Sonio Suspect is intended to assist interpreting physicians, during or after fetal ultrasound examinations, by automatically identifying and characterizing abnormal fetal ultrasound findings on detected views, using machine learning techniques.

The device is intended for use as a concurrent reading aid on acquired images, during and/or after fetal ultrasound examinations.

The device provides information on abnormal findings that may be useful in rendering potential diagnosis.

Patient management decisions should not be made solely on the results of the Sonio Suspect analysis.

Device Description

Sonio Suspect is a Software as a Service (SaaS) solution that aims at helping interpreting physicians (designated as healthcare professionals i.e. HCP in the following) to identify abnormal fetal ultrasound findings during and/or after fetal ultrasound examinations.

Sonio Suspect is a web application accessible from any device connected to the internet. It can be accessed on a tablet, computer or any other support capable of providing access to a web application.

Sonio Suspect can be used by HCPs as a concurrent reading aid on acquired images, to assist them during and/or after fetal ultrasound examinations of gestational age (GA): from 11 weeks to 41 weeks. A concurrent read by the users means a read in which the device output is available during and/or after the fetal ultrasound examination.

The way Sonio Suspect is built allows the HCP to use it at any moment. The software can process any Ultrasound image file uploaded by the HCP, at any time.

Sonio Suspect can be connected through API to external devices (as an ultrasound machine) to receive images.

Sonio Suspect workflow goes through the following steps:

As soon as an image is automatically received, it is automatically detected and associated with a view (and can be manually re-associated by the HCP). Then abnormal fetal ultrasound findings linked to the view are evaluated and displayed, individually, with one of the following status:

Suspected (abnormal findings identified on the image);
. Not Suspected (abnormal findings not identified on the image);
. Can't be analyzed (abnormal findings not evaluated due to one or several structures not detected or if the fetal position selected is "other or unknown" while it's required to evaluate the abnormal finding).

Each abnormal finding status can be manually overridden to Present or Not Present by the user.

AI/ML Overview

Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

Description	Acceptance Criteria (Implicit from validation studies)	Reported Device Performance
Standalone Performance (Algorithm only)	Sensitivity: High sensitivity desired for detecting abnormal findings. Specificity: High specificity desired to minimize false positives.	Average Sensitivity: 93.2% (95% CI: 91.6%-94.6%) Average Specificity: 90.8% (95% CI: 89.5%-92.0%) (Individual abnormal finding performance detailed in Table 3)
Clinical Performance (Human reader with AI assistance vs. without)	Reader Accuracy Improvement: The performance of readers assisted by Sonio Suspect should be superior to their performance when unassisted.	AUC Improvement: AUC in "Unassisted" setting: 68.9%. AUC in "Assisted" setting: 90.0%. Significant difference of 21.9%. (ROC curves (Figure 1) and AUC for individual findings (Table 4) confirm consistent improvement)

Detailed Study Information:

