(184 days)
CT Cardiomegaly is a command line software application intended to be run on its own or as part of another medical device to automatically calculate linear and area based cardiothoracic ratio (CTR) from a CT image containing the heart.
CT Cardiomegaly is designed to measure the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity and calculate the CTR from an axial CT slice containing the heart using a non-adaptive machine learning algorithm.
Intended users of the software are aimed to the physicians or other licensed practitioners in the healthcare institutions, such as clinics, hospitals, healthcare facilities, residential care facilities and long-term care services.
The system is suitable for adults and transitional adolescents (18 to 21 years old but treated as an adult).
Its results are not intended to be used on a stand-alone basis for clinical-decision making or otherwise preclude clinical assessment of any disease.
The CT Cardiomegaly application is a software only (SaMD) medical device which includes automated algorithms and non-adaptive machine learning to analyze chest computed tomography (CT) images. CT Cardiomegaly is a command line software intended to be run on its own or as part of another medical device.
CT Cardiomegaly scans the existing images for the presence of specific anatomical structures (i.e., heart and chest cavity). If the target structures are present, the software segments and performs automated measurements which may be helpful in assisting with the detection of certain diseases and/or conditions (i.e., cardiomegaly). The quantitative information is provided to the clinician in the form of a summary report. The clinician (using all available information) then decides if further diagnostic work-up, analysis or measurements are indicated.
The results from CT Cardiomegaly are not intended to be used as the primary input for clinicaldecision making or diagnosis.
A reference standard was created to train the machine learning algorithms in CT Cardiomegaly. Data for training and testing were sampled from this database based on exclusion criteria. Data was also selected to ensure no site was shared by training and testing cohorts. The training dataset included 1600 unique patient cases from 267 unique sites across 20 U.S. states.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Measurement | Acceptance Criteria (Mean Difference Target) | Reported Device Performance (Mean Difference [95% CI]) | Result |
|---|---|---|---|
| Primary Endpoints | |||
| Cardiothoracic Ratio (Linear) | < 0.0100 | 0.0012 [-0.0008, 0.0033] | Pass |
| Heart to Chest Area Ratio (Area) | < 0.0100 | 0.0036 [0.0017, 0.0055] | Pass |
| Secondary Endpoints | |||
| Key Heart Slice Position | < 5 mm | 0.46 mm [-0.49, 1.41] | Pass |
| Segmentation Comparison | Observed Dice [95% CI] | ||
| Heart | 0.950, 0.956 | 0.95 [0.950, 0.956] | - |
| Inner Chest | 0.982, 0.984 | 0.98 [0.982, 0.984] | - |
Study Details
1. A table of acceptance criteria and the reported device performance:
See table above. The acceptance criteria for the primary endpoints are defined by "Mean Difference Target" and for the secondary endpoint (Key Slice Position) by "Mean Difference Target". For segmentation, "Observed Dice [95% CI]" serves as the performance metric.
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: 275 unique patient cases.
- Data Provenance: Data was sampled from a database curated by the University of Alabama at Birmingham. The test set included cases from sites across 12 U.S. states. The dataset included various patient demographics (age, sex, race, ethnicity), confounding conditions, and imaging characteristics (protocol, slice thickness, scanner manufacturer, presence or absence of contrast, kVp), making it representative of diverse clinical scenarios.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Three.
- Qualifications: All three experts were board-certified radiologists.
4. Adjudication method for the test set:
- The text states that each radiologist "provided a segmentation for the heart and the inner chest independently from the other radiologists." It also mentions that "Measurement among the three radiologists was very high for all measured values." This implies that while initial segmentations were independent, a consensus or average of these high-agreement measurements was used as the reference standard, rather than a specific 2+1 or 3+1 adjudication rule.
5. 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:
- No, an MRMC comparative effectiveness study that assesses human reader improvement with AI assistance versus without AI assistance was not explicitly described. The study focused on the standalone performance of the device against a human-derived reference standard.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, a standalone performance assessment was conducted. The study validated the accuracy of the CT Cardiomegaly's measurements (linear-based CTR and area-based CTR), key heart slice detection, and segmentation accuracy ("algorithm only") against the measurements provided by human readers (the reference standard).
7. The type of ground truth used:
- Expert Consensus: The ground truth was established by segmentations and measurements provided by three board-certified radiologists, whose measurements showed "very high" agreement. This falls under expert consensus.
