Deep Learning-Based Automatic Endometrium Segmentation and Thickness Measurement for 2D Transvaginal Ultrasound

Hu, Szu-Yeu; Xu, Hong; Li, Qian; Telfer, Brian A.; Brattain, Laura J.; Samir, Anthony E.

doi:10.1109/embc.2019.8856367

Cited by 13 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 46 Using segmentation based on U‐net, the medial axis transformation method was used to estimate endometrial thickness. 47 The results were within the clinically acceptable range of 2 mm, which greatly reduced the error of manual measurement. Another ultrasound feature in the evaluation of ER is the endometrial pattern, which can be divided into a trilinear (or leaf), semi‐trilinear, and unilinear (or homogeneous) patterns.…”

Section: Ai‐aided Ultrasound: Improving Accuracy In the Assessment Of...mentioning

confidence: 54%

See 1 more Smart Citation

Artificial Intelligence in the Assessment of Female Reproductive Function Using Ultrasound: A Review

Chen

Wang

et al. 2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

The incidence of infertility is continuously increasing nearly all over the world in recent years, and novel methods for accurate assessment are of great need. Artificial Intelligence (AI) has gradually become an effective supplementary method for the assessment of female reproductive function. It has been used in clinical follicular monitoring, optimum timing for transplantation, and prediction of pregnancy outcome. Some literatures summarize the use of AI in this field, but few of them focus on the assessment of female reproductive function by AI‐aided ultrasound. In this review, we mainly discussed the applicability, feasibility, and value of clinical application of AI in ultrasound to monitor follicles, assess endometrial receptivity, and predict the pregnancy outcome of in vitro fertilization and embryo transfer (IVF‐ET). The limitations, challenges, and future trends of ultrasound combined with AI in providing efficient and individualized evaluation of female reproductive function had also been mentioned.

show abstract

Section: Ai‐aided Ultrasound: Improving Accuracy In the Assessment Of...mentioning

confidence: 54%

“…Application of AI in the assessment of female reproductive function. ET, embryo transfer [45][46][47]49.…”

mentioning

confidence: 99%

Artificial Intelligence in the Assessment of Female Reproductive Function Using Ultrasound: A Review

Chen

Wang

et al. 2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

show abstract

“…However, that group proposed a semiautomated endometrium segmentation from TVUS images using key point discriminators. Hu et al proposed a deep learning-based thickness measurement from TVUS images from healthy participants Hu et al (2019) . In contrast, our study was not limited to those with normal, healthy endometria, but included cases with endometrial cancer and polyps, in whom endometrium segmentation is challenging because the endometrium is usually irregular and difficult to identify.…”

Section: Discussionmentioning

confidence: 99%

“…ResNet50 serves as the backbone of SegNet, and is used to extract features in images for segmentation Hu et al (2019) . ResNet50 has 50 layers and was pretrained using the ImageNet Large Scale Visual Recognition Challenge 2012 classification dataset, consisting of 1.2 million training images, with 1,000 classes of objects He et al (2016) .…”

Section: Methodsmentioning

confidence: 99%

Automatic Measurement of Endometrial Thickness From Transvaginal Ultrasound Images

Liu

Zhou

Peng

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Purpose: Endometrial thickness is one of the most important indicators in endometrial disease screening and diagnosis. Herein, we propose a method for automated measurement of endometrial thickness from transvaginal ultrasound images.Methods: Accurate automated measurement of endometrial thickness relies on endometrium segmentation from transvaginal ultrasound images that usually have ambiguous boundaries and heterogeneous textures. Therefore, a two-step method was developed for automated measurement of endometrial thickness. First, a semantic segmentation method was developed based on deep learning, to segment the endometrium from 2D transvaginal ultrasound images. Second, we estimated endometrial thickness from the segmented results, using a largest inscribed circle searching method. Overall, 8,119 images (size: 852 × 1136 pixels) from 467 cases were used to train and validate the proposed method.Results: We achieved an average Dice coefficient of 0.82 for endometrium segmentation using a validation dataset of 1,059 images from 71 cases. With validation using 3,210 images from 214 cases, 89.3% of endometrial thickness errors were within the clinically accepted range of ±2 mm.Conclusion: Endometrial thickness can be automatically and accurately estimated from transvaginal ultrasound images for clinical screening and diagnosis.

show abstract

“…10 Deep learning for segmentation in ultrasound images has previously been studied by others. [11][12][13][14][15][16][17] Two recent studies using, in the field of prostate brachytherapy, deep learning has been utilized for needle digitization in prostate brachytherapy 18,19 trained the algorithm using patches instead of the whole image volume, and employed a weighted loss function between cross entropy and total variation for optimization. However, other metrics exist describing intersection over union, such as the Dice similarity coefficient.…”

Section: Introduction and Purposementioning

confidence: 99%

Deep learning‐based digitization of prostate brachytherapy needles in ultrasound images

et al. 2020

View full text Add to dashboard Cite

To develop, and evaluate the performance of, a deep learning-based three-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy. Methods: Transrectal ultrasound (TRUS) image volumes from 1102 treatments were used to create a clinical ground truth (CGT) including 24422 individual needles that had been manually digitized by medical physicists during brachytherapy procedures. A 3D CNN U-net with 128 × 128 × 128 TRUS image volumes as input was trained using 17215 needle examples. Predictions of voxels constituting a needle were combined to yield a 3D linear function describing the localization of each needle in a TRUS volume. Manual and AI digitizations were compared in terms of the root-mean-square distance (RMSD) along each needle, expressed as median and interquartile range (IQR). The method was evaluated on a data set including 7207 needle examples. A subgroup of the evaluation data set (n = 188) was created, where the needles were digitized once more by a medical physicist (G1) trained in brachytherapy. The digitization procedure was timed. Results: The RMSD between the AI and CGT was 0.55 (IQR: 0.35-0.86) mm. In the smaller subset, the RMSD between AI and CGT was similar (0.52 [IQR: 0.33-0.79] mm) but significantly smaller (P < 0.001) than the difference of 0.75 (IQR: 0.49-1.20) mm between AI and G1. The difference between CGT and G1 was 0.80 (IQR: 0.48-1.18) mm, implying that the AI performed as well as the CGT in relation to G1. The mean time needed for human digitization was 10 min 11 sec, while the time needed for the AI was negligible. Conclusions: A 3D CNN can be trained to identify needles in TRUS images. The performance of the network was similar to that of a medical physicist trained in brachytherapy. Incorporating a CNN for needle identification can shorten brachytherapy treatment procedures substantially.

show abstract

Deep Learning-Based Automatic Endometrium Segmentation and Thickness Measurement for 2D Transvaginal Ultrasound

Cited by 13 publications

References 21 publications

Artificial Intelligence in the Assessment of Female Reproductive Function Using Ultrasound: A Review

Artificial Intelligence in the Assessment of Female Reproductive Function Using Ultrasound: A Review

Automatic Measurement of Endometrial Thickness From Transvaginal Ultrasound Images

Deep learning‐based digitization of prostate brachytherapy needles in ultrasound images

Contact Info

Product

Resources

About