(224 days)
Not Found
Yes
The document explicitly states the inclusion of "Al segmentation deep learning algorithms" and "artificial intelligence (AI) segmentation models" which consist of "convolutional neural networks".
No.
The device is a software product that helps manage and monitor radiation therapy treatment plans and sessions, and generate and modify radiation therapy treatment plans, but does not directly deliver therapy or alleviate disease.
No
The device is indicated for use in managing and monitoring radiation therapy treatment plans and sessions, and generating and modifying radiation therapy treatment plans, not for diagnosing a disease or condition.
Yes
The device description explicitly states "Ethos Treatment Planning is a standalone software device". While it interacts with imaging modalities and is used in conjunction with other systems, the core device being described and submitted for 510(k) appears to be the software itself.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVD Definition: In Vitro Diagnostics are devices intended for use in the collection, preparation, and examination of specimens taken from the human body (such as blood, urine, or tissue) to provide information for the diagnosis, treatment, or prevention of disease.
- Device Function: The description clearly states that this device is a software product used for managing and monitoring radiation therapy treatment plans and sessions and generating and modifying radiation therapy treatment plans. It operates on medical images (CBCT, CT) of the patient's anatomy.
- Lack of Specimen Analysis: There is no mention of the device analyzing any biological specimens taken from the patient. Its function is centered around planning and managing a medical treatment based on imaging data.
While the device uses AI for image segmentation, which is a form of analysis, this analysis is performed on medical images of the patient's body, not on in vitro specimens.
Therefore, based on the intended use and device description, this device falls under the category of medical devices used in the planning and delivery of radiation therapy, not In Vitro Diagnostics.
No
The clearance letter does not explicitly state that the FDA has reviewed and approved or cleared a PCCP for this specific device. The 'Control Plan Authorized (PCCP) and relevant text' section is marked "Not Found," indicating the absence of such information.
Intended Use / Indications for Use
Ethos Treatment Management is indicated for use in managing and monitoring radiation therapy treatment plans and sessions.
Ethos Treatment Planning is indicated for use in generating and modifying radiation therapy treatment plans.
Product codes
IYE, MUJ
Device Description
Ethos Treatment Management is a software product designed to help radiation therapy medical professionals manage treatments for patients with malignant or benign diseases for whom radiation therapy is indicated. It allows the physician to create and communicate radiation treatment intent (RT intent) to the treatment planner, review and approve candidate plans, and monitor treatment progress. It is intended to be used with a treatment planning system to treat or alleviate disease in humans by streamlining the treatment management and monitoring processes.
Ethos Treatment Planning is a standalone software device designed to generate and modify radiation therapy treatment plans and manage treatment sessions. The device supports the traditional and adapted treatments, in which the scheduled plan is adapted to the patient's anatomy at the time of treatment.
Mentions image processing
Not Found
Mentions AI, DNN, or ML
Organs are detected on the patient image via artificial intelligence (AI) segmentation models. These models consist of convolutional neural networks, the weights of which are static. They are not adapted during the operation of the product. That means, the models do not continuously learn and thus do not alter their behavior over time based on user input.
The AI models operate on image resolutions that are suitable for representation of the organs they were trained for. Patient images are re sampled before inference (running the detection network). After inference, the resulting label maps are sampled back onto the patient image grid.
Contouring performance undergoes rigorous evaluation through verification and validation processes. The verification process aims to identify eligible models for subsequent validation. This initial stage relies on quantitative metrics such as the DICE similarity coefficient.
Input Imaging Modality
CBCT, CT
Anatomical Site
full body, head and neck, thorax, abdomen, bowel, pelvis
Indicated Patient Age Range
Not Found
Intended User / Care Setting
radiation therapy medical professionals, physician, treatment planner, experts, including radiation oncologists, dosimetrists, and physicists from various healthcare facilities worldwide.
Description of the training set, sample size, data source, and annotation protocol
For the training datasets, a variety of subjects and scans were used according to the body site of interest. The overall total number of training scans used was 4769, while the total for testing scans was 1045. These scans consisted of the following body sites with the respective patient count (#, inclusive of training and testing subjects): full body (179), head and neck (1173), thorax (600), abdomen (527), bowel (507), and pelvis (1192).