8. The sample size for the training set:
- 1600 unique patient cases.
9. How the ground truth for the training set was established:
- A reference standard was created to train the machine learning algorithms in CT Cardiomegaly. While the document doesn't explicitly detail the method for establishing the training set ground truth, it's reasonable to infer that a similar process involving expert radiologists and their segmentations/measurements would have been used, perhaps with subsequent review or consensus, given the explicit mention of a reference standard being created for training. The document states, "Data for training and testing were sampled from this database based on exclusion criteria. Data was also selected to ensure no site was shared by training and testing cohorts."
{0}------------------------------------------------
February 28, 2024
Image /page/0/Picture/1 description: The image shows 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.
Innolitics, LLC % Meritxell Martinez Project Manager and Regulatory Specialist 1101 West 34th St Austin, Texas 78705
Re: K232613
Trade/Device Name: CT Cardiomegaly Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: OIH Dated: January 30, 2024 Received: January 30, 2024
Dear Meritxell Martinez:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
{1}------------------------------------------------
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Samul Zik for
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
Indications for Use
510(k) Number (if known) K232613
Device Name CT Cardiomegaly
Indications for Use (Describe)
CT Cardiomegaly is a command line software application intended to be run on its own or as part of another medical device to automatically calculate linear and area based cardiothoracic ratio (CTR) from a CT image containing the heart.
CT Cardiomegaly is designed to measure the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity and calculate the CTR from an axial CT slice containing the heart using a non-adaptive machine learning algorithm.
Intended users of the software are aimed to the physicians or other licensed practitioners in the healthcare institutions, such as clinics, hospitals, healthcare facilities, residential care facilities and long-term care services.
The system is suitable for adults and transitional adolescents (18 to 21 years old but treated as an adult).
Its results are not intended to be used on a stand-alone basis for clinical-decision making or otherwise preclude clinical assessment of any disease.
| 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 |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
Image /page/3/Picture/0 description: The image contains the logo for "Body Check". The logo consists of a green circle with a check mark that is partially navy blue. The text "Body Check" is to the right of the logo, with "Body" in green and "Check" in navy blue.
K232613
1. ADMINISTRATIVE INFORMATION
| Submitter Name | Innolitics LLC |
|---|---|
| Address | 1101 West 34th St #550, Austin, TX 78705, US |
| Phone Number | +1 (512) 967-6088 |
| Fax Number | N/A |
| Company Representative | Meritxell Martinez |
| Additional Company Representatives | Yujan Shrestha, MDEthan UlrichAndrew Smith, MD, PhDSteven Rothenberg, MDJim Luker, RN, MS |
| fda@innolitics.com | |
| Date Summary Prepared | January 30th, 2024 |
| Documentation Prepared Using | Innolitics Medtech OS Framework |
2. SUBJECT DEVICE INFORMATION
| Trade Name | CT Cardiomegaly |
|---|---|
| Subject Device K Number | K232613 |
| Common Name | Automated Radiological Image Processing Software |
| Product Code | QIH |
| Regulation Number | 892.2050 |
| Regulatory Class | Class II |
| Review Panel | Radiology |
Image /page/3/Picture/7 description: The image contains the logo for Innolitics SaMD Simplified. The logo consists of a blue hexagon-like shape on the left, followed by the text "Innolitics" in a bold, blue font. Below "Innolitics" is the text "SaMD Simplified" in a smaller, lighter blue font. The logo is clean and professional, suggesting a company in the technology or software industry.
{4}------------------------------------------------
3. PREDICATE DEVICE INFORMATION
| Predicate Device Name | EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System |
|---|---|
| Predicate Device K Number | K212624 |
| Common Name | EFAI iCTR |
| Product Code | QIH |
| Regulation Number | 892.2050 |
| Regulatory Class | Class II |
| Review Panel | Radiology |
4. DEVICE DESCRIPTION
The CT Cardiomegaly application is a software only (SaMD) medical device which includes automated algorithms and non-adaptive machine learning to analyze chest computed tomography (CT) images. CT Cardiomegaly is a command line software intended to be run on its own or as part of another medical device.
CT Cardiomegaly scans the existing images for the presence of specific anatomical structures (i.e., heart and chest cavity). If the target structures are present, the software segments and performs automated measurements which may be helpful in assisting with the detection of certain diseases and/or conditions (i.e., cardiomegaly). The quantitative information is provided to the clinician in the form of a summary report. The clinician (using all available information) then decides if further diagnostic work-up, analysis or measurements are indicated.
