Application Value of Multimodal Ultrasound Imaging Technology in Diagnosis of Liver Diseases

WU Shuangdou，BAI Yanhong，TANG Zhongcai，GUO Jiankang

doi:10.3969/j.issn.1674-1633.20241827

PDF(2666 KB)

China Medical Devices ›› 2025, Vol. 40 ›› Issue (4) : 55-60. DOI: 10.3969/j.issn.1674-1633.20241827

RESEARCHWORK

Application Value of Multimodal Ultrasound Imaging Technology in Diagnosis of Liver Diseases

WU Shuangdou，BAI Yanhong，TANG Zhongcai，GUO Jiankang

Author information +

History +

Abstract

Objective To propose a multimodal ultrasound diagnosis method, which combines deep learning with multimodal ultrasound imaging technology, in order to further improve the application value of multimodal ultrasound imaging technology in the diagnosis of liver diseases, and achieve higher precision disease diagnosis. Methods: Firstly, the concept of edge perception was introduced, and a network framework for image segmentation was proposed. The image segmentation model was obtained by training, and the multi-modal ultrasound images were preprocessed. Then, support vector machine (SVM) was used as the base classifier, and multiple base classifiers were established by combining the characteristics of multimodal ultrasound images. Finally, the coefficients of the base classifiers were determined according to the information entropy, dispersion and mean-variance ratio, and the fused multimodal ultrasound diagnosis Results were obtained. Results: The research Results showed that the diagnostic accuracy of the multi-modal ultrasonic imaging diagnostic model combined with deep learning method reached 95.78%, the false positive rate and false negative rate were 4.23% and 4.50% respectively, F1 score reached 0.93, and Kappa statistic reached 0.92, with high diagnostic accuracy. Conclusion: The multimodal ultrasound diagnosis method proposed in this study has high application value in the diagnosis of liver diseases, which can help doctors to determine the disease status of patients

Key words

multimodal;ultrasonic imaging;liver disease;diagnosis;image segmentation;categorize;support vector machine (SVM)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

WU Shuangdou，BAI Yanhong，TANG Zhongcai，GUO Jiankang. Application Value of Multimodal Ultrasound Imaging Technology in Diagnosis of Liver Diseases[J]. China Medical Devices, 2025, 40(4): 55-60 https://doi.org/10.3969/j.issn.1674-1633.20241827