The scans are obtained from different patient subgroups which are primarily comprised of those with treatment indications for cancers (assorted tumors, brain cancer, lung cancer, breast cancer, liver cancer, pancreatic cancer, stomach cancer, adrenal cancer, bladder cancer, prostate cancer, cervical cancer, vaginal cancer, uterus cancer, rectal cancer, anal cancer, and/or spinal cancer). Some scans came from post prostatectomy or post hysterectomy sourcing. Patient demographics from a large portion of the scans are anonymized, but the largest number and percentage proportionally of scans originated from patients in the United States.
Other confounding details in the images used to train and test models would include contrasting agents, catheters, radioactive seeds, compression devices, external devices (tracheostomy tubes), breast implants, teeth implants, and/or radiotherapy masks.
The scans are comprised of CBCT (734 training, 398 testing) and CT (4035 training, 647 testing) image types; these were obtained on a variety of scanner manufacturers and models, including systems from GE Medical Systems (553 total), Phillips (1194), Siemens (274), Varian Medical Systems (1973), and others. The patient position for most of the scans (~90%) was head first supine (HFS).
Ground truth annotations were established by human anatomy experts as part of the algorithm development following RTOG and DAHANCA clinical guidelines. A single set of contours was produced for each training image. These clinical experts have significant clinical experience in segmentation of CT imaging for the different disease sites covered by the AI models. To ensure accuracy, contour definitions available in contouring guidelines are established prior to contouring tasks.
The partitioning of training and test sets was done at the patient level, such that no scans from a patient could be used within both the training set and the test set.
Description of the test set, sample size, data source, and annotation protocol
For the training datasets, a variety of subjects and scans were used according to the body site of interest. The overall total number of training scans used was 4769, while the total for testing scans was 1045. These scans consisted of the following body sites with the respective patient count (#, inclusive of training and testing subjects): full body (179), head and neck (1173), thorax (600), abdomen (527), bowel (507), and pelvis (1192).
The scans are obtained from different patient subgroups which are primarily comprised of those with treatment indications for cancers (assorted tumors, brain cancer, lung cancer, breast cancer, liver cancer, pancreatic cancer, stomach cancer, adrenal cancer, bladder cancer, prostate cancer, cervical cancer, vaginal cancer, uterus cancer, rectal cancer, anal cancer, and/or spinal cancer). Some scans came from post prostatectomy or post hysterectomy sourcing. Patient demographics from a large portion of the scans are anonymized, but the largest number and percentage proportionally of scans originated from patients in the United States.
Other confounding details in the images used to train and test models would include contrasting agents, catheters, radioactive seeds, compression devices, external devices (tracheostomy tubes), breast implants, teeth implants, and/or radiotherapy masks.
The scans are comprised of CBCT (734 training, 398 testing) and CT (4035 training, 647 testing) image types; these were obtained on a variety of scanner manufacturers and models, including systems from GE Medical Systems (553 total), Phillips (1194), Siemens (274), Varian Medical Systems (1973), and others. The patient position for most of the scans (~90%) was head first supine (HFS).
Ground truth annotations were established by human anatomy experts as part of the algorithm development following RTOG and DAHANCA clinical guidelines. A single set of contours was produced for each training image. These clinical experts have significant clinical experience in segmentation of CT imaging for the different disease sites covered by the AI models. To ensure accuracy, contour definitions available in contouring guidelines are established prior to contouring tasks.
The partitioning of training and test sets was done at the patient level, such that no scans from a patient could be used within both the training set and the test set.
Summary of Performance Studies
Study Type: Design validation testing, Software Verification and Validation Testing, AI Model Validation.
Sample Size: Not specified for performance studies directly. Training dataset used 4769 scans and testing dataset used 1045 scans.
AUC: Not Mentioned.
MRMC: Not Mentioned.
Standalone Performance: Not Mentioned.
Key Results: Contouring performance undergoes rigorous evaluation through verification and validation processes. The verification process aims to identify eligible models for subsequent validation. This initial stage relies on quantitative metrics such as the DICE similarity coefficient. The DICE coefficient serves as a comparison benchmark against references published in the literature, especially when introducing a model for a new organ. In cases of model replacement, The validation process emulates the usage of the auto contouring solution in clinical practice. Experts, including radiation oncologists, dosimetrists, and physicists from various healthcare facilities worldwide, evaluated the quality of the contours across test sets to assess the need and the type of contour adjustments, which consequently gives an estimate of the time saved on contouring tasks. Models were only considered eligible for production if they consistently produced contours that needed minor or no adjustments in at least 80% of the test cases.