The results from CT Cardiomegaly are not intended to be used as the primary input for clinicaldecision making or diagnosis.
A reference standard was created to train the machine learning algorithms in CT Cardiomegaly. Data for training and testing were sampled from this database based on exclusion criteria. Data was also selected to ensure no site was shared by training and testing cohorts. The training dataset included 1600 unique patient cases from 267 unique sites across 20 U.S. states.
Image /page/4/Picture/9 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in large, bold, blue font. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, lighter blue font. The logo is clean and modern, with a focus on simplicity and clarity.
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image contains the logo for Body Check. The logo consists of a green and blue checkmark inside of a green circle. To the right of the logo is the text "Body Check", with "Body" in green and "Check" in blue.
5. INDICATIONS FOR USE
CT Cardiomegaly is a command line software application intended to be run on its own or as part of another medical device to automatically calculate linear and area based cardiothoracic ratio (CTR) from a CT image containing the heart.
CT Cardiomegaly is designed to measure the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity and calculate the CTR from an axial CT slice containing the heart using a non-adaptive machine learning algorithm.
Intended users of the software are aimed to the physicians or other licensed practitioners in the healthcare institutions, such as clinics, hospitals, healthcare facilities, residential care facilities and long-term care services.
The system is suitable for adults and transitional adolescents (18 to 21 years old but treated as an adult).
Its results are not intended to be used on a stand-alone basis for clinical-decision making or otherwise preclude clinical assessment of any disease.
5.1. Indications for Use Equivalence Discussion
Both the subject (CT Cardiomegaly) and predicate device (EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System) have similar indications for use, with the exception that the subject device analyzes CT images while the predicate device is limited to X-ray images.
Another difference between the indications for use for both devices is that the predicate uses an artificial intelligence algorithm using an unknown framework while the subject device utilizes a non-adaptive machine learning algorithm using the MONAI framework.
However, these are differences in technological characteristics that do not affect safety and effectiveness of the device, and have been supported with appropriate verification and validation testing.
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
|---|---|---|---|
| Manufacturer | Innolitics LLC | Ever Fortune. AI Co.,Ltd. | N/A |
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
| RegulationNumber | 892.2050 | 892.2050 | Same |
| Regulatory Class | Class II | Class II | Same |
| Product Code | QIH | QIH | Same |
| Regulation Name | Medical image processingand management system | Medical image processingand management system | Same |
| Device Property | SaMD | SaMD | Same |
| Intended Use/Indications for Use | CT Cardiomegaly issoftware intended to be runon its own or as part ofanother medical device toautomatically calculatelinear and area basedcardiothoracic ratio (CTR)from a CT imagecontaining the heart.CT Cardiomegaly isdesigned to measure themaximal transversediameter of heart andmaximal inner transversediameter of thoracic cavityand calculate the CTR froman axial CT slicecontaining the heart using anon-adaptive machinelearning algorithm.Intended users of thesoftware are aimed to thephysicians or otherlicensed practitioners in thehealthcare institutions,such as clinics, hospitals,healthcare facilities,residential care facilitiesand long-term careservices.The system is suitable foradults and transitionaladolescents (18 to 21 yearsold but treated as an adult).Its results are not intendedto be used on a stand-alonebasis for clinical-decision | EFAI IntelligentCardiothoracic RatioAssessment System (oriCTR) is a software for useby hospital and clinics toautomatically assess thecardiothoracic ratio (CTR)of a chest X-ray image fromthe X-ray imager subject.The iCTR is designed tomeasure the maximaltransverse diameter of heartand maximal innertransverse diameter ofthoracic cavity and calculatethe CTR of a chest X-rayimage in posterior-anterior(PA) chest view using anartificial intelligencealgorithm.Intended users of thesoftware are aimed to thephysicians or other licensedpractitioners in thehealthcare institutions, suchas clinics, hospitals,healthcare facilities,residential care facilities andlong-term care services.The system is suitable foradults between 20 - 80 yearsof age.Its results are not intendedto be used on a stand-alonebasis for clinical-decisionmaking or otherwisepreclude clinical assessment | Both the subject (CT Cardiomegaly)and predicate device (iCTR) haveidentical indications for use, with theexception that the subject deviceanalyzes CT images while the predicatedevice is limited to X-ray images.Another difference between theindications for use for both devices isthat the predicate uses artificialintelligence algorithms using anunknown framework while the subjectdevice utilizes non-adaptive machinelearning algorithms using the MONAIframework.However, these differences intechnological characteristics do notaffect safety and effectiveness of thedevice, and have been supported withverification and validation testing. |
