Development and external evaluation of a self-learning auto-segmentation model for Colorectal Cancer Liver Metastases Assessment (COALA).

Autor:	Bereska JI; Cancer Center Amsterdam, Amsterdam, The Netherlands. j.i.bereska@amsterdamUMC.nl.; Amsterdam UMC, University of Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands. j.i.bereska@amsterdamUMC.nl.; Amsterdam UMC, University of Amsterdam, Department of Biomedical Engineering and Physics, Amsterdam, The Netherlands. j.i.bereska@amsterdamUMC.nl., Zeeuw M; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Wagenaar L; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Biomedical Engineering and Physics, Amsterdam, The Netherlands., Jenssen HB; Oslo University Hospital, Department of Radiology and Nuclear Medicine, Oslo, Norway., Wesdorp NJ; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, The Netherlands., van der Meulen D; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Bereska LF; University of Amsterdam, Video and Image Sense Lab, Amsterdam, The Netherlands., Gavves E; University of Amsterdam, Video and Image Sense Lab, Amsterdam, The Netherlands., Janssen BV; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam Gastroenterology Endocrinology and Metabolism, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Besselink MG; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam Gastroenterology Endocrinology and Metabolism, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Marquering HA; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Biomedical Engineering and Physics, Amsterdam, The Netherlands., van Waesberghe JTM; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands., Aghayan DL; Oslo University Hospital, Department of Hepato-Pancreato-Biliary Surgery, Oslo, Norway.; Oslo University Hospital, The Intervention Centre, Oslo, Norway., Pelanis E; Oslo University Hospital, Department of Hepato-Pancreato-Biliary Surgery, Oslo, Norway.; Oslo University Hospital, The Intervention Centre, Oslo, Norway., van den Bergh J; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands., Nota IIM; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands., Moos S; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands., Kemmerich G; Oslo University Hospital, Department of Radiology and Nuclear Medicine, Oslo, Norway., Syversveen T; Oslo University Hospital, Department of Radiology and Nuclear Medicine, Oslo, Norway., Kolrud FK; Oslo University Hospital, Department of Radiology and Nuclear Medicine, Oslo, Norway., Huiskens J; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Swijnenburg RJ; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands., Punt CJA; Amsterdam UMC, University of Amsterdam, Department of Medical Oncology, Amsterdam, The Netherlands.; Department of Epidemiology, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht, The Netherlands., Stoker J; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, University of Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands.; Amsterdam Gastroenterology Endocrinology and Metabolism, Amsterdam, The Netherlands., Edwin B; Oslo University Hospital, Department of Hepato-Pancreato-Biliary Surgery, Oslo, Norway.; Oslo University Hospital, The Intervention Centre, Oslo, Norway., Fretland ÅA; Oslo University Hospital, Department of Hepato-Pancreato-Biliary Surgery, Oslo, Norway.; Oslo University Hospital, The Intervention Centre, Oslo, Norway., Kazemier G; Cancer Center Amsterdam, Amsterdam, The Netherlands.; Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, The Netherlands., Verpalen IM; Cancer Center Amsterdam, Amsterdam, The Netherlands. i.m.verpalen@amsterdamUMC.nl.; Amsterdam UMC, University of Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam, The Netherlands. i.m.verpalen@amsterdamUMC.nl.
Jazyk:	angličtina
Zdroj:	Insights into imaging [Insights Imaging] 2024 Nov 22; Vol. 15 (1), pp. 279. Date of Electronic Publication: 2024 Nov 22.
DOI:	10.1186/s13244-024-01820-7
Abstrakt:	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. Competing Interests: Declarations. Ethics approval and consent to participate: The Medical Ethics Review Committee of the Amsterdam UMC, the Regional Ethical Committee of Norway, and the Data Protection Officer of Oslo University Hospital approved this study protocol. All patients were managed per institutional practices. All patients signed a written informed consent form permitting the use of their data for studies. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. (© 2024. The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu Plný text ve formátu PDF