Design verification and design validation testing demonstrates that Ethos Treatment 3.0 and Ethos Treatment Planning 2.0 performs as intended and meets its essential performance.
Key Metrics
DICE similarity coefficient.
Models were only considered eligible for production if they consistently produced contours that needed minor or no adjustments in at least 80% of the test cases.
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.
0
April 30, 2024
Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA acronym and name on the right. The Department of Health & Human Services logo is a stylized depiction of a human figure, while the FDA acronym and name are written in blue, with the acronym in a square and the name in a sans-serif font.
Varian Medical Systems Inc. % Lynn Allman Sr. Director Regulatory Affairs Varian Medical Systems, Inc 3100 Hansen Way PALO ALTO, CA 94304
Re: K232923
Trade/Device Name: Ethos Treatment Management 3.0, Ethos Treatment Planning 2.0 Regulation Number: 21 CFR 892.5050 Regulation Name: Medical Charged-Particle Radiation Therapy System Regulatory Class: Class II Product Code: IYE, MUJ Dated: April 1, 2024 Received: September 20, 2023
Dear Lynn Allman:
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
2
Your device is also subject to, among other requirements, the Quality System (OS) 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.
Loca Weidner
Lora D. Weidner, Ph.D. Assistant Director Radiation Therapy Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
2
Indications for Use
Submission Number (if known)
Device Name
Ethos Treatment Management (3.0);
Ethos Treatment Planning (2.0)
Indications for Use (Describe)
Ethos Treatment Management is indicated for use in managing and monitoring radiation therapy treatment plans and sessions.
Ethos Treatment Planning is indicated for use in generating and modifying radiation therapy treatment plans.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
Image /page/3/Picture/0 description: The image shows three gray circles in a horizontal line. To the right of the circles is the text "K232923". The text is in a sans-serif font and is black. The background of the image is white.
Image /page/3/Picture/1 description: The image displays the logo for Varian, a Siemens Healthineers Company. The word "Varian" is written in a bold, sans-serif font, with each letter in uppercase except for the "a", which is lowercase. Below the logo, in a smaller font size, is the text "A Siemens Healthineers Company", indicating Varian's affiliation with Siemens Healthineers. The logo is simple and modern, with a focus on the company name and its connection to Siemens Healthineers.
Varian Medical Systems
3100 Hansen Way Palo Alto, CA 94304
650.493.4000 800.544.4636
varian.com
SUBMITTER CONTACT DETAILS l.
510(k) Summary
| Applicant Name | Varian Medical Systems, Inc. |
|---|---|
| Applicant Address | 3100 Hansen Way |
| Palo Alto, CA 94304 | |
| Applicant Contact Telephone | +1 (650) 424 5369 (phone) +1 (650) 646 9200 (fax) |
| Applicant Contact | Dr. Lynn Allman Sr. Director, Regulatory Affairs |
| Applicant Contact Email | submissions.support@varian.com |
| Date | 12 January 2024 |
DEVICE NAME II.
This is a bundled 510(k) for two devices: Ethos Treatment Management and Ethos Treatment Planning. The devices are submitted together to ensure that the shared scientific and regulatory considerations they raise are addressed within one review.
| Device Trade name: | Ethos Treatment Management, version 3.0 | Ethos Treatment Planning, version 2.0 |
|---|---|---|
| Common name: | Treatment plan and image management | |
| application | Treatment planning system | |
| Classification name: | Medical charged particle radiation therapy | |
| system | ||
| (21 CFR 892.5050) | Medical charged particle radiation therapy | |
| system | ||
| (21 CFR 892.5050) | ||
| Regulatory class: | Class II | Class II |
| Product code: | IYE | MUJ |
III. LEGALLY MARKETED PREDICATE DEVICES
| Predicate device: | |
|---|---|
| Ethos Treatment Management, version 2.1 | |
| (K212294) | Ethos Treatment Planning, version 1.1 |
| (K212294) |
4
Image /page/4/Picture/0 description: The image shows the logo for Varian, a Siemens Healthineers Company. The word "varian" is written in a bold, sans-serif font. Below the word "varian" is the text "A Siemens Healthineers Company" in a smaller, sans-serif font. The logo is in grayscale.