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
| making or otherwisepreclude clinicalassessment of any disease. | of cardiothoracic ratio(CTR) cases. | ||
| TechnicalCharacteristics | |||
| Input | CT image study | Post-anterior (PA) viewchest X-ray image | The input for the predicate device is a2-dimensional chest X-ray image, whilethe subject device's input is an entireCT study. The subject device will selectout of the CT study an axial slicecontaining the heart, if present, andperform measurements. The maindifference is that the predicate operateson images that are post-anterior (PA)view chest X-ray, while the subjectdevice's operates on images that areaxial CT. Nonetheless, this differencein imaging modality does not raise anynew concerns and has been verified andvalidated in testing. |
| Output files | PDF and JSON Reports | Reports, DICOMSecondary Captureseries | The output format of the predicatedevice includes reports and DICOMsecondary capture series, while thesubject device's only output format is areport (in both PDF and JSON format).Thus, the subject device's outputformat is a subset of the predicate'savailable output formats (i.e., report).This lack of a feature does not raise anynew concerns. |
| Outputmeasurements | Linear-based CTR andarea-based CTR | Linear-based CTR | The predicate device outputs a linear-based CTR measurement while thesubject device outputs both linear andarea-based CTR measurements.Although this output measurement ofarea-based CTR is not included in thepredicate device, it does not raisedifferent questions of safety oreffectiveness and has been properlyverified and validated in testing. |
| Report Structure | Report will be output inthe PDF and JSONfile format which isstructured with following | Report will be output inthe DICOM and JSONfile format which isstructured with following | Both devices produce reports thatoutput CTR and patient information.One of the main differences betweenboth devices is that the predicate only |
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
| information:1) CTR (both linear andarea-based)2) Patient information3) Reference value(s) | information and functiontool:1) CTR2) adjustable annotation line(maximal inner borderdiameter of thoracic cavityand maximal diameter ofheart)3) the trajectory of CTR(including chest X-ray)4) Patient information | has one CTR output, while the subjectdevice outputs both linear-based CTRand area-based CTR. This difference isfurther discussed in the row above.Additionally, the predicate devicepresents the feature to modify theannotation line, which is not availablein the subject device. However, CTCardiomegaly 's indications for useexplicitly state that the results producedby the device are not intended to besolely relied upon for clinical decision-making, nor do they replace the needfor clinical assessment of any disease.Furthermore, the user manual of thedevice contains instructions mandatinghealthcare professionals to review theresults presented in the report.Both devices produce reports thatcontain relevant patient information.The predicate device includes atrajectory of the CTR in the report. Thesubject device includes segmentationsof the heart area and inner chest area.Lastly, the subject device introduces afeature to have user-specified referencevalue(s) stated in the report. Thehealthcare professional is able to setreference value(s) linear and area-basedCTR, based on published literature ortheir practice of medicine. This featureis not found in the predicate device, buthas been properly verified andvalidated. | |
| Intended Users | Physicians or otherlicensed practitioners inthe healthcareinstitutions | Physicians or otherlicensed practitioners inthe healthcareinstitutions | Same |
| Target Population | Adults and transitionaladolescents (18 to 21 yearsold but treated as an adult)" | Adults of 20-80 years old | Both devices have similar intendedtarget populations. The subject device'spatient population age range has beensupported by appropriate performancetesting. |
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
| Location ofanatomicalstructures | Chest | Chest | Same |
| Imaging Modality | Computed Tomography(CT) | Chest X-ray in DigitalRadiography (DR) | Although the predicate and subjectdevice are compatible with differentimaging modalities, this technologicaldifference does not raise new questionsof safety or effectiveness. Additionally,this difference has been properlysupported with verification andvalidation testing. |
| Intended UseEnvironment | Healthcare institutions(Clinics, hospitals,healthcare facilities,residential care facilitiesand long-term careservices) | Healthcare institutions(Clinics, hospitals,healthcare facilities,residential care facilitiesand long-term careservices) | Same |
| Software devicethatoperates on off-the-shelfhardware | Yes | Yes | Same |
| Software devicesusessoftwarealgorithms forimage | Yes | Yes | Same |
| DiameterMeasurement | Yes - Automated | Yes - Automated | Same, with the main difference thatdiameter measurements are performedon an axial slice of the CT series for thesubject device (not on chest x-ray, asdone for the predicate). |
