An Ultrasound Image Segmentation Method for Thyroid Nodules Based on Dual-path Attention Mechanism-enhanced UNet+

Overview

Journal BMC Med Imaging

Publisher Biomed Central

Specialty Radiology

Date 2024 Dec 19

PMID 39695984

Authors

Peizhen Dong

Ronghua Zhang

Jun Li

Changzheng Liu

Wen Liu

Jiale Hu

Yongqiang Yang

Xiang Li

Affiliations

Soon will be listed here.

Abstract

Purpose: This study aims to design an auxiliary segmentation model for thyroid nodules to increase diagnostic accuracy and efficiency, thereby reducing the workload of medical personnel.

Methods: This study proposes a Dual-Path Attention Mechanism (DPAM)-UNet++ model, which can automatically segment thyroid nodules in ultrasound images. Specifically, the model incorporates dual-path attention modules into the skip connections of the UNet++ network to capture global contextual information in feature maps. The model's performance was evaluated using Intersection over Union (IoU), F1_score, accuracy, etc. Additionally, a new integrated loss function was designed for the DPAM-UNet++ network.

Results: Comparative experiments with classical segmentation models revealed that the DPAM-UNet++ model achieved an IoU of 0.7451, an F1_score of 0.8310, an accuracy of 0.9718, a precision of 0.8443, a recall of 0.8702, an Area Under Curve (AUC) of 0.9213, and an HD95 of 35.31. Except for the precision metric, this model outperformed the other models on all the indicators and achieved a segmentation effect that was more similar to that of the ground truth labels. Additionally, ablation experiments verified the effectiveness and necessity of the dual-path attention mechanism and the integrated loss function.

Conclusion: The segmentation model proposed in this study can effectively capture global contextual information in ultrasound images and accurately identify the locations of nodule areas. The model yields excellent segmentation results, especially for small and multiple nodules. Additionally, the integrated loss function improves the segmentation of nodule edges, enhancing the model's accuracy in segmenting edge details.

References

Sun G, Pan Y, Kong W, Xu Z, Ma J, Racharak T . DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation. Front Bioeng Biotechnol. 2024; 12():1398237. PMC: 11141164. DOI: 10.3389/fbioe.2024.1398237. View

Cui R, Yang R, Liu F, Geng H . HDA-Net: A novel dual gated attention network using comprehensive hybrid dilated convolutions for medical image segmentation. Comput Biol Med. 2022; 152:106384. DOI: 10.1016/j.compbiomed.2022.106384. View

Nie X, Zhou X, Tong T, Lin X, Wang L, Zheng H . N-Net: A novel dense fully convolutional neural network for thyroid nodule segmentation. Front Neurosci. 2022; 16:872601. PMC: 9475170. DOI: 10.3389/fnins.2022.872601. View

Kang Q, Lao Q, Li Y, Jiang Z, Qiu Y, Zhang S . Thyroid nodule segmentation and classification in ultrasound images through intra- and inter-task consistent learning. Med Image Anal. 2022; 79:102443. DOI: 10.1016/j.media.2022.102443. View

Shahroudnejad A, Vega R, Forouzandeh A, Balachandran S, Jaremko J, Noga M . Thyroid Nodule Segmentation and Classification Using Deep Convolutional Neural Network and Rule-based Classifiers. Annu Int Conf IEEE Eng Med Biol Soc. 2021; 2021:3118-3121. DOI: 10.1109/EMBC46164.2021.9629557. View

Chambara N, Ying M . The Diagnostic Efficiency of Ultrasound Computer-Aided Diagnosis in Differentiating Thyroid Nodules: A Systematic Review and Narrative Synthesis. Cancers (Basel). 2019; 11(11). PMC: 6896127. DOI: 10.3390/cancers11111759. View

Tang L, Tian C, Yang H, Cui Z, Hui Y, Xu K . TS-DSANN: Texture and shape focused dual-stream attention neural network for benign-malignant diagnosis of thyroid nodules in ultrasound images. Med Image Anal. 2023; 89:102905. DOI: 10.1016/j.media.2023.102905. View

Yeung M, Sala E, Schonlieb C, Rundo L . Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Comput Med Imaging Graph. 2021; 95:102026. PMC: 8785124. DOI: 10.1016/j.compmedimag.2021.102026. View

Rehman A, Ehsan M, Javed H, Ameer M, Mohsin A, Rehman M . Solitary and multiple thyroid nodules as predictors of malignancy: a systematic review and meta-analysis. Thyroid Res. 2022; 15(1):22. PMC: 9720983. DOI: 10.1186/s13044-022-00140-6. View

10.

Chen G, Tan G, Duan M, Pu B, Luo H, Li S . MLMSeg: A multi-view learning model for ultrasound thyroid nodule segmentation. Comput Biol Med. 2024; 169:107898. DOI: 10.1016/j.compbiomed.2023.107898. View

11.

Wang Z, Bovik A, Sheikh H, Simoncelli E . Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004; 13(4):600-12. DOI: 10.1109/tip.2003.819861. View

12.

Gong H, Chen J, Chen G, Li H, Li G, Chen F . Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules. Comput Biol Med. 2023; 155:106389. DOI: 10.1016/j.compbiomed.2022.106389. View

13.

Wang S, Li Z, Liao L, Zhang C, Zhao J, Sang L . DPAM-PSPNet: ultrasonic image segmentation of thyroid nodule based on dual-path attention mechanism. Phys Med Biol. 2023; 68(16). DOI: 10.1088/1361-6560/ace6f1. View

14.

Bray F, Laversanne M, Sung H, Ferlay J, Siegel R, Soerjomataram I . Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024; 74(3):229-263. DOI: 10.3322/caac.21834. View

15.

Chen J, You H, Li K . A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images. Comput Methods Programs Biomed. 2020; 185:105329. DOI: 10.1016/j.cmpb.2020.105329. View

16.

Yang B, Yan M, Yan Z, Zhu C, Xu D, Dong F . Segmentation and classification of thyroid follicular neoplasm using cascaded convolutional neural network. Phys Med Biol. 2020; 65(24):245040. DOI: 10.1088/1361-6560/abc6f2. View

17.

Ma J, Chen J, Ng M, Huang R, Li Y, Li C . Loss odyssey in medical image segmentation. Med Image Anal. 2021; 71:102035. DOI: 10.1016/j.media.2021.102035. View

18.

Yadav N, Dass R, Virmani J . Objective assessment of segmentation models for thyroid ultrasound images. J Ultrasound. 2022; 26(3):673-685. PMC: 10469139. DOI: 10.1007/s40477-022-00726-8. View

19.

Song J, Chen X, Zhu Q, Shi F, Xiang D, Chen Z . Global and Local Feature Reconstruction for Medical Image Segmentation. IEEE Trans Med Imaging. 2022; 41(9):2273-2284. DOI: 10.1109/TMI.2022.3162111. View