Sample size used for the test set and the data provenance:
- Standalone Test Set: 8,745 fetal ultrasound images from 1,115 exams.
- Clinical Test Set: 750 fetal ultrasound images (between 11 and 41 weeks) evaluated by each reader, from 287 distinct exams.
- Data Provenance: The standalone test set included data from 75 sites, with 64 located in the United States. The clinical test set included data from 47 sites, with 37 located in the United States. This indicates a mix of US and OUS (Outside US) data, explicitly representing the intended use population. The study was retrospective.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document implies that ground truth for the clinical study was based on expert consensus, as it refers to a "fully-crossed multiple case (MRMC) retrospective reader study" where readers provide a "binary determination of the presence or absence of an abnormal finding." However, the exact number of experts explicitly establishing the ground truth for the test set (as opposed to participating as readers) or their specific qualifications for ground truth establishment are not explicitly stated in the provided text. The readers themselves were:
  - 13 readers: 5 MFM (Maternal-Fetal Medicine), 6 OB/GYN (Obstetrician-Gynecologists), and 2 Diagnostic radiologists.
  - Experience: 1-30+ years' experience.
Adjudication method for the test set:
- The document states that in the clinical study, "For each image, each reader was required to provide a binary determination of the presence or absence of an abnormal finding and to provide a score representing their confidence in their annotation." It also mentions "two independent reading sessions separated by a washout period." While this describes the reader process, it does not explicitly describe an adjudication method (like 2+1 or 3+1) used to establish a definitive ground truth from multiple expert opinions. It implies that the ground truth was pre-established for the images used in the reader study.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- Yes, an MRMC comparative effectiveness study was done.
- Effect Size: The study demonstrated a significant improvement in reader accuracy. The Area Under the Curve (AUC) for readers:
  - Without AI assistance ("Unassisted"): 68.9%
  - With AI assistance ("Assisted"): 90.0%
  - This represents a significant difference (effect size) of 21.9% in AUC.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance testing was conducted.
- The results are detailed in Table 3, showing an average sensitivity of 93.2% and specificity of 90.8% for abnormal finding detection.
The type of ground truth used:
- Implicitly, expert consensus or pre-established clinical diagnosis. For the standalone study, the robust sensitivity and specificity metrics suggest comparison against a definitive "ground truth" for the presence or absence of abnormal findings. For the clinical study, readers compared their findings against this ground truth. The document does not specify if pathology or outcomes data were directly used to define the ground truth for every case, but it's common for such studies to rely on a panel of experts or established clinical reports to define the ground truth for imaging-based diagnoses.
The sample size for the training set:
- The sample size for the training set is not explicitly stated. The document mentions that the global validation dataset for standalone testing "was independent of the data used during model development (training/internal validation) and the establishment of device operating points," implying a separate training set existed, but its size is not provided.
How the ground truth for the training set was established:
- This information is not explicitly provided. It can be inferred that similar methods to the test set (e.g., expert review and consensus) would have been used, but no specifics are given in the text.

Summary

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

Image /page/0/Picture/0 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.

Sonio Florian Akpakpa Head of Regulatory Affairs and Quality Assurance 17 rue du Faubourg Montmartre Paris, 75009 France

February 21, 2025

Re: K243614

Trade/Device Name: Sonio Suspect Regulation Number: 21 CFR 892.2060 Regulation Name: Radiological computer-assisted diagnostic software for lesions suspicious of cancer Regulatory Class: Class II Product Code: POK Dated: January 24, 2025 Received: January 24, 2025

Dear Florian Akpakpa:

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 (that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

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

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

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

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

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

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rue"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

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

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

Page

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

Sincerely,

Jessica Lamb

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

Enclosure

{3}------------------------------------------------

Indications for Use

Submission Number (if known)

K243614

Device Name

Sonio Suspect

Indications for Use (Describe)

The device is intended for use as a concurrent reading aid on acquired images, during and/or after fetal ultrasound examinations.

The device provides information on abnormal findings that may be useful in rendering potential diagnosis.

Patient management decisions should not be made solely on the results of the Sonio Suspect analysis.

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."

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

Image /page/4/Picture/1 description: The image contains the logo for Sonio. The logo consists of a stylized blue icon resembling a person with a circular head and curved body, followed by the word "sonio" in a sans-serif font, also in blue. The logo is simple and modern, with a clean design.

510(k) Summary

In accordance with 21 CFR 807.92 the 510(k) summary for Sonio Suspect is provided below.

I. Submitter

Applicant:	Sonio
	147 Rue d'Aboukir,75002, Paris France
Primary Contact Person:	Florian Akpakpa
	Director Regulatory Affairs and Quality Assurance
	Sonio
	Phone: +33 6 19 38 71 45
	Email: florian.akpakpa@sonio.ai

Date Prepared:	February 19, 2025

II. Device

Device Trade	Sonio Suspect
Name:
Classification	21 CFR 892.2060 - Radiological computer-assisted diagnostic
Name:	software for lesions suspicious of cancer

Regulatory Class:	Class II
Product Code:	POK (primary)

III. Predicate Device

Koios DS from the manufacturer Koios Medical, Inc. cleared in K212616.

This predicate has not been subject to a design-related recall.

The following reference device was used: Sonio Detect-K240406.

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

Image /page/5/Picture/1 description: The image contains the logo for "sonio". The logo consists of a stylized, abstract symbol to the left of the word "sonio". The symbol is a blue, curved shape with a dot above it. The word "sonio" is written in a sans-serif font and is also blue. The logo is simple and modern.

IV. Device Description

The way Sonio Suspect is built allows the HCP to use it at any moment. The software can process any Ultrasound image file uploaded by the HCP, at any time.

