RT-Mind-AI
Device Facts
| Record ID | K213155 |
|---|---|
| Device Name | RT-Mind-AI |
| Applicant | Medmind Technology Co., Ltd. |
| Product Code | QKB · Radiology |
| Decision Date | Dec 15, 2021 |
| Decision | SESE |
| Submission Type | Traditional |
| Regulation | 21 CFR 892.2050 |
| Device Class | Class 2 |
| Attributes | AI/ML, Software as a Medical Device |
AI Performance
| Output | Algorithm | Acceptance | Observed | Dev DS | Dev Readers | Test DS | Test Readers |
|---|---|---|---|---|---|---|---|
| Organ-at-risk (OAR) segmentation | Deep learning | — | Non-inferiority in DSC compared to predicate device | — | — | Segmentation performance test using images from US healthcare institutions covering three major vendors (GE, Siemens, Philips). | 3 (licensed physicians) |
Indications for Use
It is used by radiation oncology department to segment (non-contrast) CT images, to generate needed information for treatment planning, treatment evaluation and treatment adaptation
Device Story
RT-Mind-AI is standalone software for radiation oncology departments; inputs non-contrast CT images. Uses deep learning to automatically contour organs-at-risk (OAR) in head/neck, thorax, abdomen, and pelvis. Features include desktop/web-based automatic segmentation, manual adjustment tools, preset templates, and DICOM transmission. Clinicians review and edit contours to assist in radiation therapy treatment planning, evaluation, and adaptation. Benefits include automated, accurate contouring to streamline clinical workflows.
Clinical Evidence
No clinical data. Bench testing only. Segmentation accuracy evaluated using DICE similarity coefficients (DSC) on datasets from US healthcare institutions covering GE, Siemens, and Philips scanners. Ground truth established by consensus of at least three licensed physicians. Results showed non-inferiority of the proposed device compared to the predicate device for shared organs, and non-inferiority of additional organs compared to the device's own baseline performance.
Technological Characteristics
Standalone software; Windows-based; server-deployed. Uses deep learning algorithms for automated image segmentation. Compatible with non-contrast CT images (DICOM 3.0 compliant). No specific hardware requirements; supports LAN-based web and desktop access.
Indications for Use
Indicated for adults (>21 years) in radiation oncology departments for segmentation of non-contrast CT images to support treatment planning, evaluation, and adaptation.
Regulatory Classification
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.
Special Controls
*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).
Predicate Devices
- AccuContour™ (K191928)
Submission Summary (Full Text)
{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.
MedMind Technology Co., Ltd. % Diana Hong General Manager Mid-Link Consulting Co., Ltd. P.O. Box 120-119 Shanghai. 200120 CHINA
Re: K213155
Trade/Device Name: RT-Mind-AI Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QKB Dated: September 18, 2021 Received: September 28, 2021
Dear Diana Hong:
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
{1}------------------------------------------------
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 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 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,
Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration
# Indications for Use
510(k) Number (if known)
K213155
Device Name RT-Mind-AI
Indications for Use (Describe)
It is used by radiation oncology department to segment (non-contrast) CT images, to generate needed information for treatment planning, treatment evaluation and treatment adaptation
| Type of Use (Select one or both, as applicable) | |
|---------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------|
| <div><span style="font-family: Arial, sans-serif;"> </span>Prescription Use (Part 21 CFR 801 Subpart D)</div> | <div><span style="font-family: Arial, sans-serif;"> </span>Over-The-Counter Use (21 CFR 801 Subpart C)</div> |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
***DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.***
The burden time for this collection of information is estimated to average 79 hours per response, including the
time to review instructions, search existing data sources, gather and maintain the data needed and complete
and review the collection of information. Send comments regarding this burden estimate or any other aspect
of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
*PRAStaff@fda.hhs.gov*
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of
information unless it displays a currently valid OMB number."
{3}------------------------------------------------
# 510(k) Summary
This 510(k) Summary is being submitted in accordance with requirements of Title 21, CFR Section 807.92.
The assigned 510(k) Number: K213155
- 1. Date of Preparation: 12/08/2021
- 2. Sponsor Identification
### MedMind Technology Co., Ltd.
A502-503, Techart Plaza, No.30, Xueyuan Road, Haidian District, Beijing, 100083, China.
Establishment Registration Number: Not registered yet.
