Deep learning for the determination of myometrial invasion depth and automatic lesion identification in endometrial cancer MR imaging: a preliminary study in a single institution
- 26 April 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in European Radiology
- Vol. 30 (9), 4985-4994
- https://doi.org/10.1007/s00330-020-06870-1
Abstract
Objective To determine the diagnostic performance of a deep learning (DL) model in evaluating myometrial invasion (MI) depth on T2-weighted imaging (T2WI)–based endometrial cancer (EC) MR imaging (ECM). Methods We retrospectively enrolled 530 patients with pathologically proven EC at our institution between January 1, 2013, and December 31, 2017. All imaging data were reviewed on picture archiving and communication systems (PACS) server. Both sagittal and coronal T2WI-based MR images were used for lesion area determination. All MR images were divided into two groups: deep (more than 50%) and shallow (less than 50%) MI based on their pathological diagnosis. We trained a detection model based on YOLOv3 algorithm to locate the lesion area on ECM. Then, the detected regions were fed into a classification model based on DL network to identify MI depth automatically. Results In the testing dataset, the trained model detected lesion regions with an average precision rate of 77.14% and 86.67% in both sagittal and coronal images, respectively. The classification model yielded an accuracy of 84.78%, a sensitivity of 66.67%, a specificity of 87.50%, a positive predictive value of 44.44%, and a negative predictive value of 94.59% in determining deep MI. The radiologists and trained network model together yielded an accuracy of 86.2%, a sensitivity of 77.8%, a specificity of 87.5%, a positive predictive value of 48.3%, and a negative predictive value of 96.3%. Conclusion In this study, the DL network model derived from MR imaging provided a competitive, time-efficient diagnostic performance in MI depth identification. Key Points • The models established with the deep learning method could help improve the diagnostic confidence and performance of MI identification based on endometrial cancer MR imaging. • The models enabled the classification of endometrial cancer MR images to the two categories with a sensitivity of 0.67, a specificity of 0.88, and an accuracy of 0.85. • Using the detected lesion region to evaluate myometrial invasion depth could remove redundant information in the image and provide more effective features.Keywords
Funding Information
- National Natural Science Foundation of China (61731009, 81771816)
This publication has 34 references indexed in Scilit:
- Endometrial cancerThe Lancet, 2015
- Endometrial Cancer: Combined MR Volumetry and Diffusion-weighted Imaging for Assessment of Myometrial and Lymphovascular Invasion and Tumor GradeRadiology, 2015
- Preoperative MRI and Intraoperative Frozen Section Diagnosis of Myometrial Invasion In Patients With Endometrial CancerInternational Journal of Gynecologic Cancer, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Endometrial cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-upAnnals of Oncology, 2013
- The Added Role of MR Imaging in Treatment Stratification of Patients with Gynecologic Malignancies: What the Radiologist Needs to KnowRadiology, 2013
- Recurrent Processing during Object RecognitionFrontiers in Psychology, 2013
- Endometrial cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-upAnnals of Oncology, 2010
- NATURE AND ACTIVITY OF VITAMIN B6 BOUND IN HEAT-PROCESSED FOODSNutrition Reviews, 2009
- The relationship between Precision-Recall and ROC curvesPublished by Association for Computing Machinery (ACM) ,2006