The Segmentation of Multiple Types of Uterine Lesions in Magnetic Resonance Images Using a Sequential Deep Learning Method with Image-Level Annotations
Authors:
- 16 January 2024
- journal article
- research article
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 37 (1) , 374-385
Abstract
Fully supervised medical image segmentation methods use pixel-level labels to achieve good results, but obtaining such large-scale, high-quality labels is cumbersome and time consuming. This study aimed to develop a weakly supervised model that only used image-level labels to achieve automatic segmentation of four types of uterine lesions and three types of normal tissues on magnetic resonance images. The MRI data of the patients were retrospectively collected from the database of our institution, and the T2-weighted sequence images were selected and only image-level annotations were made. The proposed two-stage model can be divided into four sequential parts: the pixel correlation module, the class re-activation map module, the inter-pixel relation network module, and the Deeplab v3 + module. The dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average symmetric surface distance (ASSD) were employed to evaluate the performance of the model. The original dataset consisted of 85,730 images from 316 patients with four different types of lesions (i.e., endometrial cancer, uterine leiomyoma, endometrial polyps, and atypical hyperplasia of endometrium). A total number of 196, 57, and 63 patients were randomly selected for model training, validation, and testing. After being trained from scratch, the proposed model showed a good segmentation performance with an average DSC of 83.5%, HD of 29.3 mm, and ASSD of 8.83 mm, respectively. As far as the weakly supervised methods using only image-level labels are concerned, the performance of the proposed model is equivalent to the state-of-the-art weakly supervised methods.Keywords
Funding Information
- National Natural Science Foundation of China (82003843)
- Natural Science Foundation of Liaoning Province (2020-BS-221)
- Dalian medical science research program (2211023)
This publication has 24 references indexed in Scilit:
- Automatic coronary artery segmentation and diagnosis of stenosis by deep learning based on computed tomographic coronary angiographyEuropean Radiology, 2022
- Semi-supervised medical image segmentation via a tripled-uncertainty guided mean teacher model with contrastive learningMedical Image Analysis, 2022
- Fully automated intracardiac 4D flow MRI post-processing using deep learning for biventricular segmentationEuropean Radiology, 2022
- Polycystic liver: automatic segmentation using deep learning on CT is faster and as accurate compared to manual segmentationEuropean Radiology, 2022
- Combined model-based and deep learning-based automated 3D zonal segmentation of the prostate on T2-weighted MR images: clinical evaluationEuropean Radiology, 2022
- Puzzle-CAM: Improved Localization Via Matching Partial And Full Features2021
- Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations2019
- Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation2018
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation2016
- Learning Deep Features for Discriminative Localization2016