Contact Person: Shaobin Wang Position: Chief Executive Officer Tel: +86-10-58352266 Email: wangshaobin@medicalmind.cn
- 3. Designated Submission Correspondent
Ms. Diana Hong (Primary Contact Person) Ms. Jing Cheng (Alternative Contact Person)
### Mid-Link Consulting Co., Ltd
P.O. Box 120-119, Shanghai, 200120, China
Tel: +86-21-22815850 Fax: 360-925-3199 Email: info@mid-link.net
{4}------------------------------------------------
#### 4. Identification of Proposed Device
Trade Name: RT-Mind-AI Common Name: Medical Imaging Software
### Regulatory Information
Classification Name: Medical Image Management and Processing System Classification: II; Product Code: QKB; Regulation Number: 21CFR 892.2050 Review Panel: Radiology;
### Indication for Use:
It is used by radiation oncology department to segment (non-contrast) CT images, to generate needed information for treatment planning, treatment evaluation and treatment adaptation
### Device Description
The proposed device, RT-Mind-AI, is a standalone software which used by radiation oncology department to segment (non-contrast) CT images, to generate needed information for treatment planning. treatment evaluation and treatment adaptation.
The proposed device has four main function:
- 1) Deep learning contouring:
- ♪ Automatic segment on desktop: it can automatically contour the organ-at-risk (ORA), including Head and Neck, thorax and abdominal and pelvic.
- Automatic segment on the Web: it can realize automatic contouring the OAR on the web and A sending to the specified network node in a local area network (LAN). Note: only the administrator account and operator accounts can carry out the automatic segment on the Web.
- Manual segment: Adjust the segment result after automatic segment. 2)
It also has the following general functions:
- A Preset ROIs
- > Preset templates
- > Transmit DICOM data:
- > Desktop patient management
- > Review images;
- A ROI management;
- > Web-based patient management
{5}------------------------------------------------
- A Open and save of files.
- 5. Identification of Predicate Device
510(k) Number: K191928 Product Name: AccuContour™
#### Non-Clinical Test Conclusion 6.
The proposed device can contour additional OARs than the predicate device, including:
- A Head&Neck: 1) External Auditory Meatus L; 2) External Auditory Meatus R; 3) Middle Ear L-include mastoid; 4) Midle Ear R-include mastoid; 5) Body
- > Abdominal &Pelvic: 1) Spleen: 2) Intestinal Tube; 3) Peritoneal Cavity; 4) Femoral Head Neck L; 5) Femoral Head Neck R; 6) Body
- > Thorax: 1) Humeral Head L; 2) Humeral Head R; 3) Breast L; 4) Breast R; 5) Body
For the same segment organs between proposed device and predicate device, the segmentation performance test was performed on proposed device and predicate device to evaluate the automated segmentation accuracy. The involved images generated in healthcare institutions in US using scanner models available in US covering three major vendors. The three major vendors were GE, Siemens and Philips. For each body parts, all intended organs were included in images. Ground truthing of each image was generated from the consensus of at least three licensed physicians. DICE similarity coefficients (DSC) was used for evaluation. DSC values were calculated on two sets of images for test group and control group, respectively. According to the results, it could be concluded that the DSC of proposed device was non-inferiority compared with that of the predicate device.
For the additional segment organs of the proposed device than predicate device, the automatic and manual segmentation was performed on proposed device to evaluate the automated segmentation accuracy. The manual segmentation was generated from the consensus of at least three licensed physicians. The involved images generated in healthcare institutions in US using scanner models available in US covering three major vendors. The three major vendors were GE, Siemens and Philips. For each body parts, all intended organs were included in images. DSC values were calculated. The average DSC of additional segment organs was compared to the average DSC of other segment organs. According to the results, it could be concluded that the DSC of additional segment organs of proposed device was non-inferiority compared with that of other segment organs of proposed device
#### 7. Clinical Test Conclusion
No clinical study is included in this submission.
