||||||
| workflow tool designed to aid | |||||||
| radiologists in prioritizing | |||||||
| exams within the standard-of- | |||||||
| care image worklist for full- | |||||||
| field digital mammography | |||||||
| (FFDM) and digital breast | |||||||
| tomosynthesis (DBT) | |||||||
| screening mammograms. | |||||||
| Saige-Q uses an artificial | |||||||
| intelligence algorithm to | |||||||
| generate a code for a given | |||||||
| mammogram, indicative of | |||||||
| the software's suspicion that | |||||||
| the mammogram contains at | |||||||
| least one suspicious finding. | |||||||
| Saige-Q makes the assigned | |||||||
| codes available to a | |||||||
| PACS/EPR/RIS/workstation | |||||||
| for worklist prioritization or | |||||||
| triage. | |||||||
| Saige-Q is intended for | |||||||
| passive notification only and | |||||||
| does not provide any | |||||||
| diagnostic information | |||||||
| beyond triage and | |||||||
| prioritization. Thus, it is not | |||||||
| intended to replace the review | |||||||
| of images or be used on a | |||||||
| stand-alone basis for clinical | |||||||
| decision-making. The | |||||||
| decision to use Saige-Q codes | |||||||
| and how to use those codes is | |||||||
| ultimately up to the | |||||||
| interpreting radiologist. The | |||||||
| interpreting radiologist is | |||||||
| responsible for reviewing | |||||||
| each exam on a diagnostic | |||||||
| viewer and evaluating each | |||||||
| patient according to the | |||||||
| current standard of care. | cmTriage is a passive | ||||||
| prioritization-only, parallel- | |||||||
| workflow software tool used by | |||||||
| radiologists to prioritize specific | |||||||
| patients within the standard-of- | |||||||
| care image worklist for 2D | |||||||
| FFDM screening mammograms. | |||||||
| cmTriage uses an artificial | |||||||
| intelligence algorithm to | |||||||
| analyze 2D FFDM screening | |||||||
| mammograms and flags those | |||||||
| that are suggestive of the | |||||||
| presence of at least one | |||||||
| suspicious finding at the exam | |||||||
| level. These flags are viewed by | |||||||
| the radiologist via their PACS | |||||||
| worklist. The decision to use | |||||||
| cmTriage codes and how to use | |||||||
| cmTriage codes is ultimately up | |||||||
| to the radiologist. cmTriage | |||||||
| does not send a proactive alert | |||||||
| directly to the radiologist. | |||||||
| Radiologists are responsible for | |||||||
| reviewing each exam on a | |||||||
| diagnostic viewer according to | |||||||
| the current standard of care. | |||||||
| cmTriage is limited to the | |||||||
| categorization of exams, does | |||||||
| not provide any diagnostic | |||||||
| information beyond triage and | |||||||
| prioritization, does not remove | |||||||
| images from the radiologist's | |||||||
| worklist, and should not be used | |||||||
| in lieu of full patient evaluation, | |||||||
| or relied upon to make or | |||||||
| confirm diagnosis. | |||||||
| cmTriage is for prescription use | |||||||
| only. | Both devices have the | ||||||
| same intended use | |||||||
| per 21 CFR 892.2080 | |||||||
| Technical | |||||||
| Method | The device provides triage or | ||||||
| notification that is informed | |||||||
| by artificial intelligence | |||||||
| algorithms. | The device provides triage or | ||||||
| notification that is informed by | |||||||
| artificial intelligence | |||||||
| algorithms. | Same |
5
6
| Anatomical Site | Breast | Breast | Same |
|---|---|---|---|
| Clinical | |||
| condition | Breast cancer | Breast cancer | Same |
| Notification- | |||
| only, parallel | |||
| workflow tool | Yes | Yes | Same |
| Alert to finding | Passive notification flagged | ||
| for review | Passive notification flagged for | ||
| review | Same | ||
| Preview Image | Preview of the | ||
| study for initial assessment, | |||
| not meant for diagnostic | |||
| purposes. | |||
| The device operates in | |||
| parallel with the standard of | |||
| care, which remains the | |||
| default option for all cases. | Preview of the study for initial | ||
| assessment, not meant for | |||
| diagnostic purposes. | |||
| The device operates in parallel | |||
| with the standard of care, which | |||
| remains the default option for | |||
| all cases. | Same | ||
| Multiple | |||
| operating | |||
| points | Yes; 3 operating points | Yes; a continuous range of | |
| operating points. | Similar but Saige-Q | ||
| uses a more | |||
| conservative | |||
| approach by pre- | |||
| specifying a discrete | |||
| number of operating | |||
| points. | |||
| Independent of | |||
| standard of care | |||
| workflow | Yes; no cases are removed | ||
| from worklist | Yes; no cases are removed from | ||
| worklist | Same | ||
| End users | Radiologists | Radiologists | Same |
| Type of | |||
| mammograms | FFDM and DBT screening | ||
| mammograms. | FFDM screening mammograms. | Both devices operate | |
| on screening | |||
| mammograms (x-ray | |||
| images), but | |||
| cmTriage is intended | |||
| for FFDM cases only | |||
| whereas Saige-Q is | |||
| intended for both | |||
| FFDM and DBT | |||
| cases. | |||
| Deployment | On-premise | On-premise with cloud | |
| processing | Different, but does | ||
| not raise any new | |||
| questions regarding | |||
| safety and | |||
| effectiveness. | |||
| Output device | The end user interacts with | The end user interacts with the | There is no |
| the output of the device in the | |||
| facility's PACS/EPR/RIS | |||
| software (worklist). | output of the device in the | ||
| facility's PACS software | |||
| (worklist). | significant difference. | ||
| Software levels | |||
| of concern | Moderate | Moderate | Same |
7
Performance Data
DeepHealth conducted two retrospective, blinded, multi-center studies to evaluate the standalone performance of Saige-Q, one study using FFDM and a separate study using DBT mammograms. The primary objective was the same for each study: to assess the sensitivity and specificity of Saige-Q relative to radiologist performance, as estimated by BCSC. The secondary objective was to assess the processing time performance when executing Saige-Q software on FFDM and separately on DBT mammograms to ensure processing times are within clinically acceptable ranges.
