Multiparametric MRI-based radiomics combined with 3D deep transfer learning to predict cervical stromal invasion in patients with endometrial carcinoma

Xianhong Wang; Qiu Bi; Cheng Deng; Yaoxin Wang; Yunbo Miao; Ruize Kong; Jie Chen; Chenrong Li; Xiulan Liu; Xiarong Gong; Ya Zhang; Guoli Bi

doi:10.1007/s00261-024-04577-1

Multiparametric MRI-based radiomics combined with 3D deep transfer learning to predict cervical stromal invasion in patients with endometrial carcinoma

Abdom Radiol (NY). 2024 Sep 14. doi: 10.1007/s00261-024-04577-1. Online ahead of print.

Authors

Xianhong Wang^{1

2}, Qiu Bi^{1

2}, Cheng Deng³, Yaoxin Wang⁴, Yunbo Miao^{1

5}, Ruize Kong^{1

6}, Jie Chen⁷, Chenrong Li^{1

2}, Xiulan Liu^{1

2}, Xiarong Gong^{1

2}, Ya Zhang⁷, Guoli Bi^{8

9}

Affiliations

¹ The Affiliated Hospital of Kunming University of Science and Technology, Kunming, China.
² Department of MRI, the First People's Hospital of Yunnan Province, Kunming, China.
³ Department of Radiology, the Second Affiliated Hospital of Kunming Medical University, Kunming, China.
⁴ Department of Radiology, Shenzhen Traditional Chinese Medicine Hospital, the Fourth Clinical Medical College of Guangzhou University of Chinese Medicine, Shenzhen, China.
⁵ Department of Geriatrie Medicine, the First People's Hospital of Yunnan Province, Kunming, China.
⁶ Department of Vascular Surgery, the First People's Hospital of Yunnan Province, Kunming, China.
⁷ Department of Radiology, the Third Affiliated Hospital of Kunming Medical University, Kunming, China.
⁸ The Affiliated Hospital of Kunming University of Science and Technology, Kunming, China. guolibi76@aliyun.com.
⁹ Department of MRI, the First People's Hospital of Yunnan Province, Kunming, China. guolibi76@aliyun.com.

PMID: 39276192
DOI: 10.1007/s00261-024-04577-1

Abstract

Objective: To develop and compare various preoperative cervical stromal invasion (CSI) prediction models, including radiomics, three-dimensional (3D) deep transfer learning (DTL), and integrated models, using single-sequence and multiparametric MRI.

Methods: Data from 466 early-stage endometrial carcinoma (EC) patients from three centers were collected. Radiomics models were constructed based on T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) mapping, contrast-enhanced T1-weighted imaging (CE-T1WI), and four combined sequences as well as 3D DTL models. Two integrated models were created using ensemble and stacking algorithms based on optimal radiomics and DTL models. Model performance and clinical benefits were assessed using area under the curve (AUC), decision curve analysis (DCA), net reclassification index (NRI), integrated discrimination index (IDI), and the Delong test for model comparisons.

Results: Multiparametric MRI models were superior to single-sequence models for radiomics or DTL models. Ensemble and stacking integrated models displayed excellent performance. The stacking model had the highest average AUC (0.908) and accuracy (0.883) in external validation groups 1 and 2 (AUC = 0.965 and 0.851, respectively) and emerged as the best predictive model for CSI. All models significantly outperformed the radiologist (P < 0.05). In terms of net benefits, all models demonstrated favorable outcomes in DCA, NRI, and IDI, with the stacking model yielding the highest net benefit.

Conclusion: Multiparametric MRI-based radiomics combined with 3D DTL can be used to noninvasively predict CSI in EC patients with greater diagnostic accuracy than the radiologist. Stacking integrated models showed significant potential utility in predicting CSI. Which helps to provide new treatment strategy for clinicians to treat early-stage EC patients.

Keywords: Cervical stromal invasion; Deep transfer learning; Endometrial carcinoma; Magnetic resonance imaging; Radiomics.

Abstract

Grants and funding