Frontiers in Medicine (Nov 2024)

Automated lung segmentation on chest MRI in children with cystic fibrosis

  • Friedemann G. Ringwald,
  • Friedemann G. Ringwald,
  • Lena Wucherpfennig,
  • Lena Wucherpfennig,
  • Lena Wucherpfennig,
  • Niclas Hagen,
  • Niclas Hagen,
  • Jonas Mücke,
  • Sebastian Kaletta,
  • Monika Eichinger,
  • Monika Eichinger,
  • Monika Eichinger,
  • Mirjam Stahl,
  • Mirjam Stahl,
  • Mirjam Stahl,
  • Mirjam Stahl,
  • Simon M. F. Triphan,
  • Simon M. F. Triphan,
  • Simon M. F. Triphan,
  • Patricia Leutz-Schmidt,
  • Patricia Leutz-Schmidt,
  • Patricia Leutz-Schmidt,
  • Sonja Gestewitz,
  • Sonja Gestewitz,
  • Sonja Gestewitz,
  • Simon Y. Graeber,
  • Simon Y. Graeber,
  • Simon Y. Graeber,
  • Simon Y. Graeber,
  • Hans-Ulrich Kauczor,
  • Hans-Ulrich Kauczor,
  • Hans-Ulrich Kauczor,
  • Abdulsattar Alrajab,
  • Jens-Peter Schenk,
  • Olaf Sommerburg,
  • Olaf Sommerburg,
  • Olaf Sommerburg,
  • Marcus A. Mall,
  • Marcus A. Mall,
  • Marcus A. Mall,
  • Marcus A. Mall,
  • Petra Knaup,
  • Petra Knaup,
  • Mark O. Wielpütz,
  • Mark O. Wielpütz,
  • Mark O. Wielpütz,
  • Urs Eisenmann,
  • Urs Eisenmann

DOI
https://doi.org/10.3389/fmed.2024.1401473
Journal volume & issue
Vol. 11

Abstract

Read online

IntroductionSegmentation 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.MethodsOur 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.ResultsThe 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 conclusionOverall, 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.

Keywords