Data for the FFDM study was collected from eight clinical sites across two states in the United States with 501 malignant exams and 832 normal exams. Data for the DBT study was collected from six clinical sites across two states in the United States, with 517 malignant exams and 1011 normal exams. The test dataset excludes screening BI-RADS 0 cases that were determined to be benign after diagnostic workup. DeepHealth had never collected data from the clinical sites previous to this study either for training or testing. Malignant exams were confirmed using pathology reports from biopsied lesions and normal cases were confirmed with a negative clinical interpretation (BIRADS 1 or 2) followed by another negative clinical interpretation at least two years later. Each case was reviewed by two independent expert radiologists (and an adjudicator if discordance was observed) to establish the reference standard for each case.
In the FFDM study, Saige-Q achieved an overall area under the receiver operating characteristic curve (AUC) of 0.966 (95% C1: [0.957, 0.975]). In the DBT study, Saige-Q achieved an overall AUC of 0.985 (95% Cl: [0.979, 0.990]) on the DBT data. This performance meets or exceeds the performance of the predicate device and exceeds the requirement specified for the QFM product code for effective triage with an AUC >0.95.
The primary endpoints of the studies consisted of sensitivity and specificity targets to validate that Saige-Q operates with a 95% CI for both sensitivity and specificity above the 80% CI reported in BCSC data.
The primary endpoint for FFDM was successfully met with Saige-Q demonstrating a specificity at 86.9% sensitivity of 92.2% (95% Cl: 190.2%, 93.8%)) and a sensitivity at 88.9% specificity of 91.2% (95%: [88.4%, 93.4%]).
The primary endpoint for DBT was also successfully met with Saige-Q demonstrating a specificity at 86.9% sensitivity: 98.3% (95% Cl: [97.3%, 99.0%]) and a sensitivity at 89.9% specificity of 95.7% (95% CI: [93.6%, 97.2%]).
A sub-analysis of performance by lesion type (soft tissue densities vs. calcifications), breast density (dense vs. non-dense), age, and lesion size showed similar performance across subcategories. For instance, on FFDM, Saige-Q achieved an AUC of 0.964 (95% Cl: [0.954,
8
0.974)) on soft tissue densities and an AUC of 0.973 (95% Cl: [0.958, 0.988]) on calcifications. For DBT, Saige-Q achieved an AUC of 0.983 (95% Cl: [0.977, 0.990]) on soft tissue densities and an AUC of 0.989 (95% Cl: [0.983, 0.996]) on calcifications. For breast density, Saige-Q achieved an AUC of 0.959 (95% Cl: [0.945, 0.973]) on dense breasts and an AUC of 0.972 (95% Cl: [0.961, 0.984]) on non-dense breasts for FFDM exams. For DBT, Saige-Q achieved an AUC of 0.980 (95% Cl: [0.971, 0.988]) on dense breasts and an AUC of 0.988 (95% Cl: [0.981, 0.996]) on non-dense breasts.
The secondary endpoints required the processing time for each FFDM and DBT mammogram to be within clinical operational expectations of breast cancer screening. The median processing time for FFDM was 15.5 seconds and was 196.8 seconds for DBT. These processing times are within the clinical expectations for screening mammograms.
Based on the clinical performance as documented in the pivotal clinical study, Saige-Q has a safety and effectiveness profile that is similar to the predicate device.
Conclusions
Saige-Q is as safe and effective as cmTriage. Saige-Q has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. The minor differences in indications do not alter the intended use of the device and do not affect its safety and effectiveness when used as labeled. In addition, the minor technological differences between Saige-Q and its predicate device raise no new issues of safety or effectiveness. Performance data demonstrate that Saige-Q is as safe and effective as cmTriage. Thus, Saige-Q is substantially equivalent to the legally marketed predicate device.