| Storage | Saved in JSON andPDF file format | Saved in JSON andDICOM file format textfor DICOM andDICOM file format | Both devices store study reports inmachine-readable JSON format.The predicate device also stores files inDICOM format. On the other hand, thesubject device also outputs reports inPDF format. This difference in fileformat does not raise any new questionsof safety or effectiveness, and is |
| Characteristic | CT Cardiomegaly | EFAI IntelligentCardiothoracic Ratio(iCTR) AssessmentSystem (K212624) | Substantial Equivalence Discussion |
| supported by verification and validationtesting. | |||
| SoftwareRequirement | Ubuntu 20.04.5 LTS(provided as a Dockercontainer)Docker 23.0.1 or above | Ubuntu 18.04(Web browser :chrome 88.0.4324.182or above) | Both devices have similar softwarerequirements. The subject devicerequires a newer version of theoperating system that runs inside acontainer. The main difference is thatthe predicate device is intended to runon a web browser while the subject |
| Algorithm type | Machine learning basedalgorithm (non-adaptive) | Artificial Intelligence | Same. Machine learning basedalgorithm is a subset of artificialintelligence. |
6. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS
Image /page/5/Picture/14 description: The image shows the logo for Innolitics. The logo consists of a blue hexagon made up of smaller triangles on the left, and the word "Innolitics" in a bold, blue font on the right. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, blue font.
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image contains the logo for "Body Check". The logo consists of a green and blue check mark inside of a circle. The text "Body" is in green and the text "Check" is in blue.
Image /page/6/Picture/3 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in a bold, blue font. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, lighter blue font. The logo is clean and modern, with a focus on simplicity and clarity.
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image contains the logo for "Body Check". The logo consists of a green and blue check mark on the left side of the image. The words "Body Check" are on the right side of the image, with "Body" in green and "Check" in blue.
Image /page/7/Picture/3 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon shape on the left, with the word "Innolitics" in bold, blue letters to the right of the hexagon. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, blue font.
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image contains the logo for "Body Check". The logo consists of a green and blue check mark on the left side of the image. The words "Body Check" are on the right side of the image, with "Body" in green and "Check" in blue.
Image /page/8/Picture/3 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in a bold, blue font. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, lighter blue font. The logo is clean and modern, with a focus on simplicity and clarity.
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo for "Body Check". The logo consists of a green and blue check mark on the left, followed by the words "Body Check" in green and blue. The word "Body" is in green, and the word "Check" is in blue.
Image /page/9/Picture/3 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon-like shape on the left, with the word "Innolitics" in bold, blue letters to the right of the shape. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, lighter blue font.
{10}------------------------------------------------
Image /page/10/Picture/0 description: The image shows the logo for Body Check. The logo consists of a green circle with a white checkmark inside, and the words "Body Check" in green and blue. The word "Body" is in green, and the word "Check" is in blue.
7. PERFORMANCE DATA
7.1. 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, "Guidance for the Content of Premarket Submissions for Device Software Functions".
The software verification and validation testing verified that the design requirements were successfully met. The Intended use and user needs were successfully validated.
As the intended use, functionality and performance of CT Cardiomegaly and predicate device are equivalent, the result of the performance testing is evidence that CT Cardiomegaly performs in an equivalent manner to the EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System.
7.2. Performance Assessment
A technical performance assessment was performed for CT Cardiomegaly to validate the accuracy for both linear-based CTR (i.e. Cardiothoracic Index) and area-based CTR (i.e., Heart to Chest Area Ratio) against the measurements provided by human readers using manual segmentation tools (i.e., reference standard).
Image /page/10/Picture/10 description: The image contains the logo for Innolitics SaMD Simplified. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in large, bold, blue font. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, lighter blue font. The overall design is clean and professional.
{11}------------------------------------------------
Image /page/11/Picture/0 description: The image contains the logo for "Body Check". The logo consists of a green circle with a check mark that is partially green and partially dark blue. To the right of the logo is the text "Body Check", with the word "Body" in green and the word "Check" in dark blue.