{6}------------------------------------------------
#### 8. Summary of Technological Characteristics
| ITEM | Proposed Device | Predicate Device<br>K191928 | Remark |
|------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------|
| Product Code | QKB | QKB | Same |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Same |
| Class | II | II | Same |
| Indication for Use | It is used by radiation oncology<br>department to segment<br>(non-contrast) CT images, to<br>generate needed information for<br>treatment planning, treatment<br>evaluation and treatment<br>adaptation | It is used by radiation oncology<br>department to register<br>multimodality images and segment<br>(non-contrast) CT images, to<br>generate needed information for<br>treatment planning, treatment<br>evaluation and treatment<br>adaptation. | Different |
| Label/labeling | Conform with 21CFR Part 801 | Conform with 21CFR Part 801 | Same |
| Operation System | Windows | Windows | Same |
| Segmentation Features | | | |
| Algorithm | Deep Learning | Deep Learning | Same |
| Segmentation<br>of<br>Organ at Risk in the<br>Anatomic Regions | Head & Neck, Thorax, Abdomen<br>&Pelvis | Head & Neck, Thorax, Abdomen<br>&Pelvis | Same |
| Compatible<br>Modality | Non-Contrast CT | Non-Contrast CT | Same |
| Compatible Scanner<br>Models | No Limitation on scanner model,<br>DICOM 3.0 compliance required | No Limitation on scanner model,<br>DICOM 3.0 compliance required | Same |
| Compatible<br>Treatment Planning<br>System | No limitation on TPS model,<br>DICOM 3.0 compliance required | No limitation on TPS model,<br>DICOM 3.0 compliance required | Same |
| Target Population | Adults Only (greater than 21 years<br>of age) | Any patient type for whom<br>Relevant multimodality images<br>and segment (noncontrast) CT<br>images are available. | Different |
| Clinical condition<br>the device is<br>intended to<br>diagnose, treat or<br>manage | Limited to patients previously<br>selected for Radiation Therapy.<br>However, RT-Mind-AI can be used<br>for treatment evaluation and<br>treatment adaptation. | Limited to patients previously<br>selected for Radiation Therapy.<br>However, AccuContour can be<br>used for treatment evaluation and<br>treatment adaptation. | Same |
| Software<br>Architecture | Server based | Cloud and/or Server based | Different |
| Deployment<br>Feature | Server | Cloud Deployment and Server | Different |
| Automated<br>workflow | RT-Mind-AI<br>automatically<br>processes input image data | AccuContour<br>automatically<br>processes input image data | Same |
| Contour<br>visualization<br>and<br>editing feature | RT-Mind-AI provides basic result<br>preview of automatic segmentation<br>results. Manual segment is<br>possible. | AccuContour provides basic result<br>preview of automatic segmentation<br>results. Manual segment is<br>possible. | Same |
| Segmentation<br>Performance | The segmentation performance<br>was validated using datasets from<br>the USA using three major vendors<br>(GE, Siemens and Phillips). The<br>segmentation accuracy is evaluated<br>using DICE coefficient. | The segmentation performance<br>was validated using datasets from<br>China and the USA using three<br>major vendors (GE, Siemens and<br>Phillips). The segmentation<br>accuracy is evaluated using DICE<br>coefficient. | Different |
| User<br>Interface<br>Results Preview<br>(Confirmation) | Basic result preview of automatic<br>segmentation results. Manual<br>segment is possible. | Basic result preview of automatic<br>segmentation results. Manual<br>segment is possible. | Same |
| User<br>Interface<br>Configuration | Configuration menu | Configuration menu | Same |
| Human Factors | Design to be used by trained<br>clinicians. | Design to be used by trained<br>clinicians. | Same |
| Contraindications | None | None | Same |
## Table 1 Comparison of Technology Characteristics
{7}------------------------------------------------
Different - Indication for Use
The Indication for Use of the proposed device is different from that of the predicate device, because the predicate device contains registration and segmentation function, but the proposed device only contains segmentation function. The indication for use of the proposed device is within the range of that of predicate device, therefore, the proposed device will not have new adverse effect.
In addition, the segmentation performance test has been conducted on the proposed device and predicate device. And the test result show that the DSC of proposed device was non-inferiority compared with that of the predicate device
Therefore, the proposed device will not have new adverse effect.
### Different - Target Population
The target population is different from that of the predicate device. However, the target population range of the proposed device is within that of the predicate device. In addition, the segmentation performance
{8}------------------------------------------------
test has been conducted on the proposed device and predicate device. And the test result show that the DSC of proposed device was non-inferiority compared with that of the predicate device, the proposed device will not have new adverse effect.
### Different - Software Architecture
The software architecture of the proposed device is different from that of the predicate device. However, the software architecture used in proposed device is within the range of that of the predicate device. Therefore, the proposed device will not have new adverse effect.
### Different - Deployment Feature
The deployment feature of the proposed device is different from that of the predicate device. However, the deployment feature used in proposed device is within the range of that of the predicate device. Therefore, the proposed device will not have new adverse effect.
### Different - Segmentation Performance
The datasets used in segmentation performance test for the proposed device is different from that of the predicate device. However, the datasets used in segmentation performance test for the proposed device is from the USA. Therefore, the proposed device will not have new adverse effect.
#### 9. Substantially Equivalent (SE) Conclusion
The conclusions drawn from the nonclinical tests demonstrate that the proposed subject device is as safe, as effective, and performs as well as the legally marketed predicate device K191928.
