The intelligent diagnosis of thyroid nodules in ultrasound image is an important research issue. Automatically locating the region of interest (ROI) of thyroid nodules and providing pre-diagnosis results can help doctors to diagnose faster and more accurate.
OBJECTIVES:
This study aims to propose a model, which can detect multiple nodules stably and accurately in order to avoid missed detection and misjudgment. In addition, the detection speed of the model needs to be fast for real-time diagnosis in ultrasound images.
METHODS:
Based on the object detection technology, we propose an accurate, robust and high-speed network with multiscale fusion strategy called Efficient-YOLO, which can realize the localization and recognition of nodules at the same time. Finally, multiple metrics are used to measure the diagnostic ability of the model.
RESULTS:
Experimental results conducted on 3,562 ultrasound images show that our new model greatly increases the accuracy and speed of the detection compared with the baseline model. The best mAP is 92.64%, and the fastest detection speed is 45.1 frames per second.
CONCLUSIONS:
This study proposed an effective method to diagnosis thyroid nodules automatically, which can meet the real-time requirements, indicating that its effectiveness and feasibility for future clinical application.
SanabriaA., KowalskiL.P., ShahJ.P.et al., Growing incidence of thyroid carcinoma in recent years: Factors underlying overdiagnosis, Head & Neck40(4) (2018), 855–866.
2.
ZhuC., ZhengT., KilfoyB.A.et al., A birth cohort analysis of the incidence of papillary thyroid cancer in the United States, –, Thyroid19(10) (2009), 1061–1066.
3.
IkekuboK., IkaK., HashimotoS.et al., Early diagnosis and medical management of thyroid nodules in health check-ups: & mdash; With a focus on urtrasonograhy & mdash, Health Evaluation and Promotion42(2) (2015), 261–271.
4.
TriantafillouE., PapadakisG., ManitarouP.et al., The diagnostic value of FNAB for early diagnosis of thyroid cancer: A Greek center experience, Endocrine Abstracts, Bioscientifica, 2016.
5.
DuranteC., GraniG., LamartinaL.et al., The diagnosis and management of thyroid nodules: A review, JAMA319(9) (2018), 914–924.
6.
MaiW., ZhouM., LiJ.et al., The value of the Demetics ultrasound-assisted diagnosis system in the differential diagnosis of benign from malignant thyroid nodules and analysis of the influencing factors, European Radiology31(10) (2021), 7936–7944.
7.
QuadirS., QuadirS., UddinM.M.et al., Ultrasonographic evaluation of solitary thyroid nodule with histopathological comparison, Bangladesh Journal of Otorhinolaryngology25(2) (2019), 76–84.
8.
IqbalM.A., WangX., ZhangG.et al., A comparison of the efficiency of diagnostic ultrasound and magnetic resonance imaging of cervical lymph nodes in papillary thyroid carcinoma, Journal of X-ray Science and Technology29(6) (2021), 1033–1044.
9.
ShahroudnejadA., QinX., BalachandranS.et al., TUN-Det: A novel network for thyroid ultrasound nodule detection, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, (2021), pp. 656–667.
10.
ZhangL., ZhuangY., HuaZ.et al., Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network, Journal of X-ray Science and Technology29(1) (2021), 75–90.
11.
BochkovskiyA., WangC.Y., LiaoH.Y.M. YOLOv4: Optimal Speed and Accuracy of Object Detection, arXiv preprint arXiv:2004.10934, 2020.
LinT.Y., DollárP., GirshickR.et al., Feature pyramid networks for object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125.
KrizhevskyA., SutskeverI., HintonG.E.Imagenet classification with deep convolutional neural networks, Communication of the ACM60(7) (2012), 84–90.
16.
SzegedyC., LiuW., JiaY.et al., Going deeper with convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1–9.
17.
SimonyanK., ZissermanA. deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556, 2014.
18.
ChuC., ZhengJ., ZhouY.Ultrasonic thyroid nodule detection method based on U-Net network, Comput Meth Prog Bio199(1) (2021), 105906.
19.
AbdolaliF., KapurJ., JaremkoJ.L.et al., Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks, Comput Biol Med122 (2020), 103871.
20.
WangY., KeW., WanP.A Method of ultrasonic image recognition for thyroid papillary carcinoma based on deep convolution neural network, NeuroQuantology16(5) (2018), 757–768.
21.
SongW., LiS., LiuJ.et al., Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition, IEEE J Biomed Health Inform23(3) (2019), 1215–1224.
22.
MaJ., WuF., ZhuJ.et al., A pre-trained convolutional neural network based method for thyroid nodule diagnosis, Ultrasonics100(73) (2017), 221–230.
23.
MaJ., DuanS., ZhangY.et al., Efficient deep learning architecture for detection and recognition of thyroid nodules, Computational Intelligence and Neuroscience2020(6) (2020), 1–15.
24.
NarayanN.S., MarzilianoP., HobbsC.G. Automatic removal of manually induced artefacts in ultrasound images of thyroid gland, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2013, pp. 3399–3402.
25.
HowardA.G., ZhuM., ChenB.et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861, 2017.
26.
SandlerM., HowardA., ZhuM.et al., Mobilenetv2: Inverted residuals and linear bottlenecks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, 4510–4520.
27.
TanM., ChenB., PangR.et al., Mnasnet: Platform-aware neural architecture search for mobile, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2820–2828.
28.
HeK., ZhangX., RenS.et al., Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
29.
HuangG., LiuZ., Van Der MaatenL.et al., Densely connected convolutional networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
30.
SzegedyC., VanhouckeV., IoffeS.et al., Rethinking the inception architecture for computer vision, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826.
31.
CholletF. Xception: Deep learning with depthwise separable convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1251–1258.
32.
WangC.Y., LiaoH.Y.M., WuY.H.et al., CSPNet: A new backbone that can enhance learning capability of CNN,Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionWorkshops, 2020, pp. 390–391.
33.
WangQ., WuB., ZhuP.et al., ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
34.
HuJ., ShenL., SunG. Squeeze-and-excitation networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141.
35.
GirshickR. Fast R-CNN, Proceedings of the IEEE International Conference on ComputerVision, 2015, pp. 1440–1448.
36.
LiuW., AnguelovD., ErhanD.et al., SSD: Single shot multibox detector, European Conference on Computer Vision, Springer, 2016, pp.21–37.
37.
GeZ., LiuS., WangF.et al., YOLOX: Exceeding YOLO Series in 2021, arXiv preprint arXiv:2107.08430, 2021.
