EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A multi‐stage 3D convolutional neural network algorithm for CT‐based lung segment parcellation

Trishul Siddharthan, Zhoubing Xu, Bruce Spottiswoode, Chris Schettino, Yoel Siegel, Michalis Georgiou, Thomas Eluvathingal, Bernhard Geiger, Sasa Grbic, Partha Gosh, Rachid Fahmi, Naresh Punjabi

Journal of Applied Clinical Medical Physics · 2025-08 · 26 (8)

DOI: 10.1002/acm2.70193 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 23.07.2025. Verfasst von Trishul Siddharthan und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Pulmonary, Critical Care and Sleep Medicine, University of Miami, Miami, Florida, USA. Hauptthemen laut MEDLINE: Algorithms, Deep Learning, Image Processing, Computer-Assisted, Imaging, Three-Dimensional. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Current approaches to lung parcellation utilize established fissures between lobes to provide estimates of lobar volume. However, deep learning segment parcellation provides the ability to better assess regional heterogeneity in ventilation and perfusion.

Purpose

We aimed to validate and demonstrate the clinical applicability of CT‐based lung segment parcellation using deep learning on a clinical cohort with mixed airways disease.

Methods

Using a 3D convolutional neural network, airway centerlines were determined using an image‐to‐image network. Tertiary bronchi were identified on top of the airway centerline, and the pulmonary segments were parcellated based on the spatial relationship with tertiary and subsequent bronchi. The data obtained by following this workflow was used to train a neural network to enable end‐to‐end lung segment parcellation directly from 123 chest CT images. The performance of the parcellation network was then evaluated quantitatively using expert‐defined reference masks on 20 distinct CTs from the training set, where the Dice score and inclusion rate (i.e., percentage of the detected bronchi covered by the correct segment) between the manual segmentation and automatic parcellation results were calculated for each lung segment. Lastly, a qualitative evaluation of external validation was performed on 20 CTs prospectively collected by having two radiologists review the parcellation accuracy in healthy individuals ( n = 10) and in patients with chronic obstructive pulmonary disease (COPD) ( n = 10).

Results

Means and standard deviation of Dice score and inclusion rate between automatic and manual segmentation of twenty patient CTs were 86.81 (SD = 24.54) and 0.75 (SD = 0.19), respectively, across all lung segments. The mean age of the qualitative dataset was 54.4 years (SD = 16.4 years), with 45% ( n = 9) women. There was 99.2% intra‐reader agreement on average with the produced segments. Individuals with COPD had greater mismatch compared to healthy controls.

Conclusions

A deep‐learning algorithm can create parcellation masks from chest CT scans, and the quantitative and qualitative evaluations yielded encouraging results for the potential clinical usage of lung analysis at the pulmonary segment level among those with structural airway disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsDeep LearningImage Processing, Computer-AssistedImaging, Three-DimensionalLungNeural Networks, ComputerTomography, X-Ray ComputedFemaleHumansMaleMiddle AgedConvolutional Neural NetworksAdultAged

Stichwörter der Autor:innen

CT‐based lung segment parcellationairways diseasedeep learning

Autor:innen und Institutionen

  • Division of Pulmonary, Critical Care and Sleep Medicine, University of Miami, Miami, Florida, USA.
  • Siemens Medical Solutions USA, Inc., Malvern, Pennsylvania, USA.
  • Department of Radiology, Miller School of Medicine, University of Miami, Miami, Florida, USA.
  • Department of Nuclear Medicine, Miller School of Medicine, University of Miami, Miami, Florida, USA.

Zitieren

APA

Siddharthan, T., Xu, Z., Spottiswoode, B., Schettino, C., Siegel, Y., Georgiou, M., Eluvathingal, T., Geiger, B., Grbic, S., Gosh, P., Fahmi, R., & Punjabi, N. (2025). A multi‐stage 3D convolutional neural network algorithm for CT‐based lung segment parcellation. Journal of Applied Clinical Medical Physics, 26(8). https://doi.org/10.1002/acm2.70193

Vancouver

Siddharthan T, Xu Z, Spottiswoode B, Schettino C, Siegel Y, Georgiou M, et al. A multi‐stage 3D convolutional neural network algorithm for CT‐based lung segment parcellation. Journal of Applied Clinical Medical Physics. 2025;26(8). doi:10.1002/acm2.70193

BibTeX
@article{Siddharthan2025,
  author = {Siddharthan, Trishul and Xu, Zhoubing and Spottiswoode, Bruce and Schettino, Chris and Siegel, Yoel and Georgiou, Michalis and Eluvathingal, Thomas and Geiger, Bernhard and Grbic, Sasa and Gosh, Partha and Fahmi, Rachid and Punjabi, Naresh},
  title = {A multi‐stage 3D convolutional neural network algorithm for CT‐based lung segment parcellation},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2025},
  volume = {26},
  number = {8},
  doi = {10.1002/acm2.70193}
}
Kostenlos starten →