Abstract
Automated nodule detection in the ultrasound image is essential for computer-aided thyroid tumor diagnosis. However, in the ultrasound image, the solid nodule has imaging characteristics similar to other tissues, making it challenging to detect such nodules. Therefore, we proposed a feature-enhanced dual-branch network (FDnet) to complete the nodule detection task by adding a semantic segmentation branch and a feature enhancement mechanism into the detection network. This design improves the target area’s proposal score and suppresses the interference of similar tissues, which can reduce the false-positive rate of the proposed bounding box and finally obtain more reliable detection results. Additionally, to solve the lack of fine-grained mask information for semantic segmentation branch training in the actual scenario, we also proposed an iterative training strategy that combines the ground-truth boundary box with the branch results to generate a pseudo-label mask. Finally, we carried out various comparative experiments to verify the feasibility of the proposed network and training strategy. A series of experiments showed that FDnet could achieve competitive detection performance (mAP: 61.8/92.5/65.9), which metrics are better than the state-of-the-art detection methods. Besides, the performance using the pseudo-label mask training is also close to using the ground-truth mask in the public dataset, and the inference speed per image is also comparable to that of other networks both in the two datasets. This result shows that our method can improve the efficiency of thyroid nodule detection without fine-grained annotation, and the output result of the trained semantic segmentation branch can guide the further segmentation of nodule edge, which has practical clinical significance. We will release the source code and the public dataset at https://github.com/songruoning/Thyroid_Solid_Nodule.
Similar content being viewed by others
References
Song R, Zhang L, Zhu C, Liu J, Yang J, Zhang T (2020) Thyroid nodule ultrasound image classification through hybrid feature cropping network. IEEE Access 8:64,064–64,074. https://doi.org/10.1109/ACCESS.2020.2982767
Vander JB, Gaston EA, Dawber TR (1968) The significance of nontoxic thyroid nodules: final report of a 15-year study of the incidence of thyroid malignancy. Ann Intern Med 69(3):537–540
Tan GH, Gharib H (1997) Thyroid incidentalomas: management approaches to nonpalpable nodules discovered incidentally on thyroid imaging. Ann Intern Med 126(3):226–231
Qin P, Wu K, Hu Y, Zeng J, Chai X (2019) Diagnosis of benign and malignant thyroid nodules using combined conventional ultrasound and ultrasound elasticity imaging. IEEE J Biomed Health Inform 24 (4):1028–1036
Kwak JY, Han KH, Yoon JH, Moon HJ, Son EJ, Park SH, Jung HK, Choi JS, Kim BM, Kim EK (2011) Thyroid imaging reporting and data system for us features of nodules: a step in establishing better stratification of cancer risk. Radiology 260(3):892–899
Smith-Bindman R, Lebda P, Feldstein VA, Sellami D, Goldstein RB, Brasic N, Jin C, Kornak J (2013) Risk of thyroid cancer based on thyroid ultrasound imaging characteristics: results of a population-based study. JAMA Int Med 173(19):1788–1795
Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L (2017) European thyroid association guidelines for ultrasound malignancy risk stratification of thyroid nodules in adults: the eu-tirads. Eur Thyroid J 6(5):225–237
Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imaging 25(8):987–1010
Maroulis DE, Savelonas MA, Iakovidis DK, Karkanis SA, Dimitropoulos N (2007) Variable background active contour model for computer-aided delineation of nodules in thyroid ultrasound images. IEEE J Biomed Health Inform 11(5):537– 543
Cheng HD, Shan J, Ju W, Guo Y, Zhang L (2010) Automated breast cancer detection and classification using ultrasound images: A survey. Pattern Recognit 43(1):299–317
Lee YH, Kim DW, In HS, Park JS, Kim SH, Eom JW, Kim B, Lee EJ, Rho MH (2011) Differentiation between benign and malignant solid thyroid nodules using an us classification system. Korean J Radiol 12(5):559–567
