See the published version of this preprint at EJNMMI Research.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Original research
Elisabeth Pfaehler
Universitair Medisch Centrum Groningen
Corresponding Author
ORCiD: https://orcid.org/0000-0002-6160-3011
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background: Positron Emission Tomography (PET) is routinely used for cancer staging and treatment follow up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV - including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis (TLG) derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge.
Methods: In this study, we compare two semi-automatic artificial intelligence (AI) based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a Convolutional Neural Network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard Coefficient (JC). Additionally, the approaches are externally tested on a fully independent test-retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUVMAX, and a SUV>4 segmentation (SUV4). Repeatability is assessed with test-retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC>0.9 was regarded as representing excellent repeatability.
Results: The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73) Both segmentation approaches outperformed most other conventional segmentation methods in terms of test-retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUVMAX: 28.1%, SUV4: 18.1% ) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUVMAX: 0.68).
Conclusion: The semi-automatic AI based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.
Keywords
repeatability, textural segmentation, convolutional neural network, tumor segmentation PET
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
This is a list of supplementary files associated with this preprint. Click to download.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at EJNMMI Research.
Version 3
Posted 20 Dec, 2020
No community comments so far
Reviewer #1 agreed
On 09 Dec, 2020
Review #1 received
Received 09 Dec, 2020
Editorial decision: Accept
On 09 Dec, 2020
Reviewers invited
Invitations sent on 07 Dec, 2020
Editor assigned
On 06 Dec, 2020
Submission checks complete
On 06 Dec, 2020
Editor invited
On 06 Dec, 2020
No comments provided
Editorial decision: Major Revision
On 01 Nov, 2020
Review #2 received
Received 31 Oct, 2020
Review #1 received
Received 27 Oct, 2020
Editor assigned
On 19 Oct, 2020
Reviewers invited
Invitations sent on 19 Oct, 2020
Reviewer #1 agreed
On 19 Oct, 2020
Reviewer #2 agreed
On 19 Oct, 2020
Submission checks complete
On 18 Oct, 2020
Editor invited
On 18 Oct, 2020
No comments provided
Editorial decision: Major Revision
On 21 Sep, 2020
Review #2 received
Received 13 Sep, 2020
Review #3 received
Received 13 Sep, 2020
Review #1 received
Received 09 Sep, 2020
Reviewer #2 agreed
On 31 Aug, 2020
Reviewer #3 agreed
On 31 Aug, 2020
Reviewers invited
Invitations sent on 15 Aug, 2020
Reviewer #1 agreed
On 15 Aug, 2020
Editor assigned
On 13 Aug, 2020
Editor invited
On 12 Aug, 2020
Submission checks complete
On 07 Aug, 2020
First submitted
On 05 Aug, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Photonics/optics
Learn more about our company.
See the published version of this preprint at EJNMMI Research.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Original research
Elisabeth Pfaehler
Universitair Medisch Centrum Groningen
Corresponding Author
ORCiD: https://orcid.org/0000-0002-6160-3011
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at EJNMMI Research.
Version 3
Posted 20 Dec, 2020
No community comments so far
Reviewer #1 agreed
On 09 Dec, 2020
Review #1 received
Received 09 Dec, 2020
Editorial decision: Accept
On 09 Dec, 2020
Reviewers invited
Invitations sent on 07 Dec, 2020
Editor assigned
On 06 Dec, 2020
Submission checks complete
On 06 Dec, 2020
Editor invited
On 06 Dec, 2020
No comments provided
Editorial decision: Major Revision
On 01 Nov, 2020
Review #2 received
Received 31 Oct, 2020
Review #1 received
Received 27 Oct, 2020
Editor assigned
On 19 Oct, 2020
Reviewers invited
Invitations sent on 19 Oct, 2020
Reviewer #1 agreed
On 19 Oct, 2020
Reviewer #2 agreed
On 19 Oct, 2020
Submission checks complete
On 18 Oct, 2020
Editor invited
On 18 Oct, 2020
No comments provided
Editorial decision: Major Revision
On 21 Sep, 2020
Review #2 received
Received 13 Sep, 2020
Review #3 received
Received 13 Sep, 2020
Review #1 received
Received 09 Sep, 2020
Reviewer #2 agreed
On 31 Aug, 2020
Reviewer #3 agreed
On 31 Aug, 2020
Reviewers invited
Invitations sent on 15 Aug, 2020
Reviewer #1 agreed
On 15 Aug, 2020
Editor assigned
On 13 Aug, 2020
Editor invited
On 12 Aug, 2020
Submission checks complete
On 07 Aug, 2020
First submitted
On 05 Aug, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Photonics/optics
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at EJNMMI Research.
Background: Positron Emission Tomography (PET) is routinely used for cancer staging and treatment follow up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV - including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis (TLG) derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge.
Methods: In this study, we compare two semi-automatic artificial intelligence (AI) based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a Convolutional Neural Network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard Coefficient (JC). Additionally, the approaches are externally tested on a fully independent test-retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUVMAX, and a SUV>4 segmentation (SUV4). Repeatability is assessed with test-retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC>0.9 was regarded as representing excellent repeatability.
Results: The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73) Both segmentation approaches outperformed most other conventional segmentation methods in terms of test-retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUVMAX: 28.1%, SUV4: 18.1% ) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUVMAX: 0.68).
Conclusion: The semi-automatic AI based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
This is a list of supplementary files associated with this preprint. Click to download.
Loading...