EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Fully automated segmentation and volumetric measurement of ocular adnexal lymphoma by deep learning-based self-configuring nnU-net on multi-sequence MRI: a multi-center study

Guorong Wang, Bingbing Yang, Xiaoxia Qu, Jian Guo, Yongheng Luo, Xiaoquan Xu, Feiyun Wu, Xiaoxue Fan, Yang Hou, Song Tian, Sicong Huang, Junfang Xian

Neuroradiology · 2024

DOI: 10.1007/s00234-024-03429-5 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Neuroradiology, 2024. Verfasst von Guorong Wang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No.1 DongJiaoMinXiang Street, DongCheng District, Beijing, 100730, Chi…. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Lymphoma. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Health Commission's Capacity Building and Continuing Education Center, Beijing Municipal Administration of Hospitals' Ascent Plan, Beijing Postdoctoral Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To evaluate nnU-net’s performance in automatically segmenting and volumetrically measuring ocular adnexal lymphoma (OAL) on multi-sequence MRI.

Methods

We collected T1-weighted (T1), T2-weighted and T1-weighted contrast-enhanced images with/without fat saturation (T2_FS/T2_nFS, T1c_FS/T1c_nFS) of OAL from four institutions. Two radiologists manually annotated lesions as the ground truth using ITK-SNAP. A deep learning framework, nnU-net, was developed and trained using two models. Model 1 was trained on T1, T2, and T1c, while Model 2 was trained exclusively on T1 and T2. A 5-fold cross-validation was utilized in the training process. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), sensitivity, and positive prediction value (PPV). Volumetric assessment was performed using Bland-Altman plots and Lin’s concordance correlation coefficient (CCC).

Results

A total of 147 patients from one center were selected as training set and 33 patients from three centers were regarded as test set. For both Model 1 and 2, nnU-net demonstrated outstanding segmentation performance on T2_FS with DSC of 0.80–0.82, PPV of 84.5–86.1%, and sensitivity of 77.6–81.2%, respectively. Model 2 failed to detect 19 cases of T1c, whereas the DSC, PPV, and sensitivity for T1_nFS were 0.59, 91.2%, and 51.4%, respectively. Bland–Altman plots revealed minor tumor volume differences with 0.22–1.24 cm 3 between nnU-net prediction and ground truth on T2_FS. The CCC were 0.96 and 0.93 in Model 1 and 2 for T2_FS images, respectively.

Conclusion

The nnU-net offered excellent performance in automated segmentation and volumetric assessment in MRI of OAL, particularly on T2_FS images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMagnetic Resonance ImagingLymphomaHumansFemaleMaleMiddle AgedAgedAdultImage Interpretation, Computer-AssistedSensitivity and SpecificityEye NeoplasmsContrast MediaAged, 80 and overRetrospective Studies

Stichwörter der Autor:innen

Deep learningMagnetic resonance imagingOcular adnexal lymphoma

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No.1 DongJiaoMinXiang Street, DongCheng District, Beijing, 100730, China.
  • Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha, China.
  • Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
  • Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China.
  • Philips Healthcare, Beijing, China.
  • Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No.1 DongJiaoMinXiang Street, DongCheng District, Beijing, 100730, China. cjr.xianjunfang@vip.163.com.

Förderung

  • National Health Commission's Capacity Building and Continuing Education Center
  • Beijing Municipal Administration of Hospitals' Ascent Plan
  • Beijing Postdoctoral Research Foundation
  • National Key R&D Program of China
  • National Health Commission’s Capacity Building and Continuing Education Center
  • Beijing Municipal Administration of Hospitals’ Ascent Plan

Zitieren

APA

Wang, G., Yang, B., Qu, X., Guo, J., Luo, Y., Xu, X., Wu, F., Fan, X., Hou, Y., Tian, S., Huang, S., & Xian, J. (2024). Fully automated segmentation and volumetric measurement of ocular adnexal lymphoma by deep learning-based self-configuring nnU-net on multi-sequence MRI: a multi-center study. Neuroradiology. https://doi.org/10.1007/s00234-024-03429-5

Vancouver

Wang G, Yang B, Qu X, Guo J, Luo Y, Xu X, et al. Fully automated segmentation and volumetric measurement of ocular adnexal lymphoma by deep learning-based self-configuring nnU-net on multi-sequence MRI: a multi-center study. Neuroradiology. 2024. doi:10.1007/s00234-024-03429-5

BibTeX
@article{Wang2024,
  author = {Wang, Guorong and Yang, Bingbing and Qu, Xiaoxia and Guo, Jian and Luo, Yongheng and Xu, Xiaoquan and Wu, Feiyun and Fan, Xiaoxue and Hou, Yang and Tian, Song and Huang, Sicong and Xian, Junfang},
  title = {Fully automated segmentation and volumetric measurement of ocular adnexal lymphoma by deep learning-based self-configuring nnU-net on multi-sequence MRI: a multi-center study},
  journal = {Neuroradiology},
  year = {2024},
  doi = {10.1007/s00234-024-03429-5}
}
Kostenlos starten →