DMU-Net: Dual-route mirroring U-Net with mutual learning for malignant thyroid nodule segmentation

Yang, Qinghan; Geng, Chong; Chen, Ruyue; Pang, Chen; Han, Run; Lyu, Lei; Zhang, Yuang

doi:10.1016/j.bspc.2022.103805

Cited by 14 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[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