Who is the manufacturer of AVIEW RT ACS?

Coreline Soft Co., Ltd. filed the 510(k) submission for AVIEW RT ACS (K220408).

What is the FDA product code for AVIEW RT ACS?

QKB. It is classified under 21 CFR 892.2050 as a Class 2 device in the Radiology panel.

What is the regulatory pathway for AVIEW RT ACS?

510(k) clearance (submission type: Traditional).

Does AVIEW RT ACS use AI or machine learning?

Yes. AVIEW RT ACS (K220408) is flagged as an AI/ML-enabled medical device in the FDA's AI/ML device list.

Who can help prepare an FDA 510(k) submission like AVIEW RT ACS?

Innolitics — a medical-device software consultancy — provides regulatory and engineering support for FDA 510(k) submissions. See https://innolitics.com/services/510ks/ or contact https://innolitics.com/contact.

Can an AI/ML device like AVIEW RT ACS get a guaranteed FDA 510(k) clearance?

Yes. Innolitics offers a guaranteed FDA 510(k) clearance engagement for AI/ML Software as a Medical Device — combining engineering and regulatory execution under one agreement with a guaranteed clearance outcome. Eligibility: the device must be an AI/ML Software as a Medical Device (SaMD), and its performance must meet the criteria Innolitics determines during an initial regulatory strategy engagement to be necessary for FDA clearance. See https://innolitics.com/services/end-to-end-samd/ or contact https://innolitics.com/contact.

AVIEW RT ACS

K220408 · Coreline Soft Co., Ltd. · QKB · Nov 10, 2022 · Radiology

Device Facts

Record ID	K220408
Device Name	AVIEW RT ACS
Applicant	Coreline Soft Co., Ltd.
Product Code	QKB · Radiology
Decision Date	Nov 10, 2022
Decision	SESE
Submission Type	Traditional
Regulation	21 CFR 892.2050
Device Class	Class 2
Attributes	AI/ML, Software as a Medical Device

Intended Use

AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates contours in RT-DICOM format from CT images which could be used as an initial contour for the clinicians to approve and edit by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

Device Story

AVIEW RT ACS is a software-based medical device for radiation oncology; it processes CT images to perform deep-learning-based auto-segmentation of organs-at-risk (OARs). The device receives CT images, applies rule-based pre-processing, and uses deep learning models to generate contours for Head & Neck, Breast, Abdomen, and Pelvis regions. Outputs are RT-DICOM structure sets. Used by clinicians in radiation oncology departments to generate initial contours for review, approval, and editing during treatment planning. The device facilitates efficient contouring workflows, potentially reducing manual delineation time and improving consistency in treatment planning, ultimately benefiting patients by supporting accurate radiation dose delivery.

Clinical Evidence

Bench testing only. No clinical studies were conducted. Performance was validated using 120 CT cases (Korean and U.S. populations) across four body parts. Accuracy was evaluated using Dice Similarity Coefficient (DSC) and 95% Hausdorff Distance (HD) compared to a gold standard generated by three radiation oncology experts. Results showed AVIEW RT ACS performance was comparable or superior to the predicate device across various vendors, slice thicknesses, and kernels.

Technological Characteristics

Standalone software for radiation therapy image processing. Uses deep learning for auto-segmentation and rule-based pre-processing. Inputs: CT images. Outputs: RT-DICOM structure sets. Connectivity: Receive/Send/Export DICOM data. Operating system: Windows. Software validation performed via unit and system testing.

Indications for Use

Indicated for radiation oncology departments or other professionals requiring segmented organ masks for treatment planning. Supports auto-segmentation of organs in Head & Neck, Breast, Abdomen, and Pelvis regions from CT images. Breast (lung, heart) validated with non-contrast/contrast CT; others (eyes, brain, mandible, kidney, liver, femur, bladder) validated with contrast CT only.

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

MIM-MRT Dosimetry (K182624)

Reference Devices

AccuContour (K191928)

Related Devices

K232928 — DeepContour (V1.0) · Wisdom Technologies., Inc. · May 7, 2024
K242745 — AI-Rad Companion Organs RT · Siemens Healthcare GmbH · Mar 27, 2025
K242994 — OncoStudio (OS-01) · Oncosoft. Co., Ltd. · Feb 24, 2025
K230082 — Auto Segmentation · Ge Medical Systems, LLC · May 4, 2023
K203610 — Automatic Anatomy Recognition (AAR) · Quantitative Radiology Solutions, LLC · Apr 20, 2021

