SGUNET: Semantic Guided UNET For Thyroid Nodule Segmentation

Pan, Huitong; Zhou, Quan; Latecki, Longin Jan

doi:10.1109/isbi48211.2021.9434051

Cited by 27 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also introduced a false output suppression mechanism that combines patch-wise classification and segmentation results to eliminate false positive. [20] adopts spatial attention on US image segmentation task.…”

Section: B Us Segmentationmentioning

confidence: 99%

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

Li¹,

Han²,

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: B Us Segmentationmentioning

confidence: 99%

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

Li¹,

Han²,

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

“…1) Semantic Guided UNet (SGUNet): SGUNet [14] is a UNet inspired architecture designed specifically for thyroid nodule segmentation in ultrasound. Their primary innovation is the SGM module, which reduces noise interference inherent to ultrasound imaging that may be propagated in the encoding layer convolutions as well as in the skip connections to the decoder layers.…”

Section: Segmentation Architecturesmentioning

confidence: 99%

“…[11] Multiple past works have developed novel deep learning architectures to address automated segmentation of thyroid nodules. [12; 13; 14; 15] A majority of these works have studied the U-Net architecture; however, this architecture uses the same convolutional filter size, resulting in a fixed receptive field which hampers the segmentation of objects that vary in size. In response to this issue, Su et al proposed MSUNet,[16] which introduces a multi-scale block in each layer of the encoder to fuse the outputs of convolution kernels with different receptive fields.…”

Section: Introductionmentioning

confidence: 99%

A Multitask Approach for Automated Detection and Segmentation of Thyroid Nodules in Ultrasound Images

Radhachandran

Kinzel

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

Objective: Poor risk stratification of thyroid nodules by ultrasound has motivated the need for a deep learning-based approach for nodule segmentation. This paper demonstrates the effectiveness of a multitask approach to detect ultrasounds containing potential nodules and segment nodules on the suspected images. Methods: Ultrasound studies were acquired from 280 patients at UCLA Health, totaling 9888 images. A novel anomaly detection (AD) module, to classify suspicious ultrasound images, was integrated with various state of the art segmentation architectures. The trained models were evaluated on a portion of the in-house dataset, as well as two external validation (EV) sets, to understand how the AD module affected segmentation performance. Results: The addition of AD to the architectures improved image-level nodule detection, evidenced by the increase in F1 scores and image-wide Dice similarity coefficient. Of the models with AD, MSUNet-AD had the highest F1 score of 0.829; however, there was a decrease in DSC on just images with nodules (DSC+) from 0.726 to 0.627. This drop was observed across all models when AD was added; however, closer analysis of DSC+by nodule size revealed that this difference was not significant in larger nodules, which are more likely to be clinically relevant. Finally, evaluation of MSUNet with and without AD on the EV datasets demonstrated comparable performance with the UCLA dataset. Conclusion: The proposed architecture is an automated multitask method that can both detect and segment nodules in ultrasound. Performance on the EV datasets demonstrates generalizability of the model.

show abstract

“…Typically, UNet or variant of UNet architecture 33,34 has been successfully used in segmentation tasks and achieves excellent performance, such as in tasks of nodules segmentation. [35][36][37] Ding et al 38 propose an improved U-Net model for ultrasound image segmentation by embedding the improved residual unit in the skip connection between encoding and decoding paths. The model also introduces an attention gate mechanism multiplied by the weighted feature maps obtained from the shallow and deep layers.The results validate the efficacy of these design principles of the improved U-Net model, resulting in a performance improvement of 4.9% against the original U-Net architecture.…”

Section: Related Workmentioning

confidence: 99%

“…The network treats the segmentation problem as a patch classification task, which takes as input the ultrasound image patches of thyroid nodules and outputs final segmentation probabilities. Typically, UNet or variant of UNet architecture 33,34 has been successfully used in segmentation tasks and achieves excellent performance, such as in tasks of nodules segmentation 35–37 . Ding et al 38 .…”

Section: Related Workmentioning

confidence: 99%

A two‐stage network with prior knowledge guidance for medullary thyroid carcinoma recognition in ultrasound images

et al. 2022

View full text Add to dashboard Cite

Accurate recognition of medullary thyroid carcinoma (MTC) is of great importance in medical diagnosis, as MTC is rare but second-most malignant thyroid cancers with a high case-fatality ratio. 1 But there is a lower recognition rate on distinguishing MTC from other thyroid nodules in ultrasound images, even by experienced experts. This paper introduces the computer-aided method to tackle the challenge of recognizing MTC from ultrasound images, including limited MTC samples, and ambiguities among MTC, benign nodules, and papillary thyroid carcinoma (PTC). Methods: The recognition of MTC based on large MTC samples of ultrasound images has never been explored, as only one existing work presented a relevant dataset with a limited 21 MTC samples. This study proposes a novel method for primarily differentiating MTC samples from benign nodules and PTC that is the most common thyroid cancer. Our method is a two-stage schema with two important components including a cascaded coarse-to-fine segmentation network and a knowledge-based classification network. The cascaded coarseto-fine segmentation network incorporates two U-Net++ networks for improving the segmentation results of thyroid nodules. Meanwhile, our knowledge-based classification network extracts and fuses semantic features of solid tissues and calcification for better recognizing the segmented nodules from the ultrasound images. In our experiments, dice similarity coefficient (DSC), intersection over union (IoU),precision,recall,and Hausdorff distance (HD) are adopted for evaluating the segmentation results of thyroid nodules, and accuracy, precision, recall, and F1-score are used for classification evaluation. Results: We present a well-annotated dataset including samples of 248 MTC, 240 benign nodules, and 239 PTC. For thyroid nodule segmentation, our designed cascaded segmentation network attains values of 0.776 DSC, 0.689 IoU, 0.778 precision, and 0.821 recall, respectively. By incorporating prior knowledge, our method achieves a mean accuracy of 82.1% in classifying thyroid nodules of MTC, PTC, and benign ones. Especially, our method gains the higher performance in recognizing MTC with an accuracy of 86.8%,compared to nearly 70% diagnosis accuracy of experienced doctors. The experimental results on our Fujian Provincial Hospital dataset further validate the efficiency of our proposed method. Conclusions: Our proposed two-stage method incorporates pipelines of thyroid nodules segmentation and classification of MTC, individually. Quantitative and qualitative results indicate that our proposed model achieves accurate segmentation of thyroid nodules. The results also validate that our learning-based

show abstract

SGUNET: Semantic Guided UNET For Thyroid Nodule Segmentation

Cited by 27 publications

References 9 publications

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

A Multitask Approach for Automated Detection and Segmentation of Thyroid Nodules in Ultrasound Images

A two‐stage network with prior knowledge guidance for medullary thyroid carcinoma recognition in ultrasound images

Contact Info

Product

Resources

About