IV. DEVICE DESCRIPTION SUMMARY
| Device Description: | Ethos Treatment Management is a software product designed to help radiation therapy medical professionals manage treatments for patients with malignant or benign diseases for whom radiation therapy is indicated. It allows the physician to create and communicate radiation treatment intent (RT intent) to the treatment planner, review and approve candidate plans, and monitor treatment progress. It is intended to be used with a treatment planning system to treat or alleviate disease in humans by streamlining the treatment management and monitoring processes. | Ethos Treatment Planning is a standalone software device designed to generate and modify radiation therapy treatment plans and manage treatment sessions. The device supports the traditional and adapted treatments, in which the scheduled plan is adapted to the patient's anatomy at the time of treatment. |
|---|---|---|
| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
V. INTENDED USE AND INDICATIONS FOR USE
| Intended Use: | Ethos Treatment Management is used to
manage and monitor radiation therapy
treatment plans and sessions; it is intended to
be used with a treatment planning system.
(Same as predicate) | Ethos Treatment Planning is used to generate
and modify radiation therapy treatment plans.
(Same as predicate) |
|-------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------|
| Indications for
Use: | Ethos Treatment Management is indicated for
use in managing and monitoring treatment
plans and sessions.
(Same as predicate) | Ethos Treatment Planning is indicated for use in
generating and modifying radiation therapy
treatment plans.
(Same as predicate) |
TECHNOLOGICAL COMPARISON VI.
Ethos Treatment Management:
There are identical technological characteristics and features that apply to the subject device and predicate. Both the subject device and the predicate device provide tools for qualified medical professionals to do initial planning, review and approve candidate plans, and monitor ongoing treatments for patients to be treated with radiation therapy. The significant differences between the subject device and predicate device are the following:
- o High fidelity mode support
- . Al segmentation deep learning algorithms added to contouring
- Hypersight images supported as planning images
- . Handling of image only sessions
- . Ethos – ARIA Coexistence in ARIA connected mode
These modifications do not raise different questions of safety and effectiveness. The verification and validation demonstrate that the device is as safe and effective as the predicate.
5
Image /page/5/Picture/0 description: The image shows the logo for Varian, a Siemens Healthineers Company. The word "Varian" is in a bold, sans-serif font. Below the logo is the text "A Siemens Healthineers Company" in a smaller, sans-serif font. The logo is simple and modern.
Ethos Treatment Planning:
Both the new device and the predicate device perform treatment planning, provide tools for gesissionals to manage treatment sessions and adapt plans for patients to be treated with radiation therapy. A subset of features is different. The significant differences in design for Ethos Treatment Planning 2.0 when compared to the predicate are:
- Enhanced Intelligent Optimizer Engine (IOE)
- High Fidelity Mode on IOE
- New Beam Geometry Optimizer
- o Al segmentation – additional anatomical site support
- Enhancement of target propagation
- o Support HyperSight CBCT - direct CBCT dose calculation
These differences are all considered by Varian to be minor enhancements of the predicate. There are no changes in the principle of operation of the device. The verification demonstrate that the device is as safe and effective as the predicate.
VII. NON-CLINICAL AND/OR CILINICAL TESTS SUMMARY & CONCLUSIONS
The following performance data were provided in support of the substantial equivalence determination.
Ethos Treatment Management 3.0 and Ethos Treatment Planning 2.0 has undergone formal design validation testing. Design verification and design validation testing demonstrates that Ethos Treatment 3.0 and Ethos Treatment Planning 2.0 performs as intended and meets its essential performance. The subject device is considered to have a "major" level of concern, since a failure or latent flaw in the software could directly result in serious injury or death to the patient or operator.
Software Verification and Validation Testing
Software design verification and design vas performed according to the FDA Quality System Regulation (21 CFR §820), ISO 13485 Quality Management System Standard, ISO 14971 Risk Management Standard, and IEC 62304 Software Life Cycle Process standard. Test results demonstrate conformance to applicable requirements specifications and assure hazard safeguards function properly. Software design validation testing was conducted, and documentation is provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (June 2023).