References

[1] 陈煌婧，陈秀华，何英. 多模态超声和基于超声深度学习的影像组学在预测乳腺癌患者新辅助化疗疗效中的研究进展[J]. 中国临床医学影像杂志，2023，34(8): 593-596.
Chen HJ, Chen XH, He Y. Research progress of multimodal ultrasound and imageomics based on ultrasound deep learning in predicting the efficacy of neoadjuvant chemotherapy in breast cancer patients[J]. J China Clin Med Imag, 2023, 34(8): 593-596.
[2] 黄梅芳，陈文华，李福源，等. 超声测量颈前软组织厚度预测喉镜暴露困难的价值[J]. 临床麻醉学杂志，2023，39(7): 688-694.
Huang MF, Chen WH, Li FY, et al. Value of ultrasound measurement of anterior neck soft tissue thickness in predicting difficult laryngoscopy[J]. J Clin Anesthesiol, 2023, 39(7): 688-694.
[3] Guitart C, Rodríguez-Fanjul J, Bobillo-Perez S, et al. An algorithm combining procalcitonin and lung ultrasound improves the diagnosis of bacterial pneumonia in critically ill children: the PROLUSP study, a randomized clinical trial[J]. Pediatr Pulmonol, 2022, 57(3): 711-723.
[4] 宋和琴，托静美，司晓娟. 超声AI联合促甲状腺激素检测在甲状腺结节良恶性诊断中的应用价值[J]. 中国医疗设备，2023，38(11): 92-97.
Song HQ, Tuo JM, Si XJ. Application value of ultrasonic AI combined with thyroid stimulating hormone detection in the diagnosis of benign and malignant diagnosis of thyroid nodule[J]. China Med Devices, 2023, 38(11): 92-97.
[5] 吴艺敏，汪珺莉. 多模态超声联合病理参数列线图预测乳腺癌腋窝淋巴结转移负荷[J]. 中国超声医学杂志，2023，39(6): 637-641.
Wu YM, Wang JL. Nomogram based on multi-modality ultrasound combined with pathological parameters prediction of axillary lymph node metastatic burden in breast cancer[J]. Chin J Ultrasound Med, 2023, 39(6): 637-641.
[6] 热娜古丽·艾合麦提尼亚孜，米吾尔依提·海拉提，王正业，等. 基于Swin Transformer的肝囊型包虫病超声图分类研究[J]. 电子技术应用，2022，48(11): 7-12.
Jenaguri A, Miuryiti K, Wang ZY, et al. Ultrasonic classification of hepatic cystic echinococcosis based on Swin Transformer[J]. Appl Electron Tech, 2022, 48(11): 7-12.
[7] 魏星月，王连双，王媛媛，等. 基于多模态超声成像数据的慢性肝病肝纤维化、炎症和脂肪变性的智能分级诊断[J]. 首都医科大学学报，2023，44(6): 928-935.
Wei XY, Wang LS, Wang YY, et al. Intelligent grading diagnosis of liver fibrosis, inflammation, and steatosis in chronic liver disease based on multimodal ultrasound imaging data[J]. J Cap Med Univ, 2023, 44(6): 928-935.
[8] Laverde-Saad A, Jfri A, García R, et al. Discriminative deep learning based benignity/malignancy diagnosis of dermatologic ultrasound skin lesions with pretrained artificial intelligence architecture[J]. Skin Res Technol, 2022, 28(1): 35-39.
[9] 王世界，邓家琦，况容，等. 基于超声造影的深度学习诊断肝恶性肿瘤的应用价值[J]. 中华超声影像学杂志，2024，33(2): 112-118.
Wang SJ, Deng JQ, Kuang R, et al. Application value of deep learning based on contrast-enhanced ultrasound for the diagnosis of liver malignant tumors[J]. Chin J Ultrason, 2024, 33(2): 112-118.
[10] 杨印凯，万鹏，石航，等. 基于多模态超声对比学习的肝癌诊断方法[J]. 数据采集与处理，2024，39(4): 874-885.
Yang YK, Wan P, Shi H, et al. Liver cancer diagnosis method based on multi-modal ultrasound contrast learning[J]. J Data Acquis Process, 2024, 39(4): 874-885.
[11] 石勇涛，柳迪，高超，等. 改进Segformer的前列腺超声图像语义分割算法[J]. 现代电子技术，2024，47(15): 65-72.
Shi YT, Liu D, Gao C, et al. Prostate ultrasound image semantic segmentation algorithm based on improved Segformer[J]. Mod Electr Tech, 2024, 47(15): 65-72.
[12] 关少亚，张诚，孟偲，等. 基于相位对称性的血管超声图像分割算法[J]. 北京航空航天大学学报，2023，49(10): 2645-2650.
Guan SY, Zhang C, Meng C, et al. Vascular ultrasound image segmentation algorithm based on phase symmetry[J]. J Beijing Univ Aeronaut Astronaut, 2023, 49(10): 2645-2650.
[13] 杜瑶，冯晓丹，吴萌，等. 基于超声影像组学构建联合模型预测乳腺癌新辅助化疗疗效[J]. 中国超声医学杂志，2023，39(12): 1353-1356.
Du Y, Feng XD, Wu M, et al. To construct a combined radiomics model based on ultrasound to predict the efficacy of neoadjuvant chemotherapy for breast cancer[J]. Chin J Ultrasound Med, 2023, 39(12): 1353-1356.
[14] Goudarzi S, Whyte J, Boily M, et al. Segmentation of arm ultrasound images in breast cancer-related lymphedema: a database and deep learning algorithm[J]. IEEE Trans Biomed Eng, 2023, 70(9): 2552-2563.
[15] 刘梦怡，马红，林静茹，等. 基于随机森林算法构建冠心病人群左心室舒张功能不全的诊断模型[J]. 中国循环杂志，2023，38(7): 730-733.
Liu MY, Ma H, Lin JR, et al. Random forest algorithm-based diagnostic model for left ventricular diastolic dysfunction in patients with coronary heart disease[J]. Chin Circ J, 2023, 38(7): 730-733.
[16] 常炳国，石华龙，常雨馨. 基于深度学习的黑色素瘤智能诊断多模型算法[J]. 计算机科学，2022，49(z1): 22-26.
Chang BG, Shi HL, Chang YX. Multi model algorithm for intelligent diagnosis of melanoma based on deep learning[J]. Comput Sci, 2022, 49(z1): 22-26.
[17] 赵凤，郑旭，周政，等. 不同壁材对超声波喷雾-冷冻干燥制备香味缓释微胶囊的影响[J]. 食品科学，2023，44(22): 296-303.
Zhao F, Zheng X, Zhou Z, et al. Effect of different wall materials on the preparation of sustained-release aroma microcapsules by ultrasonic spray-freeze drying[J]. Food Sci, 2023, 44(22): 296-303.
[18] 袁倩，徐晓红，张国丽，等. 超声双重造影在结直肠癌诊断及分期评估中的应用进展[J]. 山东医药，2024，64(1): 111-114.
[19] 李秀云，闫凤娟，徐杰，等. 超声引导下中等长度导管留置在神经外科重症患者静脉输液中的应用效果[J]. 重庆医学，2024，53(S1): 309-311.
Li XY, Yan FJ, Xu J, et al. Application effect of ultrasound-guided medium length catheter placement in intravenous infusion of critically ill neurosurgical patients[J]. Chongqing Med, 2024, 53(S1): 309-311.
[20] 黄琴，庄华，李金莲. 多模态超声诊断甲状腺转移性肺癌1例[J]. 中国超声医学杂志，2023，39(10): 1175.
[21] 刘瑞，袁文佳，刘巍. 基于人工智能深度学习算法的超声诊断系统在触诊阴性的乳腺结节良恶性鉴别中的应用[J]. 郑州大学学报(医学版)，2023，58(3): 406-410.
Liu R, Yuan WJ, Liu W. Application of ultrasound diagnosis system based on artificial intelligence deep learning algorithm in identification of benign and malignant breast nodules with negative palpation[J]. J Zhengzhou Univ (Med Sci), 2023, 58(3): 406-410.