Reference Standard 7.2.1.
The reference standard for this assessment was established by three board-certified radiologists. Each radiologist provided a segmentation for the heart and the inner chest independently from the other radiologists. Measurement among the three radiologists was very high for all measured values.
7.2.2. Training and Testing Dataset
Data was sampled from a database curated by the University of Alabama at Birmingham of over 8,000 imaging studies from over 300 unique imaging sites. Data for training (1600 cases) and testing (275 cases) were sampled from this database based on exclusion criteria. Data was also selected to ensure no site was shared by training and testing cohorts.
The testing dataset included 275 unique patients cases from sites across 12 U.S. states. Subgroups and confounders present in the dataset included patient demographics (age, sex, race, ethnicity), confounding conditions, and imaging characteristics (protocol, slice thickness, scanner manufacturer, presence or absence of contrast, kVp). Images were representative of numerous scanner manufacturers (e.g., GE, Siemens, Philips, Canon Medical Systems, Toshiba, Siemens Healthineers, United Imaging Healthcare) and imaging protocols (i.e., abdominal CT, chest CT, PET/CT and high-resolution chest CT). The data consisted of 142 male and 133 female patients of different ethnicities aged 18-96 (median 62) years. Detailed subgroup analysis are reported in the labeling.
7.2.3. Primary Endpoints
Primary endpoints involved calculating the difference between the average measurement of the human readers and the subject device's measurement. The experimental unit was per patient. Clinical performance testing showed strong agreement with physician-derived measurements, with an average difference less than 0.01. Additional analysis including the Bland Altman plot and Limits of agreement were also conducted and reported in labeling. The 95% limits of agreement were [-0.033, 0.035] and [-0.028, 0.035] for Cardiothoracic Ratio and Heart to Chest Area Ratio, respectively.
| Measurement | Mean AbsoluteDifference [95% CI] | Mean Difference[95% CI] | Mean DifferenceTarget | Standard Deviationof Differences | Result |
|---|---|---|---|---|---|
| CardiothoracicRatio | 0.009 [0.007, 0.011] | 0.0012 [-0.0008,0.0033] | < 0.0100 | 0.0172 | Pass |
| Heart to Chest AreaRatio | 0.009 [0.007, 0.010] | 0.0036 [0.0017,0.0055] | < 0.0100 | 0.0161 | Pass |
Image /page/11/Picture/10 description: The image contains the logo for Innolitics SaMD Simplified. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in large, bold, blue font. Below "Innolitics" is the text "SaMD Simplified" in a smaller, blue font. The logo is clean and professional, with a focus on simplicity and clarity.
{12}------------------------------------------------
Image /page/12/Picture/0 description: The image shows the logo for Body Check. The logo consists of a green circle with a check mark inside, with the bottom half of the check mark being dark blue. To the right of the circle is the text "Body Check", with "Body" in green and "Check" in dark blue.
7.2.4. Secondary Endpoints
Secondary endpoints of the clinical performance assessment included the precision of selecting the slice where the heart area is the largest (key heart slice detection) and the accuracy of heart and inner chest segmentations.
Key Heart Slice Detection
| Value | Mean Difference [95% CI] | Mean Difference Target | Standard Deviation of Differences | Result |
|---|---|---|---|---|
| Key Slice Position | 0.46 mm [-0.49, 1.41] | < 5 mm | 0.49 mm | Pass |
Segmentation Comparison
| Anatomical Structure | Observed Dice [95% CI] |
|---|---|
| Heart | 0.95 [0.950, 0.956] |
| Inner Chest | 0.98 [0.982, 0.984] |
8. CONCLUSION
CT Cardiomegaly is substantially equivalent to the identified predicate device EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System (K212624). Specifically, CT Cardiomegaly has similar indications for use and technological characteristics compared to the previously cleared predicate device. The minor differences in the technological characteristics of CT Cardiomegaly and EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System (e.g., including the identification of target anatomical structures and modalities supported) do not raise new issues of safety or effectiveness. The performance tests have been completed and successfully support the device performance. Therefore, CT Cardiomegaly is substantially equivalent to the predicate device.
Image /page/12/Picture/10 description: The image contains the logo for Innolitics. The logo consists of a blue hexagon-like shape on the left, followed by the word "Innolitics" in bold, blue letters. Below "Innolitics" is the phrase "SaMD Simplified" in a smaller, blue font.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).