Original Contribution| Volume 49, ISSUE 5, P1248-1258, May 2023

LN-Net: Perfusion Pattern-Guided Deep Learning for Lymph Node Metastasis Diagnosis Based on Contrast-Enhanced Ultrasound Videos


      The blood flow in lymph nodes reflects important pathological features. However, most intelligent diagnosis based on contrast-enhanced ultrasound (CEUS) video focuses only on CEUS images, ignoring the process of extracting blood flow information. In the work described here, a parametric imaging method for describing blood perfusion pattern was proposed and a multimodal network (LN-Net) to predict lymph node metastasis was designed.


      First, the commercially available artificial intelligence object detection model YOLOv5 was improved to detect the lymph node region. Then the correlation and inflection point matching algorithms were combined to calculate the parameters of the perfusion pattern. Finally, the Inception-V3 architecture was used to extract the image features of each modality, with the blood perfusion pattern taken as the guiding factor in fusing the features with CEUS by sub-network weighting.


      The average precision of the improved YOLOv5s algorithm compared with baseline was improved by 5.8%. LN-Net predicted lymph node metastasis with 84.9% accuracy, 83.7% precision and 80.3% recall. Compared with the model without blood flow feature guidance, accuracy was improved by 2.6%. The intelligent diagnosis method has good clinical interpretability.


      A static parametric imaging map could describe a dynamic blood flow perfusion pattern, and as a guiding factor, it could improve the classification ability of the model with respect to lymph node metastasis.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Ultrasound in Medicine and Biology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Mehlen P
        • Puisieux A
        Metastasis: a question of life or death.
        Nat Rev Cancer. 2006; 6: 449-458
        • Jalkanen S
        • Salmi M
        Lymphatic endothelial cells of the lymph node.
        Nat Rev Immunol. 2020; 20: 566-578
        • Jones D
        • Pereira ER
        • Padera TP
        Growth and immune evasion of lymph node metastasis.
        Front Oncol. 2018; 8: 36
        • Balasubramanian I
        • Fleming C
        • Corrigan M
        • Redmond H
        • Kerin M
        • Lowery A
        Meta-analysis of the diagnostic accuracy of ultrasound-guided fine-needle aspiration and core needle biopsy in diagnosing axillary lymph node metastasis.
        Br J Surg. 2018; 105: 1244-1253
        • Dietrich CF
        • Averkiou M
        • Nielsen MB
        • Barr RG
        • Burns PN
        • Calliada F
        • et al.
        How to perform contrast-enhanced ultrasound (CEUS).
        Ultrasound Int Open. 2018; 4: E2-15
        • Huang S
        • Zhao Y
        • Jiang X
        • Lin N
        • Zhang M
        • Wang H
        • et al.
        Clinical utility of contrast-enhanced ultrasound for the diagnosis of lymphadenopathy.
        Ultrasound Med Biol. 2021; 47: 869-879
        • Dietrich CF
        The potential of contrast-enhanced ultrasonography to evaluate lymphadenopathy.
        Gastrointest Endosc. 2019; 90: 251-253
        • Kuang M
        • Hu HT
        • Li W
        • Chen SL
        • Lu XZ
        Articles that use artificial intelligence for ultrasound: a reader's guide.
        Front Oncol. 2021; 11: 2062
        • Yu J
        • Deng Y
        • Liu T
        • Zhou J
        • Jia X
        • Xiao T
        • et al.
        Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics.
        Nat Commun. 2020; 11: 1-10
        • Jung EM
        • Jung F
        • Stroszczynski C
        • Wiesinger I
        Quantification of dynamic contrast-enhanced ultrasound (CEUS) in non-cystic breast lesions using external perfusion software.
        Sci Rep. 2021; 11: 1-9
        • Zhou LQ
        • Wu XL
        • Huang SY
        • Wu GG
        • Ye HR
        • Wei Q
        • et al.
        Lymph node metastasis prediction from primary breast cancer US images using deep learning.
        Radiology. 2020; 294: 19-28
        • Zheng X
        • Yao Z
        • Huang Y
        • Yu Y
        • Wang Y
        • Liu Y
        • et al.
        Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer.
        Nat Commun. 2020; 11: 1-9
        • Yang JR
        • Song Y
        • Jia YL
        • Ruan LT
        Application of multimodal ultrasonography for differentiating benign and malignant cervical lymphadenopathy.
        Japan J Radiol. 2021; 39: 938-945
        • Guo LH
        • Wang D
        • Qian YY
        • Zheng X
        • Zhao CK
        • Li XL
        • et al.
        A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images.
        Clin Hemorheol Microcirc. 2018; 69: 343-354
        • Yang Z
        • Gong X
        • Guo Y
        • Liu W
        A temporal sequence dual-branch network for classifying hybrid ultrasound data of breast cancer.
        IEEE Access. 2020; 8: 82688-82699
        • Chen C
        • Wang Y
        • Niu J
        • Liu X
        • Li Q
        • Gong X
        Domain knowledge powered deep learning for breast cancer diagnosis based on contrast-enhanced ultrasound videos.
        IEEE Trans Med Imaging. 2021; 40: 2439-2451
        • Yin Ss
        • Cui Ql
        • Fan ZH
        • Yang W
        • Yan K
        Diagnostic value of arrival time parametric imaging using contrast-enhanced ultrasonography in superficial enlarged lymph nodes.
        J Ultrasound Med. 2019; 38: 1287-1298
        • Zhang Q
        • Liu Y
        • Han H
        • Shi J
        • Wang W
        Artificial intelligence based diagnosis for cervical lymph node malignancy using the point-wise gated Boltzmann machine.
        IEEE Access. 2018; 6: 60605-60612
        • Zhang C
        • Yang Z
        • He X
        • Deng L
        Multimodal intelligence: representation learning, information fusion, and applications.
        IEEE J Selected Top Signal Process. 2020; 14: 478-493
        • Baltrušaitis T
        • Ahuja C
        • Morency LP
        Multimodal machine learning: a survey and taxonomy.
        IEEE Trans Pattern Anal Mach Intell. 2018; 41: 423-443
        • Wan J
        • Chen B
        • Yu Y
        Polyp detection from colorectum images by using attentive YOLOv5.
        Diagnostics. 2021; 11: 2264
      1. Bochkovskiy A, Wang CY, Liao HYM. Yolov4: optimal speed and accuracy of object detection. arXiv 2004.10934.2020.

