Genius AI Detection 2.0

K221449 · Hologic, Inc. · QDQ · Oct 6, 2022 · Radiology

Device Facts

• Record ID: K221449
• Device Name: Genius AI Detection 2.0
• Applicant: Hologic, Inc.
• Product Code: QDQ · Radiology
• Decision Date: Oct 6, 2022
• Decision: SESE
• Submission Type: Traditional
• Regulation: 21 CFR 892.2090
• Device Class: Class 2
• Attributes: AI/ML, Software as a Medical Device

Intended Use

Genius AI Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.

Device Story

Software-only CADe/CADx device; analyzes digital breast tomosynthesis (DBT) slices from Hologic systems. Uses deep learning networks to identify/mark soft tissue densities and calcifications; provides confidence scores and case scores. Operates in concurrent reading workflow; findings displayed on DICOM-compliant workstations. Physician confirms/dismisses marks during exam interpretation. Enhances workflow via worklist organization. Benefits include improved detection specificity and reduced false positives compared to predicate. No physical hardware; standalone software deployment.

Clinical Evidence

Bench-only validation using a sequestered dataset of 764 DBT exams (106 biopsy-proven cancers, 97 benign, 81 recalls, 480 screening negative). Average patient age 58. Ground truth established by radiology/pathology reports and verified by board-certified radiologists. Performance compared to predicate via fROC analysis. Results showed 12% increase in specificity (p<0.001) while maintaining sensitivity.

Technological Characteristics

Software-only device; deep learning-based image processing. Compatible with Hologic Selenia Dimensions and 3Dimensions systems. Processes 1mm standard/high-resolution DBT slices and 6mm SmartSlices. Operates on processed 3D reconstructed volumes. Software lifecycle per IEC 62304; risk management per ISO 14971.

Indications for Use

Indicated for symptomatic and asymptomatic women undergoing mammography to aid in the detection, localization, and characterization of soft tissue densities (masses, architectural distortions, asymmetries) and calcifications in digital breast tomosynthesis (DBT) exams.

Regulatory Classification

Identification

A radiological computer-assisted detection and diagnostic software is an image processing device intended to aid in the detection, localization, and characterization of fracture, lesions, or other disease-specific findings on acquired medical images (e.g., radiography, magnetic resonance, computed tomography). The device detects, identifies, and characterizes findings based on features or information extracted from images, and provides information about the presence, location, and characteristics of the findings to the user. The analysis is intended to inform the primary diagnostic and patient management decisions that are made by the clinical user. The device is not intended as a replacement for a complete clinician's review or their clinical judgment that takes into account other relevant information from the image or patient history.

Special Controls

A radiological computer assisted detection and diagnosis software must comply with the following special controls: Design verification and validation must include: 1. i. A detailed description of the image analysis algorithm, including but not limited to a description of the algorithm inputs and outputs, each major component or block, how the algorithm and output 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 improved assisted-read detection and diagnostic performance as intended in the indicated user population(s), and to characterize the standalone device performance for labeling. Performance testing includes standalone test(s), side-by-side comparison(s), and/or a reader study, as applicable. iii. Results from standalone performance testing used to characterize the independent performance of the device separate from aided user performance. The performance assessment must be based on appropriate diagnostic accuracy measures (e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Devices with localization output must include localization accuracy testing as a component of standalone testing. The test dataset must be representative of the typical patient population with enrichment made only to ensure that the test dataset contain a sufficient number of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant disease, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment. iv. Results from performance testing that demonstrate that the device provides improved assisted-read detection and/or diagnostic performance as intended in the indicated user population(s) when used in accordance with the instructions for use. The reader population must be comprised of the intended user population in terms of but not limited to clinical training, certification, and years of experience. The performance assessment must be based on appropriate diagnostic accuracy measures (e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Test datasets must meet the requirements described in 1(iii) above. v. Appropriate software documentation, including device hazard analysis, software requirements specification document, software design specification document, traceability analysis, system level test protocol, pass/fail criteria, testing results, and cybersecurity measures. 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 device instructions for use, including the intended reading protocol and how the user should interpret the device output. iii. A detailed description of the intended user, and any user training materials as programs that addresses appropriate reading protocols for the device to ensure that the end user is fully aware of how to interpret and apply the device output. iv. A detailed description of the device inputs and outputs. v. A detailed description of compatible imaging hardware and imaging protocols. vi. 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 or for certain subpopulations), as applicable. vii. A detailed summary of the performance testing, including: test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders, such as anatomical characteristics, patient demographics and medical history, user experience, and imaging equipment.