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 FDA logo is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue. Coreline Soft Co., Ltd. % Hyeyi Park RA Manager 4,5F (Yeonnam-dong), 49, World Cup buk-ro-6-gil, Mapo-gu. Seoul. 03991 REPUBLIC OF KOREA November 10, 2022 # Re: K220408 Trade/Device Name: AVIEW RT ACS Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QKB Dated: October 7, 2022 Received: October 11, 2022 Dear Hyeyi Park: 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, # Julie Sullivan -S Julie Sullivan, Ph.D. Director DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health Enclosure {2}------------------------------------------------ # Indications for Use 510(k) Number (if known) K220408 Device Name AVIEW RT ACS ### Indications for Use (Describe) AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates contours in RT-DICOM format from CT images which could be used as an mittal contour for the clinicians to approve and edit by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed. - a. Deep learning contouring from four body parts (Head & Neck, Breast, Abdomen, and Pelvis) - b. Generates RT-DICOM structure of contoured organs - c. Rule-based auto pre-processing Receive/Send/Export medical images and DICOM data Note that the Breast (Both right and left lung, Heart) were validated with non-contrast CT. Head & Neck (Both right and left Eyes, Brain and Mandible), Abdomen (Both right and Liver), and Pelvis (Both right and left Femur and Bladder) were validated with Contrast CT only. 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}------------------------------------------------ # 510(k) Summary K220408 #### SUBMITTER 1 Coreline Soft Co., Ltd. 4,5F (Yeonnam-dong), 49 World Cup buk-ro 6-gil, Mapo-gu, Seoul, 03991, Republic of Korea. Phone: 82.2.517.7321 Fax: 82.2.571.7324 Contact Person: hyeyi. Park Date Prepared: 02.10.2022 #### 2 DEVICE Name of Device: AVIEW RT ACS Common or Usual Name: Medical Imaging Software Classification Name: Radiological Image Processing Software For Radiation Therapy (21CFR 892.2050) Regulatory Class: II Product Code: QKB #### PREDICATE DEVICE 3 MIM-MRT Dosimetry by MIM Software Inc. (K182624) Name of Device: MIM-MRT Dosimetry Common or Usual Name: Medical Imaging Software Classification Name: System, image processing, radiological (21CFR 892.2050) Regulatory Class: II Product Code: LLZ This predicate has not been subject to a design-related recall #### REFERENCE DEVICE 4 AccuContour™ by Xiamen Manteia Technology LTD. (K191928) Name of Device: AccuContour™ Common or Usual Name: Medical Imaging Software Classification Name: Radiological Image Processing Software For Radiation Therapy (21CFR 892.2050) Regulatory Class: II Product Code: QKB {4}------------------------------------------------ This reference device has not been subject to a design-related recall #### 5 DEVICE DESCRIPTION The AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates contours in RT-DICOM format from CT images. This software could be used by the radiation oncology department planning, or other professions where a segmented mask of organs is needed. - Deep learning contouring: it can automatically contour the organ-at-risk (OARs) from four body parts (Head ● & Neck, Breast, Abdomen, and Pelvis) - . Generates RT-DICOM structure of contoured organs - . Rule-based auto pre-processing Receive/Send/Export medical images and DICOM data #### INDICATIONS FOR USE 6 AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates contours in RT-DICOM format from CT images which could be used as an initial contour for the clinicians to approve and edit by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed. - a. Deep learning contouring from four body parts (Head & Neck, Breast, Abdomen, and Pelvis) - Generates RT-DICOM structure of contoured organs b. - c. Rule-based auto pre-processing Receive/Send/Export medical images and DICOM data Note that the Breast (Both right and left lung, Heart) were validated with non-contrast CT. Head & Neck (Both right and left Eyes, Brain, and Mandible), Abdomen (Both right and Liver), and Pelvis (Both right and left Femur and Bladder) were validated with Contrast CT only. {5}------------------------------------------------ ## COMPARISION OF TECHNOLOGICAL CHARACTERISTICS WITH 8 THE PREDICATE DEVCIE AVIEW RT ACS has the same intended use and the principle of operation and has similar features to the predicate devices. There might be slight differences in features and menu, but these differences between the predicate device and the proposed device are not so significant since they do not raise any new or potential safety risks to the user or patient and questions of safety or effectiveness. Based on the results of software validation and verification tests, we conclude that the proposed device is substantially equivalent to the predicate devices. | Characteristic | Subject Device | Primary Predicate Device | Reference Device | | |---------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------|-----------------------------------------------------------------------|--| | Device Name | AVIEW RT ACS | MIM-MRT Dosimetry | AccuContour | | | Classification Name | Radiological Image Processing Software For Radiation Therapy | Radiological Image Processing System | Radiological Image Processing Software For Radiation Therapy | | | Regulatory Number | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 | | | Product Code | QKB | LLZ | QKB | | | Review Panel | Radiology | Radiology | Radiology | | | 510k Number | - | K182624 | K191928 | | | Indications for use | AVIEW RT ACS | | | | | | AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates contours in RT-DICOM format from CT images which could be used as an initial contour for the clinicians to approve and edit by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed. a. Deep learning contouring from four body parts (Head & Neck, Breast, Abdomen, and Pelvis) | | | | | | b. Generates RT-DICOM structure of contoured organs c. Rule-based auto pre-processing Receive/Send/Export medical images and DICOM data Note that the Breast (Both right and left lung, Heart) were validated with non-contrast and | | | | | | contrast CT. Head & Neck (Both right and left Eyes, Brain and Mandible), Abdomen (Both right and left Kidney and Liver), and Pelvis (Both right and left Femur and Bladder) were validated with Contrast CT only. | | | | | | MIM-MRT Dosimetry | | | | | | MIM software is used by trained medical professionals as a tool to aid in evaluation and information management of digital medical images. The medical image modalities include, but are not limited to, CT, MRI, CR, DX, MG, US, SPECT, PET and XA as supported by ACR/NEMA DICOM 3.0. MIM assists in the following indications: | | | | | | • Receive, transmit, store, retrieve, display, print, and process medical images and DICOM objects. | | | | | | • Create, display and print reports from medical images. | | | | | | • Registration, fusion display, and review of medical images for diagnosis, treatment evaluation, and treatment planning. | | | | | | • Evaluation of cardiac left ventricular function and perfusion, including left ventricular enddiastolic volume, end-systolic volume, and ejection fraction. | | | | | | • Localization and definition of objects such as tumors and normal tissues in medical images. | | | | | | • Creation, transformation, and modification of contours for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow- | | | | {6}------------------------------------------------ | | up and management. • Quantitative and statistical analysis of PET/SPECT brain scans by comparing to other registered PET/SPECT brain scans. • Planning and evaluation of permanent implant brachytherapy procedures (not including radioactive microspheres). • Calculating absorbed radiation dose as a result of administering radionuclide. • When using device clinically, the user should only use FDA approved radiopharmaceuticals. If using with unapproved ones, this device should only be used for research purposes. | |---------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | | Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Images that are printed to film must be printed using an FDA-approved printer for the diagnosis of digital mammography images. Mammographic images must be viewed on a display system that has been cleared by the FDA for the diagnosis of digital mammography images. The software is not to be used for mammography CAD. | | | AccuContour It is used by radiation oncology department to register multimodality images and segment | | | (non-contrast) CT images, to generate needed information for treatment planning, treatment evaluation and treatment adaptation. | | | AVIEW RT ACS | | | The AVIEW RT ACS provides deep-learning-based auto-segmented organs and generates | | | contours in RT-DICOM format from CT images. This software could be used by the radiation oncology department for treatment planning, or other professions where a segmented mask | | | of organs is needed. | | | • Deep learning contouring: it can automatically contour the organ-at-risk (OARS) | | | from four body parts (Head & Neck, Breast, Abdomen, and Pelvis) | | | • Generates RT-DICOM structure of contoured organs | | | • Rule-based auto pre-processing | | | Receive/Send/Export medical images and DICOM data | | | MIM-MRT Dosimetry | | | MIM - MRT Dosimetry extends features of MIM SurePlan. It is designed for use in medical | | | imaging and operates on both Windows and Mac computer systems. MIM - MRT Dosimetry extends the functionality of the MIM - Y90 Dosimetry (K172218) software and utilizes | | | functionality of MIM -SPECTRA Quant (K180815). Both of these are predicates for this | | | submission. The following functions have been added to allow calculations of absorbed dose | | | as a result of administering a radionuclide. | | General Description | • Allows for quantification of planar images | | | • Allows for calculation of time-integrated activity