Unsal O, Akpinar M, Turk B, Ucak I, Ozel A, Kayaoglu S, Coskun BU (2017) Sonographic scoring of solid thyroid nodules: effects of nodule size and suspicious cervical lymph node. Braz J Otorhinolaryngol 83(1):73–79
Chang RF, Wu WJ, Moon WK, Chen DR (2005) Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat 89(2):179
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142–158. https://doi.org/10.1109/TPAMI.2015.2437384
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Song W, Li S, Liu J, Qin H, Zhang B, Zhang S, Hao A (2018) Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition. IEEE J Biomed Health Inf 23 (3):1215–1224
Liu R, Zhou S, Guo Y, Wang Y, Chang C (2020) Nodule localization in thyroid ultrasound images with a joint-training convolutional neural network. J Digit Imaging 33(5):1266– 1279
Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikäinen M (2020) Deep learning for generic object detection: A survey. Int J Comput Vis 128(2):261–318
Liu H, Fang S, Zhang Z, Li D, Lin K, Wang J (2021) Mfdnet: Collaborative poses perception and matrix fisher distribution for head pose estimation. IEEE Trans Multimed
Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Dai J, He K, Sun J (2016) Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3150–3158
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961–2969
Huang Z, Huang L, Gong Y, Huang C, Wang X (2019) Mask scoring r-cnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6409–6418
Wu Y, Chen Y, Yuan L, Liu Z, Wang L, Li H, Fu Y (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10,186–10,195
Zhang H, Chang H, Ma B, Wang N, Chen X (2020) Dynamic r-cnn: Towards high quality object detection via dynamic training. In: European Conference on Computer Vision. Springer, pp 260–275
Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9627–9636
Chen H, Sun K, Tian Z, Shen C, Huang Y, Yan Y (2020) Blendmask: Top-down meets bottom-up for instance segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8573–8581
Tong K, Wu Y, Zhou F (2020) Recent advances in small object detection based on deep learning: A review. Image Vision Comput 97:103910
Lee DH, et al. (2013) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML, vol. 3
Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: Proceedings of the IEEE international conference on computer vision, pp 3754–3762
Oliver A, Odena A, Raffel C, Cubuk ED, Goodfellow IJ (2018) Realistic evaluation of deep semi-supervised learning algorithms. arXiv:1804.09170
Liu X, Van De Weijer J, Bagdanov AD (2019) Exploiting unlabeled data in cnns by self-supervised learning to rank. IEEE Trans Pattern Anal Mach Intell 41(8):1862–1878
Li X, Chen W, Xie D, Yang S, Yuan P, Pu S, Zhuang Y (2020) A free lunch for unsupervised domain adaptive object detection without source data. arXiv:2012.05400
Xie Q, Luong MT, Hovy E, Le QV (2020) Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10,687–10,698
Li S, Huang J, Hua XS, Zhang L (2021) Category dictionary guided unsupervised domain adaptation for object detection. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 1949–1957
Li Z, Liu H, Zhang Z, Liu T, Xiong NN (2021) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Trans Neural Netw Learn Syst
Zhao X, Liang S, Wei Y (2018) Pseudo mask augmented object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4061–4070
Zhang Y, Bai Y, Ding M, Li Y, Ghanem B (2018) Weakly-supervised object detection via mining pseudo ground truth bounding-boxes. Pattern Recogn 84:68–81
Yan P, Li G, Xie Y, Li Z, Wang C, Chen T, Lin L (2019) Semi-supervised video salient object detection using pseudo-labels. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 7284–7293
Liu T, Liu H, Li YF, Chen Z, Zhang Z, Liu S (2019) Flexible ftir spectral imaging enhancement for industrial robot infrared vision sensing. IEEE Trans Industr Inform 16(1):544–554
Liu J, Wang X, Wang R, Xu C, Zhao R, Li H, Zhang S, Yao X (2020) Near-infrared auto-fluorescence spectroscopy combining with fisher’s linear discriminant analysis improves intraoperative real-time identification of normal parathyroid in thyroidectomy. BMC Surgery 20(1):1–7