*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 image analysis algorithm, including a description of the algorithm inputs and outputs, each major component or block, how the algorithm and output 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 improved assisted-read detection and diagnostic performance as intended in the indicated user population(s), and to characterize the standalone device performance for labeling. Performance testing includes standalone test(s), side-by-side comparison(s), and/or a reader study, as applicable. (iii) Results from standalone performance testing used to characterize the independent performance of the device separate from aided user performance. The performance assessment must be based on appropriate diagnostic accuracy measures ( *e.g.,* receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Devices with localization output must include localization accuracy testing as a component of standalone testing. The test dataset must be representative of the typical patient population with enrichment made only to ensure that the test dataset contains a sufficient number of cases from important cohorts (*e.g.,* subsets defined by clinically relevant confounders, effect modifiers, concomitant disease, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment.(iv) Results from performance testing that demonstrate that the device provides improved assisted-read detection and/or diagnostic performance as intended in the indicated user population(s) when used in accordance with the instructions for use. The reader population must be comprised of the intended user population in terms of clinical training, certification, and years of experience. The performance assessment must be based on appropriate diagnostic accuracy measures ( *e.g.,* receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Test datasets must meet the requirements described in paragraph (b)(1)(iii) of this section.(v) Appropriate software documentation, including device hazard analysis, software requirements specification document, software design specification document, traceability analysis, system level test protocol, pass/fail criteria, testing results, and cybersecurity measures. (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 device instructions for use, including the intended reading protocol and how the user should interpret the device output. (iii) A detailed description of the intended user, and any user training materials or programs that address appropriate reading protocols for the device, to ensure that the end user is fully aware of how to interpret and apply the device output. (iv) A detailed description of the device inputs and outputs. (v) A detailed description of compatible imaging hardware and imaging protocols. (vi) 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 or for certain subpopulations), as applicable.(vii) A detailed summary of the performance testing, including test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders, such as anatomical characteristics, patient demographics and medical history, user experience, and imaging equipment.

Predicate Devices

• Genius AI Detection (K201019)

Submission Summary (Full Text)

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

October 6, 2022

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left, there is a symbol of the Department of Health & Human Services. To the right of the symbol, there is the FDA logo in blue, with the words "U.S. FOOD & DRUG" stacked on top of the word "ADMINISTRATION". The logo is simple and professional, and it is easily recognizable.

Hologic, Inc. % Deborah Thomas Senior Principal Regulatory Affairs 250 Campus Drive MARLBOROUGH MA 01730

Re: K221449

Trade/Device Name: Genius AI Detection 2.0 Regulation Number: 21 CFR 892.2090 Regulation Name: Radiological computer assisted detection and diagnosis software Regulatory Class: Class II Product Code: QDQ Dated: August 24, 2022 Received: August 25, 2022

Dear Deborah Thomas:

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/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.

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) 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 ([e-mail]) or phone [phone] or 301-796-7100).

Sincerely,

Yanna Kang, Ph.D.

Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices 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) K221449

Device Name Genius AI Detection 2.0

#### Indications for Use (Describe)

Genius AI Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.

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

| <span></span> <svg height="15" width="15"> <rect height="15" style="fill:lightgrey;stroke-width:1;stroke:rgb(0,0,0)" width="15"></rect> <line style="stroke:rgb(0,0,0);stroke-width:2" x1="2" x2="13" y1="2" y2="13"></line> <line style="stroke:rgb(0,0,0);stroke-width:2" x1="13" x2="2" y1="2" y2="13"></line> </svg> Prescription Use (Part 21 CFR 801 Subpart D) |
|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <span></span> <svg height="15" width="15"> <rect height="15" style="fill:lightgrey;stroke-width:1;stroke:rgb(0,0,0)" width="15"></rect> </svg> 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}------------------------------------------------