coefficients | | | • Allows for voxel-based dose calculation of radionuclides | | | • Allows for correction of dose for tissue density | | | Accu Contour | | | The proposed device, AccuContourTM, is a standalone software which is used by radiation oncology department to register multimodality images and segment (non-contrast) CT | | | images, to generate needed information for treatment planning, treatment evaluation and | | | treatment adaptation. | | | The product has two image process functions: | | | (1) Deep learning contouring: it can automatically contour the organ-at-risk, including head | | | and neck, | | | thorax, abdomen and pelvis (for both male and female), | | | (2) Automatic Registration, and | | | (3) Manual Contour. It also has the following general functions: | | | Receive/Send/Export medical images and DICOM data | {7}------------------------------------------------ | | • Patient management. • Review of processed images. | | | |----------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | | Open and save of files. | | | | Operating System Image format | Windows DICOM | Windows and MAC system DICOM | Windows DICOM | | Data Communications | Receive, transmit, store, retrieve and process medical images and DICOM objects | Receive, transmit, store, retrieve, display, print, and process medical images and DICOM objects. | Receive, add/edit/delete, transmit, input/export, medical images and DICOM data | | Algorithm | Deep Learning | Atlas-based | Deep Learning | | Compatible Modality | CT Images | Non-Contrast CT | Non-Contrast CT | | Segmentation of Organ | Head & Neck, Breast, Abdomen, Pelvis | Head & Neck, Breast, Abdomen, Pelvis | Head & Neck, Thorax, Abdomen & Pelvis | | Automated workflow | Automatically processes input image data contour organs and DICOM sends generated RT Structure set | Creation, transformation, and modification of contours for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow-up and management | AccuContour automatically processes input image data | | Data anonymization | Replaces the patient's name and ID with user defined prefix and suffixes and IDs and strips the birth date, referring physician name, and any private DICOM tags that exist. | Replaces the patient's name and ID with randomized generic names and IDs and strips the birth date, referring physician name, and any private DICOM tags that exist. | No information publicly available. | | Target Population | Any patient type for whom scanned with CT modality images and segment CT images are available. | Any patient type for whom relevant modalities such as CT and MR, as supported by ACR/NEMA DICOM 3.0. | Any patient type for whom Relevant multimodality images and segment (non- contrast) CT images are available. | | Segmentation Performance | The segmentation performance was validated multi-race and multi-vendor using datasets from South Korea and the USA using four major vendors (GE, Siemens, Toshiba and Phillips). The segmentation accuracy is evaluated using DICE coefficient | Contour Evaluation: Atlas- based segmentation studies have shown the accuracy of multi-atlas segmentation with an overall average dice similarity index of 0.81 for the contours tested: right and left lung, trachea, heart, and esophagus | The segmentation performance was validated using datasets from China and the USA using three major vendors (GE, Siemens and Phillips). The segmentation accuracy is evaluated using DICE coefficient | {8}------------------------------------------------ #### PERFORMANCE DATA 9 # 9.1 Handware and software verification and Validation This Medical device is not new; therefore, a clinical study was not considered necessary prior to release. Additionally, there was no clinical testing required to support the medical device as the indications for use is equivalent to the predicate device. The substantial equivalence of the device is supported by the non-clinical testing Verification, validation, and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified device passed all of the tests based on pre-determined Pass/Fail criteria. - Unit Test - Conducting Unit Test using Google C++ Unit Test Framework on major software components identified by software development team. List of Unit Test includes Functional test condition for software component unit, Performance test condition, and part of algorithm analysis for image processing algorithm. - System Test - In accordance with the document 'integration Test Cases' discussed in advanced by software development team and test team, test is conducted by installing software with recommended system specification. Despite Test case recognized in advance was not in existence. New software error discovered by 'Exploratory Test' conducted by test team will be registered and managed as new test case after discussion between development team and test team. Discovered software error will be classified into 3 categories as severity and managed. - V Major defects, which are impacting the product's