Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA)
Abstract Objectives Total tumor volume (TTV) is associated with overall and recurrence-free survival in patients with colorectal cancer liver metastases (CRLM). However, the labor-intensive nature of such manual assessments has hampered the clinical adoption of TTV as an imaging biomarker. This stud...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-11-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-024-01820-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846158467466788864 |
|---|---|
| author | Jacqueline I. Bereska Michiel Zeeuw Luuk Wagenaar Håvard Bjørke Jenssen Nina J. Wesdorp Delanie van der Meulen Leonard F. Bereska Efstratios Gavves Boris V. Janssen Marc G. Besselink Henk A. Marquering Jan-Hein T. M. van Waesberghe Davit L. Aghayan Egidijus Pelanis Janneke van den Bergh Irene I. M. Nota Shira Moos Gunter Kemmerich Trygve Syversveen Finn Kristian Kolrud Joost Huiskens Rutger-Jan Swijnenburg Cornelis J. A. Punt Jaap Stoker Bjørn Edwin Åsmund A. Fretland Geert Kazemier Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium the Dutch Colorectal Cancer Group Liver Expert Panel |
| author_facet | Jacqueline I. Bereska Michiel Zeeuw Luuk Wagenaar Håvard Bjørke Jenssen Nina J. Wesdorp Delanie van der Meulen Leonard F. Bereska Efstratios Gavves Boris V. Janssen Marc G. Besselink Henk A. Marquering Jan-Hein T. M. van Waesberghe Davit L. Aghayan Egidijus Pelanis Janneke van den Bergh Irene I. M. Nota Shira Moos Gunter Kemmerich Trygve Syversveen Finn Kristian Kolrud Joost Huiskens Rutger-Jan Swijnenburg Cornelis J. A. Punt Jaap Stoker Bjørn Edwin Åsmund A. Fretland Geert Kazemier Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium the Dutch Colorectal Cancer Group Liver Expert Panel |
| author_sort | Jacqueline I. Bereska |
| collection | DOAJ |
| description | Abstract Objectives Total tumor volume (TTV) is associated with overall and recurrence-free survival in patients with colorectal cancer liver metastases (CRLM). However, the labor-intensive nature of such manual assessments has hampered the clinical adoption of TTV as an imaging biomarker. This study aimed to develop and externally evaluate a CRLM auto-segmentation model on CT scans, to facilitate the clinical adoption of TTV. Methods We developed an auto-segmentation model to segment CRLM using 783 contrast-enhanced portal venous phase CTs (CT-PVP) of 373 patients. We used a self-learning setup whereby we first trained a teacher model on 99 manually segmented CT-PVPs from three radiologists. The teacher model was then used to segment CRLM in the remaining 663 CT-PVPs for training the student model. We used the DICE score and the intraclass correlation coefficient (ICC) to compare the student model’s segmentations and the TTV obtained from these segmentations to those obtained from the merged segmentations. We evaluated the student model in an external test set of 50 CT-PVPs from 35 patients from the Oslo University Hospital and an internal test set of 21 CT-PVPs from 10 patients from the Amsterdam University Medical Centers. Results The model reached a mean DICE score of 0.85 (IQR: 0.05) and 0.83 (IQR: 0.10) on the internal and external test sets, respectively. The ICC between the segmented volumes from the student model and from the merged segmentations was 0.97 on both test sets. Conclusion The developed colorectal cancer liver metastases auto-segmentation model achieved a high DICE score and near-perfect agreement for assessing TTV. Critical relevance statement AI model segments colorectal liver metastases on CT with high performance on two test sets. Accurate segmentation of colorectal liver metastases could facilitate the clinical adoption of total tumor volume as an imaging biomarker for prognosis and treatment response monitoring. Key Points Developed colorectal liver metastases segmentation model to facilitate total tumor volume assessment. Model achieved high performance on internal and external test sets. Model can improve prognostic stratification and treatment planning for colorectal liver metastases. Graphical Abstract |
| format | Article |
| id | doaj-art-978a8ed644cc45b5ae8587799d0eccf7 |
| institution | Kabale University |
| issn | 1869-4101 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-978a8ed644cc45b5ae8587799d0eccf72024-11-24T12:29:10ZengSpringerOpenInsights into Imaging1869-41012024-11-011511910.1186/s13244-024-01820-7Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA)Jacqueline I. Bereska0Michiel Zeeuw1Luuk Wagenaar2Håvard Bjørke Jenssen3Nina J. Wesdorp4Delanie van der Meulen5Leonard F. Bereska6Efstratios Gavves7Boris V. Janssen8Marc G. Besselink9Henk A. Marquering10Jan-Hein T. M. van Waesberghe11Davit L. Aghayan12Egidijus Pelanis13Janneke van den Bergh14Irene I. M. Nota15Shira Moos16Gunter Kemmerich17Trygve Syversveen18Finn Kristian Kolrud19Joost Huiskens20Rutger-Jan Swijnenburg21Cornelis J. A. Punt22Jaap Stoker23Bjørn Edwin24Åsmund A. Fretland25Geert Kazemier26Inez M. Verpalen27for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortiumthe Dutch Colorectal Cancer Group Liver Expert PanelCancer Center AmsterdamCancer Center AmsterdamCancer Center AmsterdamOslo University Hospital, Department of Radiology and Nuclear MedicineCancer Center AmsterdamCancer Center AmsterdamUniversity of Amsterdam, Video and Image Sense LabUniversity of Amsterdam, Video and Image Sense LabCancer Center AmsterdamCancer Center AmsterdamCancer Center AmsterdamCancer Center AmsterdamOslo University Hospital, Department of Hepato-Pancreato-Biliary SurgeryOslo University Hospital, Department of Hepato-Pancreato-Biliary SurgeryCancer Center AmsterdamCancer Center AmsterdamCancer Center AmsterdamOslo University Hospital, Department of Radiology and Nuclear MedicineOslo University Hospital, Department of Radiology and Nuclear MedicineOslo University Hospital, Department of Radiology and Nuclear MedicineCancer Center AmsterdamCancer Center AmsterdamAmsterdam UMC, University of Amsterdam, Department of Medical OncologyCancer Center AmsterdamOslo University Hospital, Department of Hepato-Pancreato-Biliary SurgeryOslo University Hospital, Department of Hepato-Pancreato-Biliary SurgeryCancer Center AmsterdamCancer Center AmsterdamAbstract