        • He K
        • Zhang X
        • Ren S
        • Sun J
        Spatial pyramid pooling in deep convolutional networks for visual recognition.
        IEEE Trans Pattern Anal Mach Intell. 2015; 37: 1904-1916
      2. PANet: few-shot image semantic segmentation with prototype alignment.
        in: Wang K Liew JH Zou Y Zhou D Feng J Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE, New York2019: 9197-9206
        • Chen LC
        • Papandreou G
        • Kokkinos I
        • Murphy K
        • Yuille AL
        Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs.
        IEEE Trans Pattern Anal Mach Intell. 2017; 40: 834-848
      3. EfficientDet: scalable and efficient object detection.
        in: Tan M Pang R Le QV Proceedings, IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, New York2020
        • Green R
        • Epstein E
        Dynamic contrast-enhanced ultrasound improves diagnostic performance in endometrial cancer staging.
        Ultrasound Obstet Gynecol. 2020; 56: 96-105
      4. Finding a "kneedle" in a haystack: detecting knee points in system behavior.
        in: Satopaa V Albrecht J Irwin D Raghavan B 31st international conference on distributed computing systems workshops. IEEE, New York2011
      5. Rethinking the inception architecture for computer vision.
        in: Szegedy C Vanhoucke V Ioffe S Shlens J Wojna Z Proceedings, IEEE Conference on Computer Vision and Pattern Recognition. IEEE, New York2016
      6. Focal loss for dense object detection.
        in: Lin TY Goyal P Girshick R He K Dollár P Proceedings, IEEE International Conference on Computer Vision. IEEE, New York2017
      7. Deep residual learning for image recognition.
        in: He K Zhang X Ren S Sun J Proceedings, IEEE Conference on Computer Vision and Pattern Recognition. IEEE, New York2016
      8. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556.2014.

      9. Mobilenetv2: inverted residuals and linear bottlenecks.
        in: Sandler M Howard A Zhu M Zhmoginov A Chen LC Proceedings, IEEE Conference on Computer Vision and Pattern Recognition. IEEE, New York2018
        • Zhuang Z
        • Fan G
        • Yuan Y
        • Raj ANJ
        • Qiu S
        A fuzzy clustering based color-coded diagram for effective illustration of blood perfusion parameters in contrast-enhanced ultrasound videos.
        Comput Methods Programs Biomed. 2020; 190105233
        • SY Chae
        • Jung HN
        • Ryoo I
        • Suh S
        Differentiating cervical metastatic lymphadenopathy and lymphoma by shear wave elastography.
        Sci Rep. 2019; 9: 1-10
        • Park VY
        • Han K
        • Kim HJ
        • Lee E
        • Youk JH
        • Kim EK
        • et al.
        Radiomics signature for prediction of lateral lymph node metastasis in conventional papillary thyroid carcinoma.
        PLoS One. 2020; 15e0227315
        • Sun Q
        • Lin X
        • Zhao Y
        • Li L
        • Yan K
        • Liang D
        • et al.
        Deep learning vs. radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: don't forget the peritumoral region.
        Front Oncol. 2020; 10: 53