intended use and no workaround is available. - > Moderate defects, which are typically related to user-interface or general quality of product, while workaround is available. - く Minor defects, which aren't impacting the product's intended use. Not significant. Success standard of System Test is not finding 'Major', 'Moderate' defect. - Performance Test - - · DICOM Test Report - · DICOM Conformance Statement - · Thin Client Server Compatibility Test Report - Compare Standalone Performacne Test - > The purpose of this test is to compare and verify the AVIEW RT ACS performance and the performance of the predicate device. The test process involves generating a robust gold standard. Three radiation oncology physicians segmented the organs to be used for validation. There were 3 experts, all trained by the "The Korean Society for Radiation Oncology", board-certified by the "Ministry of Health and Welfare", with a range of 9-21 years of experience in radiotherapy to participate in this test. The experts were attending assistant professors (n=2), and professors (n=1) from three institutions. First, the 1 expert manually delineated the organs. Second, segmentation results generated by 1 expert are sequentially edited by 2 experts. In the editing process, the first expert makes corrections, and the result is received by another expert completes the gold standard by finalizing it. This process was performed by a panel of three radiation oncology physicians' experiences. And the results of auto-segmentation of gold-standard and AVIEW RT ACS and auto-segmentation of predicate device are analyzed and evaluated using {9}------------------------------------------------ DSC and 95% HD, respectively. The data set information used in the test is 120cases (each 60cases) including both Korean and U.S, Gender: F 70, M 50, Age: 20-89 years. The TCIA data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), the result can be obtained by performing generalization without performance difference according to ethnic - > Breast (Both right and left lung, Heart) were validated with non-contrast and contrast CT. - A Head & Neck(Both right and left Eyes, Brain and Mandible), Abdomen(Both right and left Kidney and Liver), and Pelvis(Both right and left Femur and Bladder) were validated with Contrast CT only. - > DSC and 95% HD(mm) for - ◆ Total DSC & HD analysis. | Table 1 DSC for each oragn | | | | | |----------------------------|------------------------|--------------------------|--------------------------|------------| | Part | Organ | AVIEW | Predicate device | Difference | | Head& Neck | Brain (25) | 0.97 ± 0.01(0.97, 0.98) | 0.96 ± 0.01 (0.96, 0.96) | 0.01 | | | Rt. Eye (25) | 0.79 ± 0.10 (0.75, 0.83) | 0.80 ± 0.06 (0.77, 0.82) | -0.01 | | | Lt. eye (25) | 0.72 ± 0.12 (0.67, 0.76) | 0.76 ± 0.12 (0.72, 0.81) | -0.04 | | | Mandible (25) | 0.90 ± 0.05 (0.89, 0.93) | 0.83 ± 0.07 (0.80, 0.86) | 0.07 | | Breast | Heart (32) | 0.94 ± 0.03 (0.93, 0.95) | 0.78 ± 1.20 (0.70, 8.56) | 0.16 | | | Rt. Lung (31) | 0.98 ± 0.01 (0.97, 0.98) | 0.96 ± 0.02 (0.95, 0.97) | 0.02 | | | Lt. Lung (31) | 0.97 ± 0.02 (0.96, 0.98) | 0.96 ± 0.03 (0.95, 0.97) | 0.01 | | Abdom en | Liver (26) | 0.96 ± 0.01 (0.96, 0.97) | 0.87 ± 0.06 (0.85, 0.90) | 0.09 | | | Rt. Kidney (26) | 0.90 ± 0.03 (0.89, 0.91) | 0.75 ± 0.18 (0.68, 0.82) | 0.15 | | | Lt. kidney (26) | 0.90 ± 0.05 (0.88, 0.92) | 0.79 ± 0.12 (0.75, 0.84) | 0.11 | | Pelvis | Bladder (35) | 0.88 ± 0.14 (0.84, 0.93) | 0.52 ± 0.26 (0.44, 0.60) | 0.36 | | | Rt. Femur head (37) | 0.87 ± 0.14 (0.83, 0.90) | 0.58 ± 0.11 (0.54, 0.61) | 0.29 | | | Lt. Femur head (37) | 0.86 ± 0.10 (0.83, 0.90) | 0.55 ± 0.11(0.51, 0.58) | 0.31 | Table 2. 95% HD (mm) for each oragn ● | Part | Organ | AVIEW | Predicate device | Difference | |---------------|-----------------|----------------------------|-------------------------------|------------| | Head& Neck | Brain (25) | 6.92 ± 20.46 (-1.1, 14.94) | 4.61 ± 2.17 (3.76, 5.46) | 2.31 | | | Rt. Eye (25) | 3.68 ± 1.50 (3.09, 4.27) | 4.38 ± 1.36 (3.85, 4.91) | -0.70 | | | Lt. eye (25) | 6.38 ± 11.11 (2.03, 10.74) | 7.74 ± 10.83 (3.50, 11.99) | -1.36 | | | Mandible (25) | 2.01 ± 1.23 (1.53, 2.49) | 24.00 ± 93.61 (-12.69, 60.70) | -21.99 | | Breast | Heart (32) | 6.19 ± 4.21 (4.73, 7.65) | 18.90 ± 5.09 (17.14, 20.67) | -12.71 | | | Rt. Lung (31) | 2.88 ± 1.67 (2.30, 3.47) | 7.03 ± 2.94 (6.00, 8.06) | -4.14 | | | Lt. Lung (31) | 4.97 ± 13.49 (0.22, 9.72) | 4.83 ± 6.21 (2.64, 7.02) | 0.14 | | Abdom en | Liver (26) | 7.17 ± 12.07 (2.54, 11.81) | 24.62 ± 15.16 (18.79, 30.44) | -17.44 | | | Rt. Kidney (26) | 6.84 ± 9.14 (3.33, 10.35) | 14.63 ± 13.07 (9.60, 19.65) | -7.79 | {10}------------------------------------------------ | | Lt. kidney (26) | $5.34 \pm 4.30$ (3.69, 6.99) | $15.18 \pm 10.71$ (11.06, 19.26) | -9.84 | |--------|------------------------|------------------------------------|-------------------------------------|--------| | Pelvis | Bladder (35) | $10.55 \pm 20.56$ (3.74, 17.36) | $30.48 \pm 22.76$ (22.94, 