Sonio Suspect can be connected through API to external devices (as an ultrasound machine) to receive images.

Sonio Suspect workflow goes through the following steps:

Suspected (abnormal findings identified on the image);
. Not Suspected (abnormal findings not identified on the image);
. Can't be analyzed (abnormal findings not evaluated due to one or several structures not detected or if the fetal position selected is "other or unknown" while it's required to evaluate the abnormal finding).

Each abnormal finding status can be manually overridden to Present or Not Present by the user.

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

Image /page/6/Picture/0 description: The image shows the logo for Sonio. The logo consists of a stylized blue icon on the left and the word "sonio" in blue text on the right. The icon appears to be a stylized sound wave or a curved shape with a dot above it. The text is in a sans-serif font and is all lowercase.

The list of abnormal findings that Sonio Suspect can automatically detect is detailed in Table 1 below.

Table 1: list of Fetal Abnormal Findings in Sonio Suspect scope and their associated View, Fetal Anatomy and Gestational Age (GA)

FetalAnatomy	Abnormal Finding	View	GA
Chest	Absence or unusual size of at least one of the 3vessels	3 vessels	T2/T3
	Malposition of the great vessels	LVOT/RVOT	T2/T3
	Disequilibrium OR absence of at least one of thetwo ventricles	4 chambers	T1/T2/T3
	Thoracic situs inversus
Abdominal	Abdominal situs inversus	Abdominal
	Non-visibility of a single stomach bubble ORcircumferenceabnormally big stomach		T1/T2/T3
Cephalic	Absence of the cavum septum pellucidum	Transthalamic view	T2/T3
	Absence of the Corpus Callosum	Corpus callosumview*	T2/T3

*Note: The views are automatically detected by Sonio Suspect besides the Corpus callosum view on which abnormal finding identification and characterization is done by the software when it is manually associated by the users.

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

Image /page/7/Picture/1 description: The image shows the logo for Sonio. The logo consists of a stylized blue symbol to the left of the word "sonio" in blue lowercase letters. The symbol appears to be a stylized wave or abstract shape, and the overall design is clean and modern.

V. Indications for Use

The device is intended for use as a concurrent reading aid on acquired images, during and/or after fetal ultrasound examinations.

The device provides information on abnormal findings that may be useful in rendering potential diagnosis.

Patient management decisions should not be made solely on the results of the Sonio Suspect analysis.

Sonio Suspect and the predicate device, Koios DS, have similar intended use in assisting interpreting physicians in analyzing ultrasound images and characterizing ultrasound image items using machine learning techniques. Both devices are used as an aid to diagnosis and provide information that may be useful in rendering potential diagnosis.

The indication for use of Sonio Suspect and the predicate device differ in the following:

The target population: Sonio Suspect is indicated for pregnant women undergoing fetal ultrasound examinations of the fetus while Koios DS is indicated for adult female patients with soft tissue breast lesions and/or all adult patients with thyroid nodules suspicious for cancer
. Feature scope: While the predicate Koios DS, requires the user to select or confirm regions of interests (ROIs) within an image to be analyzed, Sonio Suspect automatically detects fetal ultrasound views on which abnormal fetal ultrasound findings will be identified.
. Feature scope: Koios DS allows the users to adjust, measure, and document images and output into a structured report while Sonio Suspect does not.

However, these differences should not raise new questions regarding the safety and effectiveness of the device when used as labeled.

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

VI. Comparison of Technological Characteristics with the Predicate Device

Table 2 provides a comparison of the Technological Characteristics of Sonio Suspect to the predicate Koios DS cleared in K212616.

Table 2 - comparison of the Technological Characteristics of Sonio Suspect to the predicate

Items	Predicate: Koios DSProposed device: Sonio Suspect
Manufacturername	Koios Medical	Sonio
Device name	Koios DS	Sonio Suspect
RegulationNumber	21 CFR 892.206021 CFR 892.2050	21 CFR 892.2060
Product code	POKOIH	POK
Image modality	Breast Ultrasound DataThyroid UltrasoundDataUltrasound images	Fetal Ultrasound images
AlgorithmMethodology	Computer visionMachine Learning Techniques	Computer visionMachine Learning-BasedAlgorithm
Platform	ASP.NET web applicationdeployed to a Microsoft IIS webserver inside a Windowsoperating system environment	Secure cloud-based and stand-alonesoftware compatible with anultrasound system

The technical principle of both Sonio Suspect and the predicate Koios DS is the characterization of ultrasound images items using computer vision and machine learningbased algorithms. Both devices use ultrasound images modality for analysis.

