{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T23:16:51Z","timestamp":1782515811538,"version":"3.54.5"},"reference-count":41,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T00:00:00Z","timestamp":1623801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Computer vision, biomedical image processing and deep learning are related fields with a tremendous impact on the interpretation of medical images today. Among biomedical image sensing modalities, ultrasound (US) is one of the most widely used in practice, since it is noninvasive, accessible, and cheap. Its main drawback, compared to other imaging modalities, like computed tomography (CT) or magnetic resonance imaging (MRI), consists of the increased dependence on the human operator. One important step toward reducing this dependence is the implementation of a computer-aided diagnosis (CAD) system for US imaging. The aim of the paper is to examine the application of contrast enhanced ultrasound imaging (CEUS) to the problem of automated focal liver lesion (FLL) diagnosis using deep neural networks (DNN). Custom DNN designs are compared with state-of-the-art architectures, either pre-trained or trained from scratch. Our work improves on and broadens previous work in the field in several aspects, e.g., a novel leave-one-patient-out evaluation procedure, which further enabled us to formulate a hard-voting classification scheme. We show the effectiveness of our models, i.e., 88% accuracy reported against a higher number of liver lesion types: hepatocellular carcinomas (HCC), hypervascular metastases (HYPERM), hypovascular metastases (HYPOM), hemangiomas (HEM), and focal nodular hyperplasia (FNH).<\/jats:p>","DOI":"10.3390\/s21124126","type":"journal-article","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T21:58:32Z","timestamp":1623880712000},"page":"4126","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-7047","authenticated-orcid":false,"given":"C\u0103t\u0103lin Daniel","family":"C\u0103leanu","sequence":"first","affiliation":[{"name":"Applied Electronics Department, Faculty of Electronics, Telecommunications and Information Technologies, Politehnica University Timi\u0219oara, 300223 Timi\u0219oara, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina Laura","family":"S\u00eerbu","sequence":"additional","affiliation":[{"name":"Applied Electronics Department, Faculty of Electronics, Telecommunications and Information Technologies, Politehnica University Timi\u0219oara, 300223 Timi\u0219oara, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgiana","family":"Simion","sequence":"additional","affiliation":[{"name":"Applied Electronics Department, Faculty of Electronics, Telecommunications and Information Technologies, Politehnica University Timi\u0219oara, 300223 Timi\u0219oara, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,16]]},"reference":[{"key":"ref_1","unstructured":"Bovik, A.C. (2005). Computer-aided detection and diagnosis in mammography. Handbook of Image and Video Processing, Elsevier. [2nd ed.]."},{"key":"ref_2","first-page":"260","article-title":"Computer aided diagnosis system for lung cancer detection using machine learning technique","volume":"51","author":"Gomathi","year":"2011","journal-title":"Eur. J. Sci. Res."},{"key":"ref_3","first-page":"12","article-title":"Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps","volume":"20","author":"Yoshida","year":"2002","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_4","unstructured":"Bowsher, J.E., Roper, J.R., Yan, S., Giles, W.M., and Yin, F.-F. (November, January 30). Regional SPECT imaging using sampling principles and multiple pinholes. Proceedings of the Nuclear Science Symposium Conference Record, Knoxville, TN, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/TMI.2003.809588","article-title":"A versatile wavelet domain ISE filtration technique for medical imaging","volume":"22","author":"Pizurica","year":"2003","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/34.1000236","article-title":"Mean shift: A robust approach toward feature space analysis","volume":"24","author":"Comaniciu","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rousson, M., Paragios, N., and Deriche, R. (2004, January 26\u201329). Implicit active shape models for 3D segmentation in MRI imaging. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Saint-Malo, France.","DOI":"10.1007\/978-3-540-30135-6_26"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1109\/34.969114","article-title":"Fast approximate energy minimization via graph cuts","volume":"23","author":"Boykov","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"S\u00eerbu, C.L., Simion, G., and C\u0103leanu, C.