No animal studies or clinical tests have been included in this submission.
Al Model Validation
The following are details on the validation charatseristics for the Al models:
| Validation Characteristic | As applied in the Subject Device: |
|---|---|
| Characterization of Model | |
| Performance | Organs are detected on the patient image via artificial intelligence |
| (AI) segmentation models. These models consist of convolutional | |
| neural networks, the weights of which are static. They are not | |
| adapted during the operation of the product. That means, the | |
| models do not continuously learn and thus do not alter their | |
| behavior over time based on user input. | |
| The AI models operate on image resolutions that are suitable for | |
| representation of the organs they were trained for. Patient images | |
| are re sampled before inference (running the detection network). | |
| After inference, the resulting label maps are sampled back onto the | |
| patient image grid. | |
| Contouring performance undergoes rigorous evaluation through | |
| verification and validation processes. The verification process aims | |
| to identify eligible models for subsequent validation. This initial | |
| stage relies on quantitative metrics such as the DICE similarity | |
| coefficient. The DICE coefficient serves as a comparison benchmark | |
| against references published in the literature, especially when | |
| introducing a model for a new organ. In cases of model replacement, |
|
| | The validation process emulates the usage of the auto contouring
solution in clinical practice. Experts, including radiation oncologists,
dosimetrists, and physicists from various healthcare facilities
worldwide, evaluated the quality of the contours across test sets to
assess the need and the type of contour adjustments, which
consequently gives an estimate of the time saved on contouring
tasks. Models were only considered eligible for production if they
consistently produced contours that needed minor or no
adjustments in at least 80% of the test cases. |
| Number of Patients and
Samples in Dataset | For the training datasets, a variety of subjects and scans were used
according to the body site of interest. The overall total number of
training scans used was 4769, while the total for testing scans was
1045. These scans consisted of the following body sites with the
respective patient count (#, inclusive of training and testing
subjects): full body (179), head and neck (1173), thorax (600),
abdomen (527), bowel (507), and pelvis (1192). |
| Demographic, clinical
subgroups, and confounding
details | The scans are obtained from different patient subgroups which are
primarily comprised of those with treatment indications for cancers
(assorted tumors, brain cancer, lung cancer, breast cancer, liver
cancer, pancreatic cancer, stomach cancer, adrenal cancer, bladder
cancer, prostate cancer, cervical cancer, vaginal cancer, uterus
cancer, rectal cancer, anal cancer, and/or spinal cancer). Some scans
came from post prostatectomy or post hysterectomy sourcing.
Patient demographics from a large portion of the scans are
anonymized, but the largest number and percentage proportionally
of scans originated from patients in the United States.
Other confounding details in the images used to train and test
models would include contrasting agents, catheters, radioactive
seeds, compression devices, external devices (tracheostomy tubes),
breast implants, teeth implants, and/or radiotherapy masks. |
| | |
| Equipment and protocols
used to collect images | The scans are comprised of CBCT (734 training, 398 testing) and CT
(4035 training, 647 testing) image types; these were obtained on a
variety of scanner manufacturers and models, including systems
from GE Medical Systems (553 total), Phillips (1194), Siemens (274),
Varian Medical Systems (1973), and others. The patient position for
most of the scans (~90%) was head first supine (HFS). |
| Development of Ground
Truth | Ground truth annotations were established by human anatomy
experts as part of the algorithm development following RTOG and
DAHANCA clinical guidelines. A single set of contours was produced
for each training image. These clinical experts have significant
clinical experience in segmentation of CT imaging for the different
disease sites covered by the Al models. To ensure accuracy, contour
definitions available in contouring guidelines are established prior to
contouring tasks. |
| Data Independence for
Training and Test Sets | The partitioning of training and test sets was done at the patient
level, such that no scans from a patient could be used within both
the training set and the test set. |
6
7
CONCLUSIONS VIII.
The intended use and indications for use are the predicate device. The overall verification and validation testing for Ethos Treatment Management and Ethos Treatment Planning demonstrates that the device requirements and risk control measures perform as intended at a level similar to the predicate. The subject device and the predicate device have the same intended use, and the significant differences do not result in a new intended use. Varian, therefore, believes that Ethos Treatment Management 3.0 and Ethos Treatment Planning 2.1 are substantially equivalent to their respective predicate devices.