Sonio Suspect differs from Koios DS in the following:

Operating platform: Sonio Suspect is a secure cloud-based and standalone software compatible with ultrasound systems while Koios DS the predicate is a ASP.NET web application deployed to a Microsoft IIS web server inside a Windows operating system environment.
However, these differences should not raise new questions regarding the safety and effectiveness of the device when used as labeled.

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

VII. Performance Data

The following performance data were provided in support of the substantial equivalence determination.

Software Verification and Validation Testing

Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions."

The following quality assurance measures were applied to the development of the system:

Risk Analysis
Design Reviews ●
Software Development Lifecycle ●
Algorithm Verification (Algorithm internal validation) ●
Software units verification ●
Software verification
Simulated use testing (Validation)
Performance testing
Cybersecurity testing .

Performance testing - Bench

Sonio conducted a standalone performance testing in accordance with 21 CFR §892.2060 special control 1(iv). The testing was conducted on a dataset of 8745 fetal ultrasound images from 1115 exams collected across 75 sites, 64 of which are located in the United States, representing the intended use population. This global validation dataset was independent of the data used during model development (training/finternal validation) and the establishment of device operating points.

The results of the standalone performance testing demonstrated that Sonio Suspect automatically detects abnormal findings with a sensitivity of 93.2% (Confidence Interval of [91.6%-94.6%]) and a specificity of 90.8% (Confidence Interval of [89.5%-92.0%]).

Table 3 below summarizes Sonio Suspect's performance results.

The abnormal finding "Abdominal Situs Inversus" has the highest performance in terms of both sensitivity (99.3%) and specificity (99.3%). The lowest sensitivity (87.7%) is associated with the abnormal finding "Malposition of the great vessels" and the lowest specificity (81.5%) with the abnormal finding "Absence or unusual size of at least one of the 3 vessels".

{10}------------------------------------------------

Image /page/10/Picture/0 description: The image shows the logo for Sonio. The logo consists of a stylized blue icon on the left and the word "sonio" in blue letters on the right. The icon appears to be a stylized representation of sound waves or a similar concept.

Sonio 510(k) Premarket Notification Submission

Table 3: Performance of Sonio Suspect for abnormal finding detection.
-----------------------------------------------------------------------	--

Fetal Anatomy	GestationalAge	Abnormal Finding	Sensitivity	Specificity
			Point Estimate(95% bootstrap CI)	Point Estimate(95% bootstrap CI)
AveragePerformance	T1/T2/T3	Average Performance	0.932(0.916, 0.946)	0.908(0.895, 0.920)
Chest	T2/T3	Malposition of the Great Vessels	0.877(0.840, 0.908)	0.933(0.905, 0.957)
		Absence or unusual size of at least one of the 3 vessels	0.959(0.926, 0.983)	0.815(0.759, 0.872)
	T1/T2/T3	Disequilibrium OR absence of at least one of the twoventricles	0.900(0.861, 0.934)	0.817(0.782, 0.851)
		Thoracic Situs Inversus	0.961(0.930, 0.987)	0.958(0.927, 0.982)
Abdominal	T1/T2/T3	Abdominal Situs Inversus	0.993(0.976, 1.000)	0.993(0.984, 1.000)
		Non-visibility of a single stomach bubble OR abnormallybig stomach	0.880(0.780, 0.946)	0.964(0.950, 0.977)
Cephalic	T2/T3	Absence of the Cavum Septum Pellucidum	0.911(0.861, 0.956)	0.925(0.882, 0.962)
		Absence of the Corpus Callosum	0.976(0.952, 0.994)	0.859(0.805, 0.907)

{11}------------------------------------------------

Image /page/11/Picture/0 description: The image shows the logo for "sonio". The logo consists of a stylized blue icon resembling a sound wave or a stylized letter "S", followed by the word "sonio" in a sans-serif font, also in blue. The logo is simple and modern, with a clean design.