Objectives Total tumor volume (TTV) is associated with overall and recurrence-free survival in patients with colorectal cancer liver metastases (CRLM). However, the labor-intensive nature of such manual assessments has hampered the clinical adoption of TTV as an imaging biomarker. This study aimed to develop and externally evaluate a CRLM auto-segmentation model on CT scans, to facilitate the clinical adoption of TTV. Methods We developed an auto-segmentation model to segment CRLM using 783 contrast-enhanced portal venous phase CTs (CT-PVP) of 373 patients. We used a self-learning setup whereby we first trained a teacher model on 99 manually segmented CT-PVPs from three radiologists. The teacher model was then used to segment CRLM in the remaining 663 CT-PVPs for training the student model. We used the DICE score and the intraclass correlation coefficient (ICC) to compare the student model’s segmentations and the TTV obtained from these segmentations to those obtained from the merged segmentations. We evaluated the student model in an external test set of 50 CT-PVPs from 35 patients from the Oslo University Hospital and an internal test set of 21 CT-PVPs from 10 patients from the Amsterdam University Medical Centers. Results The model reached a mean DICE score of 0.85 (IQR: 0.05) and 0.83 (IQR: 0.10) on the internal and external test sets, respectively. The ICC between the segmented volumes from the student model and from the merged segmentations was 0.97 on both test sets. Conclusion The developed colorectal cancer liver metastases auto-segmentation model achieved a high DICE score and near-perfect agreement for assessing TTV. Critical relevance statement AI model segments colorectal liver metastases on CT with high performance on two test sets. Accurate segmentation of colorectal liver metastases could facilitate the clinical adoption of total tumor volume as an imaging biomarker for prognosis and treatment response monitoring. Key Points Developed colorectal liver metastases segmentation model to facilitate total tumor volume assessment. Model achieved high performance on internal and external test sets. Model can improve prognostic stratification and treatment planning for colorectal liver metastases. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01820-7Colorectal neoplasmsLiverBiomarkersTumorArtificial intelligence |
| spellingShingle | Jacqueline I. Bereska Michiel Zeeuw Luuk Wagenaar Håvard Bjørke Jenssen Nina J. Wesdorp Delanie van der Meulen Leonard F. Bereska Efstratios Gavves Boris V. Janssen Marc G. Besselink Henk A. Marquering Jan-Hein T. M. van Waesberghe Davit L. Aghayan Egidijus Pelanis Janneke van den Bergh Irene I. M. Nota Shira Moos Gunter Kemmerich Trygve Syversveen Finn Kristian Kolrud Joost Huiskens Rutger-Jan Swijnenburg Cornelis J. A. Punt Jaap Stoker Bjørn Edwin Åsmund A. Fretland Geert Kazemier Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium the Dutch Colorectal Cancer Group Liver Expert Panel Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) Insights into Imaging Colorectal neoplasms Liver Biomarkers Tumor Artificial intelligence |
| title | Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) |
| title_full | Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) |
| title_fullStr | Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) |
| title_full_unstemmed | Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) |
| title_short | Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA) |
| title_sort | development and external evaluation of a self learning auto segmentation model for colorectal cancer liver metastases assessment coala |
| topic | Colorectal neoplasms Liver Biomarkers Tumor Artificial intelligence |
| url | https://doi.org/10.1186/s13244-024-01820-7 |
| work_keys_str_mv | AT jacquelineibereska developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT michielzeeuw developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT luukwagenaar developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT havardbjørkejenssen developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT ninajwesdorp developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT delanievandermeulen developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT leonardfbereska developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT efstratiosgavves developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT borisvjanssen developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT marcgbesselink developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT henkamarquering developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT janheintmvanwaesberghe developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT davitlaghayan developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT egidijuspelanis developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT jannekevandenbergh developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT ireneimnota developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT shiramoos developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT gunterkemmerich developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT trygvesyversveen developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT finnkristiankolrud developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT joosthuiskens developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT rutgerjanswijnenburg developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT cornelisjapunt developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT jaapstoker developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT bjørnedwin developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT asmundafretland developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT geertkazemier developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT inezmverpalen developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT forthepancreatobiliaryandhepaticartificialintelligenceresearchphairconsortium developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala AT thedutchcolorectalcancergroupliverexpertpanel developmentandexternalevaluationofaselflearningautosegmentationmodelforcolorectalcancerlivermetastasesassessmentcoala |