38.02) | -19.93 | | | Rt. Femur head (37) | $10.02 \pm 8.94$ (7.10, 12.93) | $43.65 \pm 30.38$ (33.72, 53.57) | -33.63 | | | Lt. Femur head (37) | $11.75 \pm 12.42$ (7.64, 15.86) | $46.14 \pm 24.84$ (37.91, 54.37) | -34.39 | DSC and 95% HD(mm) were obtained by race, vendors, slice thickness and kernel for sub-group analysis. | | | | | ◆ Dice Similarity Coefficient Comparison (DSC) | | | |--|--|--|--|------------------------------------------------|--|--| |--|--|--|--|------------------------------------------------|--|--| | | | | | | Table 3. DSC for Korean Population each organ. | | | |--|--|--|--|--|------------------------------------------------|--|--| |--|--|--|--|--|------------------------------------------------|--|--| | Part | Organ | AVIEW | Predicate device | Difference | |---------------|------------------------|--------------------------|--------------------------|------------| | Head& Neck | Brain (10) | 0.97 ± 0.01 (0.97, 0.98) | 0.96 ± 0.01 (0.95, 0.96) | 0.01 | | | Rt. Eye (10) | 0.81 ± 0.07 (0.76, 0.86) | 0.80 ± 0.07 (0.76, 0.84) | 0.01 | | | Lt. eye (10) | 0.77 ± 0.09 (0.71, 0.82) | 0.79 ± 0.06 (0.75, 0.83) | -0.02 | | | Mandible (10) | 0.90 ± 0.03 (0.89, 0.93) | 0.81 ± 0.09 (0.76, 0.87) | 0.09 | | Breast | Heart (21) | 0.95 ± 0.02 (0.94, 0.96) | 0.81 ± 0.10 (0.76, 0.85) | 0.14 | | | Rt. Lung (21) | 0.97 ± 0.01 (0.97, 0.98) | 0.96 ± 0.02 (0.95, 0.97) | 0.01 | | | Lt. Lung (21) | 0.96 ± 0.02 (0.96, 0.97) | 0.95 ± 0.03 (0.94, 0.97) | 0.01 | | Abdom en | Liver (10) | 0.95 ± 0.01 (0.94, 0.96) | 0.88 ± 0.08 (0.83, 0.93) | 0.07 | | | Rt. Kidney (10) | 0.89 ± 0.03 (0.87, 0.91) | 0.75 ± 0.24 (0.60, 0.90) | 0.14 | | | Lt. kidney (10) | 0.88 ± 0.06 (0.84, 0.92) | 0.80 ± 0.16 (0.70, 0.90) | 0.08 | | Pelvis | Bladder (17) | 0.92 ± 0.07 (0.89, 0.95) | 0.47 ± 0.27 (0.34, 0.59) | 0.45 | | | Rt. Femur head (19) | 0.88 ± 0.07 (0.84, 0.91) | 0.56 ± 0.11 (0.51, 0.61) | 0.32 | | | Lt. Femur head (19) | 0.87 ± 0.78 (0.84, 0.91) | 0.52 ± 0.13 (0.46, 0.58) | 0.35 | #### Table 4. DSC for U.S Population each organ. ● | Part | Organ | AVIEW | Predicate device | Difference | |------------|-----------------|---------------------------|--------------------------|------------| | Head& Neck | Brain (15) | 0.97 ± 0.01 (0.96, 0.98) | 0.96 ± 0.01 (0.96, 0.97) | 0.01 | | | Rt. Eye (15) | 0.78 ± 0.12 (0.72, 0.84) | 0.80 ± 0.06 (0.77, 0.83) | -0.02 | | | Lt. eye (15) | 0.68 ± 0.13 (0.62 ± 0.75) | 0.75 ± 0.14 (0.68, 0.82) | -0.07 | | | Mandible (15) | 0.91 ± 0.06 (0.88, 0.94) | 0.84 ± 0.06 (0.81, 0.87) | 0.07 | | Breast | Heart (11) | 0.93 ± 0.04 (0.90, 0.95) | 0.71 ± 0.09 (0.65, 0.76) | 0.22 | | | Rt. Lung (10) | 0.98 ± 0.0 (0.98, 0.99) | 0.96 ± 0.01 (0.96, 0.97) | 0.02 | | | Lt. Lung (10) | 0.97 ± 0.03 (0.95, 0.99) | 0.96 ± 0.03 (0.95, 0.98) | -0.01 | | Abdom en | Liver (16) | 0.97 ± 0.01 (0.96, 0.97) | 0.87 ± 0.05 (0.85, 0.90) | 1.0 | | | Rt. Kidney (16) | 0.91 ± 0.01 (0.91, 0.92) | 0.75 ± 0.14 (0.68, 0.82) | 0.16 | {11}------------------------------------------------ | | Lt. kidney (16) | 0.91 ± 0.02 (0.90, 0.92) | 0.79 ± 0.09 (0.74, 0.83) | 0.12 | |--------|------------------------|------------------------------|--------------------------|------| | Pelvis | Bladder (18) | 0.85 ± 0.19 (0.76, 0.94) | 0.58 ± 0.22 (0.48, 0.69) | 0.27 | | | Rt. Femur head (18) | 0.80 ± 0.12 (0.80,0.91) | 0.60 ± 0.10 (0.55,0.65) | 0.20 | | | Lt. Femur head (18) | 0.85 ± 0.13 (0.79 ± 0.91) | 0.57 ± 0.09 (0.53, 0.62) | 0.27 | � Hausdorff Distance Comparison (95% HD) | Part | Organ | AVIEW | Predicate device | Difference | |---------------|------------------------|-----------------------------|------------------------------|------------| | Head& Neck | Brain (10) | 13.19 ± 32.27 (6.81, 33.19) | 4.33 ± 1.33 (3.51, 5.16) | 8.86 | | | Rt. Eye (10) | 3.18 ± 1.01 (2.55, 3.81) | 4.14 ± 1.36 (3.30, 4.99) | -0.96 | | | Lt. eye (10) | 3.53 ± 1.40 (2.66, 4.40) | 5.22 ± 2.33 (3.78, 6.66) | -1.69 | | | Mandible (10) | 2.02 ± 0.53 (1.69, 2.35) | 6.15 ± 5.71 (2.61, 9.69) | -4.13 | | Breast | Heart (21) | 5.24 ± 2.57 (4.15, 6.34) | 18.16 ± 4.72 (16.14, 20.18) | -12.92 | | | Rt. Lung (21) | 3.41 ± 1.76 (2.66, 4.16) | 6.87 ± 3.19 (5.50, 8.23) | -3.46 | | | Lt. Lung (21) | 2.79 ± 0.52 (2.57, 3.01) | 3.24 ± 0.96 (2.83, 3.65) | -0.45 | | Abdom en | Liver (10) | 4.29 ± 1.50 (3.26, 5.22) | 21.14 ± 17.22 (10.46, 31.81) | -16.85 | | | Rt. Kidney (10) | 4.74 ± 1.77 (3.65, 5.84) | 15.24 ± 17.44 (4.43, 26.05) | -10.49 | | | Lt. kidney (10) | 6.24 ± 3.35 (2.30, 10.18) | 12.34 ± 10.54 (5.80, 18.87) | -6.10 | | Pelvis | Bladder (17) | 4.90 ± 6.03 (2.19, 7.61) | 33.96 ± 26.33 (22.13, 45.80) | -29.06 | | | Rt. Femur head (19) | 9.52 ± 6.64 (6.61, 12.43) | 41.34 ± 8.74 (37.51, 45.17) | -31.82 | | | Lt. Femur head (19) | 9.93 ± 6.83 (6.94, 12.92) | 49.19 ± 32.97 (34.73, 63.64) | -39.26 | #### Table 6. 