-D. (2020, January 5\u20136). Deep CNN for contrast-enhanced ultrasound focal liver lesions diagnosis. Proceedings of the 2020 International Symposium on Electronics and Telecommunications (ISETC), Timi\u0219oara, Romania.","DOI":"10.1109\/ISETC50328.2020.9301116"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pan, F., Huanq, Q., and Li, X. (2019, January 3\u20135). Classification of liver tumors with CEUS based on 3D-CNN. Proceedings of the IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM), Osaka, Japan.","DOI":"10.1109\/ICARM.2019.8834190"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Vancea, F., Mitrea, D., and Nedevschi, S. (2019, January 5\u20137). Hepatocellular Carcinoma Segmentation within Ultrasound Images using Convolutional Neural Networks. Proceedings of the IEEE 15th International Conference on Intelligent Computer Communication and Preprocessing (ICCP), Cluj-Napoca, Romania.","DOI":"10.1109\/ICCP48234.2019.8959687"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4427","DOI":"10.3748\/wjg.v18.i32.4427","article-title":"Contrast-enhanced ultrasonography parameters in neural network diagnosis of liver tumors","volume":"18","author":"Streba","year":"2012","journal-title":"World J. Gastroenterol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Guo, L., Wang, D., Xu, H., Qian, Y., Wang, C., Zheng, X., Zhang, Q., and Shi, J. (2017, January 11\u201315). CEUS-based classification of liver tumors with deep canonical correlation analysis and multi-kernel learning. Proceedings of the Annual International Conference IEEE Engineering Medicine and Biology Society, Jeju Island, Korea.","DOI":"10.1109\/EMBC.2017.8037181"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"200","DOI":"10.14366\/usg.18060","article-title":"Contrast-enhanced ultrasound of hepatocellular carcinoma: Where do we stand?","volume":"38","author":"Bartolotta","year":"2019","journal-title":"Ultrasonography"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.eng.2018.11.020","article-title":"Deep Learning in Medical Ultrasound Analysis: A Review","volume":"5","author":"Liu","year":"2019","journal-title":"Engineering"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"177","DOI":"10.14366\/usg.20085","article-title":"Current status of deep learning applications in abdominal ultrasonography","volume":"40","author":"Song","year":"2021","journal-title":"Ultrasonography"},{"key":"ref_18","first-page":"38","article-title":"Contrast Enhanced Ultrasound for the characterization of focal liver lesions","volume":"13","author":"Sporea","year":"2011","journal-title":"Med. Ultrason."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e13325","DOI":"10.1097\/MD.0000000000013325","article-title":"The diagnostic accuracy of contrast-enhanced ultrasound for the differentiation of benign and malignant thyroid nodules: A PRISMA compliant meta-analysis","volume":"97","author":"Liu","year":"2018","journal-title":"Medicine"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1646","DOI":"10.1109\/TMI.2021.3063421","article-title":"Hierarchical temporal attention network for thyroid dule recognition using dynamic CEUS imaging","volume":"40","author":"Wan","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Posteman, A.W., Scheltema, M.J., Mannaerts, C.K., Van Sloun, R.J., Idzenga, T., Mischi, M., Engelbrecht, M.R., De la Rosette, J.J., and Wijkstra, H. (2017). The prostate cancer detection rates of CEUS-targeted versus MRI-targeted versus systematic TRUS-guided biopsies in biopsy-na\u00efve men: A prospective, comparative clinical trial using the same patients. BMC Urol., 17.","DOI":"10.1186\/s12894-017-0213-7"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1794","DOI":"10.1109\/TCBB.2018.2835444","article-title":"A Deep learning approach for targeted contrast-enhanced ultrasound based prostate cancer detection","volume":"16","author":"Feng","year":"2019","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, L., Wang, Y.X.J., Cui, N.Y., Zou, S.M., Zhou, C.W., and Jiang, Y.X. (2014). Time-intensity curve parameters in rectal cancer measured using endorectal ultrasonography with sterile coupling gels filling the rectum: Correlations with tumor angiogenesis and clinicopathological features. BioMed Res. Int., 2014.","DOI":"10.1155\/2014\/587806"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Qin, L., Yin, H., and Zhuang, H. (2019, January 24\u201326). Classification for rectal CEUS images based on combining features by transfer