Wu X, Tan G, Zhu N, Chen Z, Yang Y, Wen H, Li K (2021) Cachetrack-yolo: Real-time detection and tracking for thyroid nodules and surrounding tissues in ultrasound videos. IEEE J Biomed Health Inf:1–1. https://doi.org/10.1109/JBHI.2021.3084962
Kumar V, Webb J, Gregory A, Meixner DD, Knudsen JM, Callstrom M, Fatemi M, Alizad A (2020) Automated segmentation of thyroid nodule, gland, and cystic components from ultrasound images using deep learning. IEEE Access 8:63,482–63,496
Gong H, Chen G, Wang R, Xie X, Mao M, Yu Y, Chen F, Li G (2021) Multi-task learning for thyroid nodule segmentation with thyroid region prior. In: 2021 IEEE 18th International symposium on biomedical imaging (ISBI). IEEE, pp 257–261
Kesarkar XA, Kulhalli K (2021) Thyroid nodule detection using artificial neural network. In: 2021 International conference on artificial intelligence and smart systems (ICAIS). IEEE, pp 11–15
Chi J, Walia E, Babyn P, Wang J, Groot G, Eramian M (2017) Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J Digital Imaging 30(4):477–486
Gomes Ataide EJ, Ponugoti N, Illanes A, Schenke S, Kreissl M, Friebe M (2020) Thyroid nodule classification for physician decision support using machine learning-evaluated geometric and morphological features. Sensors 20(21):6110
Vadhiraj VV, Simpkin A, O’Connell J, Singh Ospina N, Maraka S, O’Keeffe DT (2021) Ultrasound image classification of thyroid nodules using machine learning techniques. Medicina 57(6):527
Avola D, Cinque L, Fagioli A, Filetti S, Grani G, Rodolà E (2021) Multimodal feature fusion and knowledge-driven learning via experts consult for thyroid nodule classification. IEEE Trans Circuits Syst Video Technol
Zhu C, Tao S, Chen H, Li M, Wang Y, Liu J, Jin M (2021) Hybrid model enabling highly efficient follicular segmentation in thyroid cytopathological whole slide image. Intelligent Medicine
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Lin TY, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241
Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: A metric and a loss for bounding box regression. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 658–666
Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) Unitbox: An advanced object detection network. In: Proceedings of the 24th ACM international conference on multimedia, pp 516–520
Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X, Sun S, Feng W, Liu Z, Xu J et al (2019) Mmdetection: Open mmlab detection toolbox and benchmark. arXiv:1906.07155
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8026–8037
Pedraza L, Vargas C, Narváez F, Durán O, Muñoz E, Romero E (2015) An open access thyroid ultrasound image database. In: 10th International symposium on medical information processing and analysis, vol 9287. International Society for Optics and Photonics, p 92870W
Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the european conference on computer vision (ECCV), pp 734–750
Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: ECCV
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, pp 21–37
Chen Q, Wang Y, Yang T, Zhang X, Cheng J, Sun J (2021) You only look one-level feature. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13,039–13,048
Cai Z, Vasconcelos N (2019) Cascade r-cnn: High quality object detection and instance segmentation. IEEE Trans Pattern Anal Mach Intell
Acknowledgements
The authors thank Taolue Feng and Yanting Zhang for their assistance with data analysis and language check.
In addition, the work is conducted on the platform of Center for Data Science of Beijing University of Posts and Telecommunications.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
All data were evaluated retrospectively. All studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee. The number of ethical approval file is No. 2020056.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Ruoning Song and Chuang Zhu contributed equally to this work.
Rights and permissions
About this article
Cite this article
Song, R., Zhu, C., Zhang, L. et al. Dual-branch network via pseudo-label training for thyroid nodule detection in ultrasound image. Appl Intell 52, 11738–11754 (2022). https://doi.org/10.1007/s10489-021-02967-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02967-2