95% HD (mm) for U.S Population each organ ● | Part | Organ | AVIEW | Predicate device | Difference | |---------------|-----------------|---------------------------------|------------------------------------|------------| | Head& Neck | Brain (15) | $2.74 \pm 1.09 (2.19, 3.29)$ | $4.79 \pm 2.62 (3.47, 6.12)$ | -2.05 | | | Rt. Eye (15) | $4.01 \pm 1.71 (3.15, 4.87)$ | $4.53 \pm 1.38 (3.84, 5.23)$ | -0.52 | | | Lt. eye (15) | $8.29 \pm 14.16 (1.12, 15.45)$ | $9.42 \pm 13.78 (2.45, 16.40)$ | -1.13 | | | Mandible (15) | $2.00 \pm 1.56 (1.21, 2.79)$ | $35.91 \pm 120.91 (-25.28, 97.10)$ | -33.91 | | Breast | Heart (11) | $8.00 \pm 6.03 (4.43, 11.56)$ | $20.31 \pm 5.71 (16.94, 23.69)$ | -12.31 | | | Rt. Lung (10) | $1.78 \pm 0.66 (1.36, 2.19)$ | $7.37 \pm 2.43 (5.86, 8.88)$ | -5.59 | | | Lt. Lung (10) | $9.56 \pm 23.90 (-5.25, 24.97)$ | $8.18 \pm 10.41 (1.72, 14.63)$ | 1.38 | | Abdomen | Liver (16) | $8.98 \pm 15.24 (1.51, 16.45)$ | $26.79 \pm 13.86 (20.00, 33.58)$ | -17.81 | | en | Rt. Kidney (16) | $8.15 \pm 11.51 (3.61, 5.94)$ | $14.25 \pm 10.08 (9.31, 19.19)$ | -6.10 | | | Lt. kidney (16) | $4.77 \pm 2.38 (3.61, 5.94)$ | $16.96 \pm 10.75 (11.69, 22.22)$ | -12.19 | {12}------------------------------------------------ | Pelvis | | | | | |--------|---------------------|---------------------------------|----------------------------------|--------| | | Bladder (18) | $17.37 \pm 28.73 (3.29, 31.44)$ | $27.01 \pm 18.47 (17.96, 36.06)$ | -9.64 | | | Rt. Femur head (18) | $10.57 \pm 11.16 (5.10, 16.04)$ | $46.09 \pm 43.22 (24.91, 67.27)$ | -35.52 | | | Lt. Femur head (18) | $13.91 \pm 16.86 (5.38, 22.44)$ | $42.52 \pm 8.23 (38.35, 46.68)$ | -28.61 | ◆ DSC & 95% HD (mm) Comparison by vendors, slice thickness and kernel | Part | Organ | AVIEW | Predicate device | Difference | |---------------|---------------------|--------------------------|--------------------------|------------| | Head& Neck | Brain (4) | 0.97 ± 0.01 (0.97, 0.98) | 0.96 ± 0.0 (0.96, 0.97) | 0.01 | | | Rt. Eye (4) | 0.85 ± 0.05 (0.80, 0.90) | 0.77 ± 0.05 (0.72, 0.82) | 0.08 | | | Lt. eye (4) | 0.78 ± 0.04 (0.71, 0.86) | 0.77 ± 0.05 (0.72, 0.82) | 0.01 | | | Mandible (4) | 0.91 ± 0.04 (0.87, 0.94) | 0.81 ± 0.13 (0.68, 0.94) | 0.10 | | Breast | Heart (9) | 0.94 ± 0.02 (0.93, 0.96) | 0.75 ± 0.10 (0.69, 0.82) | 0.19 | | | Rt. Lung (9) | 0.97 ± 0.01 (0.96, 0.98) | 0.95 ± 0.02 (0.94, 0.97) | -0.02 | | | Lt. Lung (9) | 0.96 ± 0.02 (0.95, 0.97) | 0.95 ± 0.02 (0.94, 0.97) | 0.01 | | Abdomen | Liver (16) | 0.96 ± 0.01 (0.96, 0.97) | 0.86 ± 0.06 (0.84, 0.89) | 0.10 | | | Rt. Kidney (16) | 0.91 ± 0.02 (0.90, 0.92) | 0.77 ± 0.12 (0.72, 0.83) | 0.14 | | | Lt. kidney (16) | 0.91 ± 0.03 (0.89, 0.92) | 0.78 ± 0.08 (0.74, 0.82) | 0.13 | | Pelvis | Bladder (18) | 0.90 ± 0.07 (0.87, 0.93) | 0.55 ± 0.27 (0.42, 0.67) | 0.35 | | | Rt. Femur head (19) | 0.90 ± 0.06 (0.87, 0.93) | 0.56 ± 0.10 (0.51, 0.60) | 0.34 | | | Lt. Femur head (19) | 0.89 ± 0.09 (0.85, 0.93) | 0.53 ± 0.13 (0.47, 0.58) | 0.36 | ● Table 7. DSC for organ by SIEMENS vendors. #### ● Table 8. 95% HD (mm) for each organ by SIEMENS vendors. | Part | Organ | AVIEW | Predicate device | Difference | |---------------|---------------------|----------------------------------|------------------------------|------------| | Head& Neck | Brain (4) | 28.16 ± 51.23 (-22.04, 78.36) | 3.28 ± 0.45 (2.84, 3.72) | 24.88 | | | Rt. Eye (4) | 2.77 ± 0.37 (2.42, 3.13) | 4.75 ± 1.50 (3.29, 6.22) | -1.98 | | | Lt. eye (4) | 3.26 ± 0.53 (2.74, 3.78) | 5.30 ± 2.18 (3.16 ± 7.44) | -2.04 | | | Mandible (4) | 1.91 ± 0.51 (1.42, 2.41) | 5.04 ± 4.11 (1.01, 9.08) | -3.13 | | Breast | Heart (9) | 5.92 ± 2.97 (3.98, 7.86) | 20.17 ± 3.52 (17.86, 22.47) | -14.25 | | | Rt. Lung (9) | 2.73 ± 0.61 (2.33, 3.13) | 7.30 ± 2.63 (5.58, 9.02) | -4.58 | | | Lt. Lung (9) | 2.97 ± 0.26 (2.80, 3.14) | 3.63 ± 1.25 (2.81, 4.45) | -0.65 | | Abdomen | Liver (16) | 9.10 ± 15.19 (1.66, 16.55) | 29.04 ± 14.54 (21.92, 36.16) | -19.93 | | | Rt. Kidney (16) | 8.40 ± 11.42 (2.81, 14.00) | 15.54 ± 9.83 (10.73, 20.36) | -7.14 | | | Lt. kidney (16) | 5.47 ± 3.29 (3.86, 7.08) | 18.94 ± 10.02 (14.03, 23.85) | -13.47 | | Pelvis | Bladder (18) | 7.04 ± 9.22 (2.65, 11.42) | 23.99 ± 17.93 (15.71, 32.27) | -16.95 | | | Rt. Femur head (19) | 8.01 ± 6.47 (5.10, 10.92) | 50.42 ± 3.59 (32.13, 68.71) | -42.41 | | | Lt. Femur head (19) | 8.57 ± 7.05 (5.40, 11.74) | 41.98 ± 9.27 (37.70, 46.27) | -33.41 | #### Table 9. DSC for each oragn by GE vendors ● | Part | Organ | AVIEW | Predicate device | Difference | |---------------|--------------|------------------------------|------------------------------|------------| | Head& Neck | Brain (2) | $0.96 \pm 0.01 (0.96, 0.97)$ | $0.97 \pm 0.0 (0.96, 0.97)$ | -0.01 | | | Rt. Eye (2) | $0.70 \pm 0.08 (0.64, 0.76)$ | $0.81 \pm 0.04 (0.78, 0.84)$ | -0.11 | | | Lt. eye (2) | $0.61 \pm 0.12 (0.53, 0.69)$ | $0.78 \pm 0.06 (0.74, 0.81)$ | -0.17 | | | Mandible (2) | $0.88 \pm 0.07 (0.83, 0.93)$ | $0.81 \pm 0.06 (0.65, 0.76)$ | 0.07 | {13}------------------------------------------------ | Breast | Heart (12) | 0.93 ± 0.04 (0.90, 0.95) | 0.71 ± 0.09 (0.65, 0.76) | 0.22 | |----------------|--------------------|--------------------------|--------------------------|------| | | Rt. Lung (12) | 0.98 ± 0.0 (0.98, 0.99) | 0.96 ± 0.01 (0.96, 0.97) | 0.02 | | | Lt. Lung (12) | 0.97±0.03 (0.95, 0.99) | 0.96 ± 0.03 (0.95, 0.98) | 0.01 | | | Abdomen | Liver (3) | 0.97 | 0.85 | | Rt. Kidney (3) | | 0.91 | 0.50 | 0.41 | | Lt. kidney (3) | | 0.89 | 0.88 | 0.01 | | Pelvis | Bladder (9) | 0.72 ± 0.31 (0.45, 1.0) | 0.52 ± 0.25 (0.31, 0.74) | 0.20 | | | Rt. Femur head (9) | 0.84 ± 0.13 (0.73, 0.95) | 0.60 ± 0.12 (0.49, 0.71) | 0.24 | | | Lt. Femur head (9) | 0.81±0.15 (0.68, 0.94) | 0.56±0.11 (0.46, 0.65) | 0.25 | ● Table 10. 