# Traditional 510(k) Summary

This 510(k) Summary is submitted in accordance with the requirements of 21 CFR Part 807.92

| Date Prepared: | October 06, 2022 |
|-------------------------------|--------------------------------------------------------------------------|
| Manufacturer: | Hologic, Inc.<br>36 Apple Ridge Road<br>Danbury, CT 06810 USA |
| Establishment Registration #: | 1220984 |
| Contact Person: | Deborah Thomas<br>Senior Principal Regulatory Affairs<br>P: 508.210.6107 |

| Identification of the Device: | |
|-------------------------------|--------------------------------------------------------------------------------------------------|
| Proprietary/Trade Name: | Genius Al Detection 2.0 |
| Classification Name: | Radiological Computer Assisted Detection/Diagnosis<br>Software for Lesions Suspicious For Cancer |
| Regulatory Number: | 21 CFR 892.2090 |
| Product Code: | QDQ |
| Device Class: | Class II |
| Review Panel: | Radiology |

| Identification of the Legally Marketed Predicate Device: | |
|----------------------------------------------------------|------------------------------------------------------------------------------|
| Trade Name: | Genius Al Detection |
| Classification Name: | Radiological Computer Assisted<br>Software for Lesions Suspicious For Cancer |
| Regulatory Number: | 21 CFR 892.2090 |
| Product Code: | QDQ |
| Device Class: | Class II |
| Review Panel: | Radiology |
| Submitter/510(k) Holder: | Hologic, Inc. |
| Clearance: | K201019 (cleared November 18, 2020) |

## Device Description:

Genius Al Detection is a software device intended to identify potential abnormalities in breast tomosynthesis images. Genius Al Detection analyzes each standard mammographic view in a digital breast tomosynthesis examination using deep learning networks. For each detected lesion, Genius Al

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

Detection produces CAD results that include the location of the lesion, an outline of the lesion and a confidence score for that lesion. Genius Al Detection also produces a case score for the entire tomosynthesis exam.

Genius AI Detection packages all CAD findings derived from the corresponding analysis of a tomosynthesis exam into a DICOM Mammography CAD SR object and distributes it for display on DICOM compliant review workstations. The interpreting physician will have access to the CAD findings concurrently to the reading of the tomosynthesis exam. In addition, a combination of peripheral information such as number of marks and case scores may be used on the review workstation to enhance the interpreting physician's workflow by offering a better organization of the patient worklist.

## Indications for Use:

Genius Al Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.

## Standards:

- IEC 62304: 2015 Medical device software Software Life Cycle Processes (#13-79) .
- ISO 14971: 2012 – Medical devices – Application of Risk Management to Medical Devices
- DEN180005 Evaluation of automatic class III designation for OsteoDetect Decision ● summary with special controls.

## FDA Guidance Documents:

- Guidance for Industry and FDA Staff Guidance for the Content of Premarket Submissions for ● Software Contained in Medical Devices (Issued on May 11, 2005)
- Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data -Premarket Notification [510(k)] Submissions (Issued on July 3, 2012)
- . Guidance for Industry and FDA Staff - Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data -Premarket Approval (PMA) and Premarket Notification [510(k)] Submissions (Issued on January 22, 2020)
- "Off-the-Shelf Software Use in Medical Devices," issued on September 9, 1999
- "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" issued on October 2, 2014.

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

## Summary of Substantial Equivalence:

| Features and<br>Characteristics | Subject Device<br>Hologic, Inc.<br>Genius Al Detection 2.0 | Predicate Device<br>Hologic, Inc.<br>Genius Al Detection | Difference and<br>comments |
|---------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------|----------------------------|
| 510(k) Number | Pending | K201019 | |
| Regulation<br>Number/Name | 21 CFR 892.2090 /<br>Radiological Computer Assisted Detection<br>and Diagnosis Software | Same | N/A |
| Product Code | QDQ | Same | N/A |
| Regulation<br>Description | A radiological computer assisted<br>detection and diagnostic software is an<br>image processing device intended to aid<br>in the detection, localization, and<br>characterization of fracture, lesions, or<br>other disease specific findings on<br>acquired medical images (e.g.<br>radiography, MR, CT). The device<br>detects, identifies and characterizes<br>findings based on features or<br>information extracted from images, and<br>provides information about the<br>presence, location, and characteristics<br>of the findings to the user. The analysis<br>is intended to inform the primary<br>diagnostic and patient management<br>decisions that are made by the clinical<br>user. The device is not intended as a<br>replacement for a complete clinician's<br>review or their clinical judgment that<br>takes into account other relevant<br>information from the image or patient<br>history. | Same | N/A |
| Indications<br>for Use | Genius Al Detection is a computer-aided<br>detection and diagnosis (CADe/CADX)<br>software device intended to be used<br>with compatible digital breast<br>tomosynthesis (DBT) systems to identify<br>and mark regions of interest including<br>soft tissue densities (masses,<br>architectural distortions and<br>asymmetries) and calcifications in DBT<br>exams from compatible DBT systems<br>and provide confidence scores that<br>offer assessment for Certainty of<br>Findings and a Case Score.<br><br>The device intends to aid in the<br>interpretation of digital breast<br>tomosynthesis exams in a concurrent<br>fashion, where the interpreting<br>physician confirms or dismisses the | Same | N/A |
| findings during the reading of the<br>exam. | | | |
| Compatible<br>DBT<br>Systems | Hologic Selenia Dimensions<br>Hologic 3Dimensions<br>Supports both models in the following | Same | N/A |
| Type of CAD<br>Software | Radiological computer assisted<br>detection and diagnostic software. | Same | N/A |
| Mode of Action | Image processing device utilizing<br>machine learning to aid in the<br>detection, localization, and<br>characterization of soft tissue densities<br>(masses, architectural distortions and<br>asymmetries) and calcifications in the<br>1-mm 3D DBT slices. Findings are co-<br>registered to 6-mm SmartSlices. | Same | N/A |
| Clinical<br>Output | To inform the primary diagnostic and<br>patient management decisions that<br>are made by the clinical user. | Same | N/A |
| Patient<br>Population | Symptomatic and asymptomatic<br>women undergoing<br>mammography | Same | N/A |
| End Users | MQSA-Qualified Interpreting Physicians<br>and Radiologists | Same | N/A |
| Image Source<br>Modalities | Digital breast tomosynthesis slices | Same | N/A |
| <b>Output Device</b> | Softcopy Workstation | Same | N/A |
| <b>Deployment</b> | Stand-alone computer | Same | N/A |
| <b>Method Of Use</b> | Concurrent read | Same | N/A |
| <b>Visualization Features</b> | Places mark within suspicious lesion by default (Emphasize™; RightOn™) and reports confidence of finding next to each identified lesion in the image. CAD display may be toggled on/off. Option to automatically zoom into or contour the suspicious region of interest (PeerView™). | Same | N/A |

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

## Hologic, Inc. 510(k) Pre-Market Notification Genius Al Detection 2.0

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

## Comparison with Predicate Device:

The Summary of Substantial Equivalence Table above details the similarities and differences between the Genius Al Detection 2.0 device and its predicate device, Genius Al Detection, K201019. Both the proposed and predicate devices use the same technology per 21 CFR 892.2090. Both devices aid in the detection, localization, and characterization of disease specific findings on acquired medical images. The outputs of both devices serve to augment the interpretation of digital breast tomosynthesis exams as a concurrent reading tool. The output is used to inform and assist the interpreting physician, supplementing their clinical expertise and judgment.

Genius AI Detection 2.0 is the follow-up release to the initial launch of the product and provides better performance both in terms of improved specificity and fewer false positives. Algorithm enhancements as well as the expanded training data set were used during development of the 2.0 version. These changes do not raise any issues of safety and effectiveness.

Genius AI Detection 2.0 is compatible with the same imaging systems as the predicate device.

## Compatible DBT Systems

The following image types have been tested and are compatible with Genius Al Detection 2.0:

- Hologic standard resolution tomosynthesis slices (1 mm)
- Hologic high resolution tomosynthesis slices (1 mm, Clarity HD)
- Hologic high resolution SmartSlices (6 mm, 3DQuorum)

The CAD marks generated by Genius Al Detection 2.0 for the above image types can also be projected on their corresponding synthesized 2D images, providing that the diagnostic review workstation supports such a feature similar to the predicate device.

{8}------------------------------------------------

## Summary of Updates of Genius Al Detection 2.0

Genius Al Detection 2.0 has two changes compared to the previously released product aiming to improve performance, mainly in term of improved specificity, particularly for micro-calcification cancer detection.

The first change is an enlarged cancer data set used to train the deep learning Al models. The cancer database for training and evaluation is enlarged by two-fold. Subsequently, all deep learning Al models have been retrained on the enlarged dataset.

The second change in Genius AI Detection 2.0 is the adoption of a more sophisticated Convolutional Neural Network (CNN) model for the key processing step of calcification cluster classification, replacing the previously used, simpler conventional Artificial Neural Network (ANN) model. The significantly expanded dataset made it possible to train this newly introduced more complex neural network model, and to deliver significantly better performance especially for micro-calcification cancer detection.

In addition, Genius Al Detection 2.0 can now operate directly on processed tomosynthesis reconstructed slices, instead of first having to process the raw projections to a for presentation 3D reconstructed volume as it was the case for the previously approved product. This simplifies processing flow and eliminates the dependency on tomosynthesis raw projection data.

## Standalone Performance Testing:

Genius Al Detection 2.0 is a software-only device. The level of concern for the device is determined as Moderate Level of Concern.

Verification testing consisted of software unit testing, software integration testing and software system testing. The verification testing showed that the software application satisfied the software requirements.

Validation testing consisted of determining stand-alone performance of Genius Al Detection 2.0 using a sequestered dataset of digital breast tomosynthesis exams acquired from multiple centers. This dataset was not used for training of Genius Al Detection 2.0 and included tomosynthesis exams of asymptomatic women acquired with Hologic Dimensions 3D Mammography systems.

The sequestered dataset consisted of 764 tomosynthesis exams including 106 biopsy proven cancers, 97 biopsy proven benign cases, 81 recalls and 480 screening negative cases all collected using Hologic's Dimensions 3D Mammography systems. The average patient age was 58 years and collected from multiple sites across the United States. The location for ground truth was determined by a radiology expert using radiology reports, pathology reports, and diagnostic and post-biopsy images when available. The truth was verified by another MQSA-qualified, board-certified radiologist to ensure accuracy and consistency.

To evaluate the performance of Genius Al Detection 2.0 in comparison to its predicate device, a standalone study was conducted on the sequestered dataset described above. Comparison of performance between Genius Al Detection 2.0 and its predicate device was conducted using fROC analysis and by comparing key performance metrics including detection sensitivity, and rate of false positive marks per view. The fROC curves demonstrated significant improvement for Genius Al Detection 2.0 over its predicate device, Genius Al Detection (K201019). The specificity measured at the operating point of Genius Al Detection 2.0 demonstrated significant increase of 12% as compared to

{9}------------------------------------------------

the original Genius Al Detection predicate device (McNemar's p< 0.001), while maintaining the sensitivity.

Based on results of the verification and validation tests, it is concluded that the Genius Al Detection 2.0 device is safe and effective in detecting soft tissue lesions and calcification lesions at an appropriate safety level in tomosynthesis exams acquired with Hologic's 3D Mammography systems.

## Assessment of Benefit-Risk, Safety and Effectiveness, and Substantial Equivalence:

Risk management is ensured through risk analysis which is used to identify and mitigate potential hazards. Any potential hazards are controlled via software development, verification, and validation testing. In addition, device labeling contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of this device. Hologic finds that the proposed device has a positive balance in terms of probable benefits vs probable risks and thus may be considered safe and effective based verification and validation testing.

## Conclusion:

Based on the required information submitted in this premarket notification, the proposed Genius Al Detection 2.0 device has been found to be substantially equivalent to the predicate Genius AI Detection, K201019. Both devices have the same indications for use and aid in the detection, localization, and characterization of disease specific findings on acquired medical images. Standalone performance tests with the updated algorithm demonstrate that Genius Al Detection 2.0 achieves better detection performance compared to the predicate device. The are no issues of safety and effectiveness of the proposed Genius Al Detection 2.0 device.