learning. Proceedings of the Third International Symposium on Image Computing and Digital Medicine\u2014ISICDM, Xi\u2019an, China.","DOI":"10.1145\/3364836.3364873"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"82688","DOI":"10.1109\/ACCESS.2020.2990683","article-title":"A Temporal sequence dual-branch network for classifying hybrid ultrasound data of breast cancer","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"20200880","DOI":"10.1259\/bjr.20200880","article-title":"The role of contrast-enhanced ultrasound in the diagnosis of malignant non-mass breast lesions and exploration of diagnostic criteria","volume":"94","author":"Zhang","year":"2021","journal-title":"Br. J. Radiol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.clinimag.2019.12.013","article-title":"Contrast enhanced ultrasound: A review of radiology applications","volume":"60","author":"Erlichman","year":"2020","journal-title":"Clin. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Gasnier, A., Ardon, R., Ciofolo-Veit, C., Leen, E., and Correas, J.M. (2010, January 14\u201317). Assessing tumor vascularity with 3D contrast-enhanced ultrasound: A new semi-automated segmentation framework. Proceedings of the 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Rotterdam, The Netherlands.","DOI":"10.1109\/ISBI.2010.5490351"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wan, P., Chen, F., Zhu, X., Liu, C., Zhang, Y., Kong, W., and Zhang, D. (2020, January 4). CEUSNet: Lesion segmentation in dynamic contrast-enhanced ultrasound with feature-reweighted attention mechanism. Proceedings of the IEEE International Symposium on Biomedical Imaging ISBI, Iowa City, IA, USA.","DOI":"10.1109\/ISBI45749.2020.9098655"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1007\/s00261-020-02564-w","article-title":"Deep learning for differentiation of benign and malignant solid liver lesions on ultrasonography","volume":"46","author":"Xi","year":"2021","journal-title":"Abdom. Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3127","DOI":"10.1007\/s13369-016-2387-9","article-title":"Diagnosis of focal liver diseases based on deep learning technique for ultrasound images","volume":"42","author":"Hassan","year":"2017","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"4057","DOI":"10.1016\/j.ijleo.2014.01.114","article-title":"Deep learning based classification of focal liver lesions with contrast-enhanced ultrasound","volume":"125","author":"Wu","year":"2014","journal-title":"Optik"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"252","DOI":"10.11152\/mu-936","article-title":"Is Contrast Enhanced Ultrasonography a useful tool in a beginner\u2019s hand? How much can a Computer Assisted Diagnosis prototype help in characterizing the malignancy of focal liver lesions?","volume":"19","author":"Moga","year":"2017","journal-title":"Med. Ultrason."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"C\u0103leanu, C.-D., Simion, G., David, C., Gui, V., Moga, T., Popescu, A., Sirli, R., and Sporea, I. (2014, January 14\u201315). A study over the importance of arterial phase temporal parameters in focal liver lesions CEUS based diagnosis. Proceedings of the 11th International Symposium on Electronics and Telecommunications (ISETC), Timisoara, Romania.","DOI":"10.1109\/ISETC.2014.7010799"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"C\u0103leanu, C.-D., and Simion, G. (2019, January 1\u20133). A Bag of Features Approach for CEUS Liver Lesions Investigation. Proceedings of the 42nd International Conference on Telecommunications and Signal Processing (TSP), Budapest, Hungary.","DOI":"10.1109\/TSP.2019.8768851"},{"key":"ref_36","unstructured":"(2021, March 06). Keras Applications. Available online: https:\/\/keras.io\/api\/applications\/."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018, January 18\u201323). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18\u201323). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref_39","unstructured":"Tan, M., and Le, Q.V. (2019, January 10\u201315). EfficientNet: Rethinking model scaling for conutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected conutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_41","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4126\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:16:50Z","timestamp":1760163410000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,16]]},"references-count":41,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124126"],"URL":"https:\/\/doi.org\/10.3390\/s21124126","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,16]]}}}