Automated lung segmentation on chest MRI in children with cystic fibrosis.
Autor: | Ringwald FG; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany.; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany., Wucherpfennig L; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Hagen N; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany.; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany., Mücke J; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany., Kaletta S; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany., Eichinger M; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Stahl M; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Pediatric Respiratory Medicine, Immunology and Critical Care Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany.; German Center for Lung Research (DZL), Associated Partner Site, Berlin, Germany.; Berlin Institute of Health (BIH) at Charité-Universitätsmedizin Berlin, Berlin, Germany., Triphan SMF; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Leutz-Schmidt P; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Gestewitz S; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Graeber SY; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Pediatric Respiratory Medicine, Immunology and Critical Care Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany.; German Center for Lung Research (DZL), Associated Partner Site, Berlin, Germany.; Berlin Institute of Health (BIH) at Charité-Universitätsmedizin Berlin, Berlin, Germany., Kauczor HU; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Alrajab A; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany., Schenk JP; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany., Sommerburg O; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Division of Pediatric Pulmonology & Allergy and Cystic Fibrosis Center, Department of Pediatrics, University Hospital Heidelberg, Heidelberg, Germany.; Department of Translational Pulmonology, University Hospital Heidelberg, Heidelberg, Germany., Mall MA; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Pediatric Respiratory Medicine, Immunology and Critical Care Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany.; German Center for Lung Research (DZL), Associated Partner Site, Berlin, Germany.; Berlin Institute of Health (BIH) at Charité-Universitätsmedizin Berlin, Berlin, Germany., Knaup P; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany.; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany., Wielpütz MO; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.; Department of Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik at University Hospital Heidelberg, Heidelberg, Germany., Eisenmann U; Institute of Medical Informatics, Heidelberg University, Heidelberg, Germany.; Translational Lung Research Center Heidelberg (TLRC), German Center for Lung Research (DZL), Heidelberg, Germany. |
---|---|
Jazyk: | angličtina |
Zdroj: | Frontiers in medicine [Front Med (Lausanne)] 2024 Nov 12; Vol. 11, pp. 1401473. Date of Electronic Publication: 2024 Nov 12 (Print Publication: 2024). |
DOI: | 10.3389/fmed.2024.1401473 |
Abstrakt: | Introduction: Segmentation of lung structures in medical imaging is crucial for the application of automated post-processing steps on lung diseases like cystic fibrosis (CF). Recently, machine learning methods, particularly neural networks, have demonstrated remarkable improvements, often outperforming conventional segmentation methods. Nonetheless, challenges still remain when attempting to segment various imaging modalities and diseases, especially when the visual characteristics of pathologic findings significantly deviate from healthy tissue. Methods: Our study focuses on imaging of pediatric CF patients [mean age, standard deviation (7.50 ± 4.6)], utilizing deep learning-based methods for automated lung segmentation from chest magnetic resonance imaging (MRI). A total of 165 standardized annual surveillance MRI scans from 84 patients with CF were segmented using the nnU-Net framework. Patient cases represented a range of disease severities and ages. The nnU-Net was trained and evaluated on three MRI sequences (BLADE, VIBE, and HASTE), which are highly relevant for the evaluation of CF induced lung changes. We utilized 40 cases for training per sequence, and tested with 15 cases per sequence, using the Sørensen-Dice-Score, Pearson's correlation coefficient ( r ), a segmentation questionnaire, and slice-based analysis. Results: The results demonstrated a high level of segmentation performance across all sequences, with only minor differences observed in the mean Dice coefficient: BLADE (0.96 ± 0.05), VIBE (0.96 ± 0.04), and HASTE (0.95 ± 0.05). Additionally, the segmentation quality was consistent across different disease severities, patient ages, and sizes. Manual evaluation identified specific challenges, such as incomplete segmentations near the diaphragm and dorsal regions. Validation on a separate, external dataset of nine toddlers (2-24 months) demonstrated generalizability of the trained model achieving a Dice coefficient of 0.85 ± 0.03. Discussion and Conclusion: Overall, our study demonstrates the feasibility and effectiveness of using nnU-Net for automated segmentation of lung halves in pediatric CF patients, showing promising directions for advanced image analysis techniques to assist in clinical decision-making and monitoring of CF lung disease progression. Despite these achievements, further improvements are needed to address specific segmentation challenges and enhance generalizability. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The reviewer OP declared a past co-authorship with the authors MW and MM to the handling editor. The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision. (Copyright © 2024 Ringwald, Wucherpfennig, Hagen, Mücke, Kaletta, Eichinger, Stahl, Triphan, Leutz-Schmidt, Gestewitz, Graeber, Kauczor, Alrajab, Schenk, Sommerburg, Mall, Knaup, Wielpütz and Eisenmann.) |
Databáze: | MEDLINE |
Externí odkaz: |