EUVIMEDEUVIMED entdecken
Crossref

Multitask Deep Learning for Automated Segmentation and Prognostic Stratification of Endometrial Cancer via Biparametric MRI

Ruixin Yan, Ximiao Zhang, Qiqi Cao, Jiajia Xu, Yongye Chen, Siyuan Qin, Shiwen Zhang, Weili Zhao, Xiaoying Xing, Wenjie Yang, Ning Lang iD

Journal of Magnetic Resonance Imaging · 2025-10 · 62 (4) · 1009-1020

DOI: 10.1002/jmri.70012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 19.06.2025. Verfasst von Ruixin Yan und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Endometrial Neoplasms, Magnetic Resonance Imaging, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Endometrial cancer (EC) is a common gynecologic malignancy; accurate assessment of key prognostic factors is important for treatment planning.

Purpose

To develop a deep learning (DL) framework based on biparametric MRI for automated segmentation and multitask classification of EC key prognostic factors, including grade, stage, histological subtype, lymphovascular space invasion (LVSI), and deep myometrial invasion (DMI). Study Type Retrospective. Subjects A total of 325 patients with histologically confirmed EC were included: 211 training, 54 validation, and 60 test cases. Field Strength/Sequence T2‐weighted imaging (T2WI, FSE/TSE) and diffusion‐weighted imaging (DWI, SS‐EPI) sequences at 1.5 and 3 T. Assessment The DL model comprised tumor segmentation and multitask classification. Manual delineation on T2WI and DWI acted as the reference standard for segmentation. Separate models were trained using T2WI alone, DWI alone and combined T2WI + DWI to classify dichotomized key prognostic factors. Performance was assessed in validation and test cohorts. For DMI, the combined model's was compared with visual assessment by four radiologists (with 1, 4, 7, and 20 years' experience), each of whom independently reviewed all cases. Statistical Tests Segmentation was evaluated using the dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), Hausdorff distance (HD95), and average surface distance (ASD). Classification performance was assessed using area under the receiver operating characteristic curve (AUC). Model AUCs were compared using DeLong's test. p < 0.05 was considered significant.

Results

In the test cohort, DSCs were 0.80 (T2WI) and 0.78 (DWI) and JSCs were 0.69 for both. HD95 and ASD were 7.02/1.71 mm (T2WI) versus 10.58/2.13 mm (DWI). The classification framework achieved AUCs of 0.78–0.94 (validation) and 0.74–0.94 (test). For DMI, the combined model performed comparably to radiologists ( p = 0.07–0.84).

Conclusions

The unified DL framework demonstrates strong EC segmentation and classification performance, with high accuracy across multiple tasks. Evidence Level 3. Technical Efficacy Stage 3.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningEndometrial NeoplasmsMagnetic Resonance ImagingImage Interpretation, Computer-AssistedHumansFemaleRetrospective StudiesMiddle AgedPrognosisAgedReproducibility of ResultsAdultDiffusion Magnetic Resonance ImagingImage Processing, Computer-AssistedAged, 80 and overROC Curve

Stichwörter der Autor:innen

endometrial cancermultitask deep learningprognosis classificationsegmentation

Autor:innen und Institutionen

  • Department of Radiology, State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University Third Hospital, Beijing, China.
  • School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
  • Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

ORCID-Profile: Ning Lang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yan, R., Zhang, X., Cao, Q., Xu, J., Chen, Y., Qin, S., Zhang, S., Zhao, W., Xing, X., Yang, W., & Lang, N. (2025). Multitask Deep Learning for Automated Segmentation and Prognostic Stratification of Endometrial Cancer via Biparametric MRI. Journal of Magnetic Resonance Imaging, 62(4), 1009-1020. https://doi.org/10.1002/jmri.70012

Vancouver

Yan R, Zhang X, Cao Q, Xu J, Chen Y, Qin S, et al. Multitask Deep Learning for Automated Segmentation and Prognostic Stratification of Endometrial Cancer via Biparametric MRI. Journal of Magnetic Resonance Imaging. 2025;62(4):1009-1020. doi:10.1002/jmri.70012

BibTeX
@article{Yan2025,
  author = {Yan, Ruixin and Zhang, Ximiao and Cao, Qiqi and Xu, Jiajia and Chen, Yongye and Qin, Siyuan and Zhang, Shiwen and Zhao, Weili and Xing, Xiaoying and Yang, Wenjie and Lang, Ning},
  title = {Multitask Deep Learning for Automated Segmentation and Prognostic Stratification of Endometrial Cancer via Biparametric MRI},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  volume = {62},
  number = {4},
  pages = {1009--1020},
  doi = {10.1002/jmri.70012}
}
Kostenlos starten →