Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning

Wang, Yida3; Liu, Wei4; Lu, Yuanyuan5; Ling, Rennan6; Wang, Wenjing5; Li, Shengyong3; Zhang, Feiran7; Ning, Yan7; Chen, Xiaojun4; Yang, Guang2,3; Zhang, He1,8

2024-03-01

10.1002/jmri.29344

JOURNAL OF MAGNETIC RESONANCE IMAGING   影响因子和分区

1053-1807

1522-2586

Background: Early and accurate identification of lymphatic node metastasis (LNM) and lymphatic vascular space invasion (LVSI) for endometrial cancer (EC) patients is important for treatment design, but difficult on multi-parametric MRI (mpMRI) images. Purpose: To develop a deep learning (DL) model to simultaneously identify of LNM and LVSI of EC from mpMRI images. Study type: Retrospective. Population: Six hundred twenty-one patients with histologically proven EC from two institutions, including 111 LNM-positive and 168 LVSI-positive, divided into training, internal, and external test cohorts of 398, 169, and 54 patients, respectively. Field strength/sequence: T2-weighted imaging (T2WI), contrast-enhanced T1WI (CE-T1WI), and diffusion-weighted imaging (DWI) were scanned with turbo spin-echo, gradient-echo, and two-dimensional echo-planar sequences, using either a 1.5 T or 3 T system. Assessment: EC lesions were manually delineated on T2WI by two radiologists and used to train an nnU-Net model for automatic segmentation. A multi-task DL model was developed to simultaneously identify LNM and LVSI positive status using the segmented EC lesion regions and T2WI, CE-T1WI, and DWI images as inputs. The performance of the model for LNM-positive diagnosis was compared with those of three radiologists in the external test cohort. Statistical tests: Dice similarity coefficient (DSC) was used to evaluate segmentation results. Receiver Operating Characteristic (ROC) analysis was used to assess the performance of LNM and LVSI status identification. P value <0.05 was considered significant. Results: EC lesion segmentation model achieved mean DSC values of 0.700 +/- 0.25 and 0.693 +/- 0.21 in the internal and external test cohorts, respectively. For LNM positive/LVSI positive identification, the proposed model achieved AUC values of 0.895/0.848, 0.806/0.795, and 0.804/0.728 in the training, internal, and external test cohorts, respectively, and better than those of three radiologists (AUC = 0.770/0.648/0.674). Data conclusion: The proposed model has potential to help clinicians to identify LNM and LVSI status of EC patients and improve treatment planning. Evidence level: 3 TECHNICAL EFFICACY: Stage 2.

endometrial cancer deep learning magnetic resonance imaging attention mechanism

SCI

英语

其他

The Open Project of Shanghai Key Laboratory of Magnetic Resonance[20Z11900700] ; Science and Technology Commission of Shanghai Municipality["61731009","81771816"]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:001183522300001

WILEY

CLINICAL MEDICINE

Web of Science

1.419 Fangxie Rd, Shanghai, Peoples R China
2.3663,North Zhongshan Rd, Shanghai, Peoples R China
3.East China Normal Univ, Shanghai Key Lab Magnet Resonance, Shanghai, Peoples R China
4.Fudan Univ, Obstet & Gynecol Hosp, Dept Gynecol, Shanghai, Peoples R China
5.Tongji Univ, Sch Med, Shanghai Matern & Infant Hosp 1, Dept Radiol, Shanghai, Peoples R China
6.Southern Univ Sci & Technol, Jinan Univ, Affiliated Hosp 1, Dept Radiol,Shenzhen Peoples Hosp,Clin Med Coll 2, Shenzhen, Peoples R China
7.Fudan Univ, Obstet & Gynecol Hosp, Dept Pathol, Shanghai, Peoples R China
8.Fudan Univ, Obstet & Gynecol Hosp, Dept Radiol, Shanghai, Peoples R China

Wang, Yida,Liu, Wei,Lu, Yuanyuan,et al. Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning[J]. JOURNAL OF MAGNETIC RESONANCE IMAGING,2024.

Wang, Yida.,Liu, Wei.,Lu, Yuanyuan.,Ling, Rennan.,Wang, Wenjing.,...&Zhang, He.(2024).Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning.JOURNAL OF MAGNETIC RESONANCE IMAGING.

Wang, Yida,et al."Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning".JOURNAL OF MAGNETIC RESONANCE IMAGING (2024).