MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Segmentation Accuracy and Radiomics Feature Stability of Multiple U-Net Based Automatic Segmentations On Ultrasound Images for Patients with Ovarian Cancer

X Jin1*, J Jin2, C Xie3, (1) Wenzhou Medical University First Hospital, Wenzhou, ,CN, (2) ,,,(3) ,Wenzhou, ,CN

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose: studies have reported the reproducibility and stability of ultrasound (US) based radiomics features obtained from automatic segmentation in oncology. The purpose of this study is to investigate the accuracy of automatic segmentation algorithms based on multiple U-net models and their effect on radiomics features on US images for patients with ovarian cancer.


Methods:
A total of 469 ultrasound images from 127 patients were collected and randomly divided into three groups: training sets (353 images), validation sets (23 images), and test sets (93 images) for automatic segmentation models building. Manual segmentation of target volumes was delineated as ground truth. Automatic segmentations were conducted with U-net, U-net++, U-net with Resnet as the backbone (U-net with Resnet), and CE-Net. A python 3.7.0 and package Pyradiomics 2.2.0 were used to extract radiomic features from the segmented target volumes.

Results:
CE-Net and U-net with Resnet outperformed U-net and U-net++ in accuracy performance by achieving a dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and average surface distance (ASD)of 0.87, 0.79, 8.54 and 0.86, 0.78, 10.00, respectively. A total of 97 features were extracted from the delineated target volumes. The average Pearson correlation was 0.87 (95% CI, 0.84-0.90), 0.88 (95% CI, 0.86-0.91), 0.86 (95% CI, 0.83-0.89), and 0.90 (95% CI, 0.88-0.92) for U-net, U-net with Resnet, U-net++, and CE-Net, respectively. The average intraclass correlation coefficients (ICC) was 0.85 (95% CI, 0.82-0.88), 0.88 (95% CI, 0.85-0.90), 0.84 (95% CI, 0.81-0.87), and 0.89 (95% CI, 0.86-0.91) for U-net, U-net with Resnet, U-net++, and CE-Net, respectively. CE-Net based segmentation achieved the best radiomics reliability.

Conclusion: based automatic segmentation was accurate enough to delineate the target volumes on US images for patients with ovarian cancer. Radiomics features extracted from automatic segmented targets showed high reliability and reproducibility for further radiomics investigations.

Keywords

Ultrasonics, Segmentation, Image Analysis

Taxonomy

IM- Ultrasound : Segmentation

Contact Email