EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Validation of MRI-based nnU-Net model for automated segmentation of neck lymph nodes in head and neck squamous cell carcinoma: a multicenter study

Chaofan Sui, Xiaoxia Qu, Ning Xu, Xiao Wang, Hanjuan Zhang, Xinyan Wang, Pengfei Zhao, Junfang Xian

Neuroradiology · 2026

DOI: 10.1007/s00234-026-04070-0 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Neuroradiology, 2026. Verfasst von Chaofan Sui und 7 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Tongren Hospital, Capital Medical University, Beijing, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Squamous Cell Carcinoma of Head and Neck, Lymphatic Metastasis, Head and Neck Neoplasms. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To develop and externally validate an MRI-based deep learning framework for automated 3D segmentation of neck lymph nodes (LNs) in head and neck squamous cell carcinoma (HNSCC), and to assess segmentation accuracy, volumetric agreement, and time efficiency. METHODS: Axial head and neck MRI data were retrospectively collected from two centers. Each LN was manually delineated following two strategies: margin-excluding approach (excluding a 1-2 mm perinodal margin) and boundary-adherent approach (following the LN contour). For each strategy, nnU-Net (a DL framework) was applied for training three single-sequence models using contrast-enhanced T1-weighted (CE-T1w), T1-weighted (T1w), and T2-weighted (T2w) imaging. The model performance was evaluated in the internal validation cohort (n = 99) and the external test cohort (n = 150). Efficiency was assessed by comparing manual vs. DL-assisted contouring times in a separate cohort (n = 851). RESULTS: In the internal validation cohort, the model trained on CE-T1w images with boundary-adherent annotations achieved the highest overlap (median Dice similarity coefficient of 0.795). CE-T1w model showed high volumetric agreement with manual segmentation (concordance correlation coefficient of 0.939 for margin-excluding and 0.899 for boundary-adherent strategies), and its performance was confirmed in the external test cohort. DL assistance reduced contouring time by 33.14% (n = 851, mean 100.22 s vs. 149.89 s, p < 0.001). The two annotation policies yielded similar LN counts but significantly different volume endpoints (p < 0.001). CONCLUSION: We developed and validated a deep learning framework capable of accurate and efficient 3D LN segmentation using single-sequence model inputs after CE-T1w-referenced preprocessing. The model shows strong generalization across multiple centers. This tool can standardize volumetric assessments and improve clinical workflow efficiency in HNSCC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingSquamous Cell Carcinoma of Head and NeckLymphatic MetastasisHead and Neck NeoplasmsImage Interpretation, Computer-AssistedLymph NodesDeep LearningHumansRetrospective StudiesMaleFemaleReproducibility of ResultsMiddle AgedContrast MediaImaging, Three-DimensionalAged

Stichwörter der Autor:innen

Automated segmentationHead and neck squamous cell carcinomaMagnetic resonance imagingMulticenter validationNeck lymph nodes

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Beijing Tongren Hospital, Capital Medical University, Beijing, China.
  • Beijing Friendship Hospital, Capital Medical University, Beijing, China.
  • Beijing Tongren Hospital, Capital Medical University, Beijing, China. juanjuan0824@163.com.
  • Beijing Friendship Hospital, Capital Medical University, Beijing, China. zhaopengf05@163.com.
  • Beijing Tongren Hospital, Capital Medical University, Beijing, China. cjr.xianjunfang@vip.163.com.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Sui, C., Qu, X., Xu, N., Wang, X., Zhang, H., Wang, X., Zhao, P., & Xian, J. (2026). Validation of MRI-based nnU-Net model for automated segmentation of neck lymph nodes in head and neck squamous cell carcinoma: a multicenter study. Neuroradiology. https://doi.org/10.1007/s00234-026-04070-0

Vancouver

Sui C, Qu X, Xu N, Wang X, Zhang H, Wang X, et al. Validation of MRI-based nnU-Net model for automated segmentation of neck lymph nodes in head and neck squamous cell carcinoma: a multicenter study. Neuroradiology. 2026. doi:10.1007/s00234-026-04070-0

BibTeX
@article{Sui2026,
  author = {Sui, Chaofan and Qu, Xiaoxia and Xu, Ning and Wang, Xiao and Zhang, Hanjuan and Wang, Xinyan and Zhao, Pengfei and Xian, Junfang},
  title = {Validation of MRI-based nnU-Net model for automated segmentation of neck lymph nodes in head and neck squamous cell carcinoma: a multicenter study},
  journal = {Neuroradiology},
  year = {2026},
  doi = {10.1007/s00234-026-04070-0}
}
Kostenlos starten →