95% HD (mm) for each oragn by GE vendors | Table 10. 95% HD (mm) for each oragn by GE vendors | | | | | |----------------------------------------------------|--------------------|-----------------------------|-------------------------------|------------| | Part | Organ | AVIEW | Predicate device | Difference | | Head& Neck | Brain (2) | 3.37 ± 1.12 (2.60, 4.14) | 4.01 ± 0.77 (3.48, 4.55) | -0.64 | | | Rt. Eye (2) | 5.18 ± 1.16 (4.37, 5.98) | 4.57 ± 1.37 (3.62, 5.52) | 0.61 | | | Lt. eye (2) | 5.63 ± 1.06 (4.89, 6.36) | 6.27 ± 3.77 (3.66, 8.89) | -0.64 | | | Mandible (2) | 2.64 ± 1.93 (1.30, 3.97) | 64.50 ± 165.04 (16.94, 23.69) | -61.86 | | Breast | Heart (12) | 8.00 ± 6.03 (4.43, 11.56) | 20.31 ± 5.71 (16.94, 23.69) | -12.31 | | | Rt. Lung (12) | 1.78 ± 0.66 (1.36, 2.19) | 7.37 ± 2.43 (5.86, 8.88) | -5.59 | | | Lt. Lung (12) | 9.56 ± 23.90 (-5.25, 24.37) | 8.18 ± 10.41 (1.72, 14.63) | -1.38 | | Abdomen | Liver (3) | 3.27 | 32.82 | -29.55 | | | Rt. Kidney (3) | 3.27 | 5.88 | -2.61 | | | Lt. kidney (3) | 3.27 | 6.55 | -3.28 | | Pelvis | Bladder (9) | 14.13 ± 11.93 (3.68, 24.59) | 36.66 ± 31.09 (9.40, 63.91) | -22.53 | | | Rt. Femur head (9) | 10.68 ± 9.53 (2.33, 19.04) | 32.41 ± 12.58 (21.93, 43.44) | -21.73 | | | Lt. Femur head (9) | 19.93 ± 22.34 (0.35, 39.51) | 44.61 ± 11.01 (34.96, 54.26) | -24.68 | #### ● Table 11. DSC for each organ by PHILIPS vendors | Part | Organ | AVIEW | Predicate device | Difference | |---------------|----------------|--------------------------|-----------------------------|------------| | Head& Neck | Brain (11) | 0.98 ± 0.01 (0.97, 0.98) | 0.96 ± 0.01 (0.95, 0.96) | 0.02 | | | Rt. Eye (11) | 0.83 ± 0.09 (0.77, 0.88) | 0.81 ± 0.07 (0.77, 0.86) | 0.02 | | | Lt. eye (11) | 0.74 ± 0.10 (0.69, 0.80) | 0.76 ± 0.17 (0.67, 0.85) | 0.02 | | | Mandible (11) | 0.93 ± 0.03 (0.91, 0.94) | 0.85 ± 0.06 (0.82, 0.89) | 0.08 | | Breast | Heart | N/A | N/A | | | | Rt. Lung | N/A | N/A | | | | Lt. Lung | N/A | N/A | | | Abdom en | Liver (6) | 0.95 ± 0.02 (0.94, 0.97) | 0.89 ± 0.08 (0.83, 0.95) | 0.06 | | | Rt. Kidney (6) | 0.88 ± 0.04 (0.85, 0.91) | 0.67 ± 0.30 (0.43, 0.90) | 0.21 | | | Lt. kidney (6) | 0.87 ± 0.07 (0.81, 0.93) | 0.75 ± 0.19 (0.59, 0.90) | 0.12 | | Pelvis | Bladder (4) | 0.88 ± 0.05 (0.83, 0.93) | 0.31 ± 0.18 (0.14, 0.48) | 0.57 | {14}------------------------------------------------ # core:line | Rt. Femur head (4) | $0.79 \pm 0.16$ (0.63, 0.94) | $0.64 \pm 0.15$ (0.50, 0.79) | 0.15 | |-----------------------|------------------------------|------------------------------|------| | Lt. Femur head (4) | $0.77 \pm 0.14$ (0.63, 0.90) | $0.63 \pm 0.13$ (0.50, 0.75) | 0.14 | #### Table 12. 95% HD (mm) for each organ by PHILIPS vendors. ● | Part | Organ | AVIEW | Predicate device | Difference | |---------------|-----------------------|-----------------------------------|------------------------------|------------| | Head& Neck | Brain (11) | 2.57 ± 0.85 (2.07, 3.08) | 5.30 ± 2.94 (3.56, 7.04) | -2.73 | | | Rt. Eye (11) | 3.11 ± 1.31 (2.34, 3.88) | 3.97 ± 1.43 (3.12, 4.81) | -0.86 | | | Lt. eye (11) | 8.80 ± 16.77 (-1.10,18.71) | 9.96 ± 16.13 (0.43, 19.49) | -1.16 | | | Mandible (11) | 1.72 ± 0.67 (1.33, 2.12) | 5.18 ± 5.27 (2.06, 8.29) | -3.46 | | Breast | Heart | N/A | N/A | | | | Rt. Lung | N/A | N/A | | | | Lt. Lung | N/A | N/A | | | Abdomen | Liver (6) | 4.18 ± 1.95 (2.62, 5.74) | 18.06 ± 15.21 (5.89, 30.24) | -13.88 | | en | Rt. Kidney (6) | 4.54 ± 1.78 (3.12, 5.96) | 17.55 ± 22.23 (-0.24, 35.34) | -13.01 | | | Lt. kidney (6) | 6.30 ± 7.42 (0.36, 12.24) | 11.38 ± 11.62 (2.07, 20.68) | -5.08 | | Pelvis | Bladder (4) | 8.72 ± 5.85 (2.10, 15.34) | 38.68 ± 8.49 (29.07, 48.29) | -29.96 | | | Rt. Femur head (4) | 14.44 ± 18.68 (-6.70, 35.58) | 24.39 ± 23.29 (-1.96, 50.75) | -9.95 | | | Lt. Femur head (4) | 54.37 ± 59.01 (-12.40, 121.14) | 37.60 ± 5.32 (31.58, 43.61) | 16.77 | #### ● Table 13. DSC for each organ by TOSHIBA vendors | Part | Organ | AVIEW | Predicate device | Difference | |---------------|-----------------------|--------------------------|--------------------------|------------| | Head& Neck | Brain (2) | 0.96 ± 0.02 (0.93, 0.99) | 0.95 ± 0.01 (0.94, 0.97) | 0.01 | | | Rt. Eye (2) | 0.86 ± 0.05 (0.78, 0.93) | 0.75 ± 0.03 (0.71, 0.79) | 0.11 | | | Lt. eye (2) | 0.84 ± 0.06 (0.76, 0.93) | 0.74 ± 0.03 (0.70, 0.77) | 0.10 | | | Mandible (2) | 0.94 ± 0.0 (0.93, 0.94) | 0.85 ± 0.01 (0.84, 0.86) | 0.09 | | Breast | Heart (12) | 0.95 ± 0.02 (0.94, 0.96) | 0.85 ± 0.09 (0.80, 0.90) | 0.10 | | | Rt. Lung (12)…