Additionally, the performance for the detection of abnormal fetal ultrasound findings was also validated for subgroups including Indication of examination, Race, Ethnicity, BMI, Gestational Age (GA), Maternal age, Manufacturer, Geography (OUS and US), Finding Status (Findingpositive and Finding-negative images) and Fetal Anatomy, and detailed subgroup analysis results are reported in the User Manual.

Sonio Suspect was validated only on GE, Philips, Samsung and Canon Ultrasound devices.

The results of verification and performance testing demonstrate the safe and effective use of Sonio Suspect.

Performance testing - Clinical

Sonio conducted a clinical performance testing in accordance with 21 CFR §892.2060 special control 1(ii) and 1(iii). A pre-market fully-crossed multiple case (MRMC) retrospective reader study was conducted to determine the impact of Sonio Suspect on reader accuracy in identifying abnormal fetal ultrasound findings. The MRMC study consisted of two independent reading sessions separated by a washout period of at least 28 days in order to avoid memory bias.

The primary objective of this study was to determine whether the performance of readers assisted by Sonio Suspect ("Assisted") was superior to the performance of readers when not assisted by Sonio Suspect ("Unassisted").

13 readers (5 MFM, 6 OB/GYN and 2 Diagnostic radiologists of 1-30+ years' experience) each evaluated 750 fetal ultrasound images (between 11 and 41 weeks) under both "Assisted" and "Unassisted" reading settings. The dataset included 287 distinct exams from 47 sites, including 37 sites which are located in the United States. For each image, each reader was required to provide a binary determination of the presence or absence of an abnormal finding and to provide a score representing their confidence in their annotation.

The results of the study demonstrated that the accuracy of readers in identifying abnormal findings was superior when "Assisted" by Sonio Suspect than when "Unassisted". Particularly, the AUC in the "Unassisted" reading setting is estimated at 68.9%, whilst the AUC in the "Assisted" reading setting is estimated at 90.0% which represents a significant difference of 21.9%, as shown in Figure 1 and Table 4 below.

{12}------------------------------------------------

Image /page/12/Picture/0 description: The image contains the logo for "sonio". The logo consists of a stylized blue icon resembling a water droplet or a sound wave, followed by the word "sonio" in a rounded, sans-serif font, also in blue. The logo is simple and modern, with a clean and professional appearance.

Figure 1: ROC curves averaged over all readers and over all abnormal findings for ''Assisted'' (red) and ''Unassisted'' (blue) reading settings.

Image /page/12/Figure/3 description: The image is a plot comparing the true positive rate (sensitivity) and false positive rate (1 - specificity) for two reading settings: assisted and unassisted. The y-axis represents the true positive rate, ranging from 0% to 100%, while the x-axis represents the false positive rate, also ranging from 0% to 100%. The plot shows two curves, one for the assisted reading setting and one for the unassisted reading setting, along with a dashed diagonal line.

{13}------------------------------------------------

Image /page/13/Picture/0 description: The image shows the logo for Sonio. The logo consists of a blue abstract shape resembling a water droplet or a stylized letter 'S' on the left. To the right of the shape is the word "sonio" in a sans-serif font, also in blue. The logo has a clean and modern design.

Per Abnormal Finding	N offinding-positiveimages	N offinding-negativeimages	AUCDelta	AUCUnassisted	AUCAssisted
			Point Estimate(95% BDG CI)	PointEstimate(95% BDGCI)	Point Estimate(95% BDG CI)
			Overall	250	500
Abdominal SitusInversus	32	143	0.258(0.177, 0.339)	0.696(0.602, 0.789)	0.953(0.913, 0.994)
Absence of at least oneof the 2 ventricles ORdisequilibrium of the 2ventricles	31	145	0.174(0.1, 0.248)	0.742(0.668, 0.816)	0.916(0.877, 0.954)
Absence of the cavumseptum pellucidum	31	55	0.317(0.249, 0.384)	0.567(0.52, 0.614)	0.884(0.81, 0.957)
Absence of the corpuscallosum	31	55	0.253(0.206, 0.3)	0.646(0.599, 0.694)	0.899(0.851, 0.948)
Absence of the stomachOR presence of twostomachs	31	144	0.114(0.071, 0.158)	0.84(0.785, 0.895)	0.955(0.916, 0.993)
Absence or unusual sizeof at least one of the 3vessels	31	55	0.168(0.097, 0.239)	0.736(0.674, 0.798)	0.904(0.852, 0.956)
Great vesselsmalposition	31	110	0.256(0.183, 0.329)	0.616(0.555, 0.676)	0.872(0.809, 0.934)
Thoracic situs inversus	32	144	0.29(0.231, 0.349)	0.616(0.559, 0.672)	0.906(0.855, 0.957)

Table 4: AUCDelta, AUCUnassisted, AUCAssisted over all Readers per Abnormal Finding. (C1 = Confidence Interval)

{14}------------------------------------------------

Image /page/14/Picture/0 description: The image contains the logo for Sonio. The logo consists of a stylized blue icon resembling a sound wave or a stylized letter 'S', followed by the word "sonio" in a sans-serif font, also in blue. The logo is simple and modern in design.

Figure 2 and 3 below show that the "Assisted" reading curve consistently lies above the "Unassisted" curve across all 8 abnormal findings and all 13 readers, indicating the improved performance of reader accuracy in identifying abnormal findings with Sonio Suspect. This consistent pattern highlights Sonio Suspect's effectiveness in improving reader accuracy across a variety of abnormal findings and regardless of individual variability.

Figure 2: "Assisted" (red) and "Unassisted" (blue) ROC curves for each abnormal finding

Reading setting - Assisted - Unassisted

False Positive Rate (1 - Specificity)

{15}------------------------------------------------

Image /page/15/Picture/0 description: The image shows the logo for Sonio. The logo consists of a stylized blue icon on the left and the word "sonio" in blue on the right. The icon appears to be a stylized representation of a sound wave or a droplet with a smaller circle above it.

Image /page/15/Figure/2 description: The image contains 13 ROC curves comparing the performance of assisted and unassisted reading settings for different readers. Each subplot represents a different reader, labeled from Reader 1 to Reader 13. The y-axis represents the true positive rate (sensitivity), ranging from 0% to 100%, while the x-axis represents the false positive rate, also ranging from 0% to 100%. The red lines represent the assisted reading setting, and the teal lines represent the unassisted reading setting.

Figure 3: "Assisted" (red) and "Unassisted" (blue) ROC curves for each reader Reading setting — Assisted — Unassisted

False Positive Rate (1 - Specificity)

{16}------------------------------------------------

Image /page/16/Picture/1 description: The image contains the logo for Sonio. The logo consists of a stylized, abstract symbol to the left of the word "sonio". The symbol is blue and appears to be a rounded shape with a dot above it. The word "sonio" is also in blue and is written in a sans-serif font.

VIII. Conclusions

The conclusions drawn from the standalone and clinical studies demonstrate that Sonio Suspect is substantially equivalent to the predicate device Koios DS cleared in K212616.

The special controls for 21 CFR 892.2060 regulation are satisfied by demonstrating the effectiveness of the device in both the standalone testing and the clinical testing, showing the superiority of "Assisted" versus "Unassisted" readings in the clinical testing and communicating testing results in the labeling.

Sonio Suspect intended use, clinical outcome, and clinical applications are similar to those of the predicate device. The technological characteristics differences identified and discussed in Section VI do not raise any different questions of safety and effectiveness of the device.

Thus, Sonio Suspect is substantially equivalent to its predicate Koios DS cleared in K212616.

Regulation Number and Section

§ 892.2060 Radiological computer-assisted diagnostic software for lesions suspicious of cancer.

(a)
Identification. A radiological computer-assisted diagnostic software for lesions suspicious of cancer is an image processing prescription device intended to aid in the characterization of lesions as suspicious for cancer identified on acquired medical images such as magnetic resonance, mammography, radiography, or computed tomography. The device characterizes lesions based on features or information extracted from the images and provides information about the lesion(s) to the user. Diagnostic and patient management decisions are made by the clinical user.(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 image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, and algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will improve reader performance as intended.
(iii) Results from performance testing protocols that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, predictive value, and diagnostic likelihood ratio). The test dataset must contain sufficient numbers of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant diseases, 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) Standalone 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; and description of verification and validation activities including system level test protocol, pass/fail criteria, results, and cybersecurity).(2) Labeling must include:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the intended reading protocol.
(iii) A detailed description of the intended user and recommended user training.
(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, including 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) Detailed instructions for use.
(viii) 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 (
e.g., lesion